From dfd402a4c4baae42398ce9180ff424d589b8bffc Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 14 Nov 2019 19:02:54 +0100 Subject: kcsan: Add Kernel Concurrency Sanitizer infrastructure Kernel Concurrency Sanitizer (KCSAN) is a dynamic data-race detector for kernel space. KCSAN is a sampling watchpoint-based data-race detector. See the included Documentation/dev-tools/kcsan.rst for more details. This patch adds basic infrastructure, but does not yet enable KCSAN for any architecture. Signed-off-by: Marco Elver Acked-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/compiler-clang.h | 9 ++++ include/linux/compiler-gcc.h | 7 +++ include/linux/compiler.h | 37 ++++++++++--- include/linux/kcsan-checks.h | 97 ++++++++++++++++++++++++++++++++++ include/linux/kcsan.h | 115 +++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 4 ++ 6 files changed, 261 insertions(+), 8 deletions(-) create mode 100644 include/linux/kcsan-checks.h create mode 100644 include/linux/kcsan.h (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 333a6695a918..a213eb55e725 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -24,6 +24,15 @@ #define __no_sanitize_address #endif +#if __has_feature(thread_sanitizer) +/* emulate gcc's __SANITIZE_THREAD__ flag */ +#define __SANITIZE_THREAD__ +#define __no_sanitize_thread \ + __attribute__((no_sanitize("thread"))) +#else +#define __no_sanitize_thread +#endif + /* * Not all versions of clang implement the the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index d7ee4c6bad48..0eb2a1cc411d 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -145,6 +145,13 @@ #define __no_sanitize_address #endif +#if defined(__SANITIZE_THREAD__) && __has_attribute(__no_sanitize_thread__) +#define __no_sanitize_thread \ + __attribute__((__noinline__)) __attribute__((no_sanitize_thread)) +#else +#define __no_sanitize_thread +#endif + #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 5e88e7e33abe..c42fa83f23fb 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -178,6 +178,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif #include +#include #define __READ_ONCE_SIZE \ ({ \ @@ -193,12 +194,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, } \ }) -static __always_inline -void __read_once_size(const volatile void *p, void *res, int size) -{ - __READ_ONCE_SIZE; -} - #ifdef CONFIG_KASAN /* * We can't declare function 'inline' because __no_sanitize_address confilcts @@ -207,18 +202,44 @@ void __read_once_size(const volatile void *p, void *res, int size) * '__maybe_unused' allows us to avoid defined-but-not-used warnings. */ # define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused +# define __no_sanitize_or_inline __no_kasan_or_inline #else # define __no_kasan_or_inline __always_inline #endif -static __no_kasan_or_inline +#ifdef __SANITIZE_THREAD__ +/* + * Rely on __SANITIZE_THREAD__ instead of CONFIG_KCSAN, to avoid not inlining in + * compilation units where instrumentation is disabled. + */ +# define __no_kcsan_or_inline __no_sanitize_thread notrace __maybe_unused +# define __no_sanitize_or_inline __no_kcsan_or_inline +#else +# define __no_kcsan_or_inline __always_inline +#endif + +#ifndef __no_sanitize_or_inline +#define __no_sanitize_or_inline __always_inline +#endif + +static __no_kcsan_or_inline +void __read_once_size(const volatile void *p, void *res, int size) +{ + kcsan_check_atomic_read(p, size); + __READ_ONCE_SIZE; +} + +static __no_sanitize_or_inline void __read_once_size_nocheck(const volatile void *p, void *res, int size) { __READ_ONCE_SIZE; } -static __always_inline void __write_once_size(volatile void *p, void *res, int size) +static __no_kcsan_or_inline +void __write_once_size(volatile void *p, void *res, int size) { + kcsan_check_atomic_write(p, size); + switch (size) { case 1: *(volatile __u8 *)p = *(__u8 *)res; break; case 2: *(volatile __u16 *)p = *(__u16 *)res; break; diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h new file mode 100644 index 000000000000..e78220661086 --- /dev/null +++ b/include/linux/kcsan-checks.h @@ -0,0 +1,97 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_KCSAN_CHECKS_H +#define _LINUX_KCSAN_CHECKS_H + +#include + +/* + * Access type modifiers. + */ +#define KCSAN_ACCESS_WRITE 0x1 +#define KCSAN_ACCESS_ATOMIC 0x2 + +/* + * __kcsan_*: Always calls into runtime when KCSAN is enabled. This may be used + * even in compilation units that selectively disable KCSAN, but must use KCSAN + * to validate access to an address. Never use these in header files! + */ +#ifdef CONFIG_KCSAN +/** + * __kcsan_check_access - check generic access for data race + * + * @ptr address of access + * @size size of access + * @type access type modifier + */ +void __kcsan_check_access(const volatile void *ptr, size_t size, int type); + +#else +static inline void __kcsan_check_access(const volatile void *ptr, size_t size, + int type) { } +#endif + +/* + * kcsan_*: Only calls into runtime when the particular compilation unit has + * KCSAN instrumentation enabled. May be used in header files. + */ +#ifdef __SANITIZE_THREAD__ +#define kcsan_check_access __kcsan_check_access +#else +static inline void kcsan_check_access(const volatile void *ptr, size_t size, + int type) { } +#endif + +/** + * __kcsan_check_read - check regular read access for data races + * + * @ptr address of access + * @size size of access + */ +#define __kcsan_check_read(ptr, size) __kcsan_check_access(ptr, size, 0) + +/** + * __kcsan_check_write - check regular write access for data races + * + * @ptr address of access + * @size size of access + */ +#define __kcsan_check_write(ptr, size) \ + __kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE) + +/** + * kcsan_check_read - check regular read access for data races + * + * @ptr address of access + * @size size of access + */ +#define kcsan_check_read(ptr, size) kcsan_check_access(ptr, size, 0) + +/** + * kcsan_check_write - check regular write access for data races + * + * @ptr address of access + * @size size of access + */ +#define kcsan_check_write(ptr, size) \ + kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE) + +/* + * Check for atomic accesses: if atomic access are not ignored, this simply + * aliases to kcsan_check_access, otherwise becomes a no-op. + */ +#ifdef CONFIG_KCSAN_IGNORE_ATOMICS +#define kcsan_check_atomic_read(...) \ + do { \ + } while (0) +#define kcsan_check_atomic_write(...) \ + do { \ + } while (0) +#else +#define kcsan_check_atomic_read(ptr, size) \ + kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC) +#define kcsan_check_atomic_write(ptr, size) \ + kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC | KCSAN_ACCESS_WRITE) +#endif + +#endif /* _LINUX_KCSAN_CHECKS_H */ diff --git a/include/linux/kcsan.h b/include/linux/kcsan.h new file mode 100644 index 000000000000..9047048fee84 --- /dev/null +++ b/include/linux/kcsan.h @@ -0,0 +1,115 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_KCSAN_H +#define _LINUX_KCSAN_H + +#include +#include + +#ifdef CONFIG_KCSAN + +/* + * Context for each thread of execution: for tasks, this is stored in + * task_struct, and interrupts access internal per-CPU storage. + */ +struct kcsan_ctx { + int disable_count; /* disable counter */ + int atomic_next; /* number of following atomic ops */ + + /* + * We distinguish between: (a) nestable atomic regions that may contain + * other nestable regions; and (b) flat atomic regions that do not keep + * track of nesting. Both (a) and (b) are entirely independent of each + * other, and a flat region may be started in a nestable region or + * vice-versa. + * + * This is required because, for example, in the annotations for + * seqlocks, we declare seqlock writer critical sections as (a) nestable + * atomic regions, but reader critical sections as (b) flat atomic + * regions, but have encountered cases where seqlock reader critical + * sections are contained within writer critical sections (the opposite + * may be possible, too). + * + * To support these cases, we independently track the depth of nesting + * for (a), and whether the leaf level is flat for (b). + */ + int atomic_nest_count; + bool in_flat_atomic; +}; + +/** + * kcsan_init - initialize KCSAN runtime + */ +void kcsan_init(void); + +/** + * kcsan_disable_current - disable KCSAN for the current context + * + * Supports nesting. + */ +void kcsan_disable_current(void); + +/** + * kcsan_enable_current - re-enable KCSAN for the current context + * + * Supports nesting. + */ +void kcsan_enable_current(void); + +/** + * kcsan_nestable_atomic_begin - begin nestable atomic region + * + * Accesses within the atomic region may appear to race with other accesses but + * should be considered atomic. + */ +void kcsan_nestable_atomic_begin(void); + +/** + * kcsan_nestable_atomic_end - end nestable atomic region + */ +void kcsan_nestable_atomic_end(void); + +/** + * kcsan_flat_atomic_begin - begin flat atomic region + * + * Accesses within the atomic region may appear to race with other accesses but + * should be considered atomic. + */ +void kcsan_flat_atomic_begin(void); + +/** + * kcsan_flat_atomic_end - end flat atomic region + */ +void kcsan_flat_atomic_end(void); + +/** + * kcsan_atomic_next - consider following accesses as atomic + * + * Force treating the next n memory accesses for the current context as atomic + * operations. + * + * @n number of following memory accesses to treat as atomic. + */ +void kcsan_atomic_next(int n); + +#else /* CONFIG_KCSAN */ + +static inline void kcsan_init(void) { } + +static inline void kcsan_disable_current(void) { } + +static inline void kcsan_enable_current(void) { } + +static inline void kcsan_nestable_atomic_begin(void) { } + +static inline void kcsan_nestable_atomic_end(void) { } + +static inline void kcsan_flat_atomic_begin(void) { } + +static inline void kcsan_flat_atomic_end(void) { } + +static inline void kcsan_atomic_next(int n) { } + +#endif /* CONFIG_KCSAN */ + +#endif /* _LINUX_KCSAN_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 67a1d86981a9..ae4f341c1db4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -31,6 +31,7 @@ #include #include #include +#include /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; @@ -1172,6 +1173,9 @@ struct task_struct { #ifdef CONFIG_KASAN unsigned int kasan_depth; #endif +#ifdef CONFIG_KCSAN + struct kcsan_ctx kcsan_ctx; +#endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ -- cgit v1.2.3 From c48981eeb0d56e107691df590007d6699441a689 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 14 Nov 2019 19:02:55 +0100 Subject: include/linux/compiler.h: Introduce data_race(expr) macro This introduces the data_race(expr) macro, which can be used to annotate expressions for purposes of (1) documenting, and (2) giving tooling such as KCSAN information about which data races are deemed "safe". More context: http://lkml.kernel.org/r/CAHk-=wg5CkOEF8DTez1Qu0XTEFw_oHhxN98bDnFqbY7HL5AB2g@mail.gmail.com Signed-off-by: Marco Elver Cc: Alan Stern Cc: Eric Dumazet Cc: Linus Torvalds Cc: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/compiler.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c42fa83f23fb..7d3e77781578 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -310,6 +310,26 @@ unsigned long read_word_at_a_time(const void *addr) __u.__val; \ }) +#include + +/* + * data_race: macro to document that accesses in an expression may conflict with + * other concurrent accesses resulting in data races, but the resulting + * behaviour is deemed safe regardless. + * + * This macro *does not* affect normal code generation, but is a hint to tooling + * that data races here should be ignored. + */ +#define data_race(expr) \ + ({ \ + typeof(({ expr; })) __val; \ + kcsan_nestable_atomic_begin(); \ + __val = ({ expr; }); \ + kcsan_nestable_atomic_end(); \ + __val; \ + }) +#else + #endif /* __KERNEL__ */ /* -- cgit v1.2.3 From 88ecd153be9519f259b87a9f6f4c8383a8b3bbf1 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 14 Nov 2019 19:02:59 +0100 Subject: seqlock, kcsan: Add annotations for KCSAN Since seqlocks in the Linux kernel do not require the use of marked atomic accesses in critical sections, we teach KCSAN to assume such accesses are atomic. KCSAN currently also pretends that writes to `sequence` are atomic, although currently plain writes are used (their corresponding reads are READ_ONCE). Further, to avoid false positives in the absence of clear ending of a seqlock reader critical section (only when using the raw interface), KCSAN assumes a fixed number of accesses after start of a seqlock critical section are atomic. === Commentary on design around absence of clear begin/end markings === Seqlock usage via seqlock_t follows a predictable usage pattern, where clear critical section begin/end is enforced. With subtle special cases for readers needing to be flat atomic regions, e.g. because usage such as in: - fs/namespace.c:__legitimize_mnt - unbalanced read_seqretry - fs/dcache.c:d_walk - unbalanced need_seqretry But, anything directly accessing seqcount_t seems to be unpredictable. Filtering for usage of read_seqcount_retry not following 'do { .. } while (read_seqcount_retry(..));': $ git grep 'read_seqcount_retry' | grep -Ev 'while \(|seqlock.h|Doc|\* ' => about 1/3 of the total read_seqcount_retry usage. Just looking at fs/namei.c, we conclude that it is non-trivial to prescribe and migrate to an interface that would force clear begin/end seqlock markings for critical sections. As such, we concluded that the best design currently, is to simply ensure that KCSAN works well with the existing code. Signed-off-by: Marco Elver Acked-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/seqlock.h | 40 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 38 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index bcf4cf26b8c8..61232bc223fd 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -37,8 +37,24 @@ #include #include #include +#include #include +/* + * The seqlock interface does not prescribe a precise sequence of read + * begin/retry/end. For readers, typically there is a call to + * read_seqcount_begin() and read_seqcount_retry(), however, there are more + * esoteric cases which do not follow this pattern. + * + * As a consequence, we take the following best-effort approach for raw usage + * via seqcount_t under KCSAN: upon beginning a seq-reader critical section, + * pessimistically mark then next KCSAN_SEQLOCK_REGION_MAX memory accesses as + * atomics; if there is a matching read_seqcount_retry() call, no following + * memory operations are considered atomic. Usage of seqlocks via seqlock_t + * interface is not affected. + */ +#define KCSAN_SEQLOCK_REGION_MAX 1000 + /* * Version using sequence counter only. * This can be used when code has its own mutex protecting the @@ -115,6 +131,7 @@ repeat: cpu_relax(); goto repeat; } + kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); return ret; } @@ -131,6 +148,7 @@ static inline unsigned raw_read_seqcount(const seqcount_t *s) { unsigned ret = READ_ONCE(s->sequence); smp_rmb(); + kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); return ret; } @@ -183,6 +201,7 @@ static inline unsigned raw_seqcount_begin(const seqcount_t *s) { unsigned ret = READ_ONCE(s->sequence); smp_rmb(); + kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); return ret & ~1; } @@ -202,7 +221,8 @@ static inline unsigned raw_seqcount_begin(const seqcount_t *s) */ static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start) { - return unlikely(s->sequence != start); + kcsan_atomic_next(0); + return unlikely(READ_ONCE(s->sequence) != start); } /** @@ -225,6 +245,7 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) static inline void raw_write_seqcount_begin(seqcount_t *s) { + kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); } @@ -233,6 +254,7 @@ static inline void raw_write_seqcount_end(seqcount_t *s) { smp_wmb(); s->sequence++; + kcsan_nestable_atomic_end(); } /** @@ -271,9 +293,11 @@ static inline void raw_write_seqcount_end(seqcount_t *s) */ static inline void raw_write_seqcount_barrier(seqcount_t *s) { + kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); s->sequence++; + kcsan_nestable_atomic_end(); } static inline int raw_read_seqcount_latch(seqcount_t *s) @@ -398,7 +422,9 @@ static inline void write_seqcount_end(seqcount_t *s) static inline void write_seqcount_invalidate(seqcount_t *s) { smp_wmb(); + kcsan_nestable_atomic_begin(); s->sequence+=2; + kcsan_nestable_atomic_end(); } typedef struct { @@ -430,11 +456,21 @@ typedef struct { */ static inline unsigned read_seqbegin(const seqlock_t *sl) { - return read_seqcount_begin(&sl->seqcount); + unsigned ret = read_seqcount_begin(&sl->seqcount); + + kcsan_atomic_next(0); /* non-raw usage, assume closing read_seqretry */ + kcsan_flat_atomic_begin(); + return ret; } static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { + /* + * Assume not nested: read_seqretry may be called multiple times when + * completing read critical section. + */ + kcsan_flat_atomic_end(); + return read_seqcount_retry(&sl->seqcount, start); } -- cgit v1.2.3 From bf07132f96d426bcbf2098227fb680915cf44498 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 14 Nov 2019 19:03:00 +0100 Subject: seqlock: Require WRITE_ONCE surrounding raw_seqcount_barrier This patch proposes to require marked atomic accesses surrounding raw_write_seqcount_barrier. We reason that otherwise there is no way to guarantee propagation nor atomicity of writes before/after the barrier [1]. For example, consider the compiler tears stores either before or after the barrier; in this case, readers may observe a partial value, and because readers are unaware that writes are going on (writes are not in a seq-writer critical section), will complete the seq-reader critical section while having observed some partial state. [1] https://lwn.net/Articles/793253/ This came up when designing and implementing KCSAN, because KCSAN would flag these accesses as data-races. After careful analysis, our reasoning as above led us to conclude that the best thing to do is to propose an amendment to the raw_seqcount_barrier usage. Signed-off-by: Marco Elver Acked-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/seqlock.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 61232bc223fd..f52c91be8939 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -265,6 +265,13 @@ static inline void raw_write_seqcount_end(seqcount_t *s) * usual consistency guarantee. It is one wmb cheaper, because we can * collapse the two back-to-back wmb()s. * + * Note that, writes surrounding the barrier should be declared atomic (e.g. + * via WRITE_ONCE): a) to ensure the writes become visible to other threads + * atomically, avoiding compiler optimizations; b) to document which writes are + * meant to propagate to the reader critical section. This is necessary because + * neither writes before and after the barrier are enclosed in a seq-writer + * critical section that would ensure readers are aware of ongoing writes. + * * seqcount_t seq; * bool X = true, Y = false; * @@ -284,11 +291,11 @@ static inline void raw_write_seqcount_end(seqcount_t *s) * * void write(void) * { - * Y = true; + * WRITE_ONCE(Y, true); * * raw_write_seqcount_barrier(seq); * - * X = false; + * WRITE_ONCE(X, false); * } */ static inline void raw_write_seqcount_barrier(seqcount_t *s) -- cgit v1.2.3 From 5cbaefe9743bf14c9d3106db0cc19f8cb0a3ca22 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 20 Nov 2019 10:41:43 +0100 Subject: kcsan: Improve various small stylistic details Tidy up a few bits: - Fix typos and grammar, improve wording. - Remove spurious newlines that are col80 warning artifacts where the resulting line-break is worse than the disease it's curing. - Use core kernel coding style to improve readability and reduce spurious code pattern variations. - Use better vertical alignment for structure definitions and initialization sequences. - Misc other small details. No change in functionality intended. Cc: linux-kernel@vger.kernel.org Cc: Marco Elver Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Cc: Thomas Gleixner Cc: Paul E. McKenney Cc: Will Deacon Signed-off-by: Ingo Molnar --- include/linux/compiler-clang.h | 2 +- include/linux/compiler.h | 2 +- include/linux/kcsan-checks.h | 22 +++++++++------------- include/linux/kcsan.h | 23 ++++++++--------------- include/linux/seqlock.h | 8 ++++---- 5 files changed, 23 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index a213eb55e725..2cb42d8bdedc 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -16,7 +16,7 @@ #define KASAN_ABI_VERSION 5 #if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer) -/* emulate gcc's __SANITIZE_ADDRESS__ flag */ +/* Emulate GCC's __SANITIZE_ADDRESS__ flag */ #define __SANITIZE_ADDRESS__ #define __no_sanitize_address \ __attribute__((no_sanitize("address", "hwaddress"))) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 7d3e77781578..ad8c76144a3c 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -313,7 +313,7 @@ unsigned long read_word_at_a_time(const void *addr) #include /* - * data_race: macro to document that accesses in an expression may conflict with + * data_race(): macro to document that accesses in an expression may conflict with * other concurrent accesses resulting in data races, but the resulting * behaviour is deemed safe regardless. * diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index e78220661086..ef3ee233a3fa 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -8,17 +8,17 @@ /* * Access type modifiers. */ -#define KCSAN_ACCESS_WRITE 0x1 +#define KCSAN_ACCESS_WRITE 0x1 #define KCSAN_ACCESS_ATOMIC 0x2 /* - * __kcsan_*: Always calls into runtime when KCSAN is enabled. This may be used + * __kcsan_*: Always calls into the runtime when KCSAN is enabled. This may be used * even in compilation units that selectively disable KCSAN, but must use KCSAN - * to validate access to an address. Never use these in header files! + * to validate access to an address. Never use these in header files! */ #ifdef CONFIG_KCSAN /** - * __kcsan_check_access - check generic access for data race + * __kcsan_check_access - check generic access for data races * * @ptr address of access * @size size of access @@ -32,7 +32,7 @@ static inline void __kcsan_check_access(const volatile void *ptr, size_t size, #endif /* - * kcsan_*: Only calls into runtime when the particular compilation unit has + * kcsan_*: Only calls into the runtime when the particular compilation unit has * KCSAN instrumentation enabled. May be used in header files. */ #ifdef __SANITIZE_THREAD__ @@ -77,16 +77,12 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE) /* - * Check for atomic accesses: if atomic access are not ignored, this simply - * aliases to kcsan_check_access, otherwise becomes a no-op. + * Check for atomic accesses: if atomic accesses are not ignored, this simply + * aliases to kcsan_check_access(), otherwise becomes a no-op. */ #ifdef CONFIG_KCSAN_IGNORE_ATOMICS -#define kcsan_check_atomic_read(...) \ - do { \ - } while (0) -#define kcsan_check_atomic_write(...) \ - do { \ - } while (0) +#define kcsan_check_atomic_read(...) do { } while (0) +#define kcsan_check_atomic_write(...) do { } while (0) #else #define kcsan_check_atomic_read(ptr, size) \ kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC) diff --git a/include/linux/kcsan.h b/include/linux/kcsan.h index 9047048fee84..1019e3a2c689 100644 --- a/include/linux/kcsan.h +++ b/include/linux/kcsan.h @@ -94,21 +94,14 @@ void kcsan_atomic_next(int n); #else /* CONFIG_KCSAN */ -static inline void kcsan_init(void) { } - -static inline void kcsan_disable_current(void) { } - -static inline void kcsan_enable_current(void) { } - -static inline void kcsan_nestable_atomic_begin(void) { } - -static inline void kcsan_nestable_atomic_end(void) { } - -static inline void kcsan_flat_atomic_begin(void) { } - -static inline void kcsan_flat_atomic_end(void) { } - -static inline void kcsan_atomic_next(int n) { } +static inline void kcsan_init(void) { } +static inline void kcsan_disable_current(void) { } +static inline void kcsan_enable_current(void) { } +static inline void kcsan_nestable_atomic_begin(void) { } +static inline void kcsan_nestable_atomic_end(void) { } +static inline void kcsan_flat_atomic_begin(void) { } +static inline void kcsan_flat_atomic_end(void) { } +static inline void kcsan_atomic_next(int n) { } #endif /* CONFIG_KCSAN */ diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index f52c91be8939..f80d50cac199 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -48,7 +48,7 @@ * * As a consequence, we take the following best-effort approach for raw usage * via seqcount_t under KCSAN: upon beginning a seq-reader critical section, - * pessimistically mark then next KCSAN_SEQLOCK_REGION_MAX memory accesses as + * pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as * atomics; if there is a matching read_seqcount_retry() call, no following * memory operations are considered atomic. Usage of seqlocks via seqlock_t * interface is not affected. @@ -265,7 +265,7 @@ static inline void raw_write_seqcount_end(seqcount_t *s) * usual consistency guarantee. It is one wmb cheaper, because we can * collapse the two back-to-back wmb()s. * - * Note that, writes surrounding the barrier should be declared atomic (e.g. + * Note that writes surrounding the barrier should be declared atomic (e.g. * via WRITE_ONCE): a) to ensure the writes become visible to other threads * atomically, avoiding compiler optimizations; b) to document which writes are * meant to propagate to the reader critical section. This is necessary because @@ -465,7 +465,7 @@ static inline unsigned read_seqbegin(const seqlock_t *sl) { unsigned ret = read_seqcount_begin(&sl->seqcount); - kcsan_atomic_next(0); /* non-raw usage, assume closing read_seqretry */ + kcsan_atomic_next(0); /* non-raw usage, assume closing read_seqretry() */ kcsan_flat_atomic_begin(); return ret; } @@ -473,7 +473,7 @@ static inline unsigned read_seqbegin(const seqlock_t *sl) static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { /* - * Assume not nested: read_seqretry may be called multiple times when + * Assume not nested: read_seqretry() may be called multiple times when * completing read critical section. */ kcsan_flat_atomic_end(); -- cgit v1.2.3 From 944bc9cca7c392879fa2c3f911bbef7422707679 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 26 Nov 2019 15:04:05 +0100 Subject: asm-generic/atomic: Use __always_inline for fallback wrappers Use __always_inline for atomic fallback wrappers. When building for size (CC_OPTIMIZE_FOR_SIZE), some compilers appear to be less inclined to inline even relatively small static inline functions that are assumed to be inlinable such as atomic ops. This can cause problems, for example in UACCESS regions. While the fallback wrappers aren't pure wrappers, they are trivial nonetheless, and the function they wrap should determine the final inlining policy. For x86 tinyconfig we observe: - vmlinux baseline: 1315988 - vmlinux with patch: 1315928 (-60 bytes) Suggested-by: Mark Rutland Signed-off-by: Marco Elver Acked-by: Mark Rutland Signed-off-by: Paul E. McKenney --- include/linux/atomic-fallback.h | 340 ++++++++++++++++++++-------------------- 1 file changed, 171 insertions(+), 169 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic-fallback.h b/include/linux/atomic-fallback.h index a7d240e465c0..656b5489b673 100644 --- a/include/linux/atomic-fallback.h +++ b/include/linux/atomic-fallback.h @@ -6,6 +6,8 @@ #ifndef _LINUX_ATOMIC_FALLBACK_H #define _LINUX_ATOMIC_FALLBACK_H +#include + #ifndef xchg_relaxed #define xchg_relaxed xchg #define xchg_acquire xchg @@ -76,7 +78,7 @@ #endif /* cmpxchg64_relaxed */ #ifndef atomic_read_acquire -static inline int +static __always_inline int atomic_read_acquire(const atomic_t *v) { return smp_load_acquire(&(v)->counter); @@ -85,7 +87,7 @@ atomic_read_acquire(const atomic_t *v) #endif #ifndef atomic_set_release -static inline void +static __always_inline void atomic_set_release(atomic_t *v, int i) { smp_store_release(&(v)->counter, i); @@ -100,7 +102,7 @@ atomic_set_release(atomic_t *v, int i) #else /* atomic_add_return_relaxed */ #ifndef atomic_add_return_acquire -static inline int +static __always_inline int atomic_add_return_acquire(int i, atomic_t *v) { int ret = atomic_add_return_relaxed(i, v); @@ -111,7 +113,7 @@ atomic_add_return_acquire(int i, atomic_t *v) #endif #ifndef atomic_add_return_release -static inline int +static __always_inline int atomic_add_return_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -121,7 +123,7 @@ atomic_add_return_release(int i, atomic_t *v) #endif #ifndef atomic_add_return -static inline int +static __always_inline int atomic_add_return(int i, atomic_t *v) { int ret; @@ -142,7 +144,7 @@ atomic_add_return(int i, atomic_t *v) #else /* atomic_fetch_add_relaxed */ #ifndef atomic_fetch_add_acquire -static inline int +static __always_inline int atomic_fetch_add_acquire(int i, atomic_t *v) { int ret = atomic_fetch_add_relaxed(i, v); @@ -153,7 +155,7 @@ atomic_fetch_add_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_add_release -static inline int +static __always_inline int atomic_fetch_add_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -163,7 +165,7 @@ atomic_fetch_add_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_add -static inline int +static __always_inline int atomic_fetch_add(int i, atomic_t *v) { int ret; @@ -184,7 +186,7 @@ atomic_fetch_add(int i, atomic_t *v) #else /* atomic_sub_return_relaxed */ #ifndef atomic_sub_return_acquire -static inline int +static __always_inline int atomic_sub_return_acquire(int i, atomic_t *v) { int ret = atomic_sub_return_relaxed(i, v); @@ -195,7 +197,7 @@ atomic_sub_return_acquire(int i, atomic_t *v) #endif #ifndef atomic_sub_return_release -static inline int +static __always_inline int atomic_sub_return_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -205,7 +207,7 @@ atomic_sub_return_release(int i, atomic_t *v) #endif #ifndef atomic_sub_return -static inline int +static __always_inline int atomic_sub_return(int i, atomic_t *v) { int ret; @@ -226,7 +228,7 @@ atomic_sub_return(int i, atomic_t *v) #else /* atomic_fetch_sub_relaxed */ #ifndef atomic_fetch_sub_acquire -static inline int +static __always_inline int atomic_fetch_sub_acquire(int i, atomic_t *v) { int ret = atomic_fetch_sub_relaxed(i, v); @@ -237,7 +239,7 @@ atomic_fetch_sub_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_sub_release -static inline int +static __always_inline int atomic_fetch_sub_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -247,7 +249,7 @@ atomic_fetch_sub_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_sub -static inline int +static __always_inline int atomic_fetch_sub(int i, atomic_t *v) { int ret; @@ -262,7 +264,7 @@ atomic_fetch_sub(int i, atomic_t *v) #endif /* atomic_fetch_sub_relaxed */ #ifndef atomic_inc -static inline void +static __always_inline void atomic_inc(atomic_t *v) { atomic_add(1, v); @@ -278,7 +280,7 @@ atomic_inc(atomic_t *v) #endif /* atomic_inc_return */ #ifndef atomic_inc_return -static inline int +static __always_inline int atomic_inc_return(atomic_t *v) { return atomic_add_return(1, v); @@ -287,7 +289,7 @@ atomic_inc_return(atomic_t *v) #endif #ifndef atomic_inc_return_acquire -static inline int +static __always_inline int atomic_inc_return_acquire(atomic_t *v) { return atomic_add_return_acquire(1, v); @@ -296,7 +298,7 @@ atomic_inc_return_acquire(atomic_t *v) #endif #ifndef atomic_inc_return_release -static inline int +static __always_inline int atomic_inc_return_release(atomic_t *v) { return atomic_add_return_release(1, v); @@ -305,7 +307,7 @@ atomic_inc_return_release(atomic_t *v) #endif #ifndef atomic_inc_return_relaxed -static inline int +static __always_inline int atomic_inc_return_relaxed(atomic_t *v) { return atomic_add_return_relaxed(1, v); @@ -316,7 +318,7 @@ atomic_inc_return_relaxed(atomic_t *v) #else /* atomic_inc_return_relaxed */ #ifndef atomic_inc_return_acquire -static inline int +static __always_inline int atomic_inc_return_acquire(atomic_t *v) { int ret = atomic_inc_return_relaxed(v); @@ -327,7 +329,7 @@ atomic_inc_return_acquire(atomic_t *v) #endif #ifndef atomic_inc_return_release -static inline int +static __always_inline int atomic_inc_return_release(atomic_t *v) { __atomic_release_fence(); @@ -337,7 +339,7 @@ atomic_inc_return_release(atomic_t *v) #endif #ifndef atomic_inc_return -static inline int +static __always_inline int atomic_inc_return(atomic_t *v) { int ret; @@ -359,7 +361,7 @@ atomic_inc_return(atomic_t *v) #endif /* atomic_fetch_inc */ #ifndef atomic_fetch_inc -static inline int +static __always_inline int atomic_fetch_inc(atomic_t *v) { return atomic_fetch_add(1, v); @@ -368,7 +370,7 @@ atomic_fetch_inc(atomic_t *v) #endif #ifndef atomic_fetch_inc_acquire -static inline int +static __always_inline int atomic_fetch_inc_acquire(atomic_t *v) { return atomic_fetch_add_acquire(1, v); @@ -377,7 +379,7 @@ atomic_fetch_inc_acquire(atomic_t *v) #endif #ifndef atomic_fetch_inc_release -static inline int +static __always_inline int atomic_fetch_inc_release(atomic_t *v) { return atomic_fetch_add_release(1, v); @@ -386,7 +388,7 @@ atomic_fetch_inc_release(atomic_t *v) #endif #ifndef atomic_fetch_inc_relaxed -static inline int +static __always_inline int atomic_fetch_inc_relaxed(atomic_t *v) { return atomic_fetch_add_relaxed(1, v); @@ -397,7 +399,7 @@ atomic_fetch_inc_relaxed(atomic_t *v) #else /* atomic_fetch_inc_relaxed */ #ifndef atomic_fetch_inc_acquire -static inline int +static __always_inline int atomic_fetch_inc_acquire(atomic_t *v) { int ret = atomic_fetch_inc_relaxed(v); @@ -408,7 +410,7 @@ atomic_fetch_inc_acquire(atomic_t *v) #endif #ifndef atomic_fetch_inc_release -static inline int +static __always_inline int atomic_fetch_inc_release(atomic_t *v) { __atomic_release_fence(); @@ -418,7 +420,7 @@ atomic_fetch_inc_release(atomic_t *v) #endif #ifndef atomic_fetch_inc -static inline int +static __always_inline int atomic_fetch_inc(atomic_t *v) { int ret; @@ -433,7 +435,7 @@ atomic_fetch_inc(atomic_t *v) #endif /* atomic_fetch_inc_relaxed */ #ifndef atomic_dec -static inline void +static __always_inline void atomic_dec(atomic_t *v) { atomic_sub(1, v); @@ -449,7 +451,7 @@ atomic_dec(atomic_t *v) #endif /* atomic_dec_return */ #ifndef atomic_dec_return -static inline int +static __always_inline int atomic_dec_return(atomic_t *v) { return atomic_sub_return(1, v); @@ -458,7 +460,7 @@ atomic_dec_return(atomic_t *v) #endif #ifndef atomic_dec_return_acquire -static inline int +static __always_inline int atomic_dec_return_acquire(atomic_t *v) { return atomic_sub_return_acquire(1, v); @@ -467,7 +469,7 @@ atomic_dec_return_acquire(atomic_t *v) #endif #ifndef atomic_dec_return_release -static inline int +static __always_inline int atomic_dec_return_release(atomic_t *v) { return atomic_sub_return_release(1, v); @@ -476,7 +478,7 @@ atomic_dec_return_release(atomic_t *v) #endif #ifndef atomic_dec_return_relaxed -static inline int +static __always_inline int atomic_dec_return_relaxed(atomic_t *v) { return atomic_sub_return_relaxed(1, v); @@ -487,7 +489,7 @@ atomic_dec_return_relaxed(atomic_t *v) #else /* atomic_dec_return_relaxed */ #ifndef atomic_dec_return_acquire -static inline int +static __always_inline int atomic_dec_return_acquire(atomic_t *v) { int ret = atomic_dec_return_relaxed(v); @@ -498,7 +500,7 @@ atomic_dec_return_acquire(atomic_t *v) #endif #ifndef atomic_dec_return_release -static inline int +static __always_inline int atomic_dec_return_release(atomic_t *v) { __atomic_release_fence(); @@ -508,7 +510,7 @@ atomic_dec_return_release(atomic_t *v) #endif #ifndef atomic_dec_return -static inline int +static __always_inline int atomic_dec_return(atomic_t *v) { int ret; @@ -530,7 +532,7 @@ atomic_dec_return(atomic_t *v) #endif /* atomic_fetch_dec */ #ifndef atomic_fetch_dec -static inline int +static __always_inline int atomic_fetch_dec(atomic_t *v) { return atomic_fetch_sub(1, v); @@ -539,7 +541,7 @@ atomic_fetch_dec(atomic_t *v) #endif #ifndef atomic_fetch_dec_acquire -static inline int +static __always_inline int atomic_fetch_dec_acquire(atomic_t *v) { return atomic_fetch_sub_acquire(1, v); @@ -548,7 +550,7 @@ atomic_fetch_dec_acquire(atomic_t *v) #endif #ifndef atomic_fetch_dec_release -static inline int +static __always_inline int atomic_fetch_dec_release(atomic_t *v) { return atomic_fetch_sub_release(1, v); @@ -557,7 +559,7 @@ atomic_fetch_dec_release(atomic_t *v) #endif #ifndef atomic_fetch_dec_relaxed -static inline int +static __always_inline int atomic_fetch_dec_relaxed(atomic_t *v) { return atomic_fetch_sub_relaxed(1, v); @@ -568,7 +570,7 @@ atomic_fetch_dec_relaxed(atomic_t *v) #else /* atomic_fetch_dec_relaxed */ #ifndef atomic_fetch_dec_acquire -static inline int +static __always_inline int atomic_fetch_dec_acquire(atomic_t *v) { int ret = atomic_fetch_dec_relaxed(v); @@ -579,7 +581,7 @@ atomic_fetch_dec_acquire(atomic_t *v) #endif #ifndef atomic_fetch_dec_release -static inline int +static __always_inline int atomic_fetch_dec_release(atomic_t *v) { __atomic_release_fence(); @@ -589,7 +591,7 @@ atomic_fetch_dec_release(atomic_t *v) #endif #ifndef atomic_fetch_dec -static inline int +static __always_inline int atomic_fetch_dec(atomic_t *v) { int ret; @@ -610,7 +612,7 @@ atomic_fetch_dec(atomic_t *v) #else /* atomic_fetch_and_relaxed */ #ifndef atomic_fetch_and_acquire -static inline int +static __always_inline int atomic_fetch_and_acquire(int i, atomic_t *v) { int ret = atomic_fetch_and_relaxed(i, v); @@ -621,7 +623,7 @@ atomic_fetch_and_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_and_release -static inline int +static __always_inline int atomic_fetch_and_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -631,7 +633,7 @@ atomic_fetch_and_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_and -static inline int +static __always_inline int atomic_fetch_and(int i, atomic_t *v) { int ret; @@ -646,7 +648,7 @@ atomic_fetch_and(int i, atomic_t *v) #endif /* atomic_fetch_and_relaxed */ #ifndef atomic_andnot -static inline void +static __always_inline void atomic_andnot(int i, atomic_t *v) { atomic_and(~i, v); @@ -662,7 +664,7 @@ atomic_andnot(int i, atomic_t *v) #endif /* atomic_fetch_andnot */ #ifndef atomic_fetch_andnot -static inline int +static __always_inline int atomic_fetch_andnot(int i, atomic_t *v) { return atomic_fetch_and(~i, v); @@ -671,7 +673,7 @@ atomic_fetch_andnot(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot_acquire -static inline int +static __always_inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) { return atomic_fetch_and_acquire(~i, v); @@ -680,7 +682,7 @@ atomic_fetch_andnot_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot_release -static inline int +static __always_inline int atomic_fetch_andnot_release(int i, atomic_t *v) { return atomic_fetch_and_release(~i, v); @@ -689,7 +691,7 @@ atomic_fetch_andnot_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot_relaxed -static inline int +static __always_inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v) { return atomic_fetch_and_relaxed(~i, v); @@ -700,7 +702,7 @@ atomic_fetch_andnot_relaxed(int i, atomic_t *v) #else /* atomic_fetch_andnot_relaxed */ #ifndef atomic_fetch_andnot_acquire -static inline int +static __always_inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) { int ret = atomic_fetch_andnot_relaxed(i, v); @@ -711,7 +713,7 @@ atomic_fetch_andnot_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot_release -static inline int +static __always_inline int atomic_fetch_andnot_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -721,7 +723,7 @@ atomic_fetch_andnot_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot -static inline int +static __always_inline int atomic_fetch_andnot(int i, atomic_t *v) { int ret; @@ -742,7 +744,7 @@ atomic_fetch_andnot(int i, atomic_t *v) #else /* atomic_fetch_or_relaxed */ #ifndef atomic_fetch_or_acquire -static inline int +static __always_inline int atomic_fetch_or_acquire(int i, atomic_t *v) { int ret = atomic_fetch_or_relaxed(i, v); @@ -753,7 +755,7 @@ atomic_fetch_or_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_or_release -static inline int +static __always_inline int atomic_fetch_or_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -763,7 +765,7 @@ atomic_fetch_or_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_or -static inline int +static __always_inline int atomic_fetch_or(int i, atomic_t *v) { int ret; @@ -784,7 +786,7 @@ atomic_fetch_or(int i, atomic_t *v) #else /* atomic_fetch_xor_relaxed */ #ifndef atomic_fetch_xor_acquire -static inline int +static __always_inline int atomic_fetch_xor_acquire(int i, atomic_t *v) { int ret = atomic_fetch_xor_relaxed(i, v); @@ -795,7 +797,7 @@ atomic_fetch_xor_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_xor_release -static inline int +static __always_inline int atomic_fetch_xor_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -805,7 +807,7 @@ atomic_fetch_xor_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_xor -static inline int +static __always_inline int atomic_fetch_xor(int i, atomic_t *v) { int ret; @@ -826,7 +828,7 @@ atomic_fetch_xor(int i, atomic_t *v) #else /* atomic_xchg_relaxed */ #ifndef atomic_xchg_acquire -static inline int +static __always_inline int atomic_xchg_acquire(atomic_t *v, int i) { int ret = atomic_xchg_relaxed(v, i); @@ -837,7 +839,7 @@ atomic_xchg_acquire(atomic_t *v, int i) #endif #ifndef atomic_xchg_release -static inline int +static __always_inline int atomic_xchg_release(atomic_t *v, int i) { __atomic_release_fence(); @@ -847,7 +849,7 @@ atomic_xchg_release(atomic_t *v, int i) #endif #ifndef atomic_xchg -static inline int +static __always_inline int atomic_xchg(atomic_t *v, int i) { int ret; @@ -868,7 +870,7 @@ atomic_xchg(atomic_t *v, int i) #else /* atomic_cmpxchg_relaxed */ #ifndef atomic_cmpxchg_acquire -static inline int +static __always_inline int atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { int ret = atomic_cmpxchg_relaxed(v, old, new); @@ -879,7 +881,7 @@ atomic_cmpxchg_acquire(atomic_t *v, int old, int new) #endif #ifndef atomic_cmpxchg_release -static inline int +static __always_inline int atomic_cmpxchg_release(atomic_t *v, int old, int new) { __atomic_release_fence(); @@ -889,7 +891,7 @@ atomic_cmpxchg_release(atomic_t *v, int old, int new) #endif #ifndef atomic_cmpxchg -static inline int +static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; @@ -911,7 +913,7 @@ atomic_cmpxchg(atomic_t *v, int old, int new) #endif /* atomic_try_cmpxchg */ #ifndef atomic_try_cmpxchg -static inline bool +static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) { int r, o = *old; @@ -924,7 +926,7 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg_acquire -static inline bool +static __always_inline bool atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { int r, o = *old; @@ -937,7 +939,7 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg_release -static inline bool +static __always_inline bool atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { int r, o = *old; @@ -950,7 +952,7 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg_relaxed -static inline bool +static __always_inline bool atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { int r, o = *old; @@ -965,7 +967,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) #else /* atomic_try_cmpxchg_relaxed */ #ifndef atomic_try_cmpxchg_acquire -static inline bool +static __always_inline bool atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { bool ret = atomic_try_cmpxchg_relaxed(v, old, new); @@ -976,7 +978,7 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg_release -static inline bool +static __always_inline bool atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { __atomic_release_fence(); @@ -986,7 +988,7 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg -static inline bool +static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) { bool ret; @@ -1010,7 +1012,7 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) * true if the result is zero, or false for all * other cases. */ -static inline bool +static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { return atomic_sub_return(i, v) == 0; @@ -1027,7 +1029,7 @@ atomic_sub_and_test(int i, atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ -static inline bool +static __always_inline bool atomic_dec_and_test(atomic_t *v) { return atomic_dec_return(v) == 0; @@ -1044,7 +1046,7 @@ atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ -static inline bool +static __always_inline bool atomic_inc_and_test(atomic_t *v) { return atomic_inc_return(v) == 0; @@ -1062,7 +1064,7 @@ atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline bool +static __always_inline bool atomic_add_negative(int i, atomic_t *v) { return atomic_add_return(i, v) < 0; @@ -1080,7 +1082,7 @@ atomic_add_negative(int i, atomic_t *v) * Atomically adds @a to @v, so long as @v was not already @u. * Returns original value of @v */ -static inline int +static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c = atomic_read(v); @@ -1105,7 +1107,7 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u) * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ -static inline bool +static __always_inline bool atomic_add_unless(atomic_t *v, int a, int u) { return atomic_fetch_add_unless(v, a, u) != u; @@ -1121,7 +1123,7 @@ atomic_add_unless(atomic_t *v, int a, int u) * Atomically increments @v by 1, if @v is non-zero. * Returns true if the increment was done. */ -static inline bool +static __always_inline bool atomic_inc_not_zero(atomic_t *v) { return atomic_add_unless(v, 1, 0); @@ -1130,7 +1132,7 @@ atomic_inc_not_zero(atomic_t *v) #endif #ifndef atomic_inc_unless_negative -static inline bool +static __always_inline bool atomic_inc_unless_negative(atomic_t *v) { int c = atomic_read(v); @@ -1146,7 +1148,7 @@ atomic_inc_unless_negative(atomic_t *v) #endif #ifndef atomic_dec_unless_positive -static inline bool +static __always_inline bool atomic_dec_unless_positive(atomic_t *v) { int c = atomic_read(v); @@ -1162,7 +1164,7 @@ atomic_dec_unless_positive(atomic_t *v) #endif #ifndef atomic_dec_if_positive -static inline int +static __always_inline int atomic_dec_if_positive(atomic_t *v) { int dec, c = atomic_read(v); @@ -1186,7 +1188,7 @@ atomic_dec_if_positive(atomic_t *v) #endif #ifndef atomic64_read_acquire -static inline s64 +static __always_inline s64 atomic64_read_acquire(const atomic64_t *v) { return smp_load_acquire(&(v)->counter); @@ -1195,7 +1197,7 @@ atomic64_read_acquire(const atomic64_t *v) #endif #ifndef atomic64_set_release -static inline void +static __always_inline void atomic64_set_release(atomic64_t *v, s64 i) { smp_store_release(&(v)->counter, i); @@ -1210,7 +1212,7 @@ atomic64_set_release(atomic64_t *v, s64 i) #else /* atomic64_add_return_relaxed */ #ifndef atomic64_add_return_acquire -static inline s64 +static __always_inline s64 atomic64_add_return_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_add_return_relaxed(i, v); @@ -1221,7 +1223,7 @@ atomic64_add_return_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_add_return_release -static inline s64 +static __always_inline s64 atomic64_add_return_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1231,7 +1233,7 @@ atomic64_add_return_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_add_return -static inline s64 +static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v) { s64 ret; @@ -1252,7 +1254,7 @@ atomic64_add_return(s64 i, atomic64_t *v) #else /* atomic64_fetch_add_relaxed */ #ifndef atomic64_fetch_add_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_add_relaxed(i, v); @@ -1263,7 +1265,7 @@ atomic64_fetch_add_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_add_release -static inline s64 +static __always_inline s64 atomic64_fetch_add_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1273,7 +1275,7 @@ atomic64_fetch_add_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_add -static inline s64 +static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v) { s64 ret; @@ -1294,7 +1296,7 @@ atomic64_fetch_add(s64 i, atomic64_t *v) #else /* atomic64_sub_return_relaxed */ #ifndef atomic64_sub_return_acquire -static inline s64 +static __always_inline s64 atomic64_sub_return_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_sub_return_relaxed(i, v); @@ -1305,7 +1307,7 @@ atomic64_sub_return_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_sub_return_release -static inline s64 +static __always_inline s64 atomic64_sub_return_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1315,7 +1317,7 @@ atomic64_sub_return_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_sub_return -static inline s64 +static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v) { s64 ret; @@ -1336,7 +1338,7 @@ atomic64_sub_return(s64 i, atomic64_t *v) #else /* atomic64_fetch_sub_relaxed */ #ifndef atomic64_fetch_sub_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_sub_relaxed(i, v); @@ -1347,7 +1349,7 @@ atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_sub_release -static inline s64 +static __always_inline s64 atomic64_fetch_sub_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1357,7 +1359,7 @@ atomic64_fetch_sub_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_sub -static inline s64 +static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v) { s64 ret; @@ -1372,7 +1374,7 @@ atomic64_fetch_sub(s64 i, atomic64_t *v) #endif /* atomic64_fetch_sub_relaxed */ #ifndef atomic64_inc -static inline void +static __always_inline void atomic64_inc(atomic64_t *v) { atomic64_add(1, v); @@ -1388,7 +1390,7 @@ atomic64_inc(atomic64_t *v) #endif /* atomic64_inc_return */ #ifndef atomic64_inc_return -static inline s64 +static __always_inline s64 atomic64_inc_return(atomic64_t *v) { return atomic64_add_return(1, v); @@ -1397,7 +1399,7 @@ atomic64_inc_return(atomic64_t *v) #endif #ifndef atomic64_inc_return_acquire -static inline s64 +static __always_inline s64 atomic64_inc_return_acquire(atomic64_t *v) { return atomic64_add_return_acquire(1, v); @@ -1406,7 +1408,7 @@ atomic64_inc_return_acquire(atomic64_t *v) #endif #ifndef atomic64_inc_return_release -static inline s64 +static __always_inline s64 atomic64_inc_return_release(atomic64_t *v) { return atomic64_add_return_release(1, v); @@ -1415,7 +1417,7 @@ atomic64_inc_return_release(atomic64_t *v) #endif #ifndef atomic64_inc_return_relaxed -static inline s64 +static __always_inline s64 atomic64_inc_return_relaxed(atomic64_t *v) { return atomic64_add_return_relaxed(1, v); @@ -1426,7 +1428,7 @@ atomic64_inc_return_relaxed(atomic64_t *v) #else /* atomic64_inc_return_relaxed */ #ifndef atomic64_inc_return_acquire -static inline s64 +static __always_inline s64 atomic64_inc_return_acquire(atomic64_t *v) { s64 ret = atomic64_inc_return_relaxed(v); @@ -1437,7 +1439,7 @@ atomic64_inc_return_acquire(atomic64_t *v) #endif #ifndef atomic64_inc_return_release -static inline s64 +static __always_inline s64 atomic64_inc_return_release(atomic64_t *v) { __atomic_release_fence(); @@ -1447,7 +1449,7 @@ atomic64_inc_return_release(atomic64_t *v) #endif #ifndef atomic64_inc_return -static inline s64 +static __always_inline s64 atomic64_inc_return(atomic64_t *v) { s64 ret; @@ -1469,7 +1471,7 @@ atomic64_inc_return(atomic64_t *v) #endif /* atomic64_fetch_inc */ #ifndef atomic64_fetch_inc -static inline s64 +static __always_inline s64 atomic64_fetch_inc(atomic64_t *v) { return atomic64_fetch_add(1, v); @@ -1478,7 +1480,7 @@ atomic64_fetch_inc(atomic64_t *v) #endif #ifndef atomic64_fetch_inc_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_inc_acquire(atomic64_t *v) { return atomic64_fetch_add_acquire(1, v); @@ -1487,7 +1489,7 @@ atomic64_fetch_inc_acquire(atomic64_t *v) #endif #ifndef atomic64_fetch_inc_release -static inline s64 +static __always_inline s64 atomic64_fetch_inc_release(atomic64_t *v) { return atomic64_fetch_add_release(1, v); @@ -1496,7 +1498,7 @@ atomic64_fetch_inc_release(atomic64_t *v) #endif #ifndef atomic64_fetch_inc_relaxed -static inline s64 +static __always_inline s64 atomic64_fetch_inc_relaxed(atomic64_t *v) { return atomic64_fetch_add_relaxed(1, v); @@ -1507,7 +1509,7 @@ atomic64_fetch_inc_relaxed(atomic64_t *v) #else /* atomic64_fetch_inc_relaxed */ #ifndef atomic64_fetch_inc_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_inc_acquire(atomic64_t *v) { s64 ret = atomic64_fetch_inc_relaxed(v); @@ -1518,7 +1520,7 @@ atomic64_fetch_inc_acquire(atomic64_t *v) #endif #ifndef atomic64_fetch_inc_release -static inline s64 +static __always_inline s64 atomic64_fetch_inc_release(atomic64_t *v) { __atomic_release_fence(); @@ -1528,7 +1530,7 @@ atomic64_fetch_inc_release(atomic64_t *v) #endif #ifndef atomic64_fetch_inc -static inline s64 +static __always_inline s64 atomic64_fetch_inc(atomic64_t *v) { s64 ret; @@ -1543,7 +1545,7 @@ atomic64_fetch_inc(atomic64_t *v) #endif /* atomic64_fetch_inc_relaxed */ #ifndef atomic64_dec -static inline void +static __always_inline void atomic64_dec(atomic64_t *v) { atomic64_sub(1, v); @@ -1559,7 +1561,7 @@ atomic64_dec(atomic64_t *v) #endif /* atomic64_dec_return */ #ifndef atomic64_dec_return -static inline s64 +static __always_inline s64 atomic64_dec_return(atomic64_t *v) { return atomic64_sub_return(1, v); @@ -1568,7 +1570,7 @@ atomic64_dec_return(atomic64_t *v) #endif #ifndef atomic64_dec_return_acquire -static inline s64 +static __always_inline s64 atomic64_dec_return_acquire(atomic64_t *v) { return atomic64_sub_return_acquire(1, v); @@ -1577,7 +1579,7 @@ atomic64_dec_return_acquire(atomic64_t *v) #endif #ifndef atomic64_dec_return_release -static inline s64 +static __always_inline s64 atomic64_dec_return_release(atomic64_t *v) { return atomic64_sub_return_release(1, v); @@ -1586,7 +1588,7 @@ atomic64_dec_return_release(atomic64_t *v) #endif #ifndef atomic64_dec_return_relaxed -static inline s64 +static __always_inline s64 atomic64_dec_return_relaxed(atomic64_t *v) { return atomic64_sub_return_relaxed(1, v); @@ -1597,7 +1599,7 @@ atomic64_dec_return_relaxed(atomic64_t *v) #else /* atomic64_dec_return_relaxed */ #ifndef atomic64_dec_return_acquire -static inline s64 +static __always_inline s64 atomic64_dec_return_acquire(atomic64_t *v) { s64 ret = atomic64_dec_return_relaxed(v); @@ -1608,7 +1610,7 @@ atomic64_dec_return_acquire(atomic64_t *v) #endif #ifndef atomic64_dec_return_release -static inline s64 +static __always_inline s64 atomic64_dec_return_release(atomic64_t *v) { __atomic_release_fence(); @@ -1618,7 +1620,7 @@ atomic64_dec_return_release(atomic64_t *v) #endif #ifndef atomic64_dec_return -static inline s64 +static __always_inline s64 atomic64_dec_return(atomic64_t *v) { s64 ret; @@ -1640,7 +1642,7 @@ atomic64_dec_return(atomic64_t *v) #endif /* atomic64_fetch_dec */ #ifndef atomic64_fetch_dec -static inline s64 +static __always_inline s64 atomic64_fetch_dec(atomic64_t *v) { return atomic64_fetch_sub(1, v); @@ -1649,7 +1651,7 @@ atomic64_fetch_dec(atomic64_t *v) #endif #ifndef atomic64_fetch_dec_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_dec_acquire(atomic64_t *v) { return atomic64_fetch_sub_acquire(1, v); @@ -1658,7 +1660,7 @@ atomic64_fetch_dec_acquire(atomic64_t *v) #endif #ifndef atomic64_fetch_dec_release -static inline s64 +static __always_inline s64 atomic64_fetch_dec_release(atomic64_t *v) { return atomic64_fetch_sub_release(1, v); @@ -1667,7 +1669,7 @@ atomic64_fetch_dec_release(atomic64_t *v) #endif #ifndef atomic64_fetch_dec_relaxed -static inline s64 +static __always_inline s64 atomic64_fetch_dec_relaxed(atomic64_t *v) { return atomic64_fetch_sub_relaxed(1, v); @@ -1678,7 +1680,7 @@ atomic64_fetch_dec_relaxed(atomic64_t *v) #else /* atomic64_fetch_dec_relaxed */ #ifndef atomic64_fetch_dec_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_dec_acquire(atomic64_t *v) { s64 ret = atomic64_fetch_dec_relaxed(v); @@ -1689,7 +1691,7 @@ atomic64_fetch_dec_acquire(atomic64_t *v) #endif #ifndef atomic64_fetch_dec_release -static inline s64 +static __always_inline s64 atomic64_fetch_dec_release(atomic64_t *v) { __atomic_release_fence(); @@ -1699,7 +1701,7 @@ atomic64_fetch_dec_release(atomic64_t *v) #endif #ifndef atomic64_fetch_dec -static inline s64 +static __always_inline s64 atomic64_fetch_dec(atomic64_t *v) { s64 ret; @@ -1720,7 +1722,7 @@ atomic64_fetch_dec(atomic64_t *v) #else /* atomic64_fetch_and_relaxed */ #ifndef atomic64_fetch_and_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_and_relaxed(i, v); @@ -1731,7 +1733,7 @@ atomic64_fetch_and_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_and_release -static inline s64 +static __always_inline s64 atomic64_fetch_and_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1741,7 +1743,7 @@ atomic64_fetch_and_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_and -static inline s64 +static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v) { s64 ret; @@ -1756,7 +1758,7 @@ atomic64_fetch_and(s64 i, atomic64_t *v) #endif /* atomic64_fetch_and_relaxed */ #ifndef atomic64_andnot -static inline void +static __always_inline void atomic64_andnot(s64 i, atomic64_t *v) { atomic64_and(~i, v); @@ -1772,7 +1774,7 @@ atomic64_andnot(s64 i, atomic64_t *v) #endif /* atomic64_fetch_andnot */ #ifndef atomic64_fetch_andnot -static inline s64 +static __always_inline s64 atomic64_fetch_andnot(s64 i, atomic64_t *v) { return atomic64_fetch_and(~i, v); @@ -1781,7 +1783,7 @@ atomic64_fetch_andnot(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { return atomic64_fetch_and_acquire(~i, v); @@ -1790,7 +1792,7 @@ atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot_release -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { return atomic64_fetch_and_release(~i, v); @@ -1799,7 +1801,7 @@ atomic64_fetch_andnot_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot_relaxed -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { return atomic64_fetch_and_relaxed(~i, v); @@ -1810,7 +1812,7 @@ atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) #else /* atomic64_fetch_andnot_relaxed */ #ifndef atomic64_fetch_andnot_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_andnot_relaxed(i, v); @@ -1821,7 +1823,7 @@ atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot_release -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1831,7 +1833,7 @@ atomic64_fetch_andnot_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot -static inline s64 +static __always_inline s64 atomic64_fetch_andnot(s64 i, atomic64_t *v) { s64 ret; @@ -1852,7 +1854,7 @@ atomic64_fetch_andnot(s64 i, atomic64_t *v) #else /* atomic64_fetch_or_relaxed */ #ifndef atomic64_fetch_or_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_or_relaxed(i, v); @@ -1863,7 +1865,7 @@ atomic64_fetch_or_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_or_release -static inline s64 +static __always_inline s64 atomic64_fetch_or_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1873,7 +1875,7 @@ atomic64_fetch_or_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_or -static inline s64 +static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v) { s64 ret; @@ -1894,7 +1896,7 @@ atomic64_fetch_or(s64 i, atomic64_t *v) #else /* atomic64_fetch_xor_relaxed */ #ifndef atomic64_fetch_xor_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_xor_relaxed(i, v); @@ -1905,7 +1907,7 @@ atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_xor_release -static inline s64 +static __always_inline s64 atomic64_fetch_xor_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1915,7 +1917,7 @@ atomic64_fetch_xor_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_xor -static inline s64 +static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) { s64 ret; @@ -1936,7 +1938,7 @@ atomic64_fetch_xor(s64 i, atomic64_t *v) #else /* atomic64_xchg_relaxed */ #ifndef atomic64_xchg_acquire -static inline s64 +static __always_inline s64 atomic64_xchg_acquire(atomic64_t *v, s64 i) { s64 ret = atomic64_xchg_relaxed(v, i); @@ -1947,7 +1949,7 @@ atomic64_xchg_acquire(atomic64_t *v, s64 i) #endif #ifndef atomic64_xchg_release -static inline s64 +static __always_inline s64 atomic64_xchg_release(atomic64_t *v, s64 i) { __atomic_release_fence(); @@ -1957,7 +1959,7 @@ atomic64_xchg_release(atomic64_t *v, s64 i) #endif #ifndef atomic64_xchg -static inline s64 +static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 i) { s64 ret; @@ -1978,7 +1980,7 @@ atomic64_xchg(atomic64_t *v, s64 i) #else /* atomic64_cmpxchg_relaxed */ #ifndef atomic64_cmpxchg_acquire -static inline s64 +static __always_inline s64 atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { s64 ret = atomic64_cmpxchg_relaxed(v, old, new); @@ -1989,7 +1991,7 @@ atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) #endif #ifndef atomic64_cmpxchg_release -static inline s64 +static __always_inline s64 atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { __atomic_release_fence(); @@ -1999,7 +2001,7 @@ atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) #endif #ifndef atomic64_cmpxchg -static inline s64 +static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { s64 ret; @@ -2021,7 +2023,7 @@ atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) #endif /* atomic64_try_cmpxchg */ #ifndef atomic64_try_cmpxchg -static inline bool +static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; @@ -2034,7 +2036,7 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg_acquire -static inline bool +static __always_inline bool atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; @@ -2047,7 +2049,7 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg_release -static inline bool +static __always_inline bool atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; @@ -2060,7 +2062,7 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg_relaxed -static inline bool +static __always_inline bool atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; @@ -2075,7 +2077,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) #else /* atomic64_try_cmpxchg_relaxed */ #ifndef atomic64_try_cmpxchg_acquire -static inline bool +static __always_inline bool atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { bool ret = atomic64_try_cmpxchg_relaxed(v, old, new); @@ -2086,7 +2088,7 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg_release -static inline bool +static __always_inline bool atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { __atomic_release_fence(); @@ -2096,7 +2098,7 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg -static inline bool +static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { bool ret; @@ -2120,7 +2122,7 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) * true if the result is zero, or false for all * other cases. */ -static inline bool +static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) { return atomic64_sub_return(i, v) == 0; @@ -2137,7 +2139,7 @@ atomic64_sub_and_test(s64 i, atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ -static inline bool +static __always_inline bool atomic64_dec_and_test(atomic64_t *v) { return atomic64_dec_return(v) == 0; @@ -2154,7 +2156,7 @@ atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ -static inline bool +static __always_inline bool atomic64_inc_and_test(atomic64_t *v) { return atomic64_inc_return(v) == 0; @@ -2172,7 +2174,7 @@ atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline bool +static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) { return atomic64_add_return(i, v) < 0; @@ -2190,7 +2192,7 @@ atomic64_add_negative(s64 i, atomic64_t *v) * Atomically adds @a to @v, so long as @v was not already @u. * Returns original value of @v */ -static inline s64 +static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { s64 c = atomic64_read(v); @@ -2215,7 +2217,7 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ -static inline bool +static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { return atomic64_fetch_add_unless(v, a, u) != u; @@ -2231,7 +2233,7 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u) * Atomically increments @v by 1, if @v is non-zero. * Returns true if the increment was done. */ -static inline bool +static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { return atomic64_add_unless(v, 1, 0); @@ -2240,7 +2242,7 @@ atomic64_inc_not_zero(atomic64_t *v) #endif #ifndef atomic64_inc_unless_negative -static inline bool +static __always_inline bool atomic64_inc_unless_negative(atomic64_t *v) { s64 c = atomic64_read(v); @@ -2256,7 +2258,7 @@ atomic64_inc_unless_negative(atomic64_t *v) #endif #ifndef atomic64_dec_unless_positive -static inline bool +static __always_inline bool atomic64_dec_unless_positive(atomic64_t *v) { s64 c = atomic64_read(v); @@ -2272,7 +2274,7 @@ atomic64_dec_unless_positive(atomic64_t *v) #endif #ifndef atomic64_dec_if_positive -static inline s64 +static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { s64 dec, c = atomic64_read(v); @@ -2292,4 +2294,4 @@ atomic64_dec_if_positive(atomic64_t *v) #define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 25de4a2804d70f57e994fe3b419148658bb5378a +// baaf45f4c24ed88ceae58baca39d7fd80bb8101b -- cgit v1.2.3 From e33f9a169747880a008dd5e7b934fc592e91cd63 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 12 Dec 2019 01:07:09 +0100 Subject: kcsan: Add __no_kcsan function attribute Since the use of -fsanitize=thread is an implementation detail of KCSAN, the name __no_sanitize_thread could be misleading if used widely. Instead, we introduce the __no_kcsan attribute which is shorter and more accurate in the context of KCSAN. This matches the attribute name __no_kcsan_or_inline. The use of __kcsan_or_inline itself is still required for __always_inline functions to retain compatibility with older compilers. Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/compiler-gcc.h | 3 +-- include/linux/compiler.h | 7 +++++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 0eb2a1cc411d..cf294faec2f8 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -146,8 +146,7 @@ #endif #if defined(__SANITIZE_THREAD__) && __has_attribute(__no_sanitize_thread__) -#define __no_sanitize_thread \ - __attribute__((__noinline__)) __attribute__((no_sanitize_thread)) +#define __no_sanitize_thread __attribute__((no_sanitize_thread)) #else #define __no_sanitize_thread #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index ad8c76144a3c..8c0beb10c1dd 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -207,12 +207,15 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define __no_kasan_or_inline __always_inline #endif +#define __no_kcsan __no_sanitize_thread #ifdef __SANITIZE_THREAD__ /* * Rely on __SANITIZE_THREAD__ instead of CONFIG_KCSAN, to avoid not inlining in - * compilation units where instrumentation is disabled. + * compilation units where instrumentation is disabled. The attribute 'noinline' + * is required for older compilers, where implicit inlining of very small + * functions renders __no_sanitize_thread ineffective. */ -# define __no_kcsan_or_inline __no_sanitize_thread notrace __maybe_unused +# define __no_kcsan_or_inline __no_kcsan noinline notrace __maybe_unused # define __no_sanitize_or_inline __no_kcsan_or_inline #else # define __no_kcsan_or_inline __always_inline -- cgit v1.2.3 From 33225d7b0ac9903c5701bbede7dfdaeba74ad6c3 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 13 Feb 2020 10:51:33 +0100 Subject: printk: Correctly set CON_CONSDEV even when preferred console was not registered CON_CONSDEV flag was historically used to put/keep the preferred console first in console_drivers list. Where the preferred console is the last on the command line. The ordering is important only when opening /dev/console: + tty_kopen() + tty_lookup_driver() + console_device() The flag was originally an implementation detail. But it was later made accessible from userspace via /proc/consoles. It was used, for example, by the tool "showconsole" to show the real tty accessible via /dev/console, see https://github.com/bitstreamout/showconsole Now, the current code sets CON_CONSDEV only for the preferred console or when a fallback console is added. The flag is not set when the preferred console is defined on the command line but it is not registered from some reasons. Simple solution is to set CON_CONSDEV flag for the first registered console. It will work most of the time because: + Most real consoles have console->device defined. + Boot consoles are removed in printk_late_init(). + unregister_console() moves CON_CONSDEV flag to the next console. Clean solution would require checking con->device when the preferred console is registered and in unregister_console(). Conclusion: Use the simple solution for now. It is better than the current state and good enough. The clean solution is not worth it. It would complicate the already complicated code without too much gain. Instead the code would deserve a complete rewrite. Link: https://lore.kernel.org/r/20200213095133.23176-4-pmladek@suse.com Signed-off-by: Benjamin Herrenschmidt [pmladek@suse.com: Correct reasoning in the commit message, comment update.] Reviewed-by: Petr Mladek Reviewed-by: Sergey Senozhatsky Signed-off-by: Petr Mladek --- include/linux/console.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index d09951d5a94e..72141f71c014 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -135,7 +135,7 @@ static inline int con_debug_leave(void) */ #define CON_PRINTBUFFER (1) -#define CON_CONSDEV (2) /* Last on the command line */ +#define CON_CONSDEV (2) /* Preferred console, /dev/console */ #define CON_ENABLED (4) #define CON_BOOT (8) #define CON_ANYTIME (16) /* Safe to call when cpu is offline */ -- cgit v1.2.3 From db751e309ff05461a0c8e114b1238d7a69cc1f18 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:43 +0000 Subject: ELF: UAPI and Kconfig additions for ELF program properties Pull the basic ELF definitions relating to the NT_GNU_PROPERTY_TYPE_0 note from Yu-Cheng Yu's earlier x86 shstk series. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Signed-off-by: Yu-cheng Yu Reviewed-by: Catalin Marinas Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- include/linux/elf.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elf.h b/include/linux/elf.h index e3649b3e970e..f7b24c5fcfb6 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -2,6 +2,7 @@ #ifndef _LINUX_ELF_H #define _LINUX_ELF_H +#include #include #include @@ -56,4 +57,15 @@ static inline int elf_coredump_extra_notes_write(struct coredump_params *cprm) { extern int elf_coredump_extra_notes_size(void); extern int elf_coredump_extra_notes_write(struct coredump_params *cprm); #endif + +/* + * NT_GNU_PROPERTY_TYPE_0 header: + * Keep this internal until/unless there is an agreed UAPI definition. + * pr_type values (GNU_PROPERTY_*) are public and defined in the UAPI header. + */ +struct gnu_property { + u32 pr_type; + u32 pr_datasz; +}; + #endif /* _LINUX_ELF_H */ -- cgit v1.2.3 From 00e19ceec80b03a43f626f891fcc53e57919f1b3 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:44 +0000 Subject: ELF: Add ELF program property parsing support ELF program properties will be needed for detecting whether to enable optional architecture or ABI features for a new ELF process. For now, there are no generic properties that we care about, so do nothing unless CONFIG_ARCH_USE_GNU_PROPERTY=y. Otherwise, the presence of properties using the PT_PROGRAM_PROPERTY phdrs entry (if any), and notify each property to the arch code. For now, the added code is not used. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- include/linux/elf.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elf.h b/include/linux/elf.h index f7b24c5fcfb6..db5113479f5e 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -22,6 +22,9 @@ SET_PERSONALITY(ex) #endif +#define ELF32_GNU_PROPERTY_ALIGN 4 +#define ELF64_GNU_PROPERTY_ALIGN 8 + #if ELF_CLASS == ELFCLASS32 extern Elf32_Dyn _DYNAMIC []; @@ -32,6 +35,7 @@ extern Elf32_Dyn _DYNAMIC []; #define elf_addr_t Elf32_Off #define Elf_Half Elf32_Half #define Elf_Word Elf32_Word +#define ELF_GNU_PROPERTY_ALIGN ELF32_GNU_PROPERTY_ALIGN #else @@ -43,6 +47,7 @@ extern Elf64_Dyn _DYNAMIC []; #define elf_addr_t Elf64_Off #define Elf_Half Elf64_Half #define Elf_Word Elf64_Word +#define ELF_GNU_PROPERTY_ALIGN ELF64_GNU_PROPERTY_ALIGN #endif @@ -68,4 +73,18 @@ struct gnu_property { u32 pr_datasz; }; +struct arch_elf_state; + +#ifndef CONFIG_ARCH_USE_GNU_PROPERTY +static inline int arch_parse_elf_property(u32 type, const void *data, + size_t datasz, bool compat, + struct arch_elf_state *arch) +{ + return 0; +} +#else +extern int arch_parse_elf_property(u32 type, const void *data, size_t datasz, + bool compat, struct arch_elf_state *arch); +#endif + #endif /* _LINUX_ELF_H */ -- cgit v1.2.3 From 8ef8f360cf30be12382f89ff48a57fbbd9b31c14 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:45 +0000 Subject: arm64: Basic Branch Target Identification support This patch adds the bare minimum required to expose the ARMv8.5 Branch Target Identification feature to userspace. By itself, this does _not_ automatically enable BTI for any initial executable pages mapped by execve(). This will come later, but for now it should be possible to enable BTI manually on those pages by using mprotect() from within the target process. Other arches already using the generic mman.h are already using 0x10 for arch-specific prot flags, so we use that for PROT_BTI here. For consistency, signal handler entry points in BTI guarded pages are required to be annotated as such, just like any other function. This blocks a relatively minor attack vector, but comforming userspace will have the annotations anyway, so we may as well enforce them. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Catalin Marinas Signed-off-by: Catalin Marinas --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 52269e56c514..9e5fce1b2099 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -324,6 +324,9 @@ extern unsigned int kobjsize(const void *objp); #elif defined(CONFIG_SPARC64) # define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */ # define VM_ARCH_CLEAR VM_SPARC_ADI +#elif defined(CONFIG_ARM64) +# define VM_ARM64_BTI VM_ARCH_1 /* BTI guarded page, a.k.a. GP bit */ +# define VM_ARCH_CLEAR VM_ARM64_BTI #elif !defined(CONFIG_MMU) # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif -- cgit v1.2.3 From fe0f67660ee9c99408be5261ae045f8b41953b05 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 16 Mar 2020 16:50:46 +0000 Subject: elf: Allow arch to tweak initial mmap prot flags An arch may want to tweak the mmap prot flags for an ELFexecutable's initial mappings. For example, arm64 is going to need to add PROT_BTI for executable pages in an ELF process whose executable is marked as using Branch Target Identification (an ARMv8.5-A control flow integrity feature). So that this can be done in a generic way, add a hook arch_elf_adjust_prot() to modify the prot flags as desired: arches can select CONFIG_HAVE_ELF_PROT and implement their own backend where necessary. By default, leave the prot flags unchanged. Signed-off-by: Mark Brown Signed-off-by: Dave Martin Reviewed-by: Catalin Marinas Reviewed-by: Kees Cook Signed-off-by: Catalin Marinas --- include/linux/elf.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elf.h b/include/linux/elf.h index db5113479f5e..5d5b0321da0b 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -87,4 +87,16 @@ extern int arch_parse_elf_property(u32 type, const void *data, size_t datasz, bool compat, struct arch_elf_state *arch); #endif +#ifdef CONFIG_ARCH_HAVE_ELF_PROT +int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state, + bool has_interp, bool is_interp); +#else +static inline int arch_elf_adjust_prot(int prot, + const struct arch_elf_state *state, + bool has_interp, bool is_interp) +{ + return prot; +} +#endif + #endif /* _LINUX_ELF_H */ -- cgit v1.2.3 From 36e4d4dd4fc4f1d99e7966a460a2b12ce438abc2 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 21 Jan 2020 17:05:08 +0100 Subject: include/linux: Add instrumented.h infrastructure This adds instrumented.h, which provides generic wrappers for memory access instrumentation that the compiler cannot emit for various sanitizers. Currently this unifies KASAN and KCSAN instrumentation. In future this will also include KMSAN instrumentation. Note that, copy_{to,from}_user should use special instrumentation, since we should be able to instrument both source and destination memory accesses if both are kernel memory. The current patch only instruments the memory access where the address is always in kernel space, however, both may in fact be kernel addresses when a compat syscall passes an argument allocated in the kernel to a real syscall. In a future change, both KASAN and KCSAN should check both addresses in such cases, as well as KMSAN will make use of both addresses. [It made more sense to provide the completed function signature, rather than updating it and changing all locations again at a later time.] Suggested-by: Arnd Bergmann Signed-off-by: Marco Elver Acked-by: Alexander Potapenko Reviewed-by: Dmitry Vyukov Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- include/linux/instrumented.h | 109 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 109 insertions(+) create mode 100644 include/linux/instrumented.h (limited to 'include/linux') diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h new file mode 100644 index 000000000000..43e6ea591975 --- /dev/null +++ b/include/linux/instrumented.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * This header provides generic wrappers for memory access instrumentation that + * the compiler cannot emit for: KASAN, KCSAN. + */ +#ifndef _LINUX_INSTRUMENTED_H +#define _LINUX_INSTRUMENTED_H + +#include +#include +#include +#include + +/** + * instrument_read - instrument regular read access + * + * Instrument a regular read access. The instrumentation should be inserted + * before the actual read happens. + * + * @ptr address of access + * @size size of access + */ +static __always_inline void instrument_read(const volatile void *v, size_t size) +{ + kasan_check_read(v, size); + kcsan_check_read(v, size); +} + +/** + * instrument_write - instrument regular write access + * + * Instrument a regular write access. The instrumentation should be inserted + * before the actual write happens. + * + * @ptr address of access + * @size size of access + */ +static __always_inline void instrument_write(const volatile void *v, size_t size) +{ + kasan_check_write(v, size); + kcsan_check_write(v, size); +} + +/** + * instrument_atomic_read - instrument atomic read access + * + * Instrument an atomic read access. The instrumentation should be inserted + * before the actual read happens. + * + * @ptr address of access + * @size size of access + */ +static __always_inline void instrument_atomic_read(const volatile void *v, size_t size) +{ + kasan_check_read(v, size); + kcsan_check_atomic_read(v, size); +} + +/** + * instrument_atomic_write - instrument atomic write access + * + * Instrument an atomic write access. The instrumentation should be inserted + * before the actual write happens. + * + * @ptr address of access + * @size size of access + */ +static __always_inline void instrument_atomic_write(const volatile void *v, size_t size) +{ + kasan_check_write(v, size); + kcsan_check_atomic_write(v, size); +} + +/** + * instrument_copy_to_user - instrument reads of copy_to_user + * + * Instrument reads from kernel memory, that are due to copy_to_user (and + * variants). The instrumentation must be inserted before the accesses. + * + * @to destination address + * @from source address + * @n number of bytes to copy + */ +static __always_inline void +instrument_copy_to_user(void __user *to, const void *from, unsigned long n) +{ + kasan_check_read(from, n); + kcsan_check_read(from, n); +} + +/** + * instrument_copy_from_user - instrument writes of copy_from_user + * + * Instrument writes to kernel memory, that are due to copy_from_user (and + * variants). The instrumentation should be inserted before the accesses. + * + * @to destination address + * @from source address + * @n number of bytes to copy + */ +static __always_inline void +instrument_copy_from_user(const void *to, const void __user *from, unsigned long n) +{ + kasan_check_write(to, n); + kcsan_check_write(to, n); +} + +#endif /* _LINUX_INSTRUMENTED_H */ -- cgit v1.2.3 From 76d6f06c36a3b5cc402eeeb709613cb211fdaa8f Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 21 Jan 2020 17:05:12 +0100 Subject: copy_to_user, copy_from_user: Use generic instrumented.h This replaces the KASAN instrumentation with generic instrumentation, implicitly adding KCSAN instrumentation support. For KASAN no functional change is intended. Suggested-by: Arnd Bergmann Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- include/linux/uaccess.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 67f016010aad..8a215c5c1aed 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -2,9 +2,9 @@ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ +#include #include #include -#include #define uaccess_kernel() segment_eq(get_fs(), KERNEL_DS) @@ -58,7 +58,7 @@ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { - kasan_check_write(to, n); + instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); } @@ -67,7 +67,7 @@ static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { might_fault(); - kasan_check_write(to, n); + instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); } @@ -88,7 +88,7 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { - kasan_check_read(from, n); + instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } @@ -97,7 +97,7 @@ static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); - kasan_check_read(from, n); + instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } @@ -109,7 +109,7 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) unsigned long res = n; might_fault(); if (likely(access_ok(from, n))) { - kasan_check_write(to, n); + instrument_copy_from_user(to, from, n); res = raw_copy_from_user(to, from, n); } if (unlikely(res)) @@ -127,7 +127,7 @@ _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (access_ok(to, n)) { - kasan_check_read(from, n); + instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; -- cgit v1.2.3 From 7ad900d35b49af5a05f595d2274c32e69e01b055 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 3 Feb 2020 14:42:18 -0800 Subject: kcsan: Add docbook header for data_race() Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar Cc: Marco Elver Cc: Dmitry Vyukov --- include/linux/compiler.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 8c0beb10c1dd..c1bdf37571cb 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -315,13 +315,15 @@ unsigned long read_word_at_a_time(const void *addr) #include -/* - * data_race(): macro to document that accesses in an expression may conflict with - * other concurrent accesses resulting in data races, but the resulting - * behaviour is deemed safe regardless. +/** + * data_race - mark an expression as containing intentional data races + * + * This data_race() macro is useful for situations in which data races + * should be forgiven. One example is diagnostic code that accesses + * shared variables but is not a part of the core synchronization design. * - * This macro *does not* affect normal code generation, but is a hint to tooling - * that data races here should be ignored. + * This macro *does not* affect normal code generation, but is a hint + * to tooling that data races here are to be ignored. */ #define data_race(expr) \ ({ \ -- cgit v1.2.3 From d591ec3db75f9eadfa7976ff8796c674c0027715 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 6 Feb 2020 16:46:24 +0100 Subject: kcsan: Introduce KCSAN_ACCESS_ASSERT access type The KCSAN_ACCESS_ASSERT access type may be used to introduce dummy reads and writes to assert certain properties of concurrent code, where bugs could not be detected as normal data races. For example, a variable that is only meant to be written by a single CPU, but may be read (without locking) by other CPUs must still be marked properly to avoid data races. However, concurrent writes, regardless if WRITE_ONCE() or not, would be a bug. Using kcsan_check_access(&x, sizeof(x), KCSAN_ACCESS_ASSERT) would allow catching such bugs. To support KCSAN_ACCESS_ASSERT the following notable changes were made: * If an access is of type KCSAN_ASSERT_ACCESS, disable various filters that only apply to data races, so that all races that KCSAN observes are reported. * Bug reports that involve an ASSERT access type will be reported as "KCSAN: assert: race in ..." instead of "data-race"; this will help more easily distinguish them. * Update a few comments to just mention 'races' where we do not always mean pure data races. Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- include/linux/kcsan-checks.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index ef3ee233a3fa..5dcadc221026 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -6,10 +6,16 @@ #include /* - * Access type modifiers. + * ACCESS TYPE MODIFIERS + * + * : normal read access; + * WRITE : write access; + * ATOMIC: access is atomic; + * ASSERT: access is not a regular access, but an assertion; */ #define KCSAN_ACCESS_WRITE 0x1 #define KCSAN_ACCESS_ATOMIC 0x2 +#define KCSAN_ACCESS_ASSERT 0x4 /* * __kcsan_*: Always calls into the runtime when KCSAN is enabled. This may be used @@ -18,7 +24,7 @@ */ #ifdef CONFIG_KCSAN /** - * __kcsan_check_access - check generic access for data races + * __kcsan_check_access - check generic access for races * * @ptr address of access * @size size of access @@ -43,7 +49,7 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, #endif /** - * __kcsan_check_read - check regular read access for data races + * __kcsan_check_read - check regular read access for races * * @ptr address of access * @size size of access @@ -51,7 +57,7 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, #define __kcsan_check_read(ptr, size) __kcsan_check_access(ptr, size, 0) /** - * __kcsan_check_write - check regular write access for data races + * __kcsan_check_write - check regular write access for races * * @ptr address of access * @size size of access @@ -60,7 +66,7 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, __kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE) /** - * kcsan_check_read - check regular read access for data races + * kcsan_check_read - check regular read access for races * * @ptr address of access * @size size of access @@ -68,7 +74,7 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, #define kcsan_check_read(ptr, size) kcsan_check_access(ptr, size, 0) /** - * kcsan_check_write - check regular write access for data races + * kcsan_check_write - check regular write access for races * * @ptr address of access * @size size of access -- cgit v1.2.3 From f97f713dc25714ac13f3b5abdeffce2da3f6fe70 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 6 Feb 2020 16:46:25 +0100 Subject: kcsan: Introduce ASSERT_EXCLUSIVE_*() macros Introduces ASSERT_EXCLUSIVE_WRITER() and ASSERT_EXCLUSIVE_ACCESS(), which may be used to assert properties of synchronization logic, where violation cannot be detected as a normal data race. Examples of the reports that may be generated: ================================================================== BUG: KCSAN: assert: race in test_thread / test_thread write to 0xffffffffab3d1540 of 8 bytes by task 466 on cpu 2: test_thread+0x8d/0x111 debugfs_write.cold+0x32/0x44 ... assert no writes to 0xffffffffab3d1540 of 8 bytes by task 464 on cpu 0: test_thread+0xa3/0x111 debugfs_write.cold+0x32/0x44 ... ================================================================== ================================================================== BUG: KCSAN: assert: race in test_thread / test_thread assert no accesses to 0xffffffffab3d1540 of 8 bytes by task 465 on cpu 1: test_thread+0xb9/0x111 debugfs_write.cold+0x32/0x44 ... read to 0xffffffffab3d1540 of 8 bytes by task 464 on cpu 0: test_thread+0x77/0x111 debugfs_write.cold+0x32/0x44 ... ================================================================== Suggested-by: Paul E. McKenney Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- include/linux/kcsan-checks.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 5dcadc221026..cf6961794e9a 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -96,4 +96,44 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC | KCSAN_ACCESS_WRITE) #endif +/** + * ASSERT_EXCLUSIVE_WRITER - assert no other threads are writing @var + * + * Assert that there are no other threads writing @var; other readers are + * allowed. This assertion can be used to specify properties of concurrent code, + * where violation cannot be detected as a normal data race. + * + * For example, if a per-CPU variable is only meant to be written by a single + * CPU, but may be read from other CPUs; in this case, reads and writes must be + * marked properly, however, if an off-CPU WRITE_ONCE() races with the owning + * CPU's WRITE_ONCE(), would not constitute a data race but could be a harmful + * race condition. Using this macro allows specifying this property in the code + * and catch such bugs. + * + * @var variable to assert on + */ +#define ASSERT_EXCLUSIVE_WRITER(var) \ + __kcsan_check_access(&(var), sizeof(var), KCSAN_ACCESS_ASSERT) + +/** + * ASSERT_EXCLUSIVE_ACCESS - assert no other threads are accessing @var + * + * Assert that no other thread is accessing @var (no readers nor writers). This + * assertion can be used to specify properties of concurrent code, where + * violation cannot be detected as a normal data race. + * + * For example, in a reference-counting algorithm where exclusive access is + * expected after the refcount reaches 0. We can check that this property + * actually holds as follows: + * + * if (refcount_dec_and_test(&obj->refcnt)) { + * ASSERT_EXCLUSIVE_ACCESS(*obj); + * safely_dispose_of(obj); + * } + * + * @var variable to assert on + */ +#define ASSERT_EXCLUSIVE_ACCESS(var) \ + __kcsan_check_access(&(var), sizeof(var), KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT) + #endif /* _LINUX_KCSAN_CHECKS_H */ -- cgit v1.2.3 From f0f6928c2c4c19ab6171d4f468f542fac1888a8f Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 11 Feb 2020 17:04:19 +0100 Subject: kcsan: Move interfaces that affects checks to kcsan-checks.h This moves functions that affect state changing the behaviour of kcsan_check_access() to kcsan-checks.h. Since these are likely used with kcsan_check_access() it makes more sense to have them in kcsan-checks.h, to avoid including all of 'include/linux/kcsan.h'. No functional change intended. Acked-by: John Hubbard Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- include/linux/kcsan-checks.h | 48 ++++++++++++++++++++++++++++++++++++++++++-- include/linux/kcsan.h | 41 ------------------------------------- 2 files changed, 46 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index cf6961794e9a..8675411c8dbc 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -32,10 +32,54 @@ */ void __kcsan_check_access(const volatile void *ptr, size_t size, int type); -#else +/** + * kcsan_nestable_atomic_begin - begin nestable atomic region + * + * Accesses within the atomic region may appear to race with other accesses but + * should be considered atomic. + */ +void kcsan_nestable_atomic_begin(void); + +/** + * kcsan_nestable_atomic_end - end nestable atomic region + */ +void kcsan_nestable_atomic_end(void); + +/** + * kcsan_flat_atomic_begin - begin flat atomic region + * + * Accesses within the atomic region may appear to race with other accesses but + * should be considered atomic. + */ +void kcsan_flat_atomic_begin(void); + +/** + * kcsan_flat_atomic_end - end flat atomic region + */ +void kcsan_flat_atomic_end(void); + +/** + * kcsan_atomic_next - consider following accesses as atomic + * + * Force treating the next n memory accesses for the current context as atomic + * operations. + * + * @n number of following memory accesses to treat as atomic. + */ +void kcsan_atomic_next(int n); + +#else /* CONFIG_KCSAN */ + static inline void __kcsan_check_access(const volatile void *ptr, size_t size, int type) { } -#endif + +static inline void kcsan_nestable_atomic_begin(void) { } +static inline void kcsan_nestable_atomic_end(void) { } +static inline void kcsan_flat_atomic_begin(void) { } +static inline void kcsan_flat_atomic_end(void) { } +static inline void kcsan_atomic_next(int n) { } + +#endif /* CONFIG_KCSAN */ /* * kcsan_*: Only calls into the runtime when the particular compilation unit has diff --git a/include/linux/kcsan.h b/include/linux/kcsan.h index 1019e3a2c689..7a614ca558f6 100644 --- a/include/linux/kcsan.h +++ b/include/linux/kcsan.h @@ -56,52 +56,11 @@ void kcsan_disable_current(void); */ void kcsan_enable_current(void); -/** - * kcsan_nestable_atomic_begin - begin nestable atomic region - * - * Accesses within the atomic region may appear to race with other accesses but - * should be considered atomic. - */ -void kcsan_nestable_atomic_begin(void); - -/** - * kcsan_nestable_atomic_end - end nestable atomic region - */ -void kcsan_nestable_atomic_end(void); - -/** - * kcsan_flat_atomic_begin - begin flat atomic region - * - * Accesses within the atomic region may appear to race with other accesses but - * should be considered atomic. - */ -void kcsan_flat_atomic_begin(void); - -/** - * kcsan_flat_atomic_end - end flat atomic region - */ -void kcsan_flat_atomic_end(void); - -/** - * kcsan_atomic_next - consider following accesses as atomic - * - * Force treating the next n memory accesses for the current context as atomic - * operations. - * - * @n number of following memory accesses to treat as atomic. - */ -void kcsan_atomic_next(int n); - #else /* CONFIG_KCSAN */ static inline void kcsan_init(void) { } static inline void kcsan_disable_current(void) { } static inline void kcsan_enable_current(void) { } -static inline void kcsan_nestable_atomic_begin(void) { } -static inline void kcsan_nestable_atomic_end(void) { } -static inline void kcsan_flat_atomic_begin(void) { } -static inline void kcsan_flat_atomic_end(void) { } -static inline void kcsan_atomic_next(int n) { } #endif /* CONFIG_KCSAN */ -- cgit v1.2.3 From b968a08f242d51982e46041c506115b5e11a7570 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 11 Feb 2020 17:04:20 +0100 Subject: compiler.h, seqlock.h: Remove unnecessary kcsan.h includes No we longer have to include kcsan.h, since the required KCSAN interface for both compiler.h and seqlock.h are now provided by kcsan-checks.h. Acked-by: John Hubbard Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 2 -- include/linux/seqlock.h | 2 +- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c1bdf37571cb..f504edebd5d7 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -313,8 +313,6 @@ unsigned long read_word_at_a_time(const void *addr) __u.__val; \ }) -#include - /** * data_race - mark an expression as containing intentional data races * diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 239701cae376..8b97204f35a7 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -37,7 +37,7 @@ #include #include #include -#include +#include #include /* -- cgit v1.2.3 From 81af89e15862909881ff010a0adb67148487e88a Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 11 Feb 2020 17:04:22 +0100 Subject: kcsan: Add kcsan_set_access_mask() support When setting up an access mask with kcsan_set_access_mask(), KCSAN will only report races if concurrent changes to bits set in access_mask are observed. Conveying access_mask via a separate call avoids introducing overhead in the common-case fast-path. Acked-by: John Hubbard Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- include/linux/kcsan-checks.h | 11 +++++++++++ include/linux/kcsan.h | 5 +++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 8675411c8dbc..4ef5233ff3f0 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -68,6 +68,16 @@ void kcsan_flat_atomic_end(void); */ void kcsan_atomic_next(int n); +/** + * kcsan_set_access_mask - set access mask + * + * Set the access mask for all accesses for the current context if non-zero. + * Only value changes to bits set in the mask will be reported. + * + * @mask bitmask + */ +void kcsan_set_access_mask(unsigned long mask); + #else /* CONFIG_KCSAN */ static inline void __kcsan_check_access(const volatile void *ptr, size_t size, @@ -78,6 +88,7 @@ static inline void kcsan_nestable_atomic_end(void) { } static inline void kcsan_flat_atomic_begin(void) { } static inline void kcsan_flat_atomic_end(void) { } static inline void kcsan_atomic_next(int n) { } +static inline void kcsan_set_access_mask(unsigned long mask) { } #endif /* CONFIG_KCSAN */ diff --git a/include/linux/kcsan.h b/include/linux/kcsan.h index 7a614ca558f6..3b84606e1e67 100644 --- a/include/linux/kcsan.h +++ b/include/linux/kcsan.h @@ -35,6 +35,11 @@ struct kcsan_ctx { */ int atomic_nest_count; bool in_flat_atomic; + + /* + * Access mask for all accesses if non-zero. + */ + unsigned long access_mask; }; /** -- cgit v1.2.3 From 703b321501c95c658275fd76775282fe45989641 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 11 Feb 2020 17:04:23 +0100 Subject: kcsan: Introduce ASSERT_EXCLUSIVE_BITS(var, mask) This introduces ASSERT_EXCLUSIVE_BITS(var, mask). ASSERT_EXCLUSIVE_BITS(var, mask) will cause KCSAN to assume that the following access is safe w.r.t. data races (however, please see the docbook comment for disclaimer here). For more context on why this was considered necessary, please see: http://lkml.kernel.org/r/1580995070-25139-1-git-send-email-cai@lca.pw In particular, before this patch, data races between reads (that use @mask bits of an access that should not be modified concurrently) and writes (that change ~@mask bits not used by the readers) would have been annotated with "data_race()" (or "READ_ONCE()"). However, doing so would then hide real problems: we would no longer be able to detect harmful races between reads to @mask bits and writes to @mask bits. Therefore, by using ASSERT_EXCLUSIVE_BITS(var, mask), we accomplish: 1. Avoid proliferation of specific macros at the call sites: by including a single mask in the argument list, we can use the same macro in a wide variety of call sites, regardless of how and which bits in a field each call site actually accesses. 2. The existing code does not need to be modified (although READ_ONCE() may still be advisable if we cannot prove that the data race is always safe). 3. We catch bugs where the exclusive bits are modified concurrently. 4. We document properties of the current code. Acked-by: John Hubbard Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar Cc: David Hildenbrand Cc: Jan Kara Cc: Qian Cai --- include/linux/kcsan-checks.h | 69 ++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 63 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 4ef5233ff3f0..8f9f6e2191dc 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -152,9 +152,9 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, #endif /** - * ASSERT_EXCLUSIVE_WRITER - assert no other threads are writing @var + * ASSERT_EXCLUSIVE_WRITER - assert no concurrent writes to @var * - * Assert that there are no other threads writing @var; other readers are + * Assert that there are no concurrent writes to @var; other readers are * allowed. This assertion can be used to specify properties of concurrent code, * where violation cannot be detected as a normal data race. * @@ -171,11 +171,11 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, __kcsan_check_access(&(var), sizeof(var), KCSAN_ACCESS_ASSERT) /** - * ASSERT_EXCLUSIVE_ACCESS - assert no other threads are accessing @var + * ASSERT_EXCLUSIVE_ACCESS - assert no concurrent accesses to @var * - * Assert that no other thread is accessing @var (no readers nor writers). This - * assertion can be used to specify properties of concurrent code, where - * violation cannot be detected as a normal data race. + * Assert that there are no concurrent accesses to @var (no readers nor + * writers). This assertion can be used to specify properties of concurrent + * code, where violation cannot be detected as a normal data race. * * For example, in a reference-counting algorithm where exclusive access is * expected after the refcount reaches 0. We can check that this property @@ -191,4 +191,61 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, #define ASSERT_EXCLUSIVE_ACCESS(var) \ __kcsan_check_access(&(var), sizeof(var), KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT) +/** + * ASSERT_EXCLUSIVE_BITS - assert no concurrent writes to subset of bits in @var + * + * Bit-granular variant of ASSERT_EXCLUSIVE_WRITER(var). + * + * Assert that there are no concurrent writes to a subset of bits in @var; + * concurrent readers are permitted. This assertion captures more detailed + * bit-level properties, compared to the other (word granularity) assertions. + * Only the bits set in @mask are checked for concurrent modifications, while + * ignoring the remaining bits, i.e. concurrent writes (or reads) to ~@mask bits + * are ignored. + * + * Use this for variables, where some bits must not be modified concurrently, + * yet other bits are expected to be modified concurrently. + * + * For example, variables where, after initialization, some bits are read-only, + * but other bits may still be modified concurrently. A reader may wish to + * assert that this is true as follows: + * + * ASSERT_EXCLUSIVE_BITS(flags, READ_ONLY_MASK); + * foo = (READ_ONCE(flags) & READ_ONLY_MASK) >> READ_ONLY_SHIFT; + * + * Note: The access that immediately follows ASSERT_EXCLUSIVE_BITS() is + * assumed to access the masked bits only, and KCSAN optimistically assumes it + * is therefore safe, even in the presence of data races, and marking it with + * READ_ONCE() is optional from KCSAN's point-of-view. We caution, however, + * that it may still be advisable to do so, since we cannot reason about all + * compiler optimizations when it comes to bit manipulations (on the reader + * and writer side). If you are sure nothing can go wrong, we can write the + * above simply as: + * + * ASSERT_EXCLUSIVE_BITS(flags, READ_ONLY_MASK); + * foo = (flags & READ_ONLY_MASK) >> READ_ONLY_SHIFT; + * + * Another example, where this may be used, is when certain bits of @var may + * only be modified when holding the appropriate lock, but other bits may still + * be modified concurrently. Writers, where other bits may change concurrently, + * could use the assertion as follows: + * + * spin_lock(&foo_lock); + * ASSERT_EXCLUSIVE_BITS(flags, FOO_MASK); + * old_flags = READ_ONCE(flags); + * new_flags = (old_flags & ~FOO_MASK) | (new_foo << FOO_SHIFT); + * if (cmpxchg(&flags, old_flags, new_flags) != old_flags) { ... } + * spin_unlock(&foo_lock); + * + * @var variable to assert on + * @mask only check for modifications to bits set in @mask + */ +#define ASSERT_EXCLUSIVE_BITS(var, mask) \ + do { \ + kcsan_set_access_mask(mask); \ + __kcsan_check_access(&(var), sizeof(var), KCSAN_ACCESS_ASSERT);\ + kcsan_set_access_mask(0); \ + kcsan_atomic_next(1); \ + } while (0) + #endif /* _LINUX_KCSAN_CHECKS_H */ -- cgit v1.2.3 From 143324fd89eff7423c01eba79fc7044003a257e9 Mon Sep 17 00:00:00 2001 From: Rohit Sarkar Date: Wed, 18 Mar 2020 21:41:51 +0530 Subject: iio: core: Make mlock internal to the iio core "mlock" should ideally only be used by the iio core. The mlock implementation may change in the future which means that no driver should be explicitly using mlock. Signed-off-by: Rohit Sarkar Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index eed58ed2f368..e975020abaa6 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -492,7 +492,7 @@ struct iio_buffer_setup_ops { * @buffer: [DRIVER] any buffer present * @buffer_list: [INTERN] list of all buffers currently attached * @scan_bytes: [INTERN] num bytes captured to be fed to buffer demux - * @mlock: [DRIVER] lock used to prevent simultaneous device state + * @mlock: [INTERN] lock used to prevent simultaneous device state * changes * @available_scan_masks: [DRIVER] optional array of allowed bitmasks * @masklength: [INTERN] the length of the mask established from -- cgit v1.2.3 From 1443b8c9e712ef8914a2cab9ae7ce133229ed96c Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 5 Mar 2020 15:21:09 +0100 Subject: kcsan: Update API documentation in kcsan-checks.h Update the API documentation for ASSERT_EXCLUSIVE_* macros and make them generate readable documentation for the code examples. All @variable short summaries were missing ':', which was updated for the whole file. Tested with "make htmldocs". Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/kcsan-checks.h | 98 +++++++++++++++++++++++++++----------------- 1 file changed, 61 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 8f9f6e2191dc..3cd8bb03eb41 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -26,9 +26,9 @@ /** * __kcsan_check_access - check generic access for races * - * @ptr address of access - * @size size of access - * @type access type modifier + * @ptr: address of access + * @size: size of access + * @type: access type modifier */ void __kcsan_check_access(const volatile void *ptr, size_t size, int type); @@ -64,7 +64,7 @@ void kcsan_flat_atomic_end(void); * Force treating the next n memory accesses for the current context as atomic * operations. * - * @n number of following memory accesses to treat as atomic. + * @n: number of following memory accesses to treat as atomic. */ void kcsan_atomic_next(int n); @@ -74,7 +74,7 @@ void kcsan_atomic_next(int n); * Set the access mask for all accesses for the current context if non-zero. * Only value changes to bits set in the mask will be reported. * - * @mask bitmask + * @mask: bitmask */ void kcsan_set_access_mask(unsigned long mask); @@ -106,16 +106,16 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, /** * __kcsan_check_read - check regular read access for races * - * @ptr address of access - * @size size of access + * @ptr: address of access + * @size: size of access */ #define __kcsan_check_read(ptr, size) __kcsan_check_access(ptr, size, 0) /** * __kcsan_check_write - check regular write access for races * - * @ptr address of access - * @size size of access + * @ptr: address of access + * @size: size of access */ #define __kcsan_check_write(ptr, size) \ __kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE) @@ -123,16 +123,16 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, /** * kcsan_check_read - check regular read access for races * - * @ptr address of access - * @size size of access + * @ptr: address of access + * @size: size of access */ #define kcsan_check_read(ptr, size) kcsan_check_access(ptr, size, 0) /** * kcsan_check_write - check regular write access for races * - * @ptr address of access - * @size size of access + * @ptr: address of access + * @size: size of access */ #define kcsan_check_write(ptr, size) \ kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE) @@ -158,14 +158,26 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, * allowed. This assertion can be used to specify properties of concurrent code, * where violation cannot be detected as a normal data race. * - * For example, if a per-CPU variable is only meant to be written by a single - * CPU, but may be read from other CPUs; in this case, reads and writes must be - * marked properly, however, if an off-CPU WRITE_ONCE() races with the owning - * CPU's WRITE_ONCE(), would not constitute a data race but could be a harmful - * race condition. Using this macro allows specifying this property in the code - * and catch such bugs. + * For example, if we only have a single writer, but multiple concurrent + * readers, to avoid data races, all these accesses must be marked; even + * concurrent marked writes racing with the single writer are bugs. + * Unfortunately, due to being marked, they are no longer data races. For cases + * like these, we can use the macro as follows: * - * @var variable to assert on + * .. code-block:: c + * + * void writer(void) { + * spin_lock(&update_foo_lock); + * ASSERT_EXCLUSIVE_WRITER(shared_foo); + * WRITE_ONCE(shared_foo, ...); + * spin_unlock(&update_foo_lock); + * } + * void reader(void) { + * // update_foo_lock does not need to be held! + * ... = READ_ONCE(shared_foo); + * } + * + * @var: variable to assert on */ #define ASSERT_EXCLUSIVE_WRITER(var) \ __kcsan_check_access(&(var), sizeof(var), KCSAN_ACCESS_ASSERT) @@ -177,16 +189,22 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, * writers). This assertion can be used to specify properties of concurrent * code, where violation cannot be detected as a normal data race. * - * For example, in a reference-counting algorithm where exclusive access is - * expected after the refcount reaches 0. We can check that this property - * actually holds as follows: + * For example, where exclusive access is expected after determining no other + * users of an object are left, but the object is not actually freed. We can + * check that this property actually holds as follows: + * + * .. code-block:: c * * if (refcount_dec_and_test(&obj->refcnt)) { * ASSERT_EXCLUSIVE_ACCESS(*obj); - * safely_dispose_of(obj); + * do_some_cleanup(obj); + * release_for_reuse(obj); * } * - * @var variable to assert on + * Note: For cases where the object is freed, `KASAN `_ is a better + * fit to detect use-after-free bugs. + * + * @var: variable to assert on */ #define ASSERT_EXCLUSIVE_ACCESS(var) \ __kcsan_check_access(&(var), sizeof(var), KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT) @@ -200,7 +218,7 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, * concurrent readers are permitted. This assertion captures more detailed * bit-level properties, compared to the other (word granularity) assertions. * Only the bits set in @mask are checked for concurrent modifications, while - * ignoring the remaining bits, i.e. concurrent writes (or reads) to ~@mask bits + * ignoring the remaining bits, i.e. concurrent writes (or reads) to ~mask bits * are ignored. * * Use this for variables, where some bits must not be modified concurrently, @@ -210,17 +228,21 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, * but other bits may still be modified concurrently. A reader may wish to * assert that this is true as follows: * + * .. code-block:: c + * * ASSERT_EXCLUSIVE_BITS(flags, READ_ONLY_MASK); * foo = (READ_ONCE(flags) & READ_ONLY_MASK) >> READ_ONLY_SHIFT; * - * Note: The access that immediately follows ASSERT_EXCLUSIVE_BITS() is - * assumed to access the masked bits only, and KCSAN optimistically assumes it - * is therefore safe, even in the presence of data races, and marking it with - * READ_ONCE() is optional from KCSAN's point-of-view. We caution, however, - * that it may still be advisable to do so, since we cannot reason about all - * compiler optimizations when it comes to bit manipulations (on the reader - * and writer side). If you are sure nothing can go wrong, we can write the - * above simply as: + * Note: The access that immediately follows ASSERT_EXCLUSIVE_BITS() is assumed + * to access the masked bits only, and KCSAN optimistically assumes it is + * therefore safe, even in the presence of data races, and marking it with + * READ_ONCE() is optional from KCSAN's point-of-view. We caution, however, that + * it may still be advisable to do so, since we cannot reason about all compiler + * optimizations when it comes to bit manipulations (on the reader and writer + * side). If you are sure nothing can go wrong, we can write the above simply + * as: + * + * .. code-block:: c * * ASSERT_EXCLUSIVE_BITS(flags, READ_ONLY_MASK); * foo = (flags & READ_ONLY_MASK) >> READ_ONLY_SHIFT; @@ -230,15 +252,17 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, * be modified concurrently. Writers, where other bits may change concurrently, * could use the assertion as follows: * + * .. code-block:: c + * * spin_lock(&foo_lock); * ASSERT_EXCLUSIVE_BITS(flags, FOO_MASK); - * old_flags = READ_ONCE(flags); + * old_flags = flags; * new_flags = (old_flags & ~FOO_MASK) | (new_foo << FOO_SHIFT); * if (cmpxchg(&flags, old_flags, new_flags) != old_flags) { ... } * spin_unlock(&foo_lock); * - * @var variable to assert on - * @mask only check for modifications to bits set in @mask + * @var: variable to assert on + * @mask: only check for modifications to bits set in @mask */ #define ASSERT_EXCLUSIVE_BITS(var, mask) \ do { \ -- cgit v1.2.3 From 09606b5446c25b2c3b16c5bd2977eca730e3a570 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 22 Mar 2018 17:09:42 +0100 Subject: dma-buf: add peer2peer flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a peer2peer flag noting that the importer can deal with device resources which are not backed by pages. Signed-off-by: Christian König Acked-by: Daniel Vetter Acked-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/359286/ --- include/linux/dma-buf.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 1ade486fc2bb..82e0a4a64601 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -334,6 +334,14 @@ struct dma_buf { * Attachment operations implemented by the importer. */ struct dma_buf_attach_ops { + /** + * @allow_peer2peer: + * + * If this is set to true the importer must be able to handle peer + * resources without struct pages. + */ + bool allow_peer2peer; + /** * @move_notify * @@ -362,6 +370,7 @@ struct dma_buf_attach_ops { * @node: list of dma_buf_attachment, protected by dma_resv lock of the dmabuf. * @sgt: cached mapping. * @dir: direction of cached mapping. + * @peer2peer: true if the importer can handle peer resources without pages. * @priv: exporter specific attachment data. * @importer_ops: importer operations for this attachment, if provided * dma_buf_map/unmap_attachment() must be called with the dma_resv lock held. @@ -382,6 +391,7 @@ struct dma_buf_attachment { struct list_head node; struct sg_table *sgt; enum dma_data_direction dir; + bool peer2peer; const struct dma_buf_attach_ops *importer_ops; void *importer_priv; void *priv; -- cgit v1.2.3 From 2c758e301ed95aefde68f98584204811d55c9bb8 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 25 Mar 2020 18:31:22 +0100 Subject: soc / drm: mediatek: Move routing control to mmsys device Provide a mtk_mmsys_ddp_connect() and mtk_mmsys_disconnect() functions to replace mtk_ddp_add_comp_to_path() and mtk_ddp_remove_comp_from_path(). Those functions will allow DRM driver and others to control the data path routing. Signed-off-by: Enric Balletbo i Serra Reviewed-by: Matthias Brugger Reviewed-by: CK Hu Acked-by: CK Hu Tested-by: Anders Roxell Reviewed-by: Chun-Kuang Hu Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-mmsys.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/linux/soc/mediatek/mtk-mmsys.h (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h new file mode 100644 index 000000000000..7bab5d9a3d31 --- /dev/null +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2015 MediaTek Inc. + */ + +#ifndef __MTK_MMSYS_H +#define __MTK_MMSYS_H + +enum mtk_ddp_comp_id; +struct device; + +void mtk_mmsys_ddp_connect(struct device *dev, + enum mtk_ddp_comp_id cur, + enum mtk_ddp_comp_id next); + +void mtk_mmsys_ddp_disconnect(struct device *dev, + enum mtk_ddp_comp_id cur, + enum mtk_ddp_comp_id next); + +#endif /* __MTK_MMSYS_H */ -- cgit v1.2.3 From f454f4d1915b44cc3857148aac7a297a31591501 Mon Sep 17 00:00:00 2001 From: Maciej Grochowski Date: Thu, 9 Apr 2020 01:03:37 -0400 Subject: include/ntb: Fix typo in ntb_unregister_device description Signed-off-by: Maciej Grochowski Signed-off-by: Jon Mason --- include/linux/ntb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 8c13538aeffe..a07252f78770 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -478,7 +478,7 @@ void ntb_unregister_client(struct ntb_client *client); int ntb_register_device(struct ntb_dev *ntb); /** - * ntb_register_device() - unregister a ntb device + * ntb_unregister_device() - unregister a ntb device * @ntb: NTB device context. * * The device will be removed from the list of ntb devices. If the ntb device -- cgit v1.2.3 From 757a4cefde76697af2b2c284c8a320912b77e7e6 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 25 Mar 2020 17:41:56 +0100 Subject: kcsan: Add support for scoped accesses This adds support for scoped accesses, where the memory range is checked for the duration of the scope. The feature is implemented by inserting the relevant access information into a list of scoped accesses for the current execution context, which are then checked (until removed) on every call (through instrumentation) into the KCSAN runtime. An alternative, more complex, implementation could set up a watchpoint for the scoped access, and keep the watchpoint set up. This, however, would require first exposing a handle to the watchpoint, as well as dealing with cases such as accesses by the same thread while the watchpoint is still set up (and several more cases). It is also doubtful if this would provide any benefit, since the majority of delay where the watchpoint is set up is likely due to the injected delays by KCSAN. Therefore, the implementation in this patch is simpler and avoids hurting KCSAN's main use-case (normal data race detection); it also implicitly increases scoped-access race-detection-ability due to increased probability of setting up watchpoints by repeatedly calling __kcsan_check_access() throughout the scope of the access. The implementation required adding an additional conditional branch to the fast-path. However, the microbenchmark showed a *speedup* of ~5% on the fast-path. This appears to be due to subtly improved codegen by GCC from moving get_ctx() and associated load of preempt_count earlier. Suggested-by: Boqun Feng Suggested-by: Paul E. McKenney Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/kcsan-checks.h | 57 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/kcsan.h | 3 +++ 2 files changed, 60 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 3cd8bb03eb41..b24253d3a442 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -3,6 +3,8 @@ #ifndef _LINUX_KCSAN_CHECKS_H #define _LINUX_KCSAN_CHECKS_H +/* Note: Only include what is already included by compiler.h. */ +#include #include /* @@ -12,10 +14,12 @@ * WRITE : write access; * ATOMIC: access is atomic; * ASSERT: access is not a regular access, but an assertion; + * SCOPED: access is a scoped access; */ #define KCSAN_ACCESS_WRITE 0x1 #define KCSAN_ACCESS_ATOMIC 0x2 #define KCSAN_ACCESS_ASSERT 0x4 +#define KCSAN_ACCESS_SCOPED 0x8 /* * __kcsan_*: Always calls into the runtime when KCSAN is enabled. This may be used @@ -78,6 +82,52 @@ void kcsan_atomic_next(int n); */ void kcsan_set_access_mask(unsigned long mask); +/* Scoped access information. */ +struct kcsan_scoped_access { + struct list_head list; + const volatile void *ptr; + size_t size; + int type; +}; +/* + * Automatically call kcsan_end_scoped_access() when kcsan_scoped_access goes + * out of scope; relies on attribute "cleanup", which is supported by all + * compilers that support KCSAN. + */ +#define __kcsan_cleanup_scoped \ + __maybe_unused __attribute__((__cleanup__(kcsan_end_scoped_access))) + +/** + * kcsan_begin_scoped_access - begin scoped access + * + * Begin scoped access and initialize @sa, which will cause KCSAN to + * continuously check the memory range in the current thread until + * kcsan_end_scoped_access() is called for @sa. + * + * Scoped accesses are implemented by appending @sa to an internal list for the + * current execution context, and then checked on every call into the KCSAN + * runtime. + * + * @ptr: address of access + * @size: size of access + * @type: access type modifier + * @sa: struct kcsan_scoped_access to use for the scope of the access + */ +struct kcsan_scoped_access * +kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type, + struct kcsan_scoped_access *sa); + +/** + * kcsan_end_scoped_access - end scoped access + * + * End a scoped access, which will stop KCSAN checking the memory range. + * Requires that kcsan_begin_scoped_access() was previously called once for @sa. + * + * @sa: a previously initialized struct kcsan_scoped_access + */ +void kcsan_end_scoped_access(struct kcsan_scoped_access *sa); + + #else /* CONFIG_KCSAN */ static inline void __kcsan_check_access(const volatile void *ptr, size_t size, @@ -90,6 +140,13 @@ static inline void kcsan_flat_atomic_end(void) { } static inline void kcsan_atomic_next(int n) { } static inline void kcsan_set_access_mask(unsigned long mask) { } +struct kcsan_scoped_access { }; +#define __kcsan_cleanup_scoped __maybe_unused +static inline struct kcsan_scoped_access * +kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type, + struct kcsan_scoped_access *sa) { return sa; } +static inline void kcsan_end_scoped_access(struct kcsan_scoped_access *sa) { } + #endif /* CONFIG_KCSAN */ /* diff --git a/include/linux/kcsan.h b/include/linux/kcsan.h index 3b84606e1e67..17ae59e4b685 100644 --- a/include/linux/kcsan.h +++ b/include/linux/kcsan.h @@ -40,6 +40,9 @@ struct kcsan_ctx { * Access mask for all accesses if non-zero. */ unsigned long access_mask; + + /* List of scoped accesses. */ + struct list_head scoped_accesses; }; /** -- cgit v1.2.3 From d8949ef1d9f1062848cd068cf369a57ce33dae6f Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 25 Mar 2020 17:41:58 +0100 Subject: kcsan: Introduce scoped ASSERT_EXCLUSIVE macros Introduce ASSERT_EXCLUSIVE_*_SCOPED(), which provide an intuitive interface to use the scoped-access feature, without having to explicitly mark the start and end of the desired scope. Basing duration of the checks on scope avoids accidental misuse and resulting false positives, which may be hard to debug. See added comments for usage. The macros are implemented using __attribute__((__cleanup__(func))), which is supported by all compilers that currently support KCSAN. Suggested-by: Boqun Feng Suggested-by: Paul E. McKenney Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/kcsan-checks.h | 73 +++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 72 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index b24253d3a442..101df7f46d89 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -234,11 +234,63 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, * ... = READ_ONCE(shared_foo); * } * + * Note: ASSERT_EXCLUSIVE_WRITER_SCOPED(), if applicable, performs more thorough + * checking if a clear scope where no concurrent writes are expected exists. + * * @var: variable to assert on */ #define ASSERT_EXCLUSIVE_WRITER(var) \ __kcsan_check_access(&(var), sizeof(var), KCSAN_ACCESS_ASSERT) +/* + * Helper macros for implementation of for ASSERT_EXCLUSIVE_*_SCOPED(). @id is + * expected to be unique for the scope in which instances of kcsan_scoped_access + * are declared. + */ +#define __kcsan_scoped_name(c, suffix) __kcsan_scoped_##c##suffix +#define __ASSERT_EXCLUSIVE_SCOPED(var, type, id) \ + struct kcsan_scoped_access __kcsan_scoped_name(id, _) \ + __kcsan_cleanup_scoped; \ + struct kcsan_scoped_access *__kcsan_scoped_name(id, _dummy_p) \ + __maybe_unused = kcsan_begin_scoped_access( \ + &(var), sizeof(var), KCSAN_ACCESS_SCOPED | (type), \ + &__kcsan_scoped_name(id, _)) + +/** + * ASSERT_EXCLUSIVE_WRITER_SCOPED - assert no concurrent writes to @var in scope + * + * Scoped variant of ASSERT_EXCLUSIVE_WRITER(). + * + * Assert that there are no concurrent writes to @var for the duration of the + * scope in which it is introduced. This provides a better way to fully cover + * the enclosing scope, compared to multiple ASSERT_EXCLUSIVE_WRITER(), and + * increases the likelihood for KCSAN to detect racing accesses. + * + * For example, it allows finding race-condition bugs that only occur due to + * state changes within the scope itself: + * + * .. code-block:: c + * + * void writer(void) { + * spin_lock(&update_foo_lock); + * { + * ASSERT_EXCLUSIVE_WRITER_SCOPED(shared_foo); + * WRITE_ONCE(shared_foo, 42); + * ... + * // shared_foo should still be 42 here! + * } + * spin_unlock(&update_foo_lock); + * } + * void buggy(void) { + * if (READ_ONCE(shared_foo) == 42) + * WRITE_ONCE(shared_foo, 1); // bug! + * } + * + * @var: variable to assert on + */ +#define ASSERT_EXCLUSIVE_WRITER_SCOPED(var) \ + __ASSERT_EXCLUSIVE_SCOPED(var, KCSAN_ACCESS_ASSERT, __COUNTER__) + /** * ASSERT_EXCLUSIVE_ACCESS - assert no concurrent accesses to @var * @@ -258,6 +310,9 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, * release_for_reuse(obj); * } * + * Note: ASSERT_EXCLUSIVE_ACCESS_SCOPED(), if applicable, performs more thorough + * checking if a clear scope where no concurrent accesses are expected exists. + * * Note: For cases where the object is freed, `KASAN `_ is a better * fit to detect use-after-free bugs. * @@ -266,10 +321,26 @@ static inline void kcsan_check_access(const volatile void *ptr, size_t size, #define ASSERT_EXCLUSIVE_ACCESS(var) \ __kcsan_check_access(&(var), sizeof(var), KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT) +/** + * ASSERT_EXCLUSIVE_ACCESS_SCOPED - assert no concurrent accesses to @var in scope + * + * Scoped variant of ASSERT_EXCLUSIVE_ACCESS(). + * + * Assert that there are no concurrent accesses to @var (no readers nor writers) + * for the entire duration of the scope in which it is introduced. This provides + * a better way to fully cover the enclosing scope, compared to multiple + * ASSERT_EXCLUSIVE_ACCESS(), and increases the likelihood for KCSAN to detect + * racing accesses. + * + * @var: variable to assert on + */ +#define ASSERT_EXCLUSIVE_ACCESS_SCOPED(var) \ + __ASSERT_EXCLUSIVE_SCOPED(var, KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT, __COUNTER__) + /** * ASSERT_EXCLUSIVE_BITS - assert no concurrent writes to subset of bits in @var * - * Bit-granular variant of ASSERT_EXCLUSIVE_WRITER(var). + * Bit-granular variant of ASSERT_EXCLUSIVE_WRITER(). * * Assert that there are no concurrent writes to a subset of bits in @var; * concurrent readers are permitted. This assertion captures more detailed -- cgit v1.2.3 From 01b4ff58f72dbee926077d9afa0650f6e685e866 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 31 Mar 2020 21:32:32 +0200 Subject: kcsan: Move kcsan_{disable,enable}_current() to kcsan-checks.h Both affect access checks, and should therefore be in kcsan-checks.h. This is in preparation to use these in compiler.h. Acked-by: Will Deacon Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/kcsan-checks.h | 16 ++++++++++++++++ include/linux/kcsan.h | 16 ---------------- 2 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 101df7f46d89..ef95ddc49182 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -36,6 +36,20 @@ */ void __kcsan_check_access(const volatile void *ptr, size_t size, int type); +/** + * kcsan_disable_current - disable KCSAN for the current context + * + * Supports nesting. + */ +void kcsan_disable_current(void); + +/** + * kcsan_enable_current - re-enable KCSAN for the current context + * + * Supports nesting. + */ +void kcsan_enable_current(void); + /** * kcsan_nestable_atomic_begin - begin nestable atomic region * @@ -133,6 +147,8 @@ void kcsan_end_scoped_access(struct kcsan_scoped_access *sa); static inline void __kcsan_check_access(const volatile void *ptr, size_t size, int type) { } +static inline void kcsan_disable_current(void) { } +static inline void kcsan_enable_current(void) { } static inline void kcsan_nestable_atomic_begin(void) { } static inline void kcsan_nestable_atomic_end(void) { } static inline void kcsan_flat_atomic_begin(void) { } diff --git a/include/linux/kcsan.h b/include/linux/kcsan.h index 17ae59e4b685..53340d8789f9 100644 --- a/include/linux/kcsan.h +++ b/include/linux/kcsan.h @@ -50,25 +50,9 @@ struct kcsan_ctx { */ void kcsan_init(void); -/** - * kcsan_disable_current - disable KCSAN for the current context - * - * Supports nesting. - */ -void kcsan_disable_current(void); - -/** - * kcsan_enable_current - re-enable KCSAN for the current context - * - * Supports nesting. - */ -void kcsan_enable_current(void); - #else /* CONFIG_KCSAN */ static inline void kcsan_init(void) { } -static inline void kcsan_disable_current(void) { } -static inline void kcsan_enable_current(void) { } #endif /* CONFIG_KCSAN */ -- cgit v1.2.3 From d071e91361bbfef524ae8abf7e560fb294d0ad64 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 31 Mar 2020 21:32:33 +0200 Subject: kcsan: Change data_race() to no longer require marking racing accesses Thus far, accesses marked with data_race() would still require the racing access to be marked in some way (be it with READ_ONCE(), WRITE_ONCE(), or data_race() itself), as otherwise KCSAN would still report a data race. This requirement, however, seems to be unintuitive, and some valid use-cases demand *not* marking other accesses, as it might hide more serious bugs (e.g. diagnostic reads). Therefore, this commit changes data_race() to no longer require marking racing accesses (although it's still recommended if possible). The alternative would have been introducing another variant of data_race(), however, since usage of data_race() already needs to be carefully reasoned about, distinguishing between these cases likely adds more complexity in the wrong place. Link: https://lkml.kernel.org/r/20200331131002.GA30975@willie-the-truck Cc: Paul E. McKenney Cc: Will Deacon Cc: Qian Cai Acked-by: Will Deacon Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/compiler.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index f504edebd5d7..1729bd17e9b7 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -326,9 +326,9 @@ unsigned long read_word_at_a_time(const void *addr) #define data_race(expr) \ ({ \ typeof(({ expr; })) __val; \ - kcsan_nestable_atomic_begin(); \ + kcsan_disable_current(); \ __val = ({ expr; }); \ - kcsan_nestable_atomic_end(); \ + kcsan_enable_current(); \ __val; \ }) #else -- cgit v1.2.3 From 70771c69ab9be6e37618b1ec6c105f370e510f94 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 3 Apr 2020 18:10:17 +0100 Subject: firmware: arm_scmi: Add include guard to linux/scmi_protocol.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If this header is include twice, it will generate loads of compile time error with the following below error pattern. It was reported by 0day kbuild robot on a branch pushed with double inclusion by accident. error: conflicting types for ‘...’ note: previous declaration of ‘...’ was here error: redefinition of ‘...’ Add a header include guard just in case. Link: https://lore.kernel.org/r/20200403171018.1230-1-sudeep.holla@arm.com Reported-by: kbuild test robot Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 5c873a59b387..ce2f5c28b2df 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -4,6 +4,10 @@ * * Copyright (C) 2018 ARM Ltd. */ + +#ifndef _LINUX_SCMI_PROTOCOL_H +#define _LINUX_SCMI_PROTOCOL_H + #include #include @@ -319,3 +323,5 @@ static inline void scmi_driver_unregister(struct scmi_driver *driver) {} typedef int (*scmi_prot_init_fn_t)(struct scmi_handle *); int scmi_protocol_register(int protocol_id, scmi_prot_init_fn_t fn); void scmi_protocol_unregister(int protocol_id); + +#endif /* _LINUX_SCMI_PROTOCOL_H */ -- cgit v1.2.3 From 23818b3d8590a79d56af9659cf709ebfae30f832 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 3 Apr 2020 18:10:18 +0100 Subject: firmware: arm_scpi: Add include guard to linux/scpi_protocol.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If this header is include twice, it will generate loads of compile time error with the following below error pattern. It was reported by 0day kbuild robot on a branch pushed with double inclusion by accident. This is based on the similar change in linux/scmi_protocol.h error: conflicting types for ‘...’ note: previous declaration of ‘...’ was here error: redefinition of ‘...’ Add a header include guard just in case. Link: https://lore.kernel.org/r/20200403171018.1230-2-sudeep.holla@arm.com Reported-by: kbuild test robot Signed-off-by: Sudeep Holla --- include/linux/scpi_protocol.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h index ecb004711acf..afbf8037d8db 100644 --- a/include/linux/scpi_protocol.h +++ b/include/linux/scpi_protocol.h @@ -4,6 +4,10 @@ * * Copyright (C) 2014 ARM Ltd. */ + +#ifndef _LINUX_SCPI_PROTOCOL_H +#define _LINUX_SCPI_PROTOCOL_H + #include struct scpi_opp { @@ -71,3 +75,5 @@ struct scpi_ops *get_scpi_ops(void); #else static inline struct scpi_ops *get_scpi_ops(void) { return NULL; } #endif + +#endif /* _LINUX_SCPI_PROTOCOL_H */ -- cgit v1.2.3 From bceb5646a15dad49ceb29ec16b8acc10075d0627 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 31 Mar 2020 18:54:48 +0200 Subject: thermal: core: Make thermal_zone_set_trips private The function thermal_zone_set_trips() is used by the thermal core code in order to update the next trip points, there are no other users. Move the function definition in the thermal_core.h, remove the EXPORT_SYMBOL_GPL and document the function. Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Reviewed-by: Amit Kucheria Link: https://lore.kernel.org/r/20200331165449.30355-1-daniel.lezcano@linaro.org --- include/linux/thermal.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index c91b1e344d56..448841ab0dca 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -439,7 +439,6 @@ int thermal_zone_unbind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *); void thermal_zone_device_update(struct thermal_zone_device *, enum thermal_notify_event); -void thermal_zone_set_trips(struct thermal_zone_device *); struct thermal_cooling_device *thermal_cooling_device_register(const char *, void *, const struct thermal_cooling_device_ops *); @@ -497,8 +496,6 @@ static inline int thermal_zone_unbind_cooling_device( static inline void thermal_zone_device_update(struct thermal_zone_device *tz, enum thermal_notify_event event) { } -static inline void thermal_zone_set_trips(struct thermal_zone_device *tz) -{ } static inline struct thermal_cooling_device * thermal_cooling_device_register(char *type, void *devdata, const struct thermal_cooling_device_ops *ops) -- cgit v1.2.3 From 8097db407a08f33236b6fa6ba8b62d669321c720 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 2 Apr 2020 16:27:39 +0200 Subject: thermal: Move default governor config option to the internal header The default governor set at compilation time is a thermal internal business, no need to export to the global thermal header. Move the config options to the internal header. Signed-off-by: Daniel Lezcano Reviewed-by: Amit Kucheria Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20200402142747.8307-1-daniel.lezcano@linaro.org --- include/linux/thermal.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 448841ab0dca..71cff87dcb46 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -32,17 +32,6 @@ /* use value, which < 0K, to indicate an invalid/uninitialized temperature */ #define THERMAL_TEMP_INVALID -274000 -/* Default Thermal Governor */ -#if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE) -#define DEFAULT_THERMAL_GOVERNOR "step_wise" -#elif defined(CONFIG_THERMAL_DEFAULT_GOV_FAIR_SHARE) -#define DEFAULT_THERMAL_GOVERNOR "fair_share" -#elif defined(CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE) -#define DEFAULT_THERMAL_GOVERNOR "user_space" -#elif defined(CONFIG_THERMAL_DEFAULT_GOV_POWER_ALLOCATOR) -#define DEFAULT_THERMAL_GOVERNOR "power_allocator" -#endif - struct thermal_zone_device; struct thermal_cooling_device; struct thermal_instance; -- cgit v1.2.3 From c68df440b07f88210c5839d4507b5cbfa35e3df9 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 2 Apr 2020 16:27:40 +0200 Subject: thermal: Move struct thermal_attr to the private header The structure belongs to the thermal core internals but it is exported in the include/linux/thermal.h For better self-encapsulation and less impact for the compilation if a change is made on it. Move the structure in the thermal core internal header file. Signed-off-by: Daniel Lezcano Reviewed-by: Amit Kucheria Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20200402142747.8307-2-daniel.lezcano@linaro.org --- include/linux/thermal.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 71cff87dcb46..5aa80fb2fb61 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -35,6 +35,7 @@ struct thermal_zone_device; struct thermal_cooling_device; struct thermal_instance; +struct thermal_attr; enum thermal_device_mode { THERMAL_DEVICE_DISABLED = 0, @@ -119,11 +120,6 @@ struct thermal_cooling_device { struct list_head node; }; -struct thermal_attr { - struct device_attribute attr; - char name[THERMAL_NAME_LENGTH]; -}; - /** * struct thermal_zone_device - structure for a thermal zone * @id: unique id number for each thermal zone -- cgit v1.2.3 From 33a88af10944edc7fd390000cd6bc9bbde918bc3 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 2 Apr 2020 16:27:41 +0200 Subject: thermal: Move internal IPA functions The exported IPA functions are used by the IPA. It is pointless to declare the functions in the thermal.h file. For better self-encapsulation and less impact for the compilation if a change is made on it. Move the code in the thermal core internal header file. As the users depends on THERMAL then it is pointless to have the stub, remove them. Take also the opportunity to fix checkpatch warnings/errors when moving the code around. Signed-off-by: Daniel Lezcano Reviewed-by: Amit Kucheria Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20200402142747.8307-3-daniel.lezcano@linaro.org --- include/linux/thermal.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 5aa80fb2fb61..e0279f7b43f4 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -399,18 +399,6 @@ void devm_thermal_zone_of_sensor_unregister(struct device *dev, #endif #if IS_ENABLED(CONFIG_THERMAL) -static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) -{ - return cdev->ops->get_requested_power && cdev->ops->state2power && - cdev->ops->power2state; -} - -int power_actor_get_max_power(struct thermal_cooling_device *, - struct thermal_zone_device *tz, u32 *max_power); -int power_actor_get_min_power(struct thermal_cooling_device *, - struct thermal_zone_device *tz, u32 *min_power); -int power_actor_set_power(struct thermal_cooling_device *, - struct thermal_instance *, u32); struct thermal_zone_device *thermal_zone_device_register(const char *, int, int, void *, struct thermal_zone_device_ops *, struct thermal_zone_params *, int, int); @@ -447,18 +435,6 @@ struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, void thermal_cdev_update(struct thermal_cooling_device *); void thermal_notify_framework(struct thermal_zone_device *, int); #else -static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) -{ return false; } -static inline int power_actor_get_max_power(struct thermal_cooling_device *cdev, - struct thermal_zone_device *tz, u32 *max_power) -{ return 0; } -static inline int power_actor_get_min_power(struct thermal_cooling_device *cdev, - struct thermal_zone_device *tz, - u32 *min_power) -{ return -ENODEV; } -static inline int power_actor_set_power(struct thermal_cooling_device *cdev, - struct thermal_instance *tz, u32 power) -{ return 0; } static inline struct thermal_zone_device *thermal_zone_device_register( const char *type, int trips, int mask, void *devdata, struct thermal_zone_device_ops *ops, -- cgit v1.2.3 From 2e7700dc336dde93cdc9394d10ccd79593fff214 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 2 Apr 2020 16:27:42 +0200 Subject: thermal: Move trip point structure definition to private header The struct thermal_trip is only used by the thermal internals, it is pointless to export the definition in the global header. Move the structure to the thermal_core.h internal header. Signed-off-by: Daniel Lezcano Reviewed-by: Amit Kucheria Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20200402142747.8307-4-daniel.lezcano@linaro.org --- include/linux/thermal.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index e0279f7b43f4..7adbfe092281 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -332,21 +332,6 @@ struct thermal_zone_of_device_ops { int (*set_trip_temp)(void *, int, int); }; -/** - * struct thermal_trip - representation of a point in temperature domain - * @np: pointer to struct device_node that this trip point was created from - * @temperature: temperature value in miliCelsius - * @hysteresis: relative hysteresis in miliCelsius - * @type: trip point type - */ - -struct thermal_trip { - struct device_node *np; - int temperature; - int hysteresis; - enum thermal_trip_type type; -}; - /* Function declarations */ #ifdef CONFIG_THERMAL_OF int thermal_zone_of_get_sensor_id(struct device_node *tz_np, -- cgit v1.2.3 From f0129c231772a85a726b233756cdc58ea42a9d84 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 2 Apr 2020 16:27:43 +0200 Subject: thermal: Move get_tz_trend to the internal header The function is not used any place other than the thermal directory. It does not make sense to export its definition in the global header as there is no use of it. Move the definition to the internal header and allow better self-encapsulation. Take the opportunity to add the parameter names to make checkpatch happy and remove the pointless stubs. Signed-off-by: Daniel Lezcano Reviewed-by: Amit Kucheria Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20200402142747.8307-5-daniel.lezcano@linaro.org --- include/linux/thermal.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 7adbfe092281..8006ba5de855 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -414,7 +414,6 @@ int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); int thermal_zone_get_slope(struct thermal_zone_device *tz); int thermal_zone_get_offset(struct thermal_zone_device *tz); -int get_tz_trend(struct thermal_zone_device *, int); struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, struct thermal_cooling_device *, int); void thermal_cdev_update(struct thermal_cooling_device *); @@ -473,8 +472,7 @@ static inline int thermal_zone_get_slope( static inline int thermal_zone_get_offset( struct thermal_zone_device *tz) { return -ENODEV; } -static inline int get_tz_trend(struct thermal_zone_device *tz, int trip) -{ return -ENODEV; } + static inline struct thermal_instance * get_thermal_instance(struct thermal_zone_device *tz, struct thermal_cooling_device *cdev, int trip) -- cgit v1.2.3 From 06f1041f5023c00a54f63c269b997c61d1b3b739 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 2 Apr 2020 16:27:44 +0200 Subject: thermal: Move get_thermal_instance to the internal header The function is not used any place other than the thermal directory. It does not make sense to export its definition in the global header as there is no use of it. Move the definition to the internal header and allow better self-encapsulation. Take the opportunity to add the parameter names to make checkpatch happy and remove the pointless stubs. Signed-off-by: Daniel Lezcano Reviewed-by: Amit Kucheria Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20200402142747.8307-6-daniel.lezcano@linaro.org --- include/linux/thermal.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 8006ba5de855..47e745c5dfca 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -414,8 +414,6 @@ int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); int thermal_zone_get_slope(struct thermal_zone_device *tz); int thermal_zone_get_offset(struct thermal_zone_device *tz); -struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, - struct thermal_cooling_device *, int); void thermal_cdev_update(struct thermal_cooling_device *); void thermal_notify_framework(struct thermal_zone_device *, int); #else @@ -473,10 +471,6 @@ static inline int thermal_zone_get_offset( struct thermal_zone_device *tz) { return -ENODEV; } -static inline struct thermal_instance * -get_thermal_instance(struct thermal_zone_device *tz, - struct thermal_cooling_device *cdev, int trip) -{ return ERR_PTR(-ENODEV); } static inline void thermal_cdev_update(struct thermal_cooling_device *cdev) { } static inline void thermal_notify_framework(struct thermal_zone_device *tz, -- cgit v1.2.3 From 60518260cab21e749704baa5246ff13f7559fa91 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 2 Apr 2020 16:27:45 +0200 Subject: thermal: Change IS_ENABLED to IFDEF in the header file The thermal framework can not be compiled as a module. The IS_ENABLED macro is useless here and can be replaced by an ifdef. Signed-off-by: Daniel Lezcano Reviewed-by: Amit Kucheria Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20200402142747.8307-7-daniel.lezcano@linaro.org --- include/linux/thermal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 47e745c5dfca..12df9ff0182d 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -383,7 +383,7 @@ void devm_thermal_zone_of_sensor_unregister(struct device *dev, #endif -#if IS_ENABLED(CONFIG_THERMAL) +#ifdef CONFIG_THERMAL struct thermal_zone_device *thermal_zone_device_register(const char *, int, int, void *, struct thermal_zone_device_ops *, struct thermal_zone_params *, int, int); -- cgit v1.2.3 From 708418500644c248d6f266e4df0bf43ce53bf746 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 2 Apr 2020 16:27:46 +0200 Subject: thermal: Remove stubs for thermal_zone_[un]bind_cooling_device All callers of the functions depends on THERMAL, it is pointless to define stubs. Remove them. Signed-off-by: Daniel Lezcano Reviewed-by: Amit Kucheria Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20200402142747.8307-8-daniel.lezcano@linaro.org --- include/linux/thermal.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 12df9ff0182d..7b3dbfe15b59 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -426,16 +426,6 @@ static inline struct thermal_zone_device *thermal_zone_device_register( static inline void thermal_zone_device_unregister( struct thermal_zone_device *tz) { } -static inline int thermal_zone_bind_cooling_device( - struct thermal_zone_device *tz, int trip, - struct thermal_cooling_device *cdev, - unsigned long upper, unsigned long lower, - unsigned int weight) -{ return -ENODEV; } -static inline int thermal_zone_unbind_cooling_device( - struct thermal_zone_device *tz, int trip, - struct thermal_cooling_device *cdev) -{ return -ENODEV; } static inline void thermal_zone_device_update(struct thermal_zone_device *tz, enum thermal_notify_event event) { } -- cgit v1.2.3 From 0145f67866b71e8c1da3c1d9412623db7ba8a0c8 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 2 Apr 2020 16:27:47 +0200 Subject: thermal: Remove thermal_zone_device_update() stub All users of the function depends on THERMAL, no stub is needed. Remove it. Signed-off-by: Daniel Lezcano Reviewed-by: Amit Kucheria Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20200402142747.8307-9-daniel.lezcano@linaro.org --- include/linux/thermal.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 7b3dbfe15b59..216185bb3014 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -426,9 +426,6 @@ static inline struct thermal_zone_device *thermal_zone_device_register( static inline void thermal_zone_device_unregister( struct thermal_zone_device *tz) { } -static inline void thermal_zone_device_update(struct thermal_zone_device *tz, - enum thermal_notify_event event) -{ } static inline struct thermal_cooling_device * thermal_cooling_device_register(char *type, void *devdata, const struct thermal_cooling_device_ops *ops) -- cgit v1.2.3 From 9554bfe403bdfc084823df8695a01f28c680af61 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Fri, 14 Feb 2020 14:27:15 -0800 Subject: x86/mce: Convert the CEC to use the MCE notifier The CEC code has its claws in a couple of routines in mce/core.c. Convert it to just register itself on the normal MCE notifier chain. [ bp: Make cec_add_elem() and cec_init() static. ] Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Tested-by: Tony Luck Link: https://lkml.kernel.org/r/20200214222720.13168-3-tony.luck@intel.com --- include/linux/ras.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ras.h b/include/linux/ras.h index 7c3debb47c87..1f4048bf2674 100644 --- a/include/linux/ras.h +++ b/include/linux/ras.h @@ -17,12 +17,7 @@ static inline int ras_add_daemon_trace(void) { return 0; } #endif #ifdef CONFIG_RAS_CEC -void __init cec_init(void); int __init parse_cec_param(char *str); -int cec_add_elem(u64 pfn); -#else -static inline void __init cec_init(void) { } -static inline int cec_add_elem(u64 pfn) { return -ENODEV; } #endif #ifdef CONFIG_RAS -- cgit v1.2.3 From 7fc0b9b995f222646ece8d5bca528060c098ee88 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Fri, 14 Feb 2020 14:27:20 -0800 Subject: EDAC: Drop the EDAC report status checks When acpi_extlog was added, we were worried that the same error would be reported more than once by different subsystems. But in the ensuing years I've seen complaints that people could not find an error log (because this mechanism suppressed the log they were looking for). Rip it all out. People are smart enough to notice the same address from different reporting mechanisms. Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Tested-by: Tony Luck Link: https://lkml.kernel.org/r/20200214222720.13168-8-tony.luck@intel.com --- include/linux/edac.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 0f20b986b0ab..6eb7d55d7c3d 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -31,14 +31,6 @@ struct device; extern int edac_op_state; struct bus_type *edac_get_sysfs_subsys(void); -int edac_get_report_status(void); -void edac_set_report_status(int new); - -enum { - EDAC_REPORTING_ENABLED, - EDAC_REPORTING_DISABLED, - EDAC_REPORTING_FORCE -}; static inline void opstate_init(void) { -- cgit v1.2.3 From 12479382877dcf6623af4676caa8d3c647469a1b Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Thu, 2 Apr 2020 22:36:44 +0200 Subject: regmap-irq: make it possible to add irq_chip do a specific device node Add a new function regmap_add_irq_chip_np() with its corresponding devm_regmap_add_irq_chip_np() variant. Sometimes one want to register the IRQ domain on a different device node that the one of the regmap node. For example when using a MFD where there are different interrupt controllers and particularly for the generic regmap gpio_chip/irq_chip driver. In this case it is not desireable to have the IRQ domain on the parent node. Signed-off-by: Michael Walle Link: https://lore.kernel.org/r/20200402203656.27047-5-michael@walle.cc Signed-off-by: Mark Brown --- include/linux/regmap.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 40b07168fd8e..ae5034b2d7c3 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -21,6 +21,7 @@ struct module; struct clk; struct device; +struct device_node; struct i2c_client; struct i3c_device; struct irq_domain; @@ -1310,12 +1311,21 @@ struct regmap_irq_chip_data; int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, int irq_base, const struct regmap_irq_chip *chip, struct regmap_irq_chip_data **data); +int regmap_add_irq_chip_np(struct device_node *np, struct regmap *map, int irq, + int irq_flags, int irq_base, + const struct regmap_irq_chip *chip, + struct regmap_irq_chip_data **data); void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *data); int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq, int irq_flags, int irq_base, const struct regmap_irq_chip *chip, struct regmap_irq_chip_data **data); +int devm_regmap_add_irq_chip_np(struct device *dev, struct device_node *np, + struct regmap *map, int irq, int irq_flags, + int irq_base, + const struct regmap_irq_chip *chip, + struct regmap_irq_chip_data **data); void devm_regmap_del_irq_chip(struct device *dev, int irq, struct regmap_irq_chip_data *data); -- cgit v1.2.3 From bd3ddb495762575ab14e7bd2e4017dc1f9a80b2f Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Thu, 2 Apr 2020 10:41:11 +0200 Subject: regmap: add reg_sequence helpers Add helper to make it easier to define a reg_sequence array. Signed-off-by: Marco Felsch Link: https://lore.kernel.org/r/20200402084111.30123-1-m.felsch@pengutronix.de Signed-off-by: Mark Brown --- include/linux/regmap.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 40b07168fd8e..0b5582a78df8 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -71,6 +71,13 @@ struct reg_sequence { unsigned int delay_us; }; +#define REG_SEQ(_reg, _def, _delay_us) { \ + .reg = _reg, \ + .def = _def, \ + .delay_us = _delay_us, \ + } +#define REG_SEQ0(_reg, _def) REG_SEQ(_reg, _def, 0) + #define regmap_update_bits(map, reg, mask, val) \ regmap_update_bits_base(map, reg, mask, val, NULL, false, false) #define regmap_update_bits_async(map, reg, mask, val)\ -- cgit v1.2.3 From 4c5b566c2193e2af82c891daa5303c8899e61044 Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Tue, 31 Mar 2020 02:15:44 +0800 Subject: crash_dump: Remove no longer used saved_max_pfn saved_max_pfn was originally introduced in commit 92aa63a5a1bf ("[PATCH] kdump: Retrieve saved max pfn") It used to make sure that the user does not try to read the physical memory beyond saved_max_pfn. But since commit 921d58c0e699 ("vmcore: remove saved_max_pfn check") it's no longer used for the check. This variable doesn't have any users anymore so just remove it. [ bp: Drop the Calgary IOMMU reference from the commit message. ] Signed-off-by: Kairui Song Signed-off-by: Borislav Petkov Acked-by: "Eric W. Biederman" Link: https://lkml.kernel.org/r/20200330181544.1595733-1-kasong@redhat.com --- include/linux/crash_dump.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 4664fc1871de..bc156285d097 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -97,8 +97,6 @@ extern void unregister_oldmem_pfn_is_ram(void); static inline bool is_kdump_kernel(void) { return 0; } #endif /* CONFIG_CRASH_DUMP */ -extern unsigned long saved_max_pfn; - /* Device Dump information to be filled by drivers */ struct vmcoredd_data { char dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Unique name of the dump */ -- cgit v1.2.3 From 5429ef62bcf360aae06740cbe065be01e5cfb6fc Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 22 Jan 2020 19:38:21 +0000 Subject: compiler/gcc: Raise minimum GCC version for kernel builds to 4.8 It is very rare to see versions of GCC prior to 4.8 being used to build the mainline kernel. These old compilers are also know to have codegen issues which can lead to silent miscompilation: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 Raise the minimum GCC version for kernel build to 4.8 and remove some tautological Kconfig dependencies as a consequence. Cc: Masahiro Yamada Acked-by: Arnd Bergmann Reviewed-by: Nick Desaulniers Signed-off-by: Will Deacon --- include/linux/compiler-gcc.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index d7ee4c6bad48..e2f725273261 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -10,7 +10,8 @@ + __GNUC_MINOR__ * 100 \ + __GNUC_PATCHLEVEL__) -#if GCC_VERSION < 40600 +/* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */ +#if GCC_VERSION < 40800 # error Sorry, your compiler is too old - please upgrade it. #endif @@ -126,9 +127,7 @@ #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ -#if GCC_VERSION >= 40800 #define __HAVE_BUILTIN_BSWAP16__ -#endif #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */ #if GCC_VERSION >= 70000 -- cgit v1.2.3 From a5460b5e5fb82656807840d40d3deaecad094044 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 16 Dec 2019 16:51:45 +0000 Subject: READ_ONCE: Simplify implementations of {READ,WRITE}_ONCE() The implementations of {READ,WRITE}_ONCE() suffer from a significant amount of indirection and complexity due to a historic GCC bug: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 which was originally worked around by 230fa253df63 ("kernel: Provide READ_ONCE and ASSIGN_ONCE"). Since GCC 4.8 is fairly vintage at this point and we emit a warning if we detect it during the build, return {READ,WRITE}_ONCE() to their former glory with an implementation that is easier to understand and, crucially, more amenable to optimisation. A side effect of this simplification is that WRITE_ONCE() no longer returns a value, but nobody seems to be relying on that and the new behaviour is aligned with smp_store_release(). Suggested-by: Linus Torvalds Cc: Peter Zijlstra Cc: Michael Ellerman Cc: Arnd Bergmann Cc: Christian Borntraeger Signed-off-by: Will Deacon --- include/linux/compiler.h | 118 ++++++++++++++++------------------------------- 1 file changed, 39 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 034b0a644efc..338111a448d0 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -177,60 +177,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__) #endif -#include - -#define __READ_ONCE_SIZE \ -({ \ - switch (size) { \ - case 1: *(__u8 *)res = *(volatile __u8 *)p; break; \ - case 2: *(__u16 *)res = *(volatile __u16 *)p; break; \ - case 4: *(__u32 *)res = *(volatile __u32 *)p; break; \ - case 8: *(__u64 *)res = *(volatile __u64 *)p; break; \ - default: \ - barrier(); \ - __builtin_memcpy((void *)res, (const void *)p, size); \ - barrier(); \ - } \ -}) - -static __always_inline -void __read_once_size(const volatile void *p, void *res, int size) -{ - __READ_ONCE_SIZE; -} - -#ifdef CONFIG_KASAN -/* - * We can't declare function 'inline' because __no_sanitize_address confilcts - * with inlining. Attempt to inline it may cause a build failure. - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - * '__maybe_unused' allows us to avoid defined-but-not-used warnings. - */ -# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused -#else -# define __no_kasan_or_inline __always_inline -#endif - -static __no_kasan_or_inline -void __read_once_size_nocheck(const volatile void *p, void *res, int size) -{ - __READ_ONCE_SIZE; -} - -static __always_inline void __write_once_size(volatile void *p, void *res, int size) -{ - switch (size) { - case 1: *(volatile __u8 *)p = *(__u8 *)res; break; - case 2: *(volatile __u16 *)p = *(__u16 *)res; break; - case 4: *(volatile __u32 *)p = *(__u32 *)res; break; - case 8: *(volatile __u64 *)p = *(__u64 *)res; break; - default: - barrier(); - __builtin_memcpy((void *)p, (const void *)res, size); - barrier(); - } -} - /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of @@ -240,11 +186,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * statements. * * These two macros will also work on aggregate data types like structs or - * unions. If the size of the accessed data type exceeds the word size of - * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will - * fall back to memcpy(). There's at least two memcpy()s: one for the - * __builtin_memcpy() and then one for the macro doing the copy of variable - * - '__u' allocated on the stack. + * unions. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, @@ -256,23 +198,49 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #include #include -#define __READ_ONCE(x, check) \ +#define __READ_ONCE(x) (*(volatile typeof(x) *)&(x)) + +#define READ_ONCE(x) \ ({ \ - union { typeof(x) __val; char __c[1]; } __u; \ - if (check) \ - __read_once_size(&(x), __u.__c, sizeof(x)); \ - else \ - __read_once_size_nocheck(&(x), __u.__c, sizeof(x)); \ - smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \ - __u.__val; \ + typeof(x) __x = __READ_ONCE(x); \ + smp_read_barrier_depends(); \ + __x; \ }) -#define READ_ONCE(x) __READ_ONCE(x, 1) + +#define WRITE_ONCE(x, val) \ +do { \ + *(volatile typeof(x) *)&(x) = (val); \ +} while (0) + +#ifdef CONFIG_KASAN +/* + * We can't declare function 'inline' because __no_sanitize_address conflicts + * with inlining. Attempt to inline it may cause a build failure. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + * '__maybe_unused' allows us to avoid defined-but-not-used warnings. + */ +# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused +#else +# define __no_kasan_or_inline __always_inline +#endif + +static __no_kasan_or_inline +unsigned long __read_once_word_nocheck(const void *addr) +{ + return __READ_ONCE(*(unsigned long *)addr); +} /* - * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need - * to hide memory access from KASAN. + * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a + * word from memory atomically but without telling KASAN. This is usually + * used by unwinding code when walking the stack of a running process. */ -#define READ_ONCE_NOCHECK(x) __READ_ONCE(x, 0) +#define READ_ONCE_NOCHECK(x) \ +({ \ + unsigned long __x = __read_once_word_nocheck(&(x)); \ + smp_read_barrier_depends(); \ + __x; \ +}) static __no_kasan_or_inline unsigned long read_word_at_a_time(const void *addr) @@ -281,14 +249,6 @@ unsigned long read_word_at_a_time(const void *addr) return *(unsigned long *)addr; } -#define WRITE_ONCE(x, val) \ -({ \ - union { typeof(x) __val; char __c[1]; } __u = \ - { .__val = (__force typeof(x)) (val) }; \ - __write_once_size(&(x), __u.__c, sizeof(x)); \ - __u.__val; \ -}) - #endif /* __KERNEL__ */ /* -- cgit v1.2.3 From 9e343b467c70379e66b8b771d96f03ae23eba351 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 13 Dec 2019 14:47:02 +0000 Subject: READ_ONCE: Enforce atomicity for {READ,WRITE}_ONCE() memory accesses {READ,WRITE}_ONCE() cannot guarantee atomicity for arbitrary data sizes. This can be surprising to callers that might incorrectly be expecting atomicity for accesses to aggregate structures, although there are other callers where tearing is actually permissable (e.g. if they are using something akin to sequence locking to protect the access). Linus sayeth: | We could also look at being stricter for the normal READ/WRITE_ONCE(), | and require that they are | | (a) regular integer types | | (b) fit in an atomic word | | We actually did (b) for a while, until we noticed that we do it on | loff_t's etc and relaxed the rules. But maybe we could have a | "non-atomic" version of READ/WRITE_ONCE() that is used for the | questionable cases? The slight snag is that we also have to support 64-bit accesses on 32-bit architectures, as these appear to be widespread and tend to work out ok if either the architecture supports atomic 64-bit accesses (x86, armv7) or if the variable being accesses represents a virtual address and therefore only requires 32-bit atomicity in practice. Take a step in that direction by introducing a variant of 'compiletime_assert_atomic_type()' and use it to check the pointer argument to {READ,WRITE}_ONCE(). Expose __{READ,WRITE}_ONCE() variants which are allowed to tear and convert the one broken caller over to the new macros. Suggested-by: Linus Torvalds Cc: Peter Zijlstra Cc: Michael Ellerman Cc: Arnd Bergmann Signed-off-by: Will Deacon --- include/linux/compiler.h | 33 ++++++++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 338111a448d0..50bb2461648f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -198,20 +198,37 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #include #include -#define __READ_ONCE(x) (*(volatile typeof(x) *)&(x)) +/* + * Use __READ_ONCE() instead of READ_ONCE() if you do not require any + * atomicity or dependency ordering guarantees. Note that this may result + * in tears! + */ +#define __READ_ONCE(x) (*(const volatile typeof(x) *)&(x)) -#define READ_ONCE(x) \ +#define __READ_ONCE_SCALAR(x) \ ({ \ typeof(x) __x = __READ_ONCE(x); \ smp_read_barrier_depends(); \ __x; \ }) -#define WRITE_ONCE(x, val) \ +#define READ_ONCE(x) \ +({ \ + compiletime_assert_rwonce_type(x); \ + __READ_ONCE_SCALAR(x); \ +}) + +#define __WRITE_ONCE(x, val) \ do { \ *(volatile typeof(x) *)&(x) = (val); \ } while (0) +#define WRITE_ONCE(x, val) \ +do { \ + compiletime_assert_rwonce_type(x); \ + __WRITE_ONCE(x, val); \ +} while (0) + #ifdef CONFIG_KASAN /* * We can't declare function 'inline' because __no_sanitize_address conflicts @@ -313,6 +330,16 @@ static inline void *offset_to_ptr(const int *off) compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") +/* + * Yes, this permits 64-bit accesses on 32-bit architectures. These will + * actually be atomic in many cases (namely x86), but for others we rely on + * the access being split into 2x32-bit accesses for a 32-bit quantity (e.g. + * a virtual address) and a strong prevailing wind. + */ +#define compiletime_assert_rwonce_type(t) \ + compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ + "Unsupported access size for {READ,WRITE}_ONCE().") + /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) -- cgit v1.2.3 From dee081bf8f824cabeb7c7495367d5dad0a444eb1 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 19 Dec 2019 14:22:31 +0000 Subject: READ_ONCE: Drop pointer qualifiers when reading from scalar types Passing a volatile-qualified pointer to READ_ONCE() is an absolute trainwreck for code generation: the use of 'typeof()' to define a temporary variable inside the macro means that the final evaluation in macro scope ends up forcing a read back from the stack. When stack protector is enabled (the default for arm64, at least), this causes the compiler to vomit up all sorts of junk. Unfortunately, dropping pointer qualifiers inside the macro poses quite a challenge, especially since the pointed-to type is permitted to be an aggregate, and this is relied upon by mm/ code accessing things like 'pmd_t'. Based on numerous hacks and discussions on the mailing list, this is the best I've managed to come up with. Introduce '__unqual_scalar_typeof()' which takes an expression and, if the expression is an optionally qualified 8, 16, 32 or 64-bit scalar type, evaluates to the unqualified type. Other input types, including aggregates, remain unchanged. Hopefully READ_ONCE() on volatile aggregate pointers isn't something we do on a fast-path. Cc: Peter Zijlstra Cc: Arnd Bergmann Suggested-by: Linus Torvalds Reported-by: Michael Ellerman Signed-off-by: Will Deacon --- include/linux/compiler.h | 6 +++--- include/linux/compiler_types.h | 21 +++++++++++++++++++++ 2 files changed, 24 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 50bb2461648f..c363d8debc43 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -203,13 +203,13 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, * atomicity or dependency ordering guarantees. Note that this may result * in tears! */ -#define __READ_ONCE(x) (*(const volatile typeof(x) *)&(x)) +#define __READ_ONCE(x) (*(const volatile __unqual_scalar_typeof(x) *)&(x)) #define __READ_ONCE_SCALAR(x) \ ({ \ - typeof(x) __x = __READ_ONCE(x); \ + __unqual_scalar_typeof(x) __x = __READ_ONCE(x); \ smp_read_barrier_depends(); \ - __x; \ + (typeof(x))__x; \ }) #define READ_ONCE(x) \ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index e970f97a7fcb..233066c92f6f 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -210,6 +210,27 @@ struct ftrace_likely_data { /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) +/* + * __unqual_scalar_typeof(x) - Declare an unqualified scalar type, leaving + * non-scalar types unchanged. + * + * We build this out of a couple of helper macros in a vain attempt to + * help you keep your lunch down while reading it. + */ +#define __pick_scalar_type(x, type, otherwise) \ + __builtin_choose_expr(__same_type(x, type), (type)0, otherwise) + +#define __pick_integer_type(x, type, otherwise) \ + __pick_scalar_type(x, unsigned type, \ + __pick_scalar_type(x, signed type, otherwise)) + +#define __unqual_scalar_typeof(x) typeof( \ + __pick_integer_type(x, char, \ + __pick_integer_type(x, short, \ + __pick_integer_type(x, int, \ + __pick_integer_type(x, long, \ + __pick_integer_type(x, long long, x)))))) + /* Is this type a native word size -- useful for atomic operations */ #define __native_word(t) \ (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ -- cgit v1.2.3 From 6aba6ed879b3471903c8ada28ba968a268df6143 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 7 Apr 2020 20:38:41 +0300 Subject: pinctrl: mcp23s08: Get rid of legacy platform data Platform data is a legacy interface to supply device properties to the driver. In this case we even don't have in-kernel users for it. Just remove it for good. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200407173849.43628-1-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- include/linux/spi/mcp23s08.h | 18 ------------------ 1 file changed, 18 deletions(-) delete mode 100644 include/linux/spi/mcp23s08.h (limited to 'include/linux') diff --git a/include/linux/spi/mcp23s08.h b/include/linux/spi/mcp23s08.h deleted file mode 100644 index 738a45b435f2..000000000000 --- a/include/linux/spi/mcp23s08.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -struct mcp23s08_platform_data { - /* For mcp23s08, up to 4 slaves (numbered 0..3) can share one SPI - * chipselect, each providing 1 gpio_chip instance with 8 gpios. - * For mpc23s17, up to 8 slaves (numbered 0..7) can share one SPI - * chipselect, each providing 1 gpio_chip (port A + port B) with - * 16 gpios. - */ - u32 spi_present_mask; - - /* "base" is the number of the first GPIO or -1 for dynamic - * assignment. If there are gaps in chip addressing the GPIO - * numbers are sequential .. so for example if only slaves 0 - * and 3 are present, their GPIOs range from base to base+15 - * (or base+31 for s17 variant). - */ - unsigned base; -}; -- cgit v1.2.3 From 980737282232b752bb14dab96d77665c15889c36 Mon Sep 17 00:00:00 2001 From: Alexey Budankov Date: Thu, 2 Apr 2020 11:45:31 +0300 Subject: capabilities: Introduce CAP_PERFMON to kernel and user space Introduce the CAP_PERFMON capability designed to secure system performance monitoring and observability operations so that CAP_PERFMON can assist CAP_SYS_ADMIN capability in its governing role for performance monitoring and observability subsystems. CAP_PERFMON hardens system security and integrity during performance monitoring and observability operations by decreasing attack surface that is available to a CAP_SYS_ADMIN privileged process [2]. Providing the access to system performance monitoring and observability operations under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes the operation more secure. Thus, CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e: 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required) CAP_PERFMON meets the demand to secure system performance monitoring and observability operations for adoption in security sensitive, restricted, multiuser production environments (e.g. HPC clusters, cloud and virtual compute environments), where root or CAP_SYS_ADMIN credentials are not available to mass users of a system, and securely unblocks applicability and scalability of system performance monitoring and observability operations beyond root and CAP_SYS_ADMIN use cases. CAP_PERFMON takes over CAP_SYS_ADMIN credentials related to system performance monitoring and observability operations and balances amount of CAP_SYS_ADMIN credentials following the recommendations in the capabilities man page [1] for CAP_SYS_ADMIN: "Note: this capability is overloaded; see Notes to kernel developers, below." For backward compatibility reasons access to system performance monitoring and observability subsystems of the kernel remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN capability usage for secure system performance monitoring and observability operations is discouraged with respect to the designed CAP_PERFMON capability. Although the software running under CAP_PERFMON can not ensure avoidance of related hardware issues, the software can still mitigate these issues following the official hardware issues mitigation procedure [2]. The bugs in the software itself can be fixed following the standard kernel development process [3] to maintain and harden security of system performance monitoring and observability operations. [1] http://man7.org/linux/man-pages/man7/capabilities.7.html [2] https://www.kernel.org/doc/html/latest/process/embargoed-hardware-issues.html [3] https://www.kernel.org/doc/html/latest/admin-guide/security-bugs.html Signed-off-by: Alexey Budankov Acked-by: James Morris Acked-by: Serge E. Hallyn Acked-by: Song Liu Acked-by: Stephen Smalley Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Andi Kleen Cc: Igor Lubashev Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: intel-gfx@lists.freedesktop.org Cc: linux-doc@vger.kernel.org Cc: linux-man@vger.kernel.org Cc: linux-security-module@vger.kernel.org Cc: selinux@vger.kernel.org Link: http://lore.kernel.org/lkml/5590d543-82c6-490a-6544-08e6a5517db0@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/capability.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index ecce0f43c73a..027d7e4a853b 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -251,6 +251,10 @@ extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); +static inline bool perfmon_capable(void) +{ + return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN); +} /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); -- cgit v1.2.3 From 18aa18566218d4a46d940049b835314d2b071cc2 Mon Sep 17 00:00:00 2001 From: Alexey Budankov Date: Thu, 2 Apr 2020 11:46:24 +0300 Subject: perf/core: Open access to the core for CAP_PERFMON privileged process Open access to monitoring of kernel code, CPUs, tracepoints and namespaces data for a CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure. CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required) For backward compatibility reasons the access to perf_events subsystem remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure perf_events monitoring is discouraged with respect to CAP_PERFMON capability. Signed-off-by: Alexey Budankov Reviewed-by: James Morris Tested-by: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Andi Kleen Cc: Igor Lubashev Cc: Jiri Olsa Cc: linux-man@vger.kernel.org Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Serge Hallyn Cc: Song Liu Cc: Stephane Eranian Cc: Thomas Gleixner Cc: intel-gfx@lists.freedesktop.org Cc: linux-doc@vger.kernel.org Cc: linux-security-module@vger.kernel.org Cc: selinux@vger.kernel.org Link: http://lore.kernel.org/lkml/471acaef-bb8a-5ce2-923f-90606b78eef9@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 9c3e7619c929..87e21681759c 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1305,7 +1305,7 @@ static inline int perf_is_paranoid(void) static inline int perf_allow_kernel(struct perf_event_attr *attr) { - if (sysctl_perf_event_paranoid > 1 && !capable(CAP_SYS_ADMIN)) + if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_KERNEL); @@ -1313,7 +1313,7 @@ static inline int perf_allow_kernel(struct perf_event_attr *attr) static inline int perf_allow_cpu(struct perf_event_attr *attr) { - if (sysctl_perf_event_paranoid > 0 && !capable(CAP_SYS_ADMIN)) + if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_CPU); @@ -1321,7 +1321,7 @@ static inline int perf_allow_cpu(struct perf_event_attr *attr) static inline int perf_allow_tracepoint(struct perf_event_attr *attr) { - if (sysctl_perf_event_paranoid > -1 && !capable(CAP_SYS_ADMIN)) + if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); -- cgit v1.2.3 From ab7c1e163b525316a870a494dd4ea196e7a6c455 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 15 Apr 2020 18:45:00 +0200 Subject: firmware: Drop unused pages field from struct firmware The struct firmware contains a page table pointer that was used only internally in the past. Since the actual page tables are referred from struct fw_priv and should be never from struct firmware, we can drop this unused field gracefully. Signed-off-by: Takashi Iwai Acked-by: Luis Chamberlain Link: https://lore.kernel.org/r/20200415164500.28749-1-tiwai@suse.de Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 4bbd0afd91b7..cb3e2c06ed8a 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -12,7 +12,6 @@ struct firmware { size_t size; const u8 *data; - struct page **pages; /* firmware loader private fields */ void *priv; -- cgit v1.2.3 From 699fed4a2d8e32d77d64928e570d7ffd93a62fdf Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Thu, 16 Apr 2020 01:43:10 -0700 Subject: scsi: qed: Send BW update notifications to the protocol drivers Management firmware (MFW) sends a notification whenever there is a change in the bandwidth values. Add driver support for sending this notification to the upper layer drivers (e.g., qedf). Link: https://lore.kernel.org/r/20200416084314.18851-6-skashyap@marvell.com Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Saurav Kashyap Signed-off-by: Martin K. Petersen --- include/linux/qed/qed_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8f29e0d8a7b3..c4956374a444 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -817,6 +817,7 @@ struct qed_common_cb_ops { void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); + void (*bw_update)(void *dev); }; struct qed_selftest_ops { -- cgit v1.2.3 From 2ce0d7f9766f0e49bb54f149c77bae89464932fb Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 16 Apr 2020 19:24:02 +0100 Subject: x86/asm: Provide a Kconfig symbol for disabling old assembly annotations As x86 was converted to use the modern SYM_ annotations for assembly, ifdefs were added to remove the generic definitions of the old style annotations on x86. Rather than collect a list of architectures in the ifdefs as more architectures are converted over, provide a Kconfig symbol for this and update x86 to use it. Signed-off-by: Mark Brown Signed-off-by: Borislav Petkov Acked-by: Jiri Slaby Link: https://lkml.kernel.org/r/20200416182402.6206-1-broonie@kernel.org --- include/linux/linkage.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 9280209d1f62..d796ec20d114 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -105,7 +105,7 @@ /* === DEPRECATED annotations === */ -#ifndef CONFIG_X86 +#ifndef CONFIG_ARCH_USE_SYM_ANNOTATIONS #ifndef GLOBAL /* deprecated, use SYM_DATA*, SYM_ENTRY, or similar */ #define GLOBAL(name) \ @@ -118,10 +118,10 @@ #define ENTRY(name) \ SYM_FUNC_START(name) #endif -#endif /* CONFIG_X86 */ +#endif /* CONFIG_ARCH_USE_SYM_ANNOTATIONS */ #endif /* LINKER_SCRIPT */ -#ifndef CONFIG_X86 +#ifndef CONFIG_ARCH_USE_SYM_ANNOTATIONS #ifndef WEAK /* deprecated, use SYM_FUNC_START_WEAK* */ #define WEAK(name) \ @@ -143,7 +143,7 @@ #define ENDPROC(name) \ SYM_FUNC_END(name) #endif -#endif /* CONFIG_X86 */ +#endif /* CONFIG_ARCH_USE_SYM_ANNOTATIONS */ /* === generic annotations === */ -- cgit v1.2.3 From 123aff2a789c3975c2235653939ff00107d6156c Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 17 Apr 2020 11:38:02 -0700 Subject: net: phy: broadcom: Add support for BCM53125 internal PHYs BCM53125 has internal Gigabit PHYs which support interrupts as well as statistics, make it possible to configure both of those features with a PHY driver entry. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6462c5447872..7e1d857c8468 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -15,6 +15,7 @@ #define PHY_ID_BCMAC131 0x0143bc70 #define PHY_ID_BCM5481 0x0143bca0 #define PHY_ID_BCM5395 0x0143bcf0 +#define PHY_ID_BCM53125 0x03625f20 #define PHY_ID_BCM54810 0x03625d00 #define PHY_ID_BCM5482 0x0143bcb0 #define PHY_ID_BCM5411 0x00206070 -- cgit v1.2.3 From bb7fc863729b45f0fbcdea991d0465d855ffd831 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 5 Apr 2020 20:57:00 +0300 Subject: net/mlx5: Provide simplified command interfaces Many mlx5_cmd_exec() callers are not interested in the output from that command or have standard in/out structures. Those callers simply allocate those structure on the stack and use sizeof() to provide in/out arguments. In this naive approach provide simplified versions of mlx5_cmd_exec(). Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6f8f79ef829b..1caddfa85c4d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -903,6 +903,19 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); + +#define mlx5_cmd_exec_inout(dev, ifc_cmd, in, out) \ + ({ \ + mlx5_cmd_exec(dev, in, MLX5_ST_SZ_BYTES(ifc_cmd##_in), out, \ + MLX5_ST_SZ_BYTES(ifc_cmd##_out)); \ + }) + +#define mlx5_cmd_exec_in(dev, ifc_cmd, in) \ + ({ \ + u32 _out[MLX5_ST_SZ_DW(ifc_cmd##_out)] = {}; \ + mlx5_cmd_exec_inout(dev, ifc_cmd, in, _out); \ + }) + int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); -- cgit v1.2.3 From 66247fbb280c2a699a8621708c52dae6acd2e4bc Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Fri, 3 Apr 2020 11:28:28 +0300 Subject: net/mlx5: Remove Q counter low level helper APIs mlx5 core users are encouraged to use low level API (mlx5_cmd_exec) without the need of helper functions, do this for q counters, remove helper functions and call mlx5_cmd_exec directly from users. This will help reduce the total amount of code and reduction of the mlx5_core symbol table. Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/qp.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index ae63b1ae9004..4d25a3d24182 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -595,10 +595,6 @@ int mlx5_core_create_sq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, struct mlx5_core_qp *sq); void mlx5_core_destroy_sq_tracked(struct mlx5_core_dev *dev, struct mlx5_core_qp *sq); -int mlx5_core_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id); -int mlx5_core_dealloc_q_counter(struct mlx5_core_dev *dev, u16 counter_id); -int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id, - int reset, void *out, int out_size); struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev, int res_num, -- cgit v1.2.3 From 333fbaa0255b8d471fc7ae767ef3a1766c732d6d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sat, 4 Apr 2020 10:40:24 +0300 Subject: net/mlx5: Move QP logic to mlx5_ib The mlx5_core doesn't need any functionality coded in qp.c, so move that file to drivers/infiniband/ be under mlx5_ib responsibility. Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/cmd.h | 51 --------------------------------------------- include/linux/mlx5/driver.h | 2 -- include/linux/mlx5/qp.h | 45 --------------------------------------- 3 files changed, 98 deletions(-) delete mode 100644 include/linux/mlx5/cmd.h (limited to 'include/linux') diff --git a/include/linux/mlx5/cmd.h b/include/linux/mlx5/cmd.h deleted file mode 100644 index 68cd08f02c2f..000000000000 --- a/include/linux/mlx5/cmd.h +++ /dev/null @@ -1,51 +0,0 @@ -/* - * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#ifndef MLX5_CMD_H -#define MLX5_CMD_H - -#include - -struct manage_pages_layout { - u64 ptr; - u32 reserved; - u16 num_entries; - u16 func_id; -}; - - -struct mlx5_cmd_alloc_uar_imm_out { - u32 rsvd[3]; - u32 uarn; -}; - -#endif /* MLX5_CMD_H */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1caddfa85c4d..b60e5ab7906b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -541,7 +541,6 @@ struct mlx5_priv { struct mlx5_core_health health; /* start: qp staff */ - struct mlx5_qp_table qp_table; struct dentry *qp_debugfs; struct dentry *eq_debugfs; struct dentry *cq_debugfs; @@ -687,7 +686,6 @@ struct mlx5_core_dev { unsigned long intf_state; struct mlx5_priv priv; struct mlx5_profile *profile; - atomic_t num_qps; u32 issi; struct mlx5e_resources mlx5e_res; struct mlx5_dm *dm; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 4d25a3d24182..ef127a156a62 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -553,53 +553,8 @@ struct mlx5_qp_context { u8 rsvd1[24]; }; -static inline struct mlx5_core_qp *__mlx5_qp_lookup(struct mlx5_core_dev *dev, u32 qpn) -{ - return radix_tree_lookup(&dev->priv.qp_table.tree, qpn); -} - -int mlx5_core_create_dct(struct mlx5_core_dev *dev, - struct mlx5_core_dct *qp, - u32 *in, int inlen, - u32 *out, int outlen); -int mlx5_core_create_qp(struct mlx5_core_dev *dev, - struct mlx5_core_qp *qp, - u32 *in, - int inlen); -int mlx5_core_qp_modify(struct mlx5_core_dev *dev, u16 opcode, - u32 opt_param_mask, void *qpc, - struct mlx5_core_qp *qp); -int mlx5_core_destroy_qp(struct mlx5_core_dev *dev, - struct mlx5_core_qp *qp); -int mlx5_core_destroy_dct(struct mlx5_core_dev *dev, - struct mlx5_core_dct *dct); -int mlx5_core_qp_query(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp, - u32 *out, int outlen); -int mlx5_core_dct_query(struct mlx5_core_dev *dev, struct mlx5_core_dct *dct, - u32 *out, int outlen); - -int mlx5_core_set_delay_drop(struct mlx5_core_dev *dev, - u32 timeout_usec); - -int mlx5_core_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn); -int mlx5_core_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn); -void mlx5_init_qp_table(struct mlx5_core_dev *dev); -void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev); int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp); void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp); -int mlx5_core_create_rq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, - struct mlx5_core_qp *rq); -void mlx5_core_destroy_rq_tracked(struct mlx5_core_dev *dev, - struct mlx5_core_qp *rq); -int mlx5_core_create_sq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, - struct mlx5_core_qp *sq); -void mlx5_core_destroy_sq_tracked(struct mlx5_core_dev *dev, - struct mlx5_core_qp *sq); - -struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev, - int res_num, - enum mlx5_res_type res_type); -void mlx5_core_res_put(struct mlx5_core_rsc_common *res); static inline const char *mlx5_qp_type_str(int type) { -- cgit v1.2.3 From 59e9e8e4fe83f68e599b87c06aaf239dcc64887b Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Tue, 14 Jan 2020 05:06:25 +0200 Subject: net/mlx5: Enable SW-defined RoCEv2 UDP source port When this is enabled, UDP source port for RoCEv2 packets are defined by software instead of firmware. Signed-off-by: Mark Zhang Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 69b27c7dfc3e..6fa24918eade 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -74,6 +74,7 @@ enum { MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0, MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, + MLX5_SET_HCA_CAP_OP_MOD_ROCE = 0x4, }; enum { @@ -903,7 +904,9 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { struct mlx5_ifc_roce_cap_bits { u8 roce_apm[0x1]; - u8 reserved_at_1[0x1f]; + u8 reserved_at_1[0x3]; + u8 sw_r_roce_src_udp_port[0x1]; + u8 reserved_at_5[0x1b]; u8 reserved_at_20[0x60]; -- cgit v1.2.3 From 501d3e5dd5bd33a7119f35ee6d365a5787e32a30 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Sat, 21 Mar 2020 11:08:01 +0200 Subject: iio: ad_sigma_delta: remove unused IIO channel macros Now that all channel SigmaDelta IIO channel macros have been localized, remove the generic ones. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/ad_sigma_delta.h | 58 ---------------------------------- 1 file changed, 58 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 5a127c0ed200..a3a838dcf8e4 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -133,62 +133,4 @@ void ad_sd_cleanup_buffer_and_trigger(struct iio_dev *indio_dev); int ad_sd_validate_trigger(struct iio_dev *indio_dev, struct iio_trigger *trig); -#define __AD_SD_CHANNEL(_si, _channel1, _channel2, _address, _bits, \ - _storagebits, _shift, _extend_name, _type, _mask_all) \ - { \ - .type = (_type), \ - .differential = (_channel2 == -1 ? 0 : 1), \ - .indexed = 1, \ - .channel = (_channel1), \ - .channel2 = (_channel2), \ - .address = (_address), \ - .extend_name = (_extend_name), \ - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ - BIT(IIO_CHAN_INFO_OFFSET), \ - .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ - .info_mask_shared_by_all = _mask_all, \ - .scan_index = (_si), \ - .scan_type = { \ - .sign = 'u', \ - .realbits = (_bits), \ - .storagebits = (_storagebits), \ - .shift = (_shift), \ - .endianness = IIO_BE, \ - }, \ - } - -#define AD_SD_DIFF_CHANNEL(_si, _channel1, _channel2, _address, _bits, \ - _storagebits, _shift) \ - __AD_SD_CHANNEL(_si, _channel1, _channel2, _address, _bits, \ - _storagebits, _shift, NULL, IIO_VOLTAGE, \ - BIT(IIO_CHAN_INFO_SAMP_FREQ)) - -#define AD_SD_SHORTED_CHANNEL(_si, _channel, _address, _bits, \ - _storagebits, _shift) \ - __AD_SD_CHANNEL(_si, _channel, _channel, _address, _bits, \ - _storagebits, _shift, "shorted", IIO_VOLTAGE, \ - BIT(IIO_CHAN_INFO_SAMP_FREQ)) - -#define AD_SD_CHANNEL(_si, _channel, _address, _bits, \ - _storagebits, _shift) \ - __AD_SD_CHANNEL(_si, _channel, -1, _address, _bits, \ - _storagebits, _shift, NULL, IIO_VOLTAGE, \ - BIT(IIO_CHAN_INFO_SAMP_FREQ)) - -#define AD_SD_CHANNEL_NO_SAMP_FREQ(_si, _channel, _address, _bits, \ - _storagebits, _shift) \ - __AD_SD_CHANNEL(_si, _channel, -1, _address, _bits, \ - _storagebits, _shift, NULL, IIO_VOLTAGE, 0) - -#define AD_SD_TEMP_CHANNEL(_si, _address, _bits, _storagebits, _shift) \ - __AD_SD_CHANNEL(_si, 0, -1, _address, _bits, \ - _storagebits, _shift, NULL, IIO_TEMP, \ - BIT(IIO_CHAN_INFO_SAMP_FREQ)) - -#define AD_SD_SUPPLY_CHANNEL(_si, _channel, _address, _bits, _storagebits, \ - _shift) \ - __AD_SD_CHANNEL(_si, _channel, -1, _address, _bits, \ - _storagebits, _shift, "supply", IIO_VOLTAGE, \ - BIT(IIO_CHAN_INFO_SAMP_FREQ)) - #endif -- cgit v1.2.3 From 9159c7c06cebfab4bebca0a930b924ad29437638 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Sat, 28 Mar 2020 18:34:21 +0200 Subject: iio: buffer: drop left-over 'stufftoread' field This seems like a left-over from a7348347ba8a4 ("staging:iio: Add polling of events on the ring access chrdev."). Then it was moved into the sca3000 driver around 9dd4694dafbd8 ("iio: staging: sca3000: hide stufftoread logic"), and that one seemed to be the only user of this. Then it eventually was no longer used after 152a6a884ae1 ("staging:iio:accel:sca3000 move to hybrid hard / soft buffer design.") Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer_impl.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index a4d2d8061ef6..1e7edf6bed96 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -115,9 +115,6 @@ struct iio_buffer { */ struct attribute_group scan_el_group; - /* @stufftoread: Flag to indicate new data. */ - bool stufftoread; - /* @attrs: Standard attributes of the buffer. */ const struct attribute **attrs; -- cgit v1.2.3 From 641dedd50c488739b56ef0f716988e646295dce4 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 24 Mar 2020 15:46:29 +0200 Subject: include: fpga: adi-axi-common.h: fixup whitespace tab -> space The initial version use a tab between '#define' & 'ADI_AXI_REG_VERSION'. This changes it to space. The change is purely cosmetic. Acked-by: Moritz Fischer Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/fpga/adi-axi-common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fpga/adi-axi-common.h b/include/linux/fpga/adi-axi-common.h index 7fc95d5c95bb..ebd4e07ae3d8 100644 --- a/include/linux/fpga/adi-axi-common.h +++ b/include/linux/fpga/adi-axi-common.h @@ -11,7 +11,7 @@ #ifndef ADI_AXI_COMMON_H_ #define ADI_AXI_COMMON_H_ -#define ADI_AXI_REG_VERSION 0x0000 +#define ADI_AXI_REG_VERSION 0x0000 #define ADI_AXI_PCORE_VER(major, minor, patch) \ (((major) << 16) | ((minor) << 8) | (patch)) -- cgit v1.2.3 From 20d5fa48d333670ffbc08d387a80710be91259a0 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 24 Mar 2020 15:46:30 +0200 Subject: include: fpga: adi-axi-common.h: add version helper macros The format for all ADI AXI IP cores is the same. i.e. 'major.minor.patch'. This patch adds the helper macros to be re-used in ADI AXI drivers. Acked-by: Moritz Fischer Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/fpga/adi-axi-common.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/adi-axi-common.h b/include/linux/fpga/adi-axi-common.h index ebd4e07ae3d8..141ac3f251e6 100644 --- a/include/linux/fpga/adi-axi-common.h +++ b/include/linux/fpga/adi-axi-common.h @@ -16,4 +16,8 @@ #define ADI_AXI_PCORE_VER(major, minor, patch) \ (((major) << 16) | ((minor) << 8) | (patch)) +#define ADI_AXI_PCORE_VER_MAJOR(version) (((version) >> 16) & 0xff) +#define ADI_AXI_PCORE_VER_MINOR(version) (((version) >> 8) & 0xff) +#define ADI_AXI_PCORE_VER_PATCH(version) ((version) & 0xff) + #endif /* ADI_AXI_COMMON_H_ */ -- cgit v1.2.3 From e0fcca9fbd99e959855aa1d66c125d696f969e68 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 24 Mar 2020 15:46:32 +0200 Subject: iio: buffer-dmaengine: add dev-managed calls for buffer alloc Currently, when using a 'iio_dmaengine_buffer_alloc()', an matching call to 'iio_dmaengine_buffer_free()' must be made. With this change, this can be avoided by using 'devm_iio_dmaengine_buffer_alloc()'. The buffer will get free'd via the device's devres handling. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer-dmaengine.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/buffer-dmaengine.h b/include/linux/iio/buffer-dmaengine.h index b3a57444a886..0e503db71289 100644 --- a/include/linux/iio/buffer-dmaengine.h +++ b/include/linux/iio/buffer-dmaengine.h @@ -14,4 +14,7 @@ struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, const char *channel); void iio_dmaengine_buffer_free(struct iio_buffer *buffer); +struct iio_buffer *devm_iio_dmaengine_buffer_alloc(struct device *dev, + const char *channel); + #endif -- cgit v1.2.3 From ef04070692a21633ec6a60f80c19b6af44b3cf47 Mon Sep 17 00:00:00 2001 From: Michael Hennerich Date: Tue, 24 Mar 2020 15:46:33 +0200 Subject: iio: adc: adi-axi-adc: add support for AXI ADC IP core This change adds support for the Analog Devices Generic AXI ADC IP core. The IP core is used for interfacing with analog-to-digital (ADC) converters that require either a high-speed serial interface (JESD204B/C) or a source synchronous parallel interface (LVDS/CMOS). Usually, some other interface type (i.e SPI) is used as a control interface for the actual ADC, while the IP core (controlled via this driver), will interface to the data-lines of the ADC and handle the streaming of data into memory via DMA. Because of this, the AXI ADC driver needs the other SPI-ADC driver to register with it. The SPI-ADC needs to be register via the SPI framework, while the AXI ADC registers as a platform driver. The two cannot be ordered in a hierarchy as both drivers have their own registers, and trying to organize this [in a hierarchy becomes] problematic when trying to map memory/registers. There are some modes where the AXI ADC can operate as standalone ADC, but those will be implemented at a later point in time. DocLink: https://wiki.analog.com/resources/fpga/docs/axi_adc_ip Signed-off-by: Michael Hennerich Signed-off-by: Lars-Peter Clausen Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/adi-axi-adc.h | 64 +++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) create mode 100644 include/linux/iio/adc/adi-axi-adc.h (limited to 'include/linux') diff --git a/include/linux/iio/adc/adi-axi-adc.h b/include/linux/iio/adc/adi-axi-adc.h new file mode 100644 index 000000000000..c5d48e1c2d36 --- /dev/null +++ b/include/linux/iio/adc/adi-axi-adc.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Analog Devices Generic AXI ADC IP core driver/library + * Link: https://wiki.analog.com/resources/fpga/docs/axi_adc_ip + * + * Copyright 2012-2020 Analog Devices Inc. + */ +#ifndef __ADI_AXI_ADC_H__ +#define __ADI_AXI_ADC_H__ + +struct device; +struct iio_chan_spec; + +/** + * struct adi_axi_adc_chip_info - Chip specific information + * @name Chip name + * @id Chip ID (usually product ID) + * @channels Channel specifications of type @struct axi_adc_chan_spec + * @num_channels Number of @channels + * @scale_table Supported scales by the chip; tuples of 2 ints + * @num_scales Number of scales in the table + * @max_rate Maximum sampling rate supported by the device + */ +struct adi_axi_adc_chip_info { + const char *name; + unsigned int id; + + const struct iio_chan_spec *channels; + unsigned int num_channels; + + const unsigned int (*scale_table)[2]; + int num_scales; + + unsigned long max_rate; +}; + +/** + * struct adi_axi_adc_conv - data of the ADC attached to the AXI ADC + * @chip_info chip info details for the client ADC + * @preenable_setup op to run in the client before enabling the AXI ADC + * @reg_access IIO debugfs_reg_access hook for the client ADC + * @read_raw IIO read_raw hook for the client ADC + * @write_raw IIO write_raw hook for the client ADC + */ +struct adi_axi_adc_conv { + const struct adi_axi_adc_chip_info *chip_info; + + int (*preenable_setup)(struct adi_axi_adc_conv *conv); + int (*reg_access)(struct adi_axi_adc_conv *conv, unsigned int reg, + unsigned int writeval, unsigned int *readval); + int (*read_raw)(struct adi_axi_adc_conv *conv, + struct iio_chan_spec const *chan, + int *val, int *val2, long mask); + int (*write_raw)(struct adi_axi_adc_conv *conv, + struct iio_chan_spec const *chan, + int val, int val2, long mask); +}; + +struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev, + size_t sizeof_priv); + +void *adi_axi_adc_conv_priv(struct adi_axi_adc_conv *conv); + +#endif -- cgit v1.2.3 From c0ae3591d900c0d1a54a86666c2102dd39b3d4f7 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 1 Apr 2020 18:57:06 +0200 Subject: iio: dma-buffer: Cleanup buffer.h/buffer_impl.h includes The IIO DMA buffer is a DMA buffer implementation. As such it should include buffer_impl.h rather than buffer.h. The include to buffer.h in buffer-dma.h should be buffer_impl.h so it has access to the struct iio_buffer definition. The code currently only works because all places that use buffer-dma.h include buffer_impl.h before it. The include to buffer.h in industrialio-buffer-dma.c can be removed since those file does not reference any of buffer consumer functions. Signed-off-by: Lars-Peter Clausen Tested-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer-dma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h index 016d8a068353..ff15c61bf319 100644 --- a/include/linux/iio/buffer-dma.h +++ b/include/linux/iio/buffer-dma.h @@ -11,7 +11,7 @@ #include #include #include -#include +#include struct iio_dma_buffer_queue; struct iio_dma_buffer_ops; -- cgit v1.2.3 From 2e036804d773e00ea19c6f6b8b7a4b8232c77da1 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 10 Apr 2020 12:36:07 +0300 Subject: iio: buffer: remove 'scan_el_attrs' attribute group from buffer struct This field doesn't seem used. It seems that only 'buffer->attrs' was ever used to extend sysfs attributes for an IIO buffer. Moving forward, it may not make sense to keep it. This patch removes the field and it's initialization code. Since we want to rework IIO buffer, to be able to add more buffers per IIO device, we will merge [somehow] the 'buffer' & 'scan_elements' groups, and we will continue to add the attributes to the 'buffer' group. Removing it here, will also make the rework here a bit smaller, since this code will not be present. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer_impl.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index 1e7edf6bed96..a63dc07b7350 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -94,12 +94,6 @@ struct iio_buffer { unsigned int watermark; /* private: */ - /* - * @scan_el_attrs: Control of scan elements if that scan mode - * control method is used. - */ - struct attribute_group *scan_el_attrs; - /* @scan_timestamp: Does the scan mode include a timestamp. */ bool scan_timestamp; -- cgit v1.2.3 From 83af573e980aafa7edf56a449a6e70f6c8ac9792 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:20 +0200 Subject: iio: core: drop devm_iio_device_unregister() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index e975020abaa6..1b2630bc327e 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -593,9 +593,6 @@ void iio_device_unregister(struct iio_dev *indio_dev); * calls iio_device_register() internally. Refer to that function for more * information. * - * If an iio_dev registered with this function needs to be unregistered - * separately, devm_iio_device_unregister() must be used. - * * RETURNS: * 0 on success, negative error number on failure. */ @@ -603,7 +600,6 @@ void iio_device_unregister(struct iio_dev *indio_dev); __devm_iio_device_register((dev), (indio_dev), THIS_MODULE); int __devm_iio_device_register(struct device *dev, struct iio_dev *indio_dev, struct module *this_mod); -void devm_iio_device_unregister(struct device *dev, struct iio_dev *indio_dev); int iio_push_event(struct iio_dev *indio_dev, u64 ev_code, s64 timestamp); int iio_device_claim_direct_mode(struct iio_dev *indio_dev); void iio_device_release_direct_mode(struct iio_dev *indio_dev); -- cgit v1.2.3 From 666e4de43d942fbe0d7f1d9dbc993f5b5c81760c Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:21 +0200 Subject: iio: core: drop devm_iio_triggered_buffer_cleanup() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/triggered_buffer.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/triggered_buffer.h b/include/linux/iio/triggered_buffer.h index 238ad30ce166..e99c91799359 100644 --- a/include/linux/iio/triggered_buffer.h +++ b/include/linux/iio/triggered_buffer.h @@ -18,7 +18,5 @@ int devm_iio_triggered_buffer_setup(struct device *dev, irqreturn_t (*h)(int irq, void *p), irqreturn_t (*thread)(int irq, void *p), const struct iio_buffer_setup_ops *ops); -void devm_iio_triggered_buffer_cleanup(struct device *dev, - struct iio_dev *indio_dev); #endif -- cgit v1.2.3 From 66be392a48f9d5256b4ba582ff06303fe97b5ca2 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:22 +0200 Subject: iio: core: drop devm_iio_device_free() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. This is the last user of 'devm_iio_device_match()', so it can be removed as well in this patch. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 1b2630bc327e..4c1e320ef7ed 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -688,9 +688,7 @@ static inline struct iio_dev *iio_priv_to_dev(void *priv) } void iio_device_free(struct iio_dev *indio_dev); -int devm_iio_device_match(struct device *dev, void *res, void *data); struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); -void devm_iio_device_free(struct device *dev, struct iio_dev *indio_dev); struct iio_trigger *devm_iio_trigger_alloc(struct device *dev, const char *fmt, ...); void devm_iio_trigger_free(struct device *dev, struct iio_trigger *iio_trig); -- cgit v1.2.3 From 83381c9803a00d534f32ab52ed91588601eba43f Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:23 +0200 Subject: iio: core: drop devm_iio_trigger_unregister() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/trigger.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 84995e2967ac..cad8325903f9 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -141,9 +141,6 @@ int __devm_iio_trigger_register(struct device *dev, **/ void iio_trigger_unregister(struct iio_trigger *trig_info); -void devm_iio_trigger_unregister(struct device *dev, - struct iio_trigger *trig_info); - /** * iio_trigger_set_immutable() - set an immutable trigger on destination * -- cgit v1.2.3 From 92b7ed7fe40dd26de62ff8f5aa1605909a14e3ef Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:24 +0200 Subject: iio: core: drop devm_iio_trigger_free() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 4c1e320ef7ed..d63884a54939 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -691,8 +691,6 @@ void iio_device_free(struct iio_dev *indio_dev); struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); struct iio_trigger *devm_iio_trigger_alloc(struct device *dev, const char *fmt, ...); -void devm_iio_trigger_free(struct device *dev, struct iio_trigger *iio_trig); - /** * iio_buffer_enabled() - helper function to test if the buffer is enabled * @indio_dev: IIO device structure for device -- cgit v1.2.3 From fc1f75a0347aecc8b967c8c154564f520d6f4412 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:25 +0200 Subject: iio: inkern: drop devm_iio_channel_release{_all} API calls It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/consumer.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index 2bde8c912d4d..c4118dcb8e05 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -63,15 +63,6 @@ void iio_channel_release(struct iio_channel *chan); */ struct iio_channel *devm_iio_channel_get(struct device *dev, const char *consumer_channel); -/** - * devm_iio_channel_release() - Resource managed version of - * iio_channel_release(). - * @dev: Pointer to consumer device for which resource - * is allocared. - * @chan: The channel to be released. - */ -void devm_iio_channel_release(struct device *dev, struct iio_channel *chan); - /** * iio_channel_get_all() - get all channels associated with a client * @dev: Pointer to consumer device. @@ -106,15 +97,6 @@ void iio_channel_release_all(struct iio_channel *chan); */ struct iio_channel *devm_iio_channel_get_all(struct device *dev); -/** - * devm_iio_channel_release_all() - Resource managed version of - * iio_channel_release_all(). - * @dev: Pointer to consumer device for which resource - * is allocared. - * @chan: Array channel to be released. - */ -void devm_iio_channel_release_all(struct device *dev, struct iio_channel *chan); - struct iio_cb_buffer; /** * iio_channel_get_all_cb() - register callback for triggered capture -- cgit v1.2.3 From 05c09e3cee0aa97a51c2eac1a2f453cac0ba5683 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:26 +0200 Subject: iio: buffer: drop devm_iio_hw_consumer_free() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/hw-consumer.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/hw-consumer.h b/include/linux/iio/hw-consumer.h index 44d48bb1d39f..e8255c2e33bc 100644 --- a/include/linux/iio/hw-consumer.h +++ b/include/linux/iio/hw-consumer.h @@ -14,7 +14,6 @@ struct iio_hw_consumer; struct iio_hw_consumer *iio_hw_consumer_alloc(struct device *dev); void iio_hw_consumer_free(struct iio_hw_consumer *hwc); struct iio_hw_consumer *devm_iio_hw_consumer_alloc(struct device *dev); -void devm_iio_hw_consumer_free(struct device *dev, struct iio_hw_consumer *hwc); int iio_hw_consumer_enable(struct iio_hw_consumer *hwc); void iio_hw_consumer_disable(struct iio_hw_consumer *hwc); -- cgit v1.2.3 From 608d98a2c4a0a72c15fa16ef1542df67afe41fee Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 27 Feb 2020 15:52:27 +0200 Subject: iio: buffer: drop devm_iio_kfifo_free() API call It's unused so far, so it can be removed. Also makes sense to remove it to discourage weird uses of this call during review. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/kfifo_buf.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/kfifo_buf.h b/include/linux/iio/kfifo_buf.h index 764659e01b68..1fc1efa7799d 100644 --- a/include/linux/iio/kfifo_buf.h +++ b/include/linux/iio/kfifo_buf.h @@ -9,6 +9,5 @@ struct iio_buffer *iio_kfifo_allocate(void); void iio_kfifo_free(struct iio_buffer *r); struct iio_buffer *devm_iio_kfifo_allocate(struct device *dev); -void devm_iio_kfifo_free(struct device *dev, struct iio_buffer *r); #endif -- cgit v1.2.3 From 418fd78771220f5e522d02676758ed824c349fd5 Mon Sep 17 00:00:00 2001 From: Clement Leger Date: Fri, 10 Apr 2020 12:24:32 +0200 Subject: remoteproc: add rproc_coredump_set_elf_info This function allows drivers to correctly setup the coredump output elf information. Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Signed-off-by: Clement Leger Link: https://lore.kernel.org/r/20200410102433.2672-2-cleger@kalray.eu Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 9c07d7958c53..0547676479d3 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -518,6 +518,7 @@ struct rproc { struct list_head dump_segments; int nb_vdev; u8 elf_class; + u16 elf_machine; }; /** @@ -622,6 +623,7 @@ int rproc_coredump_add_custom_segment(struct rproc *rproc, struct rproc_dump_segment *segment, void *dest), void *priv); +int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine); static inline struct rproc_vdev *vdev_to_rvdev(struct virtio_device *vdev) { -- cgit v1.2.3 From bb15aded5144d36b2a050e1dad415876c0b94234 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 7 Apr 2020 23:56:43 +0300 Subject: mtd: spi-nor: move #define SPINOR_OP_WRDI The write disable (WRDI) opcode is not really specific to the SST flashes (anymore?) -- move the #define to the main opcode group, just before WREN. Signed-off-by: Sergei Shtylyov Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 1e2af0ec1f03..1cc8ed5d59ed 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -20,6 +20,7 @@ */ /* Flash opcodes. */ +#define SPINOR_OP_WRDI 0x04 /* Write disable */ #define SPINOR_OP_WREN 0x06 /* Write enable */ #define SPINOR_OP_RDSR 0x05 /* Read status register */ #define SPINOR_OP_WRSR 0x01 /* Write status register 1 byte */ @@ -80,7 +81,6 @@ /* Used for SST flashes only. */ #define SPINOR_OP_BP 0x02 /* Byte program */ -#define SPINOR_OP_WRDI 0x04 /* Write disable */ #define SPINOR_OP_AAI_WP 0xad /* Auto address increment word program */ /* Used for S3AN flashes only */ -- cgit v1.2.3 From c84dc6e68a1d2464e050d9694be4e4ff49e32bfd Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 14 Apr 2020 17:04:55 -0700 Subject: dma-pool: add additional coherent pools to map to gfp mask The single atomic pool is allocated from the lowest zone possible since it is guaranteed to be applicable for any DMA allocation. Devices may allocate through the DMA API but not have a strict reliance on GFP_DMA memory. Since the atomic pool will be used for all non-blockable allocations, returning all memory from ZONE_DMA may unnecessarily deplete the zone. Provision for multiple atomic pools that will map to the optimal gfp mask of the device. When allocating non-blockable memory, determine the optimal gfp mask of the device and use the appropriate atomic pool. The coherent DMA mask will remain the same between allocation and free and, thus, memory will be freed to the same atomic pool it was allocated from. __dma_atomic_pool_init() will be changed to return struct gen_pool * later once dynamic expansion is added. Signed-off-by: David Rientjes Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 2 ++ include/linux/dma-mapping.h | 6 +++--- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 24b8684aa21d..136f984df0d9 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -67,6 +67,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, } u64 dma_direct_get_required_mask(struct device *dev); +gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, + u64 *phys_mask); void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 330ad58fbf4d..b43116a6405d 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -630,9 +630,9 @@ void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot, const void *caller); void dma_common_free_remap(void *cpu_addr, size_t size); -bool dma_in_atomic_pool(void *start, size_t size); -void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags); -bool dma_free_from_pool(void *start, size_t size); +void *dma_alloc_from_pool(struct device *dev, size_t size, + struct page **ret_page, gfp_t flags); +bool dma_free_from_pool(struct device *dev, void *start, size_t size); int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, -- cgit v1.2.3 From e9d7144597b10ff13ff2264c059f7d4a7fbc89ac Mon Sep 17 00:00:00 2001 From: Mark Gross Date: Thu, 16 Apr 2020 17:23:10 +0200 Subject: x86/cpu: Add a steppings field to struct x86_cpu_id Intel uses the same family/model for several CPUs. Sometimes the stepping must be checked to tell them apart. On x86 there can be at most 16 steppings. Add a steppings bitmask to x86_cpu_id and a X86_MATCH_VENDOR_FAMILY_MODEL_STEPPING_FEATURE macro and support for matching against family/model/stepping. [ bp: Massage. ] Signed-off-by: Mark Gross Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Reviewed-by: Tony Luck Reviewed-by: Josh Poimboeuf --- include/linux/mod_devicetable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 4c2ddd0941a7..0754b8d71262 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -663,6 +663,7 @@ struct x86_cpu_id { __u16 vendor; __u16 family; __u16 model; + __u16 steppings; __u16 feature; /* bit index */ kernel_ulong_t driver_data; }; @@ -671,6 +672,7 @@ struct x86_cpu_id { #define X86_VENDOR_ANY 0xffff #define X86_FAMILY_ANY 0 #define X86_MODEL_ANY 0 +#define X86_STEPPING_ANY 0 #define X86_FEATURE_ANY 0 /* Same as FPU, you can't test for that */ /* -- cgit v1.2.3 From 02094d54870590a667f822e4032bbd1ba6c48d00 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 8 Apr 2020 19:09:02 +0300 Subject: software node: Allow register and unregister software node groups Sometimes it's more convenient to register a set of individual software nodes grouped together. Add couple of functions for that. Signed-off-by: Andy Shevchenko Acked-by: Rafael J. Wysocki Reviewed-by: Hans de Goede Tested-by: Hans de Goede Reviewed-by: Heikki Krogerus --- include/linux/property.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index d86de017c689..c7b5f3db36aa 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -440,6 +440,9 @@ software_node_find_by_name(const struct software_node *parent, int software_node_register_nodes(const struct software_node *nodes); void software_node_unregister_nodes(const struct software_node *nodes); +int software_node_register_node_group(const struct software_node **node_group); +void software_node_unregister_node_group(const struct software_node **node_group); + int software_node_register(const struct software_node *node); int software_node_notify(struct device *dev, unsigned long action); -- cgit v1.2.3 From 2a6ba3f794e892c37d67b8ebb19487ce105eabc2 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Fri, 27 Mar 2020 10:59:47 +0530 Subject: tee: enable support to register kernel memory Enable support to register kernel memory reference with TEE. This change will allow TEE bus drivers to register memory references. Signed-off-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 1412e9cc79ce..e96154d92b1e 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -26,6 +26,7 @@ #define TEE_SHM_REGISTER BIT(3) /* Memory registered in secure world */ #define TEE_SHM_USER_MAPPED BIT(4) /* Memory mapped in user space */ #define TEE_SHM_POOL BIT(5) /* Memory allocated from pool */ +#define TEE_SHM_KERNEL_MAPPED BIT(6) /* Memory mapped in kernel space */ struct device; struct tee_device; -- cgit v1.2.3 From e44ab4e14d6f4c448ae555132090c1a116b19e5c Mon Sep 17 00:00:00 2001 From: Dejin Zheng Date: Mon, 20 Apr 2020 21:46:46 +0800 Subject: regmap: Simplify implementation of the regmap_read_poll_timeout() macro Simplify the implementation of the macro regmap_read_poll_timeout() by using the macro read_poll_timeout(). Signed-off-by: Dejin Zheng Link: https://lore.kernel.org/r/20200420134647.9121-2-zhengdejin5@gmail.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 25 +++++-------------------- 1 file changed, 5 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 91420af1c30d..b50e930a9c18 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -17,6 +17,7 @@ #include #include #include +#include struct module; struct clk; @@ -130,26 +131,10 @@ struct reg_sequence { */ #define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \ ({ \ - u64 __timeout_us = (timeout_us); \ - unsigned long __sleep_us = (sleep_us); \ - ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \ - int __ret; \ - might_sleep_if(__sleep_us); \ - for (;;) { \ - __ret = regmap_read((map), (addr), &(val)); \ - if (__ret) \ - break; \ - if (cond) \ - break; \ - if ((__timeout_us) && \ - ktime_compare(ktime_get(), __timeout) > 0) { \ - __ret = regmap_read((map), (addr), &(val)); \ - break; \ - } \ - if (__sleep_us) \ - usleep_range((__sleep_us >> 2) + 1, __sleep_us); \ - } \ - __ret ?: ((cond) ? 0 : -ETIMEDOUT); \ + int __ret, __tmp; \ + __tmp = read_poll_timeout(regmap_read, __ret, __ret || (cond), \ + sleep_us, timeout_us, false, (map), (addr), &(val)); \ + __ret ?: __tmp; \ }) /** -- cgit v1.2.3 From 148c01d176237115d9c2805f6d29c0b6a72fbd10 Mon Sep 17 00:00:00 2001 From: Dejin Zheng Date: Mon, 20 Apr 2020 21:46:47 +0800 Subject: regmap: Simplify implementation of the regmap_field_read_poll_timeout() macro Simplify the implementation of the macro regmap_field_read_poll_timeout() by using the macro read_poll_timeout(). Signed-off-by: Dejin Zheng Link: https://lore.kernel.org/r/20200420134647.9121-3-zhengdejin5@gmail.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 23 ++++------------------- 1 file changed, 4 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index b50e930a9c18..4c4fbe4d41a6 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -202,25 +202,10 @@ struct reg_sequence { */ #define regmap_field_read_poll_timeout(field, val, cond, sleep_us, timeout_us) \ ({ \ - u64 __timeout_us = (timeout_us); \ - unsigned long __sleep_us = (sleep_us); \ - ktime_t timeout = ktime_add_us(ktime_get(), __timeout_us); \ - int pollret; \ - might_sleep_if(__sleep_us); \ - for (;;) { \ - pollret = regmap_field_read((field), &(val)); \ - if (pollret) \ - break; \ - if (cond) \ - break; \ - if (__timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \ - pollret = regmap_field_read((field), &(val)); \ - break; \ - } \ - if (__sleep_us) \ - usleep_range((__sleep_us >> 2) + 1, __sleep_us); \ - } \ - pollret ?: ((cond) ? 0 : -ETIMEDOUT); \ + int __ret, __tmp; \ + __tmp = read_poll_timeout(regmap_field_read, __ret, __ret || (cond), \ + sleep_us, timeout_us, false, (field), &(val)); \ + __ret ?: __tmp; \ }) #ifdef CONFIG_REGMAP -- cgit v1.2.3 From b9151e7bca82a17ff7aa442a168e0f924a07443c Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 20 Apr 2020 09:24:52 -0700 Subject: blk-mq: Add blk_mq_delay_run_hw_queues() API call We have: * blk_mq_run_hw_queue() * blk_mq_delay_run_hw_queue() * blk_mq_run_hw_queues() ...but not blk_mq_delay_run_hw_queues(), presumably because nobody needed it before now. Since we need it for a later patch in this series, add it. Signed-off-by: Douglas Anderson Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index b45148ba3291..51fbf6f76593 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -508,6 +508,7 @@ void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); +void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset); -- cgit v1.2.3 From d46430bf5a2298f55e20f59a90ebe3545d273b2f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:28:57 +0200 Subject: block: remove the disk argument from blk_drop_partitions The gendisk can be trivially deducted from the block_device. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 9b3fffdf4011..058d895544c7 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -339,7 +339,7 @@ extern dev_t blk_lookup_devt(const char *name, int partno); int bdev_disk_changed(struct block_device *bdev, bool invalidate); int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); -int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev); +int blk_drop_partitions(struct block_device *bdev); extern void printk_all_partitions(void); extern struct gendisk *__alloc_disk_node(int minors, int node_id); -- cgit v1.2.3 From 02d33b6771fcc63c98cb48cad0cd8b8fb033837a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:29:01 +0200 Subject: block: mark invalidate_partition static invalidate_partition is only used in genhd.c, so mark it static. Also drop the return value given that is is always ignored. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..2b4e9f86b151 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2723,7 +2723,6 @@ extern bool is_bad_inode(struct inode *); extern int revalidate_disk(struct gendisk *); extern int check_disk_change(struct block_device *); extern int __invalidate_device(struct block_device *, bool); -extern int invalidate_partition(struct gendisk *, int); #endif unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); -- cgit v1.2.3 From 9bc5c397d8384b50c8202f4400bf2f87fe8291d9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:29:02 +0200 Subject: block: fold bdev_unhash_inode into invalidate_partition invalidate_partition and bdev_unhash_inode are always paired, and invalidate_partition already does an icache lookup for the block device inode. Piggy back on that to remove the inode from the hash. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2b4e9f86b151..1a95e5158811 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2581,7 +2581,6 @@ extern struct kmem_cache *names_cachep; #ifdef CONFIG_BLOCK extern int register_blkdev(unsigned int, const char *); extern void unregister_blkdev(unsigned int, const char *); -extern void bdev_unhash_inode(dev_t dev); extern struct block_device *bdget(dev_t); extern struct block_device *bdgrab(struct block_device *bdev); extern void bd_set_size(struct block_device *, loff_t size); -- cgit v1.2.3 From eec517cdb4810b3843eb7707971de3164088bff1 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 20 Apr 2020 00:11:50 +0200 Subject: net: Add IF_OPER_TESTING RFC 2863 defines the operational state testing. Add support for this state, both as a IF_LINK_MODE_ and __LINK_STATE_. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/netdevice.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 130a668049ab..0750b54b3765 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -288,6 +288,7 @@ enum netdev_state_t { __LINK_STATE_NOCARRIER, __LINK_STATE_LINKWATCH_PENDING, __LINK_STATE_DORMANT, + __LINK_STATE_TESTING, }; @@ -3907,6 +3908,46 @@ static inline bool netif_dormant(const struct net_device *dev) } +/** + * netif_testing_on - mark device as under test. + * @dev: network device + * + * Mark device as under test (as per RFC2863). + * + * The testing state indicates that some test(s) must be performed on + * the interface. After completion, of the test, the interface state + * will change to up, dormant, or down, as appropriate. + */ +static inline void netif_testing_on(struct net_device *dev) +{ + if (!test_and_set_bit(__LINK_STATE_TESTING, &dev->state)) + linkwatch_fire_event(dev); +} + +/** + * netif_testing_off - set device as not under test. + * @dev: network device + * + * Device is not in testing state. + */ +static inline void netif_testing_off(struct net_device *dev) +{ + if (test_and_clear_bit(__LINK_STATE_TESTING, &dev->state)) + linkwatch_fire_event(dev); +} + +/** + * netif_testing - test if device is under test + * @dev: network device + * + * Check if device is under test + */ +static inline bool netif_testing(const struct net_device *dev) +{ + return test_bit(__LINK_STATE_TESTING, &dev->state); +} + + /** * netif_oper_up - test if device is operational * @dev: network device -- cgit v1.2.3 From 1dbd51d0a71a561056579e2d4f406e5ce5343af0 Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Tue, 10 Dec 2019 13:20:55 +0200 Subject: net/mlx5: Refactor mlx5_accel_esp_create_hw_context parameter list Currently the FPGA IPsec is the only hw implementation of the IPsec acceleration api, and so the mlx5_accel_esp_create_hw_context was wrongly made to suit this HW api, among other in its parameter list and some of its parameter endianness. This implementation might not be suitable for different HW. Refactor by group and pass all function arguments of mlx5_accel_esp_create_hw_context in common mlx5_accel_esp_xfrm_attrs struct field of mlx5_accel_esp_xfrm struct and correct the endianness according to the HW being called. Signed-off-by: Raed Salem Reviewed-by: Boris Pismenny Reviewed-by: Huy Nguyen Signed-off-by: Saeed Mahameed --- include/linux/mlx5/accel.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 5613e677a5f9..b919d143a9a6 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -92,6 +92,18 @@ struct mlx5_accel_esp_xfrm_attrs { union { struct aes_gcm_keymat aes_gcm; } keymat; + + union { + __be32 a4; + __be32 a6[4]; + } saddr; + + union { + __be32 a4; + __be32 a6[4]; + } daddr; + + u8 is_ipv6; }; struct mlx5_accel_esp_xfrm { -- cgit v1.2.3 From 72ef5e52b3f74c0be47b20f5c434b7ecc830cf40 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 14 Apr 2020 18:48:35 +0200 Subject: docs: fix broken references to text files Several references got broken due to txt to ReST conversion. Several of them can be automatically fixed with: scripts/documentation-file-ref-check --fix Reviewed-by: Mathieu Poirier # hwtracing/coresight/Kconfig Reviewed-by: Paul E. McKenney # memory-barrier.txt Acked-by: Alex Shi # translations/zh_CN Acked-by: Federico Vaga # translations/it_IT Acked-by: Marc Zyngier # kvm/arm64 Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/6f919ddb83a33b5f2a63b6b5f0575737bb2b36aa.1586881715.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a323422d783..1f2850465f59 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1219,7 +1219,7 @@ void unpin_user_pages(struct page **pages, unsigned long npages); * used to track the pincount (instead using of the GUP_PIN_COUNTING_BIAS * scheme). * - * For more information, please see Documentation/vm/pin_user_pages.rst. + * For more information, please see Documentation/core-api/pin_user_pages.rst. * * @page: pointer to page to be queried. * @Return: True, if it is likely that the page has been "dma-pinned". @@ -2834,7 +2834,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * releasing pages: get_user_pages*() pages must be released via put_page(), * while pin_user_pages*() pages must be released via unpin_user_page(). * - * Please see Documentation/vm/pin_user_pages.rst for more information. + * Please see Documentation/core-api/pin_user_pages.rst for more information. */ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) -- cgit v1.2.3 From 0c1bc6b84525b96aa9fb8f6fbe8c5cb26a5c0ead Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 14 Apr 2020 18:48:37 +0200 Subject: docs: filesystems: fix renamed references Some filesystem references got broken by a previous patch series I submitted. Address those. Signed-off-by: Mauro Carvalho Chehab Acked-by: David Sterba # fs/affs/Kconfig Link: https://lore.kernel.org/r/57318c53008dbda7f6f4a5a9e5787f4d37e8565a.1586881715.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/kobject.h | 2 +- include/linux/kobject_ns.h | 2 +- include/linux/relay.h | 2 +- include/linux/sysfs.h | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index e2ca0a292e21..fc8d83e91379 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -7,7 +7,7 @@ * Copyright (c) 2006-2008 Greg Kroah-Hartman * Copyright (c) 2006-2008 Novell Inc. * - * Please read Documentation/kobject.txt before using the kobject + * Please read Documentation/core-api/kobject.rst before using the kobject * interface, ESPECIALLY the parts about reference counts and object * destructors. */ diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h index 069aa2ebef90..2b5b64256cf4 100644 --- a/include/linux/kobject_ns.h +++ b/include/linux/kobject_ns.h @@ -8,7 +8,7 @@ * * Split from kobject.h by David Howells (dhowells@redhat.com) * - * Please read Documentation/kobject.txt before using the kobject + * Please read Documentation/core-api/kobject.rst before using the kobject * interface, ESPECIALLY the parts about reference counts and object * destructors. */ diff --git a/include/linux/relay.h b/include/linux/relay.h index c759f96e39c1..e13a333e7c37 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -141,7 +141,7 @@ struct rchan_callbacks * cause relay_open() to create a single global buffer rather * than the default set of per-cpu buffers. * - * See Documentation/filesystems/relay.txt for more info. + * See Documentation/filesystems/relay.rst for more info. */ struct dentry *(*create_buf_file)(const char *filename, struct dentry *parent, diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 80bb865b3a33..86067dbe7745 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -7,7 +7,7 @@ * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo * - * Please see Documentation/filesystems/sysfs.txt for more information. + * Please see Documentation/filesystems/sysfs.rst for more information. */ #ifndef _SYSFS_H_ -- cgit v1.2.3 From ad89c8852fde7ab0c4007f5b753517cf508d12be Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 14 Apr 2020 18:48:44 +0200 Subject: docs: spi: spi.h: fix a doc building warning We need to add a blank line to avoid this warning: ./include/linux/spi/spi.h:401: WARNING: Unexpected indentation. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/1c701b3ac903dc0bc304dca958fbdee53bd38dc3.1586881715.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/spi/spi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 38286de779e3..aac57b5b7c21 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -394,6 +394,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * for example doing DMA mapping. Called from threaded * context. * @transfer_one: transfer a single spi_transfer. + * * - return 0 if the transfer is finished, * - return 1 if the transfer is still in progress. When * the driver is finished with this transfer it must -- cgit v1.2.3 From 4951d27b099bd24f87a093f67d91618742bd3a65 Mon Sep 17 00:00:00 2001 From: Bumsik Kim Date: Fri, 3 Apr 2020 12:15:07 +0900 Subject: watchdog: clarify that stop() is optional The commit d0684c8a9354 ("watchdog: Make stop function optional") made stop function not mandatory, but the comments and the doc weren't reflected. Fix it to clarify. Signed-off-by: Bumsik Kim Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20200403031507.63487-1-k.bumsik@gmail.com Signed-off-by: Jonathan Corbet --- include/linux/watchdog.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 417d9f37077a..1464ce6ffa31 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -37,15 +37,15 @@ struct watchdog_governor; * * The watchdog_ops structure contains a list of low-level operations * that control a watchdog device. It also contains the module that owns - * these operations. The start and stop function are mandatory, all other + * these operations. The start function is mandatory, all other * functions are optional. */ struct watchdog_ops { struct module *owner; /* mandatory operations */ int (*start)(struct watchdog_device *); - int (*stop)(struct watchdog_device *); /* optional operations */ + int (*stop)(struct watchdog_device *); int (*ping)(struct watchdog_device *); unsigned int (*status)(struct watchdog_device *); int (*set_timeout)(struct watchdog_device *, unsigned int); -- cgit v1.2.3 From 90c165f0de3adad4719e65ab0c31d59edf5bd481 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Ca=C3=B1uelo?= Date: Fri, 3 Apr 2020 11:36:17 +0200 Subject: docs: pr_*() kerneldocs and basic printk docs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add kerneldocs comments to the pr_*() macros in printk.h. Add a new rst node in the core-api manual describing the basic usage of printk and the related macro aliases. Signed-off-by: Ricardo Cañuelo Link: https://lore.kernel.org/r/20200403093617.18003-1-ricardo.canuelo@collabora.com Signed-off-by: Jonathan Corbet --- include/linux/printk.h | 112 +++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 100 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index e061635e0409..ccea5d4a509e 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -279,39 +279,116 @@ static inline void printk_safe_flush_on_panic(void) extern int kptr_restrict; +/** + * pr_fmt - used by the pr_*() macros to generate the printk format string + * @fmt: format string passed from a pr_*() macro + * + * This macro can be used to generate a unified format string for pr_*() + * macros. A common use is to prefix all pr_*() messages in a file with a common + * string. For example, defining this at the top of a source file: + * + * #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + * + * would prefix all pr_info, pr_emerg... messages in the file with the module + * name. + */ #ifndef pr_fmt #define pr_fmt(fmt) fmt #endif -/* - * These can be used to print at the various log levels. - * All of these will print unconditionally, although note that pr_debug() - * and other debug macros are compiled out unless either DEBUG is defined - * or CONFIG_DYNAMIC_DEBUG is set. +/** + * pr_emerg - Print an emergency-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_EMERG loglevel. It uses pr_fmt() to + * generate the format string. */ #define pr_emerg(fmt, ...) \ printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) +/** + * pr_alert - Print an alert-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_ALERT loglevel. It uses pr_fmt() to + * generate the format string. + */ #define pr_alert(fmt, ...) \ printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) +/** + * pr_crit - Print a critical-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_CRIT loglevel. It uses pr_fmt() to + * generate the format string. + */ #define pr_crit(fmt, ...) \ printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) +/** + * pr_err - Print an error-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_ERR loglevel. It uses pr_fmt() to + * generate the format string. + */ #define pr_err(fmt, ...) \ printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) +/** + * pr_warn - Print a warning-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_WARNING loglevel. It uses pr_fmt() + * to generate the format string. + */ #define pr_warn(fmt, ...) \ printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) +/** + * pr_notice - Print a notice-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_NOTICE loglevel. It uses pr_fmt() to + * generate the format string. + */ #define pr_notice(fmt, ...) \ printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) +/** + * pr_info - Print an info-level message + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_INFO loglevel. It uses pr_fmt() to + * generate the format string. + */ #define pr_info(fmt, ...) \ printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) -/* - * Like KERN_CONT, pr_cont() should only be used when continuing - * a line with no newline ('\n') enclosed. Otherwise it defaults - * back to KERN_DEFAULT. + +/** + * pr_cont - Continues a previous log message in the same line. + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_CONT loglevel. It should only be + * used when continuing a log message with no newline ('\n') enclosed. Otherwise + * it defaults back to KERN_DEFAULT loglevel. */ #define pr_cont(fmt, ...) \ printk(KERN_CONT fmt, ##__VA_ARGS__) -/* pr_devel() should produce zero code unless DEBUG is defined */ +/** + * pr_devel - Print a debug-level message conditionally + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to a printk with KERN_DEBUG loglevel if DEBUG is + * defined. Otherwise it does nothing. + * + * It uses pr_fmt() to generate the format string. + */ #ifdef DEBUG #define pr_devel(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) @@ -325,8 +402,19 @@ extern int kptr_restrict; #if defined(CONFIG_DYNAMIC_DEBUG) #include -/* dynamic_pr_debug() uses pr_fmt() internally so we don't need it here */ -#define pr_debug(fmt, ...) \ +/** + * pr_debug - Print a debug-level message conditionally + * @fmt: format string + * @...: arguments for the format string + * + * This macro expands to dynamic_pr_debug() if CONFIG_DYNAMIC_DEBUG is + * set. Otherwise, if DEBUG is defined, it's equivalent to a printk with + * KERN_DEBUG loglevel. If DEBUG is not defined it does nothing. + * + * It uses pr_fmt() to generate the format string (dynamic_pr_debug() uses + * pr_fmt() internally). + */ +#define pr_debug(fmt, ...) \ dynamic_pr_debug(fmt, ##__VA_ARGS__) #elif defined(DEBUG) #define pr_debug(fmt, ...) \ -- cgit v1.2.3 From 1487deda19c82d30d1867277e89bc2d515b9d2d4 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Mon, 20 Apr 2020 17:15:58 -0600 Subject: remoteproc: Use kstrdup_const() rather than kstrdup() For cases where @firmware is declared "const char *", use function kstrdup_const() to avoid needlessly creating another copy on the heap. Suggested-by: Bjorn Andersson Signed-off-by: Mathieu Poirier Reviewed-by: Alex Elder Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20200420231601.16781-2-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 0547676479d3..800b4f09dc98 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -489,7 +489,7 @@ struct rproc { struct list_head node; struct iommu_domain *domain; const char *name; - char *firmware; + const char *firmware; void *priv; struct rproc_ops *ops; struct device dev; -- cgit v1.2.3 From 305ac5a766b1d0dd8a4052c8c92e5464888eaa10 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Fri, 17 Apr 2020 19:00:37 +0200 Subject: remoteproc: Add device-managed variants of rproc_alloc/rproc_add Add API functions devm_rproc_alloc() and devm_rproc_add(), which behave like rproc_alloc() and rproc_add() respectively, but register their respective cleanup function to be called on driver detach. Reviewed-by: Bjorn Andersson Signed-off-by: Paul Cercueil Link: https://lore.kernel.org/r/20200417170040.174319-2-paul@crapouillou.net Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 800b4f09dc98..ac4082f12e8b 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -600,6 +600,11 @@ int rproc_add(struct rproc *rproc); int rproc_del(struct rproc *rproc); void rproc_free(struct rproc *rproc); +struct rproc *devm_rproc_alloc(struct device *dev, const char *name, + const struct rproc_ops *ops, + const char *firmware, int len); +int devm_rproc_add(struct device *dev, struct rproc *rproc); + void rproc_add_carveout(struct rproc *rproc, struct rproc_mem_entry *mem); struct rproc_mem_entry * -- cgit v1.2.3 From 812756a82ea51e3c7ff7ba5e6fa3f34345234bc7 Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Tue, 14 Apr 2020 17:56:25 +0200 Subject: kvm_host: unify VM_STAT and VCPU_STAT definitions in a single place The macros VM_STAT and VCPU_STAT are redundantly implemented in multiple files, each used by a different architecure to initialize the debugfs entries for statistics. Since they all have the same purpose, they can be unified in a single common definition in include/linux/kvm_host.h Signed-off-by: Emanuele Giuseppe Esposito Message-Id: <20200414155625.20559-1-eesposit@redhat.com> Acked-by: Cornelia Huck Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 01276e3d01b9..658215f6102c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1130,6 +1130,11 @@ struct kvm_stats_debugfs_item { #define KVM_DBGFS_GET_MODE(dbgfs_item) \ ((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644) +#define VM_STAT(n, x, ...) \ + { n, offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ } +#define VCPU_STAT(n, x, ...) \ + { n, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ } + extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; -- cgit v1.2.3 From c36b71503a2268206ebeda6697094ffb4e7e94c2 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 16 Apr 2020 09:48:07 -0400 Subject: KVM: x86/mmu: Avoid an extra memslot lookup in try_async_pf() for L2 Create a new function kvm_is_visible_memslot() and use it from kvm_is_visible_gfn(); use the new function in try_async_pf() too, to avoid an extra memslot lookup. Opportunistically squish a multi-line comment into a single-line comment. Note, the end result, KVM_PFN_NOSLOT, is unchanged. Cc: Jim Mattson Cc: Rick Edgecombe Suggested-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 658215f6102c..7d4f1eb70274 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1357,6 +1357,12 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ +static inline bool kvm_is_visible_memslot(struct kvm_memory_slot *memslot) +{ + return (memslot && memslot->id < KVM_USER_MEM_SLOTS && + !(memslot->flags & KVM_MEMSLOT_INVALID)); +} + struct kvm_vcpu *kvm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); -- cgit v1.2.3 From 1b94f6f81007b4afaea3480ec018bc9236148961 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Thu, 16 Apr 2020 13:10:57 +0800 Subject: KVM: Remove redundant argument to kvm_arch_vcpu_ioctl_run In earlier versions of kvm, 'kvm_run' was an independent structure and was not included in the vcpu structure. At present, 'kvm_run' is already included in the vcpu structure, so the parameter 'kvm_run' is redundant. This patch simplifies the function definition, removes the extra 'kvm_run' parameter, and extracts it from the 'kvm_vcpu' structure if necessary. Signed-off-by: Tianjia Zhang Message-Id: <20200416051057.26526-1-tianjia.zhang@linux.alibaba.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7d4f1eb70274..5285a5568208 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -866,7 +866,7 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg); -int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run); +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu); int kvm_arch_init(void *opaque); void kvm_arch_exit(void); -- cgit v1.2.3 From 14bbe3e33710be52f21d61253a94c5f44a696d02 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 1 Apr 2020 10:33:43 -0700 Subject: docs: Add rbtree documentation to the core-api This file is close enough to being in rst format that I didn't feel the need to alter it in any way. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Michel Lespinasse Link: https://lore.kernel.org/r/20200401173343.17472-1-willy@infradead.org Signed-off-by: Jonathan Corbet --- include/linux/rbtree.h | 2 +- include/linux/rbtree_augmented.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index 1fd61a9af45c..d7db17996322 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -11,7 +11,7 @@ I know it's not the cleaner way, but in C (not in C++) to get performances and genericity... - See Documentation/rbtree.txt for documentation and samples. + See Documentation/core-api/rbtree.rst for documentation and samples. */ #ifndef _LINUX_RBTREE_H diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 724b0d036b57..d1c53e9d8c75 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -21,7 +21,7 @@ * rb_insert_augmented() and rb_erase_augmented() are intended to be public. * The rest are implementation details you are not expected to depend on. * - * See Documentation/rbtree.txt for documentation and samples. + * See Documentation/core-api/rbtree.rst for documentation and samples. */ struct rb_augment_callbacks { -- cgit v1.2.3 From 51161bfc66a68d21f13d15a689b3ea7980457790 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 19 Apr 2020 18:55:06 +0300 Subject: kernel/module: Hide vermagic header file from general use MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit VERMAGIC* definitions are not supposed to be used by the drivers, see this [1] bug report, so introduce special define to guard inclusion of this header file and define it in kernel/modules.h and in internal script that generates *.mod.c files. In-tree module build: ➜ kernel git:(vermagic) ✗ make clean ➜ kernel git:(vermagic) ✗ make M=drivers/infiniband/hw/mlx5 ➜ kernel git:(vermagic) ✗ modinfo drivers/infiniband/hw/mlx5/mlx5_ib.ko filename: /images/leonro/src/kernel/drivers/infiniband/hw/mlx5/mlx5_ib.ko <...> vermagic: 5.6.0+ SMP mod_unload modversions Out-of-tree module build: ➜ mlx5 make -C /images/leonro/src/kernel clean M=/tmp/mlx5 ➜ mlx5 make -C /images/leonro/src/kernel M=/tmp/mlx5 ➜ mlx5 modinfo /tmp/mlx5/mlx5_ib.ko filename: /tmp/mlx5/mlx5_ib.ko <...> vermagic: 5.6.0+ SMP mod_unload modversions [1] https://lore.kernel.org/lkml/20200411155623.GA22175@zn.tnic Reported-by: Borislav Petkov Acked-by: Borislav Petkov Acked-by: Jessica Yu Co-developed-by: Masahiro Yamada Signed-off-by: Masahiro Yamada Signed-off-by: Leon Romanovsky Signed-off-by: David S. Miller --- include/linux/vermagic.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 9aced11e9000..7768d20ada39 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -1,4 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef INCLUDE_VERMAGIC +#error "This header can be included from kernel/module.c or *.mod.c only" +#endif + #include /* Simply sanity version stamp for modules. */ -- cgit v1.2.3 From fa10fed30f2550313a8284365b3e2398526eb42c Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Sun, 19 Apr 2020 16:10:52 +0200 Subject: proc: allow to mount many instances of proc in one pid namespace This patch allows to have multiple procfs instances inside the same pid namespace. The aim here is lightweight sandboxes, and to allow that we have to modernize procfs internals. 1) The main aim of this work is to have on embedded systems one supervisor for apps. Right now we have some lightweight sandbox support, however if we create pid namespacess we have to manages all the processes inside too, where our goal is to be able to run a bunch of apps each one inside its own mount namespace without being able to notice each other. We only want to use mount namespaces, and we want procfs to behave more like a real mount point. 2) Linux Security Modules have multiple ptrace paths inside some subsystems, however inside procfs, the implementation does not guarantee that the ptrace() check which triggers the security_ptrace_check() hook will always run. We have the 'hidepid' mount option that can be used to force the ptrace_may_access() check inside has_pid_permissions() to run. The problem is that 'hidepid' is per pid namespace and not attached to the mount point, any remount or modification of 'hidepid' will propagate to all other procfs mounts. This also does not allow to support Yama LSM easily in desktop and user sessions. Yama ptrace scope which restricts ptrace and some other syscalls to be allowed only on inferiors, can be updated to have a per-task context, where the context will be inherited during fork(), clone() and preserved across execve(). If we support multiple private procfs instances, then we may force the ptrace_may_access() on /proc// to always run inside that new procfs instances. This will allow to specifiy on user sessions if we should populate procfs with pids that the user can ptrace or not. By using Yama ptrace scope, some restricted users will only be able to see inferiors inside /proc, they won't even be able to see their other processes. Some software like Chromium, Firefox's crash handler, Wine and others are already using Yama to restrict which processes can be ptracable. With this change this will give the possibility to restrict /proc// but more importantly this will give desktop users a generic and usuable way to specifiy which users should see all processes and which users can not. Side notes: * This covers the lack of seccomp where it is not able to parse arguments, it is easy to install a seccomp filter on direct syscalls that operate on pids, however /proc// is a Linux ABI using filesystem syscalls. With this change LSMs should be able to analyze open/read/write/close... In the new patch set version I removed the 'newinstance' option as suggested by Eric W. Biederman. Selftest has been added to verify new behavior. Signed-off-by: Alexey Gladkov Reviewed-by: Alexey Dobriyan Reviewed-by: Kees Cook Signed-off-by: Eric W. Biederman --- include/linux/pid_namespace.h | 12 ------------ include/linux/proc_fs.h | 22 +++++++++++++++++++++- 2 files changed, 21 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 4956e362e55e..5a5cb45ac57e 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -17,12 +17,6 @@ struct fs_pin; -enum { /* definitions for pid_namespace's hide_pid field */ - HIDEPID_OFF = 0, - HIDEPID_NO_ACCESS = 1, - HIDEPID_INVISIBLE = 2, -}; - struct pid_namespace { struct kref kref; struct idr idr; @@ -32,17 +26,11 @@ struct pid_namespace { struct kmem_cache *pid_cachep; unsigned int level; struct pid_namespace *parent; -#ifdef CONFIG_PROC_FS - struct dentry *proc_self; - struct dentry *proc_thread_self; -#endif #ifdef CONFIG_BSD_PROCESS_ACCT struct fs_pin *bacct; #endif struct user_namespace *user_ns; struct ucounts *ucounts; - kgid_t pid_gid; - int hide_pid; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; } __randomize_layout; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 45c05fd9c99d..1b98a41fdd8a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -42,6 +42,26 @@ struct proc_ops { unsigned long (*proc_get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); } __randomize_layout; +/* definitions for hide_pid field */ +enum { + HIDEPID_OFF = 0, + HIDEPID_NO_ACCESS = 1, + HIDEPID_INVISIBLE = 2, +}; + +struct proc_fs_info { + struct pid_namespace *pid_ns; + struct dentry *proc_self; /* For /proc/self */ + struct dentry *proc_thread_self; /* For /proc/thread-self */ + kgid_t pid_gid; + int hide_pid; +}; + +static inline struct proc_fs_info *proc_sb_info(struct super_block *sb) +{ + return sb->s_fs_info; +} + #ifdef CONFIG_PROC_FS typedef int (*proc_write_t)(struct file *, char *, size_t); @@ -176,7 +196,7 @@ int open_related_ns(struct ns_common *ns, /* get the associated pid namespace for a file in procfs */ static inline struct pid_namespace *proc_pid_ns(const struct inode *inode) { - return inode->i_sb->s_fs_info; + return proc_sb_info(inode->i_sb)->pid_ns; } #endif /* _LINUX_PROC_FS_H */ -- cgit v1.2.3 From 24a71ce5c47f6b1b3cdacf544cb24220f5c3b7ef Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Sun, 19 Apr 2020 16:10:53 +0200 Subject: proc: instantiate only pids that we can ptrace on 'hidepid=4' mount option If "hidepid=4" mount option is set then do not instantiate pids that we can not ptrace. "hidepid=4" means that procfs should only contain pids that the caller can ptrace. Signed-off-by: Djalal Harouni Signed-off-by: Alexey Gladkov Reviewed-by: Alexey Dobriyan Reviewed-by: Kees Cook Signed-off-by: Eric W. Biederman --- include/linux/proc_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 1b98a41fdd8a..5bdc117ae947 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -47,6 +47,7 @@ enum { HIDEPID_OFF = 0, HIDEPID_NO_ACCESS = 1, HIDEPID_INVISIBLE = 2, + HIDEPID_NOT_PTRACEABLE = 4, /* Limit pids to only ptraceable pids */ }; struct proc_fs_info { -- cgit v1.2.3 From 6814ef2d992af09451bbeda4770daa204461329e Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Sun, 19 Apr 2020 16:10:54 +0200 Subject: proc: add option to mount only a pids subset This allows to hide all files and directories in the procfs that are not related to tasks. Signed-off-by: Alexey Gladkov Reviewed-by: Alexey Dobriyan Reviewed-by: Kees Cook Signed-off-by: Eric W. Biederman --- include/linux/proc_fs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 5bdc117ae947..8bc31ba5cd9c 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -50,12 +50,19 @@ enum { HIDEPID_NOT_PTRACEABLE = 4, /* Limit pids to only ptraceable pids */ }; +/* definitions for proc mount option pidonly */ +enum { + PROC_PIDONLY_OFF = 0, + PROC_PIDONLY_ON = 1, +}; + struct proc_fs_info { struct pid_namespace *pid_ns; struct dentry *proc_self; /* For /proc/self */ struct dentry *proc_thread_self; /* For /proc/thread-self */ kgid_t pid_gid; int hide_pid; + int pidonly; }; static inline struct proc_fs_info *proc_sb_info(struct super_block *sb) -- cgit v1.2.3 From e61bb8b36a287dddc71bdf30be775e7abcaa595c Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Sun, 19 Apr 2020 16:10:57 +0200 Subject: proc: use named enums for better readability Signed-off-by: Alexey Gladkov Reviewed-by: Alexey Dobriyan Reviewed-by: Kees Cook Signed-off-by: Eric W. Biederman --- include/linux/proc_fs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 8bc31ba5cd9c..2cb424e6f36a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -43,7 +43,7 @@ struct proc_ops { } __randomize_layout; /* definitions for hide_pid field */ -enum { +enum proc_hidepid { HIDEPID_OFF = 0, HIDEPID_NO_ACCESS = 1, HIDEPID_INVISIBLE = 2, @@ -51,7 +51,7 @@ enum { }; /* definitions for proc mount option pidonly */ -enum { +enum proc_pidonly { PROC_PIDONLY_OFF = 0, PROC_PIDONLY_ON = 1, }; @@ -61,8 +61,8 @@ struct proc_fs_info { struct dentry *proc_self; /* For /proc/self */ struct dentry *proc_thread_self; /* For /proc/thread-self */ kgid_t pid_gid; - int hide_pid; - int pidonly; + enum proc_hidepid hide_pid; + enum proc_pidonly pidonly; }; static inline struct proc_fs_info *proc_sb_info(struct super_block *sb) -- cgit v1.2.3 From e64a0e16928415648d53d721b3d6fc3635eddf92 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:42:21 +0200 Subject: block: remove RQF_COPY_USER The RQF_COPY_USER is set for bio where the passthrough request mapping helpers decided that bounce buffering is required. It is then used to pad scatterlist for drivers that required it. But given that non-passthrough requests are per definition aligned, and directly mapped pass-through request must be aligned it is not actually required at all. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 32868fbedc9e..76da162b6ae9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -82,8 +82,6 @@ typedef __u32 __bitwise req_flags_t; /* set for "ide_preempt" requests and also for requests for which the SCSI "quiesce" state must be ignored. */ #define RQF_PREEMPT ((__force req_flags_t)(1 << 8)) -/* contains copies of user pages */ -#define RQF_COPY_USER ((__force req_flags_t)(1 << 9)) /* vaguely specified driver internal error. Ignored by the block layer */ #define RQF_FAILED ((__force req_flags_t)(1 << 10)) /* don't warn about errors */ -- cgit v1.2.3 From 89de1504d53b59b12bfff227328ee3e63dd3a112 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:42:22 +0200 Subject: block: provide a blk_rq_map_sg variant that returns the last element To be able to move some of the special purpose hacks in blk_rq_map_sg into the callers we need a variant that returns the last mapped S/G list element to the caller. Add that variant as __blk_rq_map_sg and make blk_rq_map_sg a trivial inline wrapper around it. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 76da162b6ae9..496dc9491026 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1136,7 +1136,15 @@ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) return max_t(unsigned short, rq->nr_phys_segments, 1); } -extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); +int __blk_rq_map_sg(struct request_queue *q, struct request *rq, + struct scatterlist *sglist, struct scatterlist **last_sg); +static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, + struct scatterlist *sglist) +{ + struct scatterlist *last_sg = NULL; + + return __blk_rq_map_sg(q, rq, sglist, &last_sg); +} extern void blk_dump_rq_flags(struct request *, char *); extern long nr_blockdev_pages(void); -- cgit v1.2.3 From cc97923a5bccc776851c242b61015faf288d5c22 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:42:24 +0200 Subject: block: move dma drain handling to scsi Don't burden the common block code with with specifics of the libata DMA draining mechanism. Instead move most of the code to the scsi midlayer. That also means the nr_phys_segments adjustments in the blk-mq fast path can go away entirely, given that SCSI never looks at nr_phys_segments after mapping the request to a scatterlist. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 ------- include/linux/libata.h | 2 ++ 2 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 496dc9491026..8e4726bce498 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -288,7 +288,6 @@ struct blk_queue_ctx; typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); struct bio_vec; -typedef int (dma_drain_needed_fn)(struct request *); enum blk_eh_timer_return { BLK_EH_DONE, /* drivers has completed the command */ @@ -397,7 +396,6 @@ struct request_queue { struct rq_qos *rq_qos; make_request_fn *make_request_fn; - dma_drain_needed_fn *dma_drain_needed; const struct blk_mq_ops *mq_ops; @@ -467,8 +465,6 @@ struct request_queue { */ unsigned long nr_requests; /* Max # of requests */ - unsigned int dma_drain_size; - void *dma_drain_buffer; unsigned int dma_pad_mask; unsigned int dma_alignment; @@ -1097,9 +1093,6 @@ extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset); extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b); extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); -extern int blk_queue_dma_drain(struct request_queue *q, - dma_drain_needed_fn *dma_drain_needed, - void *buf, unsigned int size); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_dma_alignment(struct request_queue *, int); diff --git a/include/linux/libata.h b/include/linux/libata.h index cffa4714bfa8..af832852e620 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1092,6 +1092,7 @@ extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd, #define ATA_SCSI_COMPAT_IOCTL /* empty */ #endif extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd); +bool ata_scsi_dma_need_drain(struct request *rq); extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev, unsigned int cmd, void __user *arg); extern bool ata_link_online(struct ata_link *link); @@ -1387,6 +1388,7 @@ extern struct device_attribute *ata_common_sdev_attrs[]; .ioctl = ata_scsi_ioctl, \ ATA_SCSI_COMPAT_IOCTL \ .queuecommand = ata_scsi_queuecmd, \ + .dma_need_drain = ata_scsi_dma_need_drain, \ .can_queue = ATA_DEF_QUEUE, \ .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ .this_id = ATA_SHT_THIS_ID, \ -- cgit v1.2.3 From bdf8710d69f82ee6fd41b0166300c3306898b3c1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2020 09:42:25 +0200 Subject: block: move dma_pad handling from blk_rq_map_sg into the callers There are only two callers of blk_rq_map_sg/__blk_rq_map_sg that set the dma_pad value in the queue. Move the handling into those callers instead of burdening the common code, and move the ->extra_len field from struct request to struct scsi_cmnd. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8e4726bce498..f00bd4042295 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -224,8 +224,6 @@ struct request { unsigned short write_hint; unsigned short ioprio; - unsigned int extra_len; /* length of alignment and padding */ - enum mq_rq_state state; refcount_t ref; -- cgit v1.2.3 From 66648766ef38d8d6c48ded2f59cf98420aec2cdb Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Thu, 2 Apr 2020 19:25:07 +0200 Subject: mm: Remove MPX leftovers Remove MPX leftovers in generic code. Fixes: 45fc24e89b7c ("x86/mpx: remove MPX from arch/x86") Signed-off-by: Jimmy Assarsson Signed-off-by: Borislav Petkov Acked-by: Dave Hansen Link: https://lkml.kernel.org/r/20200402172507.2786-1-jimmyassarsson@gmail.com --- include/linux/mm.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a323422d783..e1882eec1752 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -329,13 +329,6 @@ extern unsigned int kobjsize(const void *objp); # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif -#if defined(CONFIG_X86_INTEL_MPX) -/* MPX specific bounds table or bounds directory */ -# define VM_MPX VM_HIGH_ARCH_4 -#else -# define VM_MPX VM_NONE -#endif - #ifndef VM_GROWSUP # define VM_GROWSUP VM_NONE #endif -- cgit v1.2.3 From 0a32f1ff2a2e41404deaba5fb32f8a0d640c0974 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 20 Apr 2020 20:21:11 +0200 Subject: net: phy: broadcom: add helper to write/read RDB registers RDB (Register Data Base) registers are used on newer Broadcom PHYs. Add helper to read, write and modify these registers. Signed-off-by: Michael Walle Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 7e1d857c8468..897b69309964 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -115,6 +115,9 @@ #define MII_BCM54XX_SHD_VAL(x) ((x & 0x1f) << 10) #define MII_BCM54XX_SHD_DATA(x) ((x & 0x3ff) << 0) +#define MII_BCM54XX_RDB_ADDR 0x1e +#define MII_BCM54XX_RDB_DATA 0x1f + /* * AUXILIARY CONTROL SHADOW ACCESS REGISTERS. (PHY REG 0x18) */ -- cgit v1.2.3 From 6937602ed3f9ebd46ed6a6b5e609c0ae4ed99008 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 20 Apr 2020 20:21:12 +0200 Subject: net: phy: add Broadcom BCM54140 support The Broadcom BCM54140 is a Quad SGMII/QSGMII Copper/Fiber Gigabit Ethernet transceiver. This also adds support for tunables to set and get downshift and energy detect auto power-down. The PHY has four ports and each port has its own PHY address. There are per-port registers as well as global registers. Unfortunately, the global registers can only be accessed by reading and writing from/to the PHY address of the first port. Further, there is no way to find out what port you actually are by just reading the per-port registers. We therefore, have to scan the bus on the PHY probe to determine the port and thus what address we need to access the global registers. Signed-off-by: Michael Walle Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 897b69309964..8be150e69c7c 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -25,6 +25,7 @@ #define PHY_ID_BCM5461 0x002060c0 #define PHY_ID_BCM54612E 0x03625e60 #define PHY_ID_BCM54616S 0x03625d10 +#define PHY_ID_BCM54140 0xae025019 #define PHY_ID_BCM57780 0x03625d90 #define PHY_ID_BCM89610 0x03625cd0 -- cgit v1.2.3 From 38f961e744840db9044af68f4773ae5feae60a89 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 20 Apr 2020 23:29:05 +0200 Subject: net: phy: add device-managed devm_mdiobus_register If there's no special ordering requirement for mdiobus_unregister(), then driver code can be simplified by using a device-managed version of mdiobus_register(). Prerequisite is that bus allocation has been done device-managed too. Else mdiobus_free() may be called whilst bus is still registered, resulting in a BUG_ON(). Therefore let devm_mdiobus_register() return -EPERM if bus was allocated non-managed. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 2432ca463ddc..3941a6bcba10 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -241,6 +241,9 @@ struct mii_bus { int (*reset)(struct mii_bus *bus); struct mdio_bus_stats stats[PHY_MAX_ADDR]; + unsigned int is_managed:1; /* is device-managed */ + unsigned int is_managed_registered:1; + /* * A lock to ensure that only one thing can read/write * the MDIO bus at a time @@ -286,6 +289,20 @@ static inline struct mii_bus *mdiobus_alloc(void) int __mdiobus_register(struct mii_bus *bus, struct module *owner); #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) +static inline int devm_mdiobus_register(struct mii_bus *bus) +{ + int ret; + + if (!bus->is_managed) + return -EPERM; + + ret = mdiobus_register(bus); + if (!ret) + bus->is_managed_registered = 1; + + return ret; +} + void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); -- cgit v1.2.3 From 5972157c2dde11698d7bcfc55621107d97121c87 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 22 Apr 2020 11:24:55 +0200 Subject: net: mdio: of: export part of of_mdiobus_register_phy() This function will be needed in tja11xx driver for secondary PHY support. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 491a2b7e77c1..0f61a4ac6bcf 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -30,7 +30,9 @@ extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); extern int of_phy_register_fixed_link(struct device_node *np); extern void of_phy_deregister_fixed_link(struct device_node *np); extern bool of_phy_is_fixed_link(struct device_node *np); - +extern int of_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct device_node *child, u32 addr); static inline int of_mdio_parse_addr(struct device *dev, const struct device_node *np) @@ -118,6 +120,13 @@ static inline bool of_phy_is_fixed_link(struct device_node *np) { return false; } + +static inline int of_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct device_node *child, u32 addr) +{ + return -ENOSYS; +} #endif -- cgit v1.2.3 From 33467ac3c8dc80575e1b158e78d0c30ab33c1b08 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Thu, 16 Apr 2020 19:20:35 -0500 Subject: remoteproc: Add prepare and unprepare ops On some SoC architecture, it is needed to enable HW like clock, bus, regulator, memory region... before loading co-processor firmware. This patch introduces prepare and unprepare ops to execute platform specific function before firmware loading and after stop execution. Signed-off-by: Loic Pallardy Signed-off-by: Suman Anna Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200417002036.24359-2-s-anna@ti.com Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index ac4082f12e8b..0468be4d02f4 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -355,6 +355,8 @@ enum rsc_handling_status { /** * struct rproc_ops - platform-specific device handlers + * @prepare: prepare device for code loading + * @unprepare: unprepare device after stop * @start: power on the device and boot it * @stop: power off the device * @kick: kick a virtqueue (virtqueue id given as a parameter) @@ -373,6 +375,8 @@ enum rsc_handling_status { * panic at least the returned number of milliseconds */ struct rproc_ops { + int (*prepare)(struct rproc *rproc); + int (*unprepare)(struct rproc *rproc); int (*start)(struct rproc *rproc); int (*stop)(struct rproc *rproc); void (*kick)(struct rproc *rproc, int vqid); -- cgit v1.2.3 From 5cc415001bca8fe0e3f0ee6d58a953a314dd9751 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 6 Apr 2020 12:41:52 +0200 Subject: Drivers: hv: avoid passing opaque pointer to vmbus_onmessage() vmbus_onmessage() doesn't need the header of the message, it only uses it to get to the payload, we can pass the pointer to the payload directly. Signed-off-by: Vitaly Kuznetsov Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20200406104154.45010-4-vkuznets@redhat.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 692c89ccf5df..cbd24f4e68d1 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1017,7 +1017,7 @@ static inline void clear_low_latency_mode(struct vmbus_channel *c) c->low_latency = false; } -void vmbus_onmessage(void *context); +void vmbus_onmessage(struct vmbus_channel_message_header *hdr); int vmbus_request_offers(void); -- cgit v1.2.3 From 8b6a877c060ed6b86878fe66c7c6493a6054cf23 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 6 Apr 2020 02:15:06 +0200 Subject: Drivers: hv: vmbus: Replace the per-CPU channel lists with a global array of channels When Hyper-V sends an interrupt to the guest, the guest has to figure out which channel the interrupt is associated with. Hyper-V sets a bit in a memory page that is shared with the guest, indicating a particular "relid" that the interrupt is associated with. The current Linux code then uses a set of per-CPU linked lists to map a given "relid" to a pointer to a channel structure. This design introduces a synchronization problem if the CPU that Hyper-V will interrupt for a certain channel is changed. If the interrupt comes on the "old CPU" and the channel was already moved to the per-CPU list of the "new CPU", then the relid -> channel mapping will fail and the interrupt is dropped. Similarly, if the interrupt comes on the new CPU but the channel was not moved to the per-CPU list of the new CPU, then the mapping will fail and the interrupt is dropped. Relids are integers ranging from 0 to 2047. The mapping from relids to channel structures can be done by setting up an array with 2048 entries, each entry being a pointer to a channel structure (hence total size ~16K bytes, which is not a problem). The array is global, so there are no per-CPU linked lists to update. The array can be searched and updated by loading from/storing to the array at the specified index. With no per-CPU data structures, the above mentioned synchronization problem is avoided and the relid2channel() function gets simpler. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/20200406001514.19876-4-parri.andrea@gmail.com Reviewed-by: Michael Kelley Signed-off-by: Wei Liu --- include/linux/hyperv.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index cbd24f4e68d1..f5b3f008c55a 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -854,11 +854,6 @@ struct vmbus_channel { * Support per-channel state for use by vmbus drivers. */ void *per_channel_state; - /* - * To support per-cpu lookup mapping of relid to channel, - * link up channels based on their CPU affinity. - */ - struct list_head percpu_list; /* * Defer freeing channel until after all cpu's have -- cgit v1.2.3 From 9403b66e6161130ebae7e55a97491c84c1ad6f9f Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 6 Apr 2020 02:15:09 +0200 Subject: Drivers: hv: vmbus: Use a spin lock for synchronizing channel scheduling vs. channel removal Since vmbus_chan_sched() dereferences the ring buffer pointer, we have to make sure that the ring buffer data structures don't get freed while such dereferencing is happening. Current code does this by sending an IPI to the CPU that is allowed to access that ring buffer from interrupt level, cf., vmbus_reset_channel_cb(). But with the new functionality to allow changing the CPU that a channel will interrupt, we can't be sure what CPU will be running the vmbus_chan_sched() function for a particular channel, so the current IPI mechanism is infeasible. Instead synchronize vmbus_chan_sched() and vmbus_reset_channel_cb() by using the (newly introduced) per-channel spin lock "sched_lock". Move the test for onchannel_callback being NULL before the "switch" control statement in vmbus_chan_sched(), in order to not access the ring buffer if the vmbus_reset_channel_cb() has been completed on the channel. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/20200406001514.19876-7-parri.andrea@gmail.com Reviewed-by: Michael Kelley Signed-off-by: Wei Liu --- include/linux/hyperv.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index f5b3f008c55a..62b2c11d0875 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -771,6 +771,12 @@ struct vmbus_channel { void (*onchannel_callback)(void *context); void *channel_callback_context; + /* + * Synchronize channel scheduling and channel removal; see the inline + * comments in vmbus_chan_sched() and vmbus_reset_channel_cb(). + */ + spinlock_t sched_lock; + /* * A channel can be marked for one of three modes of reading: * BATCHED - callback called from taslket and should read -- cgit v1.2.3 From 8ef4c4abbbcdcd9d4bc0fd9454df03e6dac24b73 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 6 Apr 2020 02:15:11 +0200 Subject: Drivers: hv: vmbus: Remove the unused HV_LOCALIZED channel affinity logic The logic is unused since commit 509879bdb30b8 ("Drivers: hv: Introduce a policy for controlling channel affinity"). This logic assumes that a channel target_cpu doesn't change during the lifetime of a channel, but this assumption is incompatible with the new functionality that allows changing the vCPU a channel will interrupt. Signed-off-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/20200406001514.19876-9-parri.andrea@gmail.com Reviewed-by: Michael Kelley Signed-off-by: Wei Liu --- include/linux/hyperv.h | 27 --------------------------- 1 file changed, 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 62b2c11d0875..247356dbd742 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -689,11 +689,6 @@ union hv_connection_id { } u; }; -enum hv_numa_policy { - HV_BALANCED = 0, - HV_LOCALIZED, -}; - enum vmbus_device_type { HV_IDE = 0, HV_SCSI, @@ -808,10 +803,6 @@ struct vmbus_channel { u32 target_vp; /* The corresponding CPUID in the guest */ u32 target_cpu; - /* - * State to manage the CPU affiliation of channels. - */ - struct cpumask alloced_cpus_in_node; int numa_node; /* * Support for sub-channels. For high performance devices, @@ -898,18 +889,6 @@ struct vmbus_channel { */ bool low_latency; - /* - * NUMA distribution policy: - * We support two policies: - * 1) Balanced: Here all performance critical channels are - * distributed evenly amongst all the NUMA nodes. - * This policy will be the default policy. - * 2) Localized: All channels of a given instance of a - * performance critical service will be assigned CPUs - * within a selected NUMA node. - */ - enum hv_numa_policy affinity_policy; - bool probe_done; /* @@ -965,12 +944,6 @@ static inline bool is_sub_channel(const struct vmbus_channel *c) return c->offermsg.offer.sub_channel_index != 0; } -static inline void set_channel_affinity_state(struct vmbus_channel *c, - enum hv_numa_policy policy) -{ - c->affinity_policy = policy; -} - static inline void set_channel_read_mode(struct vmbus_channel *c, enum hv_callback_mode mode) { -- cgit v1.2.3 From 7527810573436f00e582d3d5ef2eb3c027c98d7d Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 6 Apr 2020 02:15:13 +0200 Subject: Drivers: hv: vmbus: Introduce the CHANNELMSG_MODIFYCHANNEL message type VMBus version 4.1 and later support the CHANNELMSG_MODIFYCHANNEL(22) message type which can be used to request Hyper-V to change the vCPU that a channel will interrupt. Introduce the CHANNELMSG_MODIFYCHANNEL message type, and define the vmbus_send_modifychannel() function to send CHANNELMSG_MODIFYCHANNEL requests to the host via a hypercall. The function is then used to define a sysfs "store" operation, which allows to change the (v)CPU the channel will interrupt by using the sysfs interface. The feature can be used for load balancing or other purposes. One interesting catch here is that Hyper-V can *not* currently ACK CHANNELMSG_MODIFYCHANNEL messages with the promise that (after the ACK is sent) the channel won't send any more interrupts to the "old" CPU. The peculiarity of the CHANNELMSG_MODIFYCHANNEL messages is problematic if the user want to take a CPU offline, since we don't want to take a CPU offline (and, potentially, "lose" channel interrupts on such CPU) if the host is still processing a CHANNELMSG_MODIFYCHANNEL message associated to that CPU. It is worth mentioning, however, that we have been unable to observe the above mentioned "race": in all our tests, CHANNELMSG_MODIFYCHANNEL requests appeared *as if* they were processed synchronously by the host. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/20200406001514.19876-11-parri.andrea@gmail.com Reviewed-by: Michael Kelley [ wei: fix conflict in channel_mgmt.c ] Signed-off-by: Wei Liu --- include/linux/hyperv.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 247356dbd742..b85d7580f2c1 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -425,7 +425,7 @@ enum vmbus_channel_message_type { CHANNELMSG_19 = 19, CHANNELMSG_20 = 20, CHANNELMSG_TL_CONNECT_REQUEST = 21, - CHANNELMSG_22 = 22, + CHANNELMSG_MODIFYCHANNEL = 22, CHANNELMSG_TL_CONNECT_RESULT = 23, CHANNELMSG_COUNT }; @@ -620,6 +620,13 @@ struct vmbus_channel_tl_connect_request { guid_t host_service_id; } __packed; +/* Modify Channel parameters, cf. vmbus_send_modifychannel() */ +struct vmbus_channel_modifychannel { + struct vmbus_channel_message_header header; + u32 child_relid; + u32 target_vp; +} __packed; + struct vmbus_channel_version_response { struct vmbus_channel_message_header header; u8 version_supported; @@ -1505,6 +1512,7 @@ extern __u32 vmbus_proto_version; int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id, const guid_t *shv_host_servie_id); +int vmbus_send_modifychannel(u32 child_relid, u32 target_vp); void vmbus_set_event(struct vmbus_channel *channel); /* Get the start of the ring buffer. */ -- cgit v1.2.3 From 6824f0ce38cb4b903a3cbf00dd528861f6c2ea7c Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Fri, 3 Apr 2020 14:43:23 +0100 Subject: parport: Add comments for parport_register_dev_model() In preparation to remove parport_register_device(), copy the comments to parport_register_dev_model() and modify the parameters according to what parport_register_dev_model() has. Signed-off-by: Sudip Mukherjee Link: https://lore.kernel.org/r/20200403134325.11523-9-sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/parport.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/parport.h b/include/linux/parport.h index 13932ce8b37b..36a0f6270238 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -337,6 +337,10 @@ struct pardevice *parport_register_device(struct parport *port, void (*irq_func)(void *), int flags, void *handle); +/* + * parport_register_dev_model declares that a device is connected to a + * port, and tells the kernel all it needs to know. + */ struct pardevice * parport_register_dev_model(struct parport *port, const char *name, const struct pardev_cb *par_dev_cb, int cnt); -- cgit v1.2.3 From bae9defb06a781083844cafd0a359f423cd98388 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Fri, 3 Apr 2020 14:43:24 +0100 Subject: parport: remove unused parport_register_device() All the drivers that are using parallel port has been converted to use the new device model api, and parport_register_device() is no longer used. Signed-off-by: Sudip Mukherjee Link: https://lore.kernel.org/r/20200403134325.11523-10-sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/parport.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/parport.h b/include/linux/parport.h index 36a0f6270238..1fb508c19e83 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -325,18 +325,6 @@ struct pardev_cb { unsigned int flags; }; -/* parport_register_device declares that a device is connected to a - port, and tells the kernel all it needs to know. - - pf is the preemption function (may be NULL for no callback) - - kf is the wake-up function (may be NULL for no callback) - - irq_func is the interrupt handler (may be NULL for no interrupts) - - handle is a user pointer that gets handed to callback functions. */ -struct pardevice *parport_register_device(struct parport *port, - const char *name, - int (*pf)(void *), void (*kf)(void *), - void (*irq_func)(void *), - int flags, void *handle); - /* * parport_register_dev_model declares that a device is connected to a * port, and tells the kernel all it needs to know. -- cgit v1.2.3 From 5d1c9a114a6efba2c8391e39d4ac3e4e5c7b6d32 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 7 Apr 2020 18:59:51 +0300 Subject: net/mlx5: Update vport.c to new cmd interface Do mass update of vport.c to reuse newly introduced mlx5_cmd_exec_in*() interfaces. Signed-off-by: Leon Romanovsky --- include/linux/mlx5/vport.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 16060fb9b5e5..8170da1e9f70 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -127,8 +127,7 @@ int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport, u8 other_vport, u64 *rx_discard_vport_down, u64 *tx_discard_vport_down); int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport, - int vf, u8 port_num, void *out, - size_t out_sz); + int vf, u8 port_num, void *out); int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev, u8 other_vport, u8 port_num, int vf, -- cgit v1.2.3 From d1f620500cde5c72c7b96a19474733c4c6c67f38 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 9 Apr 2020 11:39:14 +0300 Subject: net/mlx5: Update cq.c to new cmd interface Do mass update of cq.c to reuse newly introduced mlx5_cmd_exec_in*() interfaces. Reviewed-by: Moshe Shemesh Signed-off-by: Leon Romanovsky --- include/linux/mlx5/cq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 40748fc1b11b..b5a9399e07ee 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -188,7 +188,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); int mlx5_core_query_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, - u32 *out, int outlen); + u32 *out); int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen); int mlx5_core_modify_cq_moderation(struct mlx5_core_dev *dev, -- cgit v1.2.3 From e0b4b4722dfac09658d1519b296cf8dc349a2451 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 9 Apr 2020 21:03:33 +0300 Subject: net/mlx5: Update transobj.c new cmd interface Do mass update of transobj.c to reuse newly introduced mlx5_cmd_exec_in*() interfaces. Signed-off-by: Leon Romanovsky --- include/linux/mlx5/transobj.h | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index dc6b1e7cb8c4..028f442530cf 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -39,27 +39,20 @@ int mlx5_core_alloc_transport_domain(struct mlx5_core_dev *dev, u32 *tdn); void mlx5_core_dealloc_transport_domain(struct mlx5_core_dev *dev, u32 tdn); int mlx5_core_create_rq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *rqn); -int mlx5_core_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in, int inlen); +int mlx5_core_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in); void mlx5_core_destroy_rq(struct mlx5_core_dev *dev, u32 rqn); int mlx5_core_query_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *out); int mlx5_core_create_sq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *sqn); -int mlx5_core_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in, int inlen); +int mlx5_core_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in); void mlx5_core_destroy_sq(struct mlx5_core_dev *dev, u32 sqn); int mlx5_core_query_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *out); int mlx5_core_query_sq_state(struct mlx5_core_dev *dev, u32 sqn, u8 *state); -int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen, - u32 *tirn); -int mlx5_core_create_tir_out(struct mlx5_core_dev *dev, - u32 *in, int inlen, - u32 *out, int outlen); -int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in, - int inlen); +int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, u32 *tirn); +int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in); void mlx5_core_destroy_tir(struct mlx5_core_dev *dev, u32 tirn); -int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen, - u32 *tisn); -int mlx5_core_modify_tis(struct mlx5_core_dev *dev, u32 tisn, u32 *in, - int inlen); +int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, u32 *tisn); +int mlx5_core_modify_tis(struct mlx5_core_dev *dev, u32 tisn, u32 *in); void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn); int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *rqtn); -- cgit v1.2.3 From 6f8b12d661d09b488b9ac879b8eafbd2cc4a1450 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 Apr 2020 09:13:27 -0700 Subject: net: napi: add hard irqs deferral feature Back in commit 3b47d30396ba ("net: gro: add a per device gro flush timer") we added the ability to arm one high resolution timer, that we used to keep not-complete packets in GRO engine a bit longer, hoping that further frames might be added to them. Since then, we added the napi_complete_done() interface, and commit 364b6055738b ("net: busy-poll: return busypolling status to drivers") allowed drivers to avoid re-arming NIC interrupts if we made a promise that their NAPI poll() handler would be called in the near future. This infrastructure can be leveraged, thanks to a new device parameter, which allows to arm the napi hrtimer, instead of re-arming the device hard IRQ. We have noticed that on some servers with 32 RX queues or more, the chit-chat between the NIC and the host caused by IRQ delivery and re-arming could hurt throughput by ~20% on 100Gbit NIC. In contrast, hrtimers are using local (percpu) resources and might have lower cost. The new tunable, named napi_defer_hard_irqs, is placed in the same hierarchy than gro_flush_timeout (/sys/class/net/ethX/) By default, both gro_flush_timeout and napi_defer_hard_irqs are zero. This patch does not change the prior behavior of gro_flush_timeout if used alone : NIC hard irqs should be rearmed as before. One concrete usage can be : echo 20000 >/sys/class/net/eth1/gro_flush_timeout echo 10 >/sys/class/net/eth1/napi_defer_hard_irqs If at least one packet is retired, then we will reset napi counter to 10 (napi_defer_hard_irqs), ensuring at least 10 periodic scans of the queue. On busy queues, this should avoid NIC hard IRQ, while before this patch IRQ avoidance was only possible if napi->poll() was exhausting its budget and not call napi_complete_done(). This feature also can be used to work around some non-optimal NIC irq coalescing strategies. Having the ability to insert XX usec delays between each napi->poll() can increase cache efficiency, since we increase batch sizes. It also keeps serving cpus not idle too long, reducing tail latencies. Co-developed-by: Luigi Rizzo Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0750b54b3765..5a8d40f1ffe2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -329,6 +329,7 @@ struct napi_struct { unsigned long state; int weight; + int defer_hard_irqs_count; unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL @@ -1995,6 +1996,7 @@ struct net_device { struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; + int napi_defer_hard_irqs; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; -- cgit v1.2.3 From e7d3c33c58e0108e38e969239cd3b3678a5d8ac5 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 16 Apr 2020 11:15:42 +0300 Subject: mfd: intel_soc_pmic: Add SCU IPC member to struct intel_soc_pmic Both PMIC drivers (intel_soc_pmic_mrfld and intel_soc_pmic_bxtwc) will be using this field going forward to access the SCU IPC instance. While there add kernel-doc for the intel_soc_pmic structure. Signed-off-by: Mika Westerberg Reviewed-by: Andy Shevchenko Signed-off-by: Lee Jones --- include/linux/mfd/intel_soc_pmic.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index bfecd6bd4990..6a88e34cb955 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -13,6 +13,20 @@ #include +/** + * struct intel_soc_pmic - Intel SoC PMIC data + * @irq: Master interrupt number of the parent PMIC device + * @regmap: Pointer to the parent PMIC device regmap structure + * @irq_chip_data: IRQ chip data for the PMIC itself + * @irq_chip_data_pwrbtn: Chained IRQ chip data for the Power Button + * @irq_chip_data_tmu: Chained IRQ chip data for the Time Management Unit + * @irq_chip_data_bcu: Chained IRQ chip data for the Burst Control Unit + * @irq_chip_data_adc: Chained IRQ chip data for the General Purpose ADC + * @irq_chip_data_chgr: Chained IRQ chip data for the External Charger + * @irq_chip_data_crit: Chained IRQ chip data for the Critical Event Handler + * @dev: Pointer to the parent PMIC device + * @scu: Pointer to the SCU IPC device data structure + */ struct intel_soc_pmic { int irq; struct regmap *regmap; @@ -24,6 +38,7 @@ struct intel_soc_pmic { struct regmap_irq_chip_data *irq_chip_data_chgr; struct regmap_irq_chip_data *irq_chip_data_crit; struct device *dev; + struct intel_scu_ipc_dev *scu; }; int intel_soc_pmic_exec_mipi_pmic_seq_element(u16 i2c_address, u32 reg_address, -- cgit v1.2.3 From 25f1ca31e230598eaf3c38d387a355a64bd772a7 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 16 Apr 2020 11:15:51 +0300 Subject: platform/x86: intel_pmc_ipc: Convert to MFD This driver only creates a bunch of platform devices sharing resources belonging to the PMC device. This is pretty much what MFD subsystem is for so move the driver there, renaming it to intel_pmc_bxt.c which should be more clear what it is. MFD subsystem provides nice helper APIs for subdevice creation so convert the driver to use those. Unfortunately the ACPI device includes separate resources for most of the subdevices so we cannot simply call mfd_add_devices() to create all of them but instead we need to call it separately for each device. The new MFD driver continues to expose two sysfs attributes that allow userspace to send IPC commands to the PMC/SCU to avoid breaking any existing applications that may use these. Generally this is bad idea so document this in the ABI documentation. Signed-off-by: Mika Westerberg Reviewed-by: Andy Shevchenko Signed-off-by: Lee Jones --- include/linux/mfd/intel_pmc_bxt.h | 53 ++++++++++++++++++++++++++++++++++ include/linux/platform_data/itco_wdt.h | 11 ++++--- 2 files changed, 60 insertions(+), 4 deletions(-) create mode 100644 include/linux/mfd/intel_pmc_bxt.h (limited to 'include/linux') diff --git a/include/linux/mfd/intel_pmc_bxt.h b/include/linux/mfd/intel_pmc_bxt.h new file mode 100644 index 000000000000..f51a43d25ffd --- /dev/null +++ b/include/linux/mfd/intel_pmc_bxt.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef MFD_INTEL_PMC_BXT_H +#define MFD_INTEL_PMC_BXT_H + +/* GCR reg offsets from GCR base */ +#define PMC_GCR_PMC_CFG_REG 0x08 +#define PMC_GCR_TELEM_DEEP_S0IX_REG 0x78 +#define PMC_GCR_TELEM_SHLW_S0IX_REG 0x80 + +/* PMC_CFG_REG bit masks */ +#define PMC_CFG_NO_REBOOT_EN BIT(4) + +/** + * struct intel_pmc_dev - Intel PMC device structure + * @dev: Pointer to the parent PMC device + * @scu: Pointer to the SCU IPC device data structure + * @gcr_mem_base: Virtual base address of GCR (Global Configuration Registers) + * @gcr_lock: Lock used to serialize access to GCR registers + * @telem_base: Pointer to telemetry SSRAM base resource or %NULL if not + * available + */ +struct intel_pmc_dev { + struct device *dev; + struct intel_scu_ipc_dev *scu; + void __iomem *gcr_mem_base; + spinlock_t gcr_lock; + struct resource *telem_base; +}; + +#if IS_ENABLED(CONFIG_MFD_INTEL_PMC_BXT) +int intel_pmc_gcr_read64(struct intel_pmc_dev *pmc, u32 offset, u64 *data); +int intel_pmc_gcr_update(struct intel_pmc_dev *pmc, u32 offset, u32 mask, u32 val); +int intel_pmc_s0ix_counter_read(struct intel_pmc_dev *pmc, u64 *data); +#else +static inline int intel_pmc_gcr_read64(struct intel_pmc_dev *pmc, u32 offset, + u64 *data) +{ + return -ENOTSUPP; +} + +static inline int intel_pmc_gcr_update(struct intel_pmc_dev *pmc, u32 offset, + u32 mask, u32 val) +{ + return -ENOTSUPP; +} + +static inline int intel_pmc_s0ix_counter_read(struct intel_pmc_dev *pmc, u64 *data) +{ + return -ENOTSUPP; +} +#endif + +#endif /* MFD_INTEL_PMC_BXT_H */ diff --git a/include/linux/platform_data/itco_wdt.h b/include/linux/platform_data/itco_wdt.h index 2ccdce6a4e27..45d860cac2b0 100644 --- a/include/linux/platform_data/itco_wdt.h +++ b/include/linux/platform_data/itco_wdt.h @@ -12,13 +12,16 @@ #define ICH_RES_MEM_OFF 2 #define ICH_RES_MEM_GCS_PMC 0 +/** + * struct itco_wdt_platform_data - iTCO_wdt platform data + * @name: Name of the platform + * @version: iTCO version + * @no_reboot_use_pmc: Use PMC BXT API to set and clear NO_REBOOT bit + */ struct itco_wdt_platform_data { char name[32]; unsigned int version; - /* private data to be passed to update_no_reboot_bit API */ - void *no_reboot_priv; - /* pointer for platform specific no reboot update function */ - int (*update_no_reboot_bit)(void *priv, bool set); + bool no_reboot_use_pmc; }; #endif /* _ITCO_WDT_H_ */ -- cgit v1.2.3 From 9166cc49767a646990a73380480356416b7794eb Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 26 Mar 2020 15:09:32 +0200 Subject: mac80211: implement Operating Mode Notification extended NSS support Somehow we missed this for a long time, but similar to the extended NSS support in VHT capabilities, we need to have this in Operating Mode notification. Implement it by * parsing the 160/80+80 bit there and setting the bandwidth appropriately * having callers of ieee80211_get_vht_max_nss() pass in the current max NSS value as received in the operating mode notification in order to modify it appropriately depending on the extended NSS bits. This updates all drivers that use it, i.e. only iwlwifi/mvm. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20200326150855.098483728cfa.I4e8c25d3288441759c2793247197229f0696a37d@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 16268ef1cbcc..c326aec535c6 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -9,7 +9,7 @@ * Copyright (c) 2006, Michael Wu * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH - * Copyright (c) 2018 - 2019 Intel Corporation + * Copyright (c) 2018 - 2020 Intel Corporation */ #ifndef LINUX_IEEE80211_H @@ -859,6 +859,7 @@ enum ieee80211_ht_chanwidth_values { * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: 40 MHz channel width * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ: 80 MHz channel width * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ: 160 MHz or 80+80 MHz channel width + * @IEEE80211_OPMODE_NOTIF_BW_160_80P80: 160 / 80+80 MHz indicator flag * @IEEE80211_OPMODE_NOTIF_RX_NSS_MASK: number of spatial streams mask * (the NSS value is the value of this field + 1) * @IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT: number of spatial streams shift @@ -866,11 +867,12 @@ enum ieee80211_ht_chanwidth_values { * using a beamforming steering matrix */ enum ieee80211_vht_opmode_bits { - IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK = 3, + IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK = 0x03, IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ = 0, IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ = 1, IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ = 2, IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ = 3, + IEEE80211_OPMODE_NOTIF_BW_160_80P80 = 0x04, IEEE80211_OPMODE_NOTIF_RX_NSS_MASK = 0x70, IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT = 4, IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF = 0x80, @@ -1731,6 +1733,9 @@ struct ieee80211_mu_edca_param_set { * @ext_nss_bw_capable: indicates whether or not the local transmitter * (rate scaling algorithm) can deal with the new logic * (dot11VHTExtendedNSSBWCapable) + * @max_vht_nss: current maximum NSS as advertised by the STA in + * operating mode notification, can be 0 in which case the + * capability data will be used to derive this (from MCS support) * * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can * vary for a given BW/MCS. This function parses the data. @@ -1739,7 +1744,8 @@ struct ieee80211_mu_edca_param_set { */ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, enum ieee80211_vht_chanwidth bw, - int mcs, bool ext_nss_bw_capable); + int mcs, bool ext_nss_bw_capable, + unsigned int max_vht_nss); /* 802.11ax HE MAC capabilities */ #define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 -- cgit v1.2.3 From 2a392596d8811c6d58c014ec881b159c75a0cf45 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Thu, 26 Mar 2020 15:09:35 +0200 Subject: cfg80211: Parse HE membership selector This extends the support for drivers that rebuilds IEs in the FW (same as with HT/VHT). Signed-off-by: Ilan Peer Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20200326150855.20feaabfb484.I886252639604c8e3e84b8ef97962f1b0e4beec81@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index c326aec535c6..38f513ce7528 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1067,6 +1067,7 @@ struct ieee80211_mgmt { /* Supported rates membership selectors */ #define BSS_MEMBERSHIP_SELECTOR_HT_PHY 127 #define BSS_MEMBERSHIP_SELECTOR_VHT_PHY 126 +#define BSS_MEMBERSHIP_SELECTOR_HE_PHY 122 /* mgmt header + 1 byte category code */ #define IEEE80211_MIN_ACTION_SIZE offsetof(struct ieee80211_mgmt, u.action.u) -- cgit v1.2.3 From b572510100165ba037ba43dbbb0f05e8da12c741 Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Wed, 1 Apr 2020 18:18:02 -0700 Subject: ieee80211: share 802.11 unit conversion helpers MHZ_TO_KHZ, and KHZ_TO_MHZ are useful to drivers and elsewhere so export these in the common ieee80211 header. Move the power helpers also because we might as well. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200402011810.22947-2-thomas@adapt-ip.com Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 38f513ce7528..a561db435a4b 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -3330,6 +3330,16 @@ static inline int ieee80211_get_tdls_action(struct sk_buff *skb, u32 hdr_size) #define TU_TO_JIFFIES(x) (usecs_to_jiffies((x) * 1024)) #define TU_TO_EXP_TIME(x) (jiffies + TU_TO_JIFFIES(x)) +/* convert frequencies */ +#define MHZ_TO_KHZ(freq) ((freq) * 1000) +#define KHZ_TO_MHZ(freq) ((freq) / 1000) + +/* convert powers */ +#define DBI_TO_MBI(gain) ((gain) * 100) +#define MBI_TO_DBI(gain) ((gain) / 100) +#define DBM_TO_MBM(gain) ((gain) * 100) +#define MBM_TO_DBM(gain) ((gain) / 100) + /** * ieee80211_action_contains_tpc - checks if the frame contains TPC element * @skb: the skb containing the frame, length will be checked -- cgit v1.2.3 From 4e9a0f73f030e19a9259b69a7079021048e1f904 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 26 Mar 2020 09:24:14 +0100 Subject: efi: Clean up config table description arrays Increase legibility by adding whitespace to the efi_config_table_type_t arrays that describe which EFI config tables we look for when going over the firmware provided list. While at it, replace the 'name' char pointer with a char array, which is more space efficient on relocatable 64-bit kernels, as it avoids a 8 byte pointer and the associated relocation data (24 bytes when using RELA format) Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 251f1f783cdf..9b7c7ec319ac 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -379,8 +379,8 @@ typedef union { typedef struct { efi_guid_t guid; - const char *name; unsigned long *ptr; + const char name[16]; } efi_config_table_type_t; #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL) -- cgit v1.2.3 From acd05785e48c01edb2c4f4d014d28478b5f19fb5 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Fri, 17 Apr 2020 15:14:46 -0700 Subject: kvm: add capability for halt polling KVM_CAP_HALT_POLL is a per-VM capability that lets userspace control the halt-polling time, allowing halt-polling to be tuned or disabled on particular VMs. With dynamic halt-polling, a VM's VCPUs can poll from anywhere from [0, halt_poll_ns] on each halt. KVM_CAP_HALT_POLL sets the upper limit on the poll time. Signed-off-by: David Matlack Signed-off-by: Jon Cargille Reviewed-by: Jim Mattson Message-Id: <20200417221446.108733-1-jcargill@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5285a5568208..3cc6ccbb1183 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -503,6 +503,7 @@ struct kvm { struct srcu_struct srcu; struct srcu_struct irq_srcu; pid_t userspace_pid; + unsigned int max_halt_poll_ns; }; #define kvm_err(fmt, ...) \ -- cgit v1.2.3 From 76c70cb58ce30264af4b714109ee756da25d830a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 18 Apr 2020 18:52:30 +0200 Subject: PM: sleep: core: Rename dev_pm_may_skip_resume() The name of dev_pm_may_skip_resume() may be easily confused with the power.may_skip_resume flag which is not checked by that function, so rename the former as dev_pm_skip_resume(). No functional impact. Suggested-by: Alan Stern Signed-off-by: Rafael J. Wysocki Acked-by: Alan Stern Acked-by: Bjorn Helgaas --- include/linux/pm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index e057d1fa2469..d89b7099f241 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -758,7 +758,7 @@ extern int pm_generic_poweroff_late(struct device *dev); extern int pm_generic_poweroff(struct device *dev); extern void pm_generic_complete(struct device *dev); -extern bool dev_pm_may_skip_resume(struct device *dev); +extern bool dev_pm_skip_resume(struct device *dev); extern bool dev_pm_smart_suspend_and_suspended(struct device *dev); #else /* !CONFIG_PM_SLEEP */ -- cgit v1.2.3 From fa2bfead910322e44e7e0bb74364ac198a2abd32 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 18 Apr 2020 18:52:48 +0200 Subject: PM: sleep: core: Rename dev_pm_smart_suspend_and_suspended() Because all callers of dev_pm_smart_suspend_and_suspended use it only for checking whether or not to skip driver suspend callbacks for a device, rename it to dev_pm_skip_suspend() in analogy with dev_pm_skip_resume(). No functional impact. Suggested-by: Alan Stern Signed-off-by: Rafael J. Wysocki Acked-by: Alan Stern Acked-by: Bjorn Helgaas --- include/linux/pm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index d89b7099f241..8c59a7f0bcf4 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -759,7 +759,7 @@ extern int pm_generic_poweroff(struct device *dev); extern void pm_generic_complete(struct device *dev); extern bool dev_pm_skip_resume(struct device *dev); -extern bool dev_pm_smart_suspend_and_suspended(struct device *dev); +extern bool dev_pm_skip_suspend(struct device *dev); #else /* !CONFIG_PM_SLEEP */ -- cgit v1.2.3 From e07515563d010d8b32967634e8dc2fdc732c1aa6 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 18 Apr 2020 18:53:01 +0200 Subject: PM: sleep: core: Rename DPM_FLAG_NEVER_SKIP Rename DPM_FLAG_NEVER_SKIP to DPM_FLAG_NO_DIRECT_COMPLETE which matches its purpose more closely. No functional impact. Suggested-by: Alan Stern Signed-off-by: Rafael J. Wysocki Acked-by: Bjorn Helgaas # for PCI parts Acked-by: Jeff Kirsher Acked-by: Alan Stern Acked-by: Bjorn Helgaas Acked-by: Alex Deucher --- include/linux/pm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 8c59a7f0bcf4..cdb8fbd6ab18 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -544,7 +544,7 @@ struct pm_subsys_data { * These flags can be set by device drivers at the probe time. They need not be * cleared by the drivers as the driver core will take care of that. * - * NEVER_SKIP: Do not skip all system suspend/resume callbacks for the device. + * NO_DIRECT_COMPLETE: Do not apply direct-complete optimization to the device. * SMART_PREPARE: Check the return value of the driver's ->prepare callback. * SMART_SUSPEND: No need to resume the device from runtime suspend. * LEAVE_SUSPENDED: Avoid resuming the device during system resume if possible. @@ -554,7 +554,7 @@ struct pm_subsys_data { * their ->prepare callbacks if the driver's ->prepare callback returns 0 (in * other words, the system suspend/resume callbacks can only be skipped for the * device if its driver doesn't object against that). This flag has no effect - * if NEVER_SKIP is set. + * if NO_DIRECT_COMPLETE is set. * * Setting SMART_SUSPEND instructs bus types and PM domains which may want to * runtime resume the device upfront during system suspend that doing so is not @@ -565,7 +565,7 @@ struct pm_subsys_data { * Setting LEAVE_SUSPENDED informs the PM core and middle-layer code that the * driver prefers the device to be left in suspend after system resume. */ -#define DPM_FLAG_NEVER_SKIP BIT(0) +#define DPM_FLAG_NO_DIRECT_COMPLETE BIT(0) #define DPM_FLAG_SMART_PREPARE BIT(1) #define DPM_FLAG_SMART_SUSPEND BIT(2) #define DPM_FLAG_LEAVE_SUSPENDED BIT(3) -- cgit v1.2.3 From 2a3f34750b8b07df42ab4b30b70e029d46e0d7f3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 18 Apr 2020 18:53:20 +0200 Subject: PM: sleep: core: Rename DPM_FLAG_LEAVE_SUSPENDED Rename DPM_FLAG_LEAVE_SUSPENDED to DPM_FLAG_MAY_SKIP_RESUME which matches its purpose more closely. No functional impact. Suggested-by: Alan Stern Signed-off-by: Rafael J. Wysocki Acked-by: Wolfram Sang # for I2C Acked-by: Alan Stern Acked-by: Bjorn Helgaas --- include/linux/pm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index cdb8fbd6ab18..35796fc49e7a 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -547,7 +547,7 @@ struct pm_subsys_data { * NO_DIRECT_COMPLETE: Do not apply direct-complete optimization to the device. * SMART_PREPARE: Check the return value of the driver's ->prepare callback. * SMART_SUSPEND: No need to resume the device from runtime suspend. - * LEAVE_SUSPENDED: Avoid resuming the device during system resume if possible. + * MAY_SKIP_RESUME: Avoid resuming the device during system resume if possible. * * Setting SMART_PREPARE instructs bus types and PM domains which may want * system suspend/resume callbacks to be skipped for the device to return 0 from @@ -562,13 +562,13 @@ struct pm_subsys_data { * invocations of the ->suspend_late and ->suspend_noirq callbacks provided by * the driver if they decide to leave the device in runtime suspend. * - * Setting LEAVE_SUSPENDED informs the PM core and middle-layer code that the + * Setting MAY_SKIP_RESUME informs the PM core and middle-layer code that the * driver prefers the device to be left in suspend after system resume. */ #define DPM_FLAG_NO_DIRECT_COMPLETE BIT(0) #define DPM_FLAG_SMART_PREPARE BIT(1) #define DPM_FLAG_SMART_SUSPEND BIT(2) -#define DPM_FLAG_LEAVE_SUSPENDED BIT(3) +#define DPM_FLAG_MAY_SKIP_RESUME BIT(3) struct dev_pm_info { pm_message_t power_state; -- cgit v1.2.3 From 2fff3f73e8c27801b84d2315e1a49bce96b00eff Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 18 Apr 2020 18:55:32 +0200 Subject: Documentation: PM: sleep: Update driver flags documentation Update the documentation of the driver flags for system-wide power management to reflect the current code flows and be more consistent. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 24 +++++------------------- 1 file changed, 5 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 35796fc49e7a..121c104a4090 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -545,25 +545,11 @@ struct pm_subsys_data { * cleared by the drivers as the driver core will take care of that. * * NO_DIRECT_COMPLETE: Do not apply direct-complete optimization to the device. - * SMART_PREPARE: Check the return value of the driver's ->prepare callback. - * SMART_SUSPEND: No need to resume the device from runtime suspend. - * MAY_SKIP_RESUME: Avoid resuming the device during system resume if possible. - * - * Setting SMART_PREPARE instructs bus types and PM domains which may want - * system suspend/resume callbacks to be skipped for the device to return 0 from - * their ->prepare callbacks if the driver's ->prepare callback returns 0 (in - * other words, the system suspend/resume callbacks can only be skipped for the - * device if its driver doesn't object against that). This flag has no effect - * if NO_DIRECT_COMPLETE is set. - * - * Setting SMART_SUSPEND instructs bus types and PM domains which may want to - * runtime resume the device upfront during system suspend that doing so is not - * necessary from the driver's perspective. It also may cause them to skip - * invocations of the ->suspend_late and ->suspend_noirq callbacks provided by - * the driver if they decide to leave the device in runtime suspend. - * - * Setting MAY_SKIP_RESUME informs the PM core and middle-layer code that the - * driver prefers the device to be left in suspend after system resume. + * SMART_PREPARE: Take the driver ->prepare callback return value into account. + * SMART_SUSPEND: Avoid resuming the device from runtime suspend. + * MAY_SKIP_RESUME: Allow driver "noirq" and "early" callbacks to be skipped. + * + * See Documentation/driver-api/pm/devices.rst for details. */ #define DPM_FLAG_NO_DIRECT_COMPLETE BIT(0) #define DPM_FLAG_SMART_PREPARE BIT(1) -- cgit v1.2.3 From 5c05c1dbb177293636a3f5ea4caa872dfcf50ccd Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 23 Apr 2020 17:02:56 +0100 Subject: net: phylink, dsa: eliminate phylink_fixed_state_cb() Move the callback into the phylink_config structure, rather than providing a callback to set this up. Signed-off-by: Russell King Tested-by: Florian Fainelli Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phylink.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 3f8d37ec5503..cc5b452a184e 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -67,6 +67,9 @@ struct phylink_config { struct device *dev; enum phylink_op_type type; bool pcs_poll; + bool poll_fixed_state; + void (*get_fixed_state)(struct phylink_config *config, + struct phylink_link_state *state); }; /** @@ -366,9 +369,6 @@ void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); void phylink_disconnect_phy(struct phylink *); -int phylink_fixed_state_cb(struct phylink *, - void (*cb)(struct net_device *dev, - struct phylink_link_state *)); void phylink_mac_change(struct phylink *, bool up); -- cgit v1.2.3 From 3194915486b2bc3f77745774f1731b78f32ff688 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 23 Apr 2020 21:35:36 +0200 Subject: net: phy: remove genphy_no_soft_reset Since 6e2d85ec0559 ("net: phy: Stop with excessive soft reset") we don't need genphy_no_soft_reset() any longer. Not setting callback soft_reset results in a no-op now. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 3941a6bcba10..e2bfb9240587 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1251,10 +1251,6 @@ static inline int genphy_config_aneg(struct phy_device *phydev) return __genphy_config_aneg(phydev, false); } -static inline int genphy_no_soft_reset(struct phy_device *phydev) -{ - return 0; -} static inline int genphy_no_ack_interrupt(struct phy_device *phydev) { return 0; -- cgit v1.2.3 From fec86c6b8369b5dd8e3a1ad3752578a737163b25 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 13 Apr 2020 10:24:40 +0200 Subject: iio: imu: adis: Add Managed device functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds support for a managed device version of adis_setup_buffer_and_trigger. It works exactly as the original one but it calls all the devm_iio_* functions to setup an iio buffer and trigger. Hence we do not need to care about cleaning those and we do not need to support a remove() callback for every driver using the adis library. Signed-off-by: Nuno Sá Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index dd8219138c2e..e70814d96e1c 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -448,11 +448,15 @@ struct adis_burst { unsigned int extra_len; }; +int +devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, + irq_handler_t trigger_handler); int adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *)); void adis_cleanup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev); +int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev); int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev); void adis_remove_trigger(struct adis *adis); @@ -461,6 +465,13 @@ int adis_update_scan_mode(struct iio_dev *indio_dev, #else /* CONFIG_IIO_BUFFER */ +static inline int +devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, + irq_handler_t trigger_handler) +{ + return 0; +} + static inline int adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *)) { @@ -472,6 +483,12 @@ static inline void adis_cleanup_buffer_and_trigger(struct adis *adis, { } +static inline int devm_adis_probe_trigger(struct adis *adis, + struct iio_dev *indio_dev) +{ + return 0; +} + static inline int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev) { -- cgit v1.2.3 From 698211065d4aa71ce599b38c23452664a5a8e370 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 13 Apr 2020 10:24:41 +0200 Subject: iio: imu: adis: Add irq flag variable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are some ADIS devices that can configure the data ready pin polarity. Hence, we cannot hardcode our IRQ mask as IRQF_TRIGGER_RISING since we might want to have it as IRQF_TRIGGER_FALLING. Signed-off-by: Nuno Sá Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index e70814d96e1c..70e4d1d262f5 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -87,6 +87,7 @@ struct adis_data { * @msg: SPI message object * @xfer: SPI transfer objects to be used for a @msg * @current_page: Some ADIS devices have registers, this selects current page + * @irq_flag: IRQ handling flags as passed to request_irq() * @buffer: Data buffer for information read from the device * @tx: DMA safe TX buffer for SPI transfers * @rx: DMA safe RX buffer for SPI transfers @@ -113,6 +114,7 @@ struct adis { struct spi_message msg; struct spi_transfer *xfer; unsigned int current_page; + unsigned long irq_flag; void *buffer; uint8_t tx[10] ____cacheline_aligned; -- cgit v1.2.3 From b9c5eec725d67b548e4dfdc406d6ca2c6d30d1c2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 13 Apr 2020 10:24:42 +0200 Subject: iio: adis: Add adis_update_bits() APIs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds a `regmap_update_bits()` like API to the ADIS library. It provides locked and unlocked variant. Signed-off-by: Nuno Sá Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 59 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 70e4d1d262f5..247fc4c7185c 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -333,6 +333,65 @@ static inline int adis_read_reg_32(struct adis *adis, unsigned int reg, return ret; } +int __adis_update_bits_base(struct adis *adis, unsigned int reg, const u32 mask, + const u32 val, u8 size); +/** + * adis_update_bits_base() - ADIS Update bits function - Locked version + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @mask: Bitmask to change + * @val: Value to be written + * @size: Size of the register to update + * + * Updates the desired bits of @reg in accordance with @mask and @val. + */ +static inline int adis_update_bits_base(struct adis *adis, unsigned int reg, + const u32 mask, const u32 val, u8 size) +{ + int ret; + + mutex_lock(&adis->state_lock); + ret = __adis_update_bits_base(adis, reg, mask, val, size); + mutex_unlock(&adis->state_lock); + return ret; +} + +/** + * adis_update_bits() - Wrapper macro for adis_update_bits_base - Locked version + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @mask: Bitmask to change + * @val: Value to be written + * + * This macro evaluates the sizeof of @val at compile time and calls + * adis_update_bits_base() accordingly. Be aware that using MACROS/DEFINES for + * @val can lead to undesired behavior if the register to update is 16bit. + */ +#define adis_update_bits(adis, reg, mask, val) ({ \ + BUILD_BUG_ON(sizeof(val) == 1 || sizeof(val) == 8); \ + __builtin_choose_expr(sizeof(val) == 4, \ + adis_update_bits_base(adis, reg, mask, val, 4), \ + adis_update_bits_base(adis, reg, mask, val, 2)); \ +}) + +/** + * adis_update_bits() - Wrapper macro for adis_update_bits_base + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @mask: Bitmask to change + * @val: Value to be written + * + * This macro evaluates the sizeof of @val at compile time and calls + * adis_update_bits_base() accordingly. Be aware that using MACROS/DEFINES for + * @val can lead to undesired behavior if the register to update is 16bit. + */ +#define __adis_update_bits(adis, reg, mask, val) ({ \ + BUILD_BUG_ON(sizeof(val) == 1 || sizeof(val) == 8); \ + __builtin_choose_expr(sizeof(val) == 4, \ + __adis_update_bits_base(adis, reg, mask, val, 4), \ + __adis_update_bits_base(adis, reg, mask, val, 2)); \ +}) + int adis_enable_irq(struct adis *adis, bool enable); int __adis_check_status(struct adis *adis); int __adis_initial_startup(struct adis *adis); -- cgit v1.2.3 From 3e04cb60e872b9433e523d62c39addf0bd1a18f1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 13 Apr 2020 10:24:43 +0200 Subject: iio: adis: Support different burst sizes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add burst_max_len to `adis_burst`. This is useful for devices which support different burst modes with different sizes. The buffer to be used in the spi transfer is allocated with this variable making sure that has space for all burst modes. The spi transfer length should hold the "real" burst length depending on the current burst mode configured in the device. Moreover, `extra_len` in `adis_burst` is made const and it should contain the smallest extra length necessary for a burst transfer. In `struct adis` was added a new `burst_extra_len` that should hold the extra bytes needed depending on the device instance being used. Signed-off-by: Nuno Sá Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 247fc4c7185c..2df67448f0d1 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -83,6 +83,8 @@ struct adis_data { * @trig: IIO trigger object data * @data: ADIS chip variant specific data * @burst: ADIS burst transfer information + * @burst_extra_len: Burst extra length. Should only be used by devices that can + * dynamically change their burst mode length. * @state_lock: Lock used by the device to protect state * @msg: SPI message object * @xfer: SPI transfer objects to be used for a @msg @@ -98,7 +100,7 @@ struct adis { const struct adis_data *data; struct adis_burst *burst; - + unsigned int burst_extra_len; /** * The state_lock is meant to be used during operations that require * a sequence of SPI R/W in order to protect the SPI transfer @@ -502,11 +504,14 @@ int adis_single_conversion(struct iio_dev *indio_dev, * @en burst mode enabled * @reg_cmd register command that triggers burst * @extra_len extra length to account in the SPI RX buffer + * @burst_max_len holds the maximum burst size when the device supports + * more than one burst mode with different sizes */ struct adis_burst { bool en; unsigned int reg_cmd; - unsigned int extra_len; + const u32 extra_len; + const u32 burst_max_len; }; int -- cgit v1.2.3 From 8cf7961dab42c9177a556b719c15f5b9449c24d1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 25 Apr 2020 09:53:36 +0200 Subject: block: bypass ->make_request_fn for blk-mq drivers Call blk_mq_make_request when no ->make_request_fn is set. This is safe now that blk_alloc_queue always sets up the pointer for make_request based drivers. This avoids an indirect call in the blk-mq driver I/O fast path, which is rather expensive due to spectre mitigations. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 51fbf6f76593..d7307795439a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -578,4 +578,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq) rq->q->mq_ops->cleanup_rq(rq); } +blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio); + #endif -- cgit v1.2.3 From 0456ea170cd665ddbb9503be92e39f96055dd5fa Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 20 Apr 2020 10:46:10 -0700 Subject: bpf: Enable more helpers for BPF_PROG_TYPE_CGROUP_{DEVICE,SYSCTL,SOCKOPT} Currently the following prog types don't fall back to bpf_base_func_proto() (instead they have cgroup_base_func_proto which has a limited set of helpers from bpf_base_func_proto): * BPF_PROG_TYPE_CGROUP_DEVICE * BPF_PROG_TYPE_CGROUP_SYSCTL * BPF_PROG_TYPE_CGROUP_SOCKOPT I don't see any specific reason why we shouldn't use bpf_base_func_proto(), every other type of program (except bpf-lirc and, understandably, tracing) use it, so let's fall back to bpf_base_func_proto for those prog types as well. This basically boils down to adding access to the following helpers: * BPF_FUNC_get_prandom_u32 * BPF_FUNC_get_smp_processor_id * BPF_FUNC_get_numa_node_id * BPF_FUNC_tail_call * BPF_FUNC_ktime_get_ns * BPF_FUNC_spin_lock (CAP_SYS_ADMIN) * BPF_FUNC_spin_unlock (CAP_SYS_ADMIN) * BPF_FUNC_jiffies64 (CAP_SYS_ADMIN) I've also added bpf_perf_event_output() because it's really handy for logging and debugging. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200420174610.77494-1-sdf@google.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index fd2b2322412d..25da6ff2a880 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1523,6 +1523,7 @@ extern const struct bpf_func_proto bpf_strtoul_proto; extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; +extern const struct bpf_func_proto bpf_event_output_data_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From 6890896bd765b0504761c61901c9804fca23bfb2 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 24 Apr 2020 16:59:41 -0700 Subject: bpf: Fix missing bpf_base_func_proto in cgroup_base_func_proto for CGROUP_NET=n linux-next build bot reported compile issue [1] with one of its configs. It looks like when we have CONFIG_NET=n and CONFIG_BPF{,_SYSCALL}=y, we are missing the bpf_base_func_proto definition (from net/core/filter.c) in cgroup_base_func_proto. I'm reshuffling the code a bit to make it work. The common helpers are moved into kernel/bpf/helpers.c and the bpf_base_func_proto is exported from there. Also, bpf_get_raw_cpu_id goes into kernel/bpf/core.c akin to existing bpf_user_rnd_u32. [1] https://lore.kernel.org/linux-next/CAKH8qBsBvKHswiX1nx40LgO+BGeTmb1NX8tiTttt_0uu6T3dCA@mail.gmail.com/T/#mff8b0c083314c68c2e2ef0211cb11bc20dc13c72 Fixes: 0456ea170cd6 ("bpf: Enable more helpers for BPF_PROG_TYPE_CGROUP_{DEVICE,SYSCTL,SOCKOPT}") Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Cc: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200424235941.58382-1-sdf@google.com --- include/linux/bpf.h | 8 ++++++++ include/linux/filter.h | 2 -- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 25da6ff2a880..5147e11e53ff 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1215,6 +1215,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, struct bpf_prog *bpf_prog_by_id(u32 id); +const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -1365,6 +1366,12 @@ static inline struct bpf_prog *bpf_prog_by_id(u32 id) { return ERR_PTR(-ENOTSUPP); } + +static inline const struct bpf_func_proto * +bpf_base_func_proto(enum bpf_func_id func_id) +{ + return NULL; +} #endif /* CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, @@ -1531,6 +1538,7 @@ const struct bpf_func_proto *bpf_tracing_func_proto( /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +u64 bpf_get_raw_cpu_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #if defined(CONFIG_NET) bool bpf_sock_common_is_valid_access(int off, int size, diff --git a/include/linux/filter.h b/include/linux/filter.h index 9b5aa5c483cc..af37318bb1c5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -863,8 +863,6 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); -const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); -- cgit v1.2.3 From 71d19214776e61b33da48f7c1b46e522c7f78221 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Sun, 26 Apr 2020 09:15:25 -0700 Subject: bpf: add bpf_ktime_get_boot_ns() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On a device like a cellphone which is constantly suspending and resuming CLOCK_MONOTONIC is not particularly useful for keeping track of or reacting to external network events. Instead you want to use CLOCK_BOOTTIME. Hence add bpf_ktime_get_boot_ns() as a mirror of bpf_ktime_get_ns() based around CLOCK_BOOTTIME instead of CLOCK_MONOTONIC. Signed-off-by: Maciej Żenczykowski Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5147e11e53ff..10960cfabea4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1509,6 +1509,7 @@ extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; +extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; -- cgit v1.2.3 From 26363af5643490a817272e1cc6f1d3f1d550a699 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Apr 2020 08:43:35 +0200 Subject: mm: remove watermark_boost_factor_sysctl_handler watermark_boost_factor_sysctl_handler is just a pointless wrapper for proc_dointvec_minmax, so remove it and use proc_dointvec_minmax directly. Signed-off-by: Christoph Hellwig Acked-by: David Rientjes Signed-off-by: Al Viro --- include/linux/mmzone.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1b9de7d220fb..f37bb8f187fc 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -911,8 +911,6 @@ static inline int is_highmem(struct zone *zone) struct ctl_table; int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -int watermark_boost_factor_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; -- cgit v1.2.3 From 2374c09b1c8a883bb9b4b2fc3756703eeb618f4a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Apr 2020 08:43:36 +0200 Subject: sysctl: remove all extern declaration from sysctl.c Extern declarations in .c files are a bad style and can lead to mismatches. Use existing definitions in headers where they exist, and otherwise move the external declarations to suitable header files. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/coredump.h | 4 ++++ include/linux/file.h | 2 ++ include/linux/mm.h | 2 ++ include/linux/mmzone.h | 2 ++ include/linux/pid.h | 3 +++ include/linux/sysctl.h | 8 ++++++++ 6 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coredump.h b/include/linux/coredump.h index abf4b4e65dbb..7a899e83835d 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -22,4 +22,8 @@ extern void do_coredump(const kernel_siginfo_t *siginfo); static inline void do_coredump(const kernel_siginfo_t *siginfo) {} #endif +extern int core_uses_pid; +extern char core_pattern[]; +extern unsigned int core_pipe_limit; + #endif /* _LINUX_COREDUMP_H */ diff --git a/include/linux/file.h b/include/linux/file.h index 142d102f285e..122f80084a3e 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -94,4 +94,6 @@ extern void fd_install(unsigned int fd, struct file *file); extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); +extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; + #endif /* __LINUX_FILE_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a323422d783..9c4e7e76dedd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3140,5 +3140,7 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif +extern int sysctl_nr_trim_pages; + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f37bb8f187fc..b2af594ef0f7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -909,6 +909,7 @@ static inline int is_highmem(struct zone *zone) /* These two functions are used to setup the per zone pages min values */ struct ctl_table; + int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, @@ -925,6 +926,7 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, extern int numa_zonelist_order_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int percpu_pagelist_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 diff --git a/include/linux/pid.h b/include/linux/pid.h index cc896f0fc4e3..93543cbc0e6b 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -108,6 +108,9 @@ extern void transfer_pid(struct task_struct *old, struct task_struct *new, struct pid_namespace; extern struct pid_namespace init_pid_ns; +extern int pid_max; +extern int pid_max_min, pid_max_max; + /* * look up a PID in the hash table. Must be called with the tasklist_lock * or rcu_read_lock() held. diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 02fa84493f23..36143ca40b56 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -207,7 +207,15 @@ void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init(void); +extern int pwrsw_enabled; +extern int unaligned_enabled; +extern int unaligned_dump_stack; +extern int no_unaligned_warning; + extern struct ctl_table sysctl_mount_point[]; +extern struct ctl_table random_table[]; +extern struct ctl_table firmware_config_table[]; +extern struct ctl_table epoll_table[]; #else /* CONFIG_SYSCTL */ static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table) -- cgit v1.2.3 From 32927393dc1ccd60fb2bdc05b9e8e88753761469 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Apr 2020 08:43:38 +0200 Subject: sysctl: pass kernel pointers to ->proc_handler Instead of having all the sysctl handlers deal with user pointers, which is rather hairy in terms of the BPF interaction, copy the input to and from userspace in common code. This also means that the strings are always NUL-terminated by the common code, making the API a little bit safer. As most handler just pass through the data to one of the common handlers a lot of the changes are mechnical. Signed-off-by: Christoph Hellwig Acked-by: Andrey Ignatov Signed-off-by: Al Viro --- include/linux/bpf-cgroup.h | 9 ++++---- include/linux/compaction.h | 2 +- include/linux/fs.h | 6 ++--- include/linux/ftrace.h | 3 +-- include/linux/hugetlb.h | 15 ++++++------- include/linux/kprobes.h | 2 +- include/linux/latencytop.h | 4 ++-- include/linux/mm.h | 12 +++++----- include/linux/mmzone.h | 23 +++++++++---------- include/linux/nmi.h | 15 +++++-------- include/linux/perf_event.h | 13 +++++------ include/linux/printk.h | 2 +- include/linux/sched/sysctl.h | 44 +++++++++++++----------------------- include/linux/security.h | 2 +- include/linux/sysctl.h | 53 ++++++++++++++++++-------------------------- include/linux/timer.h | 3 +-- include/linux/vmstat.h | 8 +++---- include/linux/writeback.h | 28 +++++++++-------------- 18 files changed, 101 insertions(+), 143 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index c11b413d5b1a..0b41fd5fc96b 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -138,8 +138,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, - void __user *buf, size_t *pcount, - loff_t *ppos, void **new_buf, + void **buf, size_t *pcount, loff_t *ppos, enum bpf_attach_type type); int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level, @@ -302,12 +301,12 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, }) -#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos, nbuf) \ +#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled) \ __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ - buf, count, pos, nbuf, \ + buf, count, pos, \ BPF_CGROUP_SYSCTL); \ __ret; \ }) @@ -429,7 +428,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 4b898cdbdf05..a0eabfbeb0e1 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -86,7 +86,7 @@ static inline unsigned long compact_gap(unsigned int order) #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos); + void *buffer, size_t *length, loff_t *ppos); extern int sysctl_extfrag_threshold; extern int sysctl_compact_unevictable_allowed; diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..9b028d260649 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3536,11 +3536,11 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, struct ctl_table; int proc_nr_files(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); int proc_nr_dentry(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); int proc_nr_inodes(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); #define __FMODE_EXEC ((__force int) FMODE_EXEC) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index db95244a62d4..ddfc377de0d2 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1005,8 +1005,7 @@ extern void disable_trace_on_warning(void); extern int __disable_trace_on_warning; int tracepoint_printk_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); #else /* CONFIG_TRACING */ static inline void disable_trace_on_warning(void) { } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 43a1cef8f0f1..92c21c5ccc58 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -105,14 +105,13 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, void hugepage_put_subpool(struct hugepage_subpool *spool); void reset_vma_resv_huge_pages(struct vm_area_struct *vma); -int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -int hugetlb_treat_movable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); - -#ifdef CONFIG_NUMA -int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -#endif +int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); +int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); +int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); +int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 04bdaf01112c..594265bfd390 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -312,7 +312,7 @@ DEFINE_INSN_CACHE_OPS(optinsn); #ifdef CONFIG_SYSCTL extern int sysctl_kprobes_optimization; extern int proc_kprobes_optimization_handler(struct ctl_table *table, - int write, void __user *buffer, + int write, void *buffer, size_t *length, loff_t *ppos); #endif extern void wait_for_kprobe_optimizer(void); diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h index 9022f0c2e2e4..abe3d95f795b 100644 --- a/include/linux/latencytop.h +++ b/include/linux/latencytop.h @@ -38,8 +38,8 @@ account_scheduler_latency(struct task_struct *task, int usecs, int inter) void clear_tsk_latency_tracing(struct task_struct *p); -extern int sysctl_latencytop(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); +int sysctl_latencytop(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); #else diff --git a/include/linux/mm.h b/include/linux/mm.h index 9c4e7e76dedd..a7b1ef8ed970 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -201,10 +201,10 @@ extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; -extern int overcommit_ratio_handler(struct ctl_table *, int, void __user *, - size_t *, loff_t *); -extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, - size_t *, loff_t *); +int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); +int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) @@ -2957,8 +2957,8 @@ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); #ifdef CONFIG_SYSCTL extern int sysctl_drop_caches; -int drop_caches_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); +int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); #endif void drop_slab(void); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b2af594ef0f7..93cf20f41e26 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -910,22 +910,21 @@ static inline int is_highmem(struct zone *zone) /* These two functions are used to setup the per zone pages min values */ struct ctl_table; -int min_free_kbytes_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); +int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); +int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *, + size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; -int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); +int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *, + size_t *, loff_t *); int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); + void *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); + void *, size_t *, loff_t *); int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); - -extern int numa_zonelist_order_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); + void *, size_t *, loff_t *); +int numa_zonelist_order_handler(struct ctl_table *, int, + void *, size_t *, loff_t *); extern int percpu_pagelist_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 9003e29cde46..750c7f395ca9 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -202,16 +202,11 @@ static inline void watchdog_update_hrtimer_threshold(u64 period) { } #endif struct ctl_table; -extern int proc_watchdog(struct ctl_table *, int , - void __user *, size_t *, loff_t *); -extern int proc_nmi_watchdog(struct ctl_table *, int , - void __user *, size_t *, loff_t *); -extern int proc_soft_watchdog(struct ctl_table *, int , - void __user *, size_t *, loff_t *); -extern int proc_watchdog_thresh(struct ctl_table *, int , - void __user *, size_t *, loff_t *); -extern int proc_watchdog_cpumask(struct ctl_table *, int, - void __user *, size_t *, loff_t *); +int proc_watchdog(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_nmi_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *); +int proc_soft_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *); +int proc_watchdog_thresh(struct ctl_table *, int , void *, size_t *, loff_t *); +int proc_watchdog_cpumask(struct ctl_table *, int, void *, size_t *, loff_t *); #ifdef CONFIG_HAVE_ACPI_APEI_NMI #include diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 9c3e7619c929..347ea379622a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1280,15 +1280,12 @@ extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); -extern int perf_proc_update_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); - +int perf_proc_update_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); int perf_event_max_stack_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 diff --git a/include/linux/printk.h b/include/linux/printk.h index e061635e0409..fcde0772ec98 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -189,7 +189,7 @@ extern int printk_delay_msec; extern int dmesg_restrict; extern int -devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void __user *buf, +devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos); extern void wake_up_klogd(void); diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index d4f6215ee03f..7b4d3a49b6c5 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -12,9 +12,8 @@ extern unsigned int sysctl_hung_task_panic; extern unsigned long sysctl_hung_task_timeout_secs; extern unsigned long sysctl_hung_task_check_interval_secs; extern int sysctl_hung_task_warnings; -extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); +int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); #else /* Avoid need for ifdefs elsewhere in the code */ enum { sysctl_hung_task_timeout_secs = 0 }; @@ -43,8 +42,7 @@ extern __read_mostly unsigned int sysctl_sched_migration_cost; extern __read_mostly unsigned int sysctl_sched_nr_migrate; int sched_proc_update_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, - loff_t *ppos); + void *buffer, size_t *length, loff_t *ppos); #endif /* @@ -72,33 +70,21 @@ extern unsigned int sysctl_sched_autogroup_enabled; extern int sysctl_sched_rr_timeslice; extern int sched_rr_timeslice; -extern int sched_rr_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); - -extern int sched_rt_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); - -#ifdef CONFIG_UCLAMP_TASK -extern int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -#endif - -extern int sysctl_numa_balancing(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); - -extern int sysctl_schedstats(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); +int sched_rr_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); +int sched_rt_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); +int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); +int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) extern unsigned int sysctl_sched_energy_aware; -extern int sched_energy_aware_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); +int sched_energy_aware_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); #endif #endif /* _LINUX_SCHED_SYSCTL_H */ diff --git a/include/linux/security.h b/include/linux/security.h index a8d9310472df..6aa229b252ce 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -211,7 +211,7 @@ struct request_sock; #ifdef CONFIG_MMU extern int mmap_min_addr_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); #endif /* security_inode_init_security callback function to write xattrs */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 36143ca40b56..f2401e45a3c2 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -44,35 +44,26 @@ struct ctl_dir; extern const int sysctl_vals[]; -typedef int proc_handler (struct ctl_table *ctl, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); - -extern int proc_dostring(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_dointvec(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_douintvec(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_dointvec_minmax(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_douintvec_minmax(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -extern int proc_dointvec_jiffies(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_dointvec_ms_jiffies(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_doulongvec_minmax(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, - void __user *, size_t *, loff_t *); -extern int proc_do_large_bitmap(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -extern int proc_do_static_key(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); +typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer, + size_t *lenp, loff_t *ppos); + +int proc_dostring(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dointvec(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_douintvec(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dointvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_douintvec_minmax(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); +int proc_dointvec_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void *, size_t *, + loff_t *); +int proc_dointvec_ms_jiffies(struct ctl_table *, int, void *, size_t *, + loff_t *); +int proc_doulongvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, void *, + size_t *, loff_t *); +int proc_do_large_bitmap(struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_do_static_key(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); /* * Register a set of sysctl names by calling register_sysctl_table @@ -246,7 +237,7 @@ static inline void setup_sysctl_set(struct ctl_table_set *p, #endif /* CONFIG_SYSCTL */ -int sysctl_max_threads(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); +int sysctl_max_threads(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); #endif /* _LINUX_SYSCTL_H */ diff --git a/include/linux/timer.h b/include/linux/timer.h index 0dc19a8c39c9..07910ae5ddd9 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -201,8 +201,7 @@ struct ctl_table; extern unsigned int sysctl_timer_migration; int timer_migration_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); #endif unsigned long __round_jiffies(unsigned long j, int cpu); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 292485f3d24d..cb507151710f 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -16,8 +16,8 @@ extern int sysctl_stat_interval; #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); -extern int sysctl_vm_numa_stat_handler(struct ctl_table *table, - int write, void __user *buffer, size_t *length, loff_t *ppos); +int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos); #endif struct reclaim_stat { @@ -274,8 +274,8 @@ void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; -int vmstat_refresh(struct ctl_table *, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); +int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp, + loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index a19d845dd7eb..f8a7e1a850fb 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -362,24 +362,18 @@ extern int vm_highmem_is_dirtyable; extern int block_dump; extern int laptop_mode; -extern int dirty_background_ratio_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -extern int dirty_background_bytes_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -extern int dirty_ratio_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -extern int dirty_bytes_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); +int dirty_background_ratio_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +int dirty_background_bytes_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +int dirty_ratio_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +int dirty_bytes_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); int dirtytime_interval_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); - -struct ctl_table; -int dirty_writeback_centisecs_handler(struct ctl_table *, int, - void __user *, size_t *, loff_t *); + void *buffer, size_t *lenp, loff_t *ppos); +int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); -- cgit v1.2.3 From ddc465936643108d5ba61f88594a2868d6a156ab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Thu, 5 Mar 2020 23:22:55 +0100 Subject: Revert "rculist: Describe variadic macro argument in a Sphinx-compatible way" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit f452ee096d95482892b101bde4fd037fa025d3cc. The workaround became unnecessary with commit 43756e347f21 ("scripts/kernel-doc: Add support for named variable macro arguments"). Signed-off-by: Jonathan Neuschäfer Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 8214cdc715f2..7375bb3da140 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -371,7 +371,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. - * @cond...: optional lockdep expression if called from non-RCU protection. + * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() @@ -646,7 +646,7 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. - * @cond...: optional lockdep expression if called from non-RCU protection. + * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() -- cgit v1.2.3 From 6be7436d2245d3dd8b9a8f949367c13841c23308 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 10 Apr 2020 13:47:41 -0700 Subject: rcu: Add rcu_gp_might_be_stalled() This commit adds rcu_gp_might_be_stalled(), which returns true if there is some reason to believe that the RCU grace period is stalled. The use case is where an RCU free-memory path needs to allocate memory in order to free it, a situation that should be avoided where possible. But where it is necessary, there is always the alternative of using synchronize_rcu() to wait for a grace period in order to avoid the allocation. And if the grace period is stalled, allocating memory to asynchronously wait for it is a bad idea of epic proportions: Far better to let others use the memory, because these others might actually be able to free that memory before the grace period ends. Thus, rcu_gp_might_be_stalled() can be used to help decide whether allocating memory on an RCU free path is a semi-reasonable course of action. Cc: Joel Fernandes Cc: Uladzislau Rezki Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 1 + include/linux/rcutree.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 045c28b71f4f..dbf5ac439594 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -87,6 +87,7 @@ static inline bool rcu_inkernel_boot_has_ended(void) { return true; } static inline bool rcu_is_watching(void) { return true; } static inline void rcu_momentary_dyntick_idle(void) { } static inline void kfree_rcu_scheduler_running(void) { } +static inline bool rcu_gp_might_be_stalled(void) { return false; } /* Avoid RCU read-side critical sections leaking across. */ static inline void rcu_all_qs(void) { barrier(); } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 45f3f66bb04d..fbc26274af4d 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -39,6 +39,7 @@ void rcu_barrier(void); bool rcu_eqs_special_set(int cpu); void rcu_momentary_dyntick_idle(void); void kfree_rcu_scheduler_running(void); +bool rcu_gp_might_be_stalled(void); unsigned long get_state_synchronize_rcu(void); void cond_synchronize_rcu(unsigned long oldstate); -- cgit v1.2.3 From f0bdf6d473cf12a488a78422e15aafdfe77cf853 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Sat, 15 Feb 2020 14:52:32 -0800 Subject: rcu: Remove unused ->rcu_read_unlock_special.b.deferred_qs field The ->rcu_read_unlock_special.b.deferred_qs field is set to true in rcu_read_unlock_special() but never set to false. This is not particularly useful, so this commit removes this field. The only possible justification for this field is to ease debugging of RCU deferred quiscent states, but the combination of the other ->rcu_read_unlock_special fields plus ->rcu_blocked_node and of course ->rcu_read_lock_nesting should cover debugging needs. And if this last proves incorrect, this patch can always be reverted, along with the required setting of ->rcu_read_unlock_special.b.deferred_qs to false in rcu_preempt_deferred_qs_irqrestore(). Signed-off-by: Lai Jiangshan Signed-off-by: Paul E. McKenney --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4418f5cb8324..a4b727f57095 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -613,7 +613,7 @@ union rcu_special { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ - u8 deferred_qs; + u8 pad; /* No garbage from compiler! */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; -- cgit v1.2.3 From 2beaf3280e57bb891f8012dca49c87ed0f01e2f3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 11 Mar 2020 14:23:21 -0700 Subject: sched/core: Add function to sample state of locked-down task A running task's state can be sampled in a consistent manner (for example, for diagnostic purposes) simply by invoking smp_call_function_single() on its CPU, which may be obtained using task_cpu(), then having the IPI handler verify that the desired task is in fact still running. However, if the task is not running, this sampling can in theory be done immediately and directly. In practice, the task might start running at any time, including during the sampling period. Gaining a consistent sample of a not-running task therefore requires that something be done to lock down the target task's state. This commit therefore adds a try_invoke_on_locked_down_task() function that invokes a specified function if the specified task can be locked down, returning true if successful and if the specified function returns true. Otherwise this function simply returns false. Given that the function passed to try_invoke_on_nonrunning_task() might be invoked with a runqueue lock held, that function had better be quite lightweight. The function is passed the target task's task_struct pointer and the argument passed to try_invoke_on_locked_down_task(), allowing easy access to task state and to a location for further variables to be passed in and out. Note that the specified function will be called even if the specified task is currently running. The function can use ->on_rq and task_curr() to quickly and easily determine the task's state, and can return false if this state is not to the function's liking. The caller of the try_invoke_on_locked_down_task() would then see the false return value, and could take appropriate action, for example, trying again later or sending an IPI if matters are more urgent. It is expected that use cases such as the RCU CPU stall warning code will simply return false if the task is currently running. However, there are use cases involving nohz_full CPUs where the specified function might instead fall back to an alternative sampling scheme that relies on heavier synchronization (such as memory barriers) in the target task. Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Juri Lelli Cc: Vincent Guittot Cc: Dietmar Eggemann Cc: Ben Segall Cc: Mel Gorman [ paulmck: Apply feedback from Peter Zijlstra and Steven Rostedt. ] [ paulmck: Invoke if running to handle feedback from Mathieu Desnoyers. ] Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/wait.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index feeb6be5cad6..898c890fc153 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -1149,4 +1149,6 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i (wait)->flags = 0; \ } while (0) +bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg); + #endif /* _LINUX_WAIT_H */ -- cgit v1.2.3 From b3d73156b075014ce5b2609f4f47723d6c0c23d6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 6 Mar 2020 13:58:27 -0800 Subject: rcu: Reinstate synchronize_rcu_mult() With the advent and likely usage of synchronize_rcu_rude(), there is again a need to wait on multiple types of RCU grace periods, for example, call_rcu_tasks() and call_rcu_tasks_rude(). This commit therefore reinstates synchronize_rcu_mult() in order to allow these grace periods to be straightforwardly waited on concurrently. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_wait.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index c0578ba23c1a..699b938358bf 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -31,4 +31,23 @@ do { \ #define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) +/** + * synchronize_rcu_mult - Wait concurrently for multiple grace periods + * @...: List of call_rcu() functions for different grace periods to wait on + * + * This macro waits concurrently for multiple types of RCU grace periods. + * For example, synchronize_rcu_mult(call_rcu, call_rcu_tasks) would wait + * on concurrent RCU and RCU-tasks grace periods. Waiting on a given SRCU + * domain requires you to write a wrapper function for that SRCU domain's + * call_srcu() function, with this wrapper supplying the pointer to the + * corresponding srcu_struct. + * + * The first argument tells Tiny RCU's _wait_rcu_gp() not to + * bother waiting for RCU. The reason for this is because anywhere + * synchronize_rcu_mult() can be called is automatically already a full + * grace period. + */ +#define synchronize_rcu_mult(...) \ + _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) + #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */ -- cgit v1.2.3 From 5873b8a94e5dae04b8e11fc798df512614e6d1e7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 3 Mar 2020 11:49:21 -0800 Subject: rcu-tasks: Refactor RCU-tasks to allow variants to be added This commit splits out generic processing from RCU-tasks-specific processing in order to allow additional flavors to be added. It also adds a def_bool TASKS_RCU_GENERIC to enable the common RCU-tasks infrastructure code. This is primarily, but not entirely, a code-movement commit. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 2678a37c3169..5523145e0a78 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -129,7 +129,7 @@ static inline void rcu_init_nohz(void) { } * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ -#ifdef CONFIG_TASKS_RCU +#ifdef CONFIG_TASKS_RCU_GENERIC #define rcu_tasks_qs(t) \ do { \ if (READ_ONCE((t)->rcu_tasks_holdout)) \ @@ -140,14 +140,14 @@ void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); -#else /* #ifdef CONFIG_TASKS_RCU */ +#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_qs(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } -#endif /* #else #ifdef CONFIG_TASKS_RCU */ +#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU -- cgit v1.2.3 From c84aad765406c4c7573ce449e8a9977ebb8f4cb9 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 2 Mar 2020 21:06:43 -0800 Subject: rcu-tasks: Add an RCU-tasks rude variant This commit adds a "rude" variant of RCU-tasks that has as quiescent states schedule(), cond_resched_tasks_rcu_qs(), userspace execution, and (in theory, anyway) cond_resched(). In other words, RCU-tasks rude readers are regions of code with preemption disabled, but excluding code early in the CPU-online sequence and late in the CPU-offline sequence. Updates make use of IPIs and force an IPI and a context switch on each online CPU. This variant is useful in some situations in tracing. Suggested-by: Steven Rostedt [ paulmck: Apply EXPORT_SYMBOL_GPL() feedback from Qiujun Huang. ] Signed-off-by: Paul E. McKenney [ paulmck: Apply review feedback from Steve Rostedt. ] --- include/linux/rcupdate.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 5523145e0a78..2be97a83f266 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -37,6 +37,7 @@ /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); +void rcu_barrier_tasks_rude(void); void synchronize_rcu(void); #ifdef CONFIG_PREEMPT_RCU @@ -138,6 +139,8 @@ static inline void rcu_init_nohz(void) { } #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); +void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); +void synchronize_rcu_tasks_rude(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ -- cgit v1.2.3 From d5f177d35c24429c87db2567d20563fc16f7e8f6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 9 Mar 2020 19:56:53 -0700 Subject: rcu-tasks: Add an RCU Tasks Trace to simplify protection of tracing hooks Because RCU does not watch exception early-entry/late-exit, idle-loop, or CPU-hotplug execution, protection of tracing and BPF operations is needlessly complicated. This commit therefore adds a variant of Tasks RCU that: o Has explicit read-side markers to allow finite grace periods in the face of in-kernel loops for PREEMPT=n builds. These markers are rcu_read_lock_trace() and rcu_read_unlock_trace(). o Protects code in the idle loop, exception entry/exit, and CPU-hotplug code paths. In this respect, RCU-tasks trace is similar to SRCU, but with lighter-weight readers. o Avoids expensive read-side instruction, having overhead similar to that of Preemptible RCU. There are of course downsides: o The grace-period code can send IPIs to CPUs, even when those CPUs are in the idle loop or in nohz_full userspace. This is mitigated by later commits. o It is necessary to scan the full tasklist, much as for Tasks RCU. o There is a single callback queue guarded by a single lock, again, much as for Tasks RCU. However, those early use cases that request multiple grace periods in quick succession are expected to do so from a single task, which makes the single lock almost irrelevant. If needed, multiple callback queues can be provided using any number of schemes. Perhaps most important, this variant of RCU does not affect the vanilla flavors, rcu_preempt and rcu_sched. The fact that RCU Tasks Trace readers can operate from idle, offline, and exception entry/exit in no way enables rcu_preempt and rcu_sched readers to do so. The memory ordering was outlined here: https://lore.kernel.org/lkml/20200319034030.GX3199@paulmck-ThinkPad-P72/ This effort benefited greatly from off-list discussions of BPF requirements with Alexei Starovoitov and Andrii Nakryiko. At least some of the on-list discussions are captured in the Link: tags below. In addition, KCSAN was quite helpful in finding some early bugs. Link: https://lore.kernel.org/lkml/20200219150744.428764577@infradead.org/ Link: https://lore.kernel.org/lkml/87mu8p797b.fsf@nanos.tec.linutronix.de/ Link: https://lore.kernel.org/lkml/20200225221305.605144982@linutronix.de/ Cc: Alexei Starovoitov Cc: Andrii Nakryiko [ paulmck: Apply feedback from Steve Rostedt and Joel Fernandes. ] [ paulmck: Decrement trc_n_readers_need_end upon IPI failure. ] [ paulmck: Fix locking issue reported by rcutorture. ] Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_trace.h | 84 ++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 8 ++++ 2 files changed, 92 insertions(+) create mode 100644 include/linux/rcupdate_trace.h (limited to 'include/linux') diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h new file mode 100644 index 000000000000..ed97e10817bd --- /dev/null +++ b/include/linux/rcupdate_trace.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Read-Copy Update mechanism for mutual exclusion, adapted for tracing. + * + * Copyright (C) 2020 Paul E. McKenney. + */ + +#ifndef __LINUX_RCUPDATE_TRACE_H +#define __LINUX_RCUPDATE_TRACE_H + +#include +#include + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +extern struct lockdep_map rcu_trace_lock_map; + +static inline int rcu_read_lock_trace_held(void) +{ + return lock_is_held(&rcu_trace_lock_map); +} + +#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +static inline int rcu_read_lock_trace_held(void) +{ + return 1; +} + +#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +#ifdef CONFIG_TASKS_TRACE_RCU + +void rcu_read_unlock_trace_special(struct task_struct *t); + +/** + * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section + * + * When synchronize_rcu_trace() is invoked by one task, then that task + * is guaranteed to block until all other tasks exit their read-side + * critical sections. Similarly, if call_rcu_trace() is invoked on one + * task while other tasks are within RCU read-side critical sections, + * invocation of the corresponding RCU callback is deferred until after + * the all the other tasks exit their critical sections. + * + * For more details, please see the documentation for rcu_read_lock(). + */ +static inline void rcu_read_lock_trace(void) +{ + struct task_struct *t = current; + + WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1); + rcu_lock_acquire(&rcu_trace_lock_map); +} + +/** + * rcu_read_unlock_trace - mark end of RCU-trace read-side critical section + * + * Pairs with a preceding call to rcu_read_lock_trace(), and nesting is + * allowed. Invoking a rcu_read_unlock_trace() when there is no matching + * rcu_read_lock_trace() is verboten, and will result in lockdep complaints. + * + * For more details, please see the documentation for rcu_read_unlock(). + */ +static inline void rcu_read_unlock_trace(void) +{ + int nesting; + struct task_struct *t = current; + + rcu_lock_release(&rcu_trace_lock_map); + nesting = READ_ONCE(t->trc_reader_nesting) - 1; + WRITE_ONCE(t->trc_reader_nesting, nesting); + if (likely(!READ_ONCE(t->trc_reader_need_end)) || nesting) + return; // We assume shallow reader nesting. + rcu_read_unlock_trace_special(t); +} + +void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func); +void synchronize_rcu_tasks_trace(void); +void rcu_barrier_tasks_trace(void); + +#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ + +#endif /* __LINUX_RCUPDATE_TRACE_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index a4b727f57095..864f60e51c41 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -724,6 +724,14 @@ struct task_struct { struct list_head rcu_tasks_holdout_list; #endif /* #ifdef CONFIG_TASKS_RCU */ +#ifdef CONFIG_TASKS_TRACE_RCU + int trc_reader_nesting; + int trc_ipi_to_cpu; + bool trc_reader_need_end; + bool trc_reader_checked; + struct list_head trc_holdout_list; +#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ + struct sched_info sched_info; struct list_head tasks; -- cgit v1.2.3 From 43766c3eadcf6033c92eb953f88801aebac0f785 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 16 Mar 2020 20:38:29 -0700 Subject: rcu-tasks: Make RCU Tasks Trace make use of RCU scheduler hooks This commit makes the calls to rcu_tasks_qs() detect and report quiescent states for RCU tasks trace. If the task is in a quiescent state and if ->trc_reader_checked is not yet set, the task sets its own ->trc_reader_checked. This will cause the grace-period kthread to remove it from the holdout list if it still remains there. [ paulmck: Fix conditional compilation per kbuild test robot feedback. ] Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 44 +++++++++++++++++++++++++++++++++++++------- include/linux/rcutiny.h | 2 +- 2 files changed, 38 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 2be97a83f266..659cbfa7581a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -131,20 +131,50 @@ static inline void rcu_init_nohz(void) { } * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU_GENERIC -#define rcu_tasks_qs(t) \ - do { \ - if (READ_ONCE((t)->rcu_tasks_holdout)) \ - WRITE_ONCE((t)->rcu_tasks_holdout, false); \ + +# ifdef CONFIG_TASKS_RCU +# define rcu_tasks_classic_qs(t, preempt) \ + do { \ + if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ + WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) -#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); +# else +# define rcu_tasks_classic_qs(t, preempt) do { } while (0) +# define call_rcu_tasks call_rcu +# define synchronize_rcu_tasks synchronize_rcu +# endif + +# ifdef CONFIG_TASKS_RCU_TRACE +# define rcu_tasks_trace_qs(t) \ + do { \ + if (!likely(READ_ONCE((t)->trc_reader_checked)) && \ + !unlikely(READ_ONCE((t)->trc_reader_nesting))) { \ + smp_store_release(&(t)->trc_reader_checked, true); \ + smp_mb(); /* Readers partitioned by store. */ \ + } \ + } while (0) +# else +# define rcu_tasks_trace_qs(t) do { } while (0) +# endif + +#define rcu_tasks_qs(t, preempt) \ +do { \ + rcu_tasks_classic_qs((t), (preempt)); \ + rcu_tasks_trace_qs((t)); \ +} while (0) + +# ifdef CONFIG_TASKS_RUDE_RCU void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks_rude(void); +# endif + +#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ -#define rcu_tasks_qs(t) do { } while (0) +#define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu @@ -161,7 +191,7 @@ static inline void exit_tasks_rcu_finish(void) { } */ #define cond_resched_tasks_rcu_qs() \ do { \ - rcu_tasks_qs(current); \ + rcu_tasks_qs(current, false); \ cond_resched(); \ } while (0) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 045c28b71f4f..d77e11186afd 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -49,7 +49,7 @@ static inline void rcu_softirq_qs(void) #define rcu_note_context_switch(preempt) \ do { \ rcu_qs(); \ - rcu_tasks_qs(current); \ + rcu_tasks_qs(current, (preempt)); \ } while (0) static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) -- cgit v1.2.3 From 276c410448dbca357a2bc3539acfe04862e5f172 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 17 Mar 2020 16:02:06 -0700 Subject: rcu-tasks: Split ->trc_reader_need_end This commit splits ->trc_reader_need_end by using the rcu_special union. This change permits readers to check to see if a memory barrier is required without any added overhead in the common case where no such barrier is required. This commit also adds the read-side checking. Later commits will add the machinery to properly set the new ->trc_reader_special.b.need_mb field. This commit also makes rcu_read_unlock_trace_special() tolerate nested read-side critical sections within interrupt and NMI handlers. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_trace.h | 11 +++++++---- include/linux/sched.h | 4 ++-- 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index ed97e10817bd..c42b365ca176 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -31,7 +31,7 @@ static inline int rcu_read_lock_trace_held(void) #ifdef CONFIG_TASKS_TRACE_RCU -void rcu_read_unlock_trace_special(struct task_struct *t); +void rcu_read_unlock_trace_special(struct task_struct *t, int nesting); /** * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section @@ -50,6 +50,8 @@ static inline void rcu_read_lock_trace(void) struct task_struct *t = current; WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1); + if (t->trc_reader_special.b.need_mb) + smp_mb(); // Pairs with update-side barriers rcu_lock_acquire(&rcu_trace_lock_map); } @@ -69,10 +71,11 @@ static inline void rcu_read_unlock_trace(void) rcu_lock_release(&rcu_trace_lock_map); nesting = READ_ONCE(t->trc_reader_nesting) - 1; - WRITE_ONCE(t->trc_reader_nesting, nesting); - if (likely(!READ_ONCE(t->trc_reader_need_end)) || nesting) + if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) { + WRITE_ONCE(t->trc_reader_nesting, nesting); return; // We assume shallow reader nesting. - rcu_read_unlock_trace_special(t); + } + rcu_read_unlock_trace_special(t, nesting); } void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func); diff --git a/include/linux/sched.h b/include/linux/sched.h index 864f60e51c41..9437b53cc603 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -613,7 +613,7 @@ union rcu_special { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ - u8 pad; /* No garbage from compiler! */ + u8 need_mb; /* Readers need smp_mb(). */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; @@ -727,7 +727,7 @@ struct task_struct { #ifdef CONFIG_TASKS_TRACE_RCU int trc_reader_nesting; int trc_ipi_to_cpu; - bool trc_reader_need_end; + union rcu_special trc_reader_special; bool trc_reader_checked; struct list_head trc_holdout_list; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ -- cgit v1.2.3 From 9ae58d7bd11f1fc4c96389df11751f8593d8bd33 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 18 Mar 2020 17:16:37 -0700 Subject: rcu-tasks: Add Kconfig option to mediate smp_mb() vs. IPI This commit provides a new TASKS_TRACE_RCU_READ_MB Kconfig option that enables use of read-side memory barriers by both rcu_read_lock_trace() and rcu_read_unlock_trace() when the are executed with the current->trc_reader_special.b.need_mb flag set. This flag is currently never set. Doing that is the subject of a later commit. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_trace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index c42b365ca176..4c25a41f8b27 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -50,7 +50,8 @@ static inline void rcu_read_lock_trace(void) struct task_struct *t = current; WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1); - if (t->trc_reader_special.b.need_mb) + if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && + t->trc_reader_special.b.need_mb) smp_mb(); // Pairs with update-side barriers rcu_lock_acquire(&rcu_trace_lock_map); } -- cgit v1.2.3 From be44ae62431196ac2a55198c0855028fff3ccfb4 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 25 Feb 2020 21:09:19 -0800 Subject: locktorture.c: Fix if-statement empty body warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When using -Wextra, gcc complains about torture_preempt_schedule() when its definition is empty (i.e., when CONFIG_PREEMPTION is not set/enabled). Fix these warnings by adding an empty do-while block for that macro when CONFIG_PREEMPTION is not set. Fixes these build warnings: ../kernel/locking/locktorture.c:119:29: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] ../kernel/locking/locktorture.c:166:29: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] ../kernel/locking/locktorture.c:337:29: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] ../kernel/locking/locktorture.c:490:29: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] ../kernel/locking/locktorture.c:528:29: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] ../kernel/locking/locktorture.c:553:29: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] I have verified that there is no object code change (with gcc 7.5.0). Signed-off-by: Randy Dunlap Cc: Davidlohr Bueso Cc: Josh Triplett Signed-off-by: "Paul E. McKenney" --- include/linux/torture.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/torture.h b/include/linux/torture.h index 6241f59e2d6f..629b66e6c161 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -89,7 +89,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); #ifdef CONFIG_PREEMPTION #define torture_preempt_schedule() preempt_schedule() #else -#define torture_preempt_schedule() +#define torture_preempt_schedule() do { } while (0) #endif #endif /* __LINUX_TORTURE_H */ -- cgit v1.2.3 From 4b8d7d4c599182393421c190bae3604b4db9629a Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Sun, 26 Apr 2020 15:22:00 +0200 Subject: bridge: mrp: Extend bridge interface To integrate MRP into the bridge, first the bridge needs to be aware of ports that are part of an MRP ring and which rings are on the bridge. Therefore extend bridge interface with the following: - add new flag(BR_MPP_AWARE) to the net bridge ports, this bit will be set when the port is added to an MRP instance. In this way it knows if the frame was received on MRP ring port - add new flag(BR_MRP_LOST_CONT) to the net bridge ports, this bit will be set when the port lost the continuity of MRP Test frames. - add a list of MRP instances Reviewed-by: Nikolay Aleksandrov Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 9e57c4411734..b3a8d3054af0 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -47,6 +47,8 @@ struct br_ip_list { #define BR_BCAST_FLOOD BIT(14) #define BR_NEIGH_SUPPRESS BIT(15) #define BR_ISOLATED BIT(16) +#define BR_MRP_AWARE BIT(17) +#define BR_MRP_LOST_CONT BIT(18) #define BR_DEFAULT_AGEING_TIME (300 * HZ) -- cgit v1.2.3 From e145d9a184f23639edc864e2fa08fcc1853361a4 Mon Sep 17 00:00:00 2001 From: Akash Asthana Date: Wed, 15 Apr 2020 15:53:10 +0530 Subject: interconnect: Add devm_of_icc_get() as exported API for users Users can use devm version of of_icc_get() to benefit from automatic resource release. Signed-off-by: Akash Asthana Reviewed by: Matthias Kaehlcke Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/1586946198-13912-2-git-send-email-akashast@codeaurora.org Signed-off-by: Georgi Djakov --- include/linux/interconnect.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index d70a914cba11..770692421f4c 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -28,6 +28,7 @@ struct device; struct icc_path *icc_get(struct device *dev, const int src_id, const int dst_id); struct icc_path *of_icc_get(struct device *dev, const char *name); +struct icc_path *devm_of_icc_get(struct device *dev, const char *name); void icc_put(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); void icc_set_tag(struct icc_path *path, u32 tag); @@ -46,6 +47,12 @@ static inline struct icc_path *of_icc_get(struct device *dev, return NULL; } +static inline struct icc_path *devm_of_icc_get(struct device *dev, + const char *name) +{ + return NULL; +} + static inline void icc_put(struct icc_path *path) { } -- cgit v1.2.3 From 40a571bc408bf10ac8be0eadf838483b9cf90141 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 3 Apr 2020 23:41:27 +0300 Subject: mtd: spi-nor: fix kernel-doc for 'struct spi_nor' When introducing 'struct spi_nor', a number of issues was added in its kernel-doc comment: - double article in the heading kernel-doc comment; - "point" instead of "pointer" for the 'mtd' and 'dev' fields; - "a" articles instead of "an" for the 'dev' field; - acronyms in the lower case for the 'dev' field; - missing "pointer to" for the 'priv' field. Fix all of those at once... Fixes: 6e602ef73334 ("mtd: spi-nor: add the basic data structures") Signed-off-by: Sergei Shtylyov Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 1cc8ed5d59ed..d3fcf7654040 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -327,10 +327,10 @@ struct spi_nor_manufacturer; struct spi_nor_flash_parameter; /** - * struct spi_nor - Structure for defining a the SPI NOR layer - * @mtd: point to a mtd_info structure + * struct spi_nor - Structure for defining the SPI NOR layer + * @mtd: pointer to an mtd_info structure * @lock: the lock for the read/write/erase/lock/unlock operations - * @dev: point to a spi device, or a spi nor controller device. + * @dev: pointer to an SPI device or an SPI NOR controller device * @spimem: point to the spi mem device * @bouncebuf: bounce buffer used when the buffer passed by the MTD * layer is not DMA-able @@ -354,7 +354,7 @@ struct spi_nor_flash_parameter; * settings that can be overwritten by the spi_nor_fixups * hooks, or dynamically when parsing the SFDP tables. * @dirmap: pointers to struct spi_mem_dirmap_desc for reads/writes. - * @priv: the private data + * @priv: pointer to the private data */ struct spi_nor { struct mtd_info mtd; -- cgit v1.2.3 From ba0aa311b0eb9d0a66a1b6b6fdeaa3b7584b798a Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 3 Apr 2020 23:44:16 +0300 Subject: mtd: spi-nor: fix kernel-doc for spi_nor::mtd When embedding 'struct mtd_info' within 'struct spi_nor', the kernel-doc comment was forgotten. Fix it by dropping the "pointer to" part from the comment. Fixes: 1976367173a4 ("mtd: spi-nor: embed struct mtd_info within struct spi_nor") Signed-off-by: Sergei Shtylyov Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index d3fcf7654040..20077881c955 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -328,7 +328,7 @@ struct spi_nor_flash_parameter; /** * struct spi_nor - Structure for defining the SPI NOR layer - * @mtd: pointer to an mtd_info structure + * @mtd: an mtd_info structure * @lock: the lock for the read/write/erase/lock/unlock operations * @dev: pointer to an SPI device or an SPI NOR controller device * @spimem: point to the spi mem device -- cgit v1.2.3 From ba053dd3b4d841e17e910d0b91e22d9ea813fa39 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 3 Apr 2020 23:45:49 +0300 Subject: mtd: spi-nor: fix kernel-doc for spi_nor::reg_proto When adding the '{read|write|reg}_proto' fields to 'struct spi_nor', a colon was missed in the comment for the spi_nor::reg_proto' -- add it. Fixes: cfc5604c488c ("mtd: spi-nor: introduce SPI 1-2-2 and SPI 1-4-4 protocols") Signed-off-by: Sergei Shtylyov Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 20077881c955..1b2143d921ac 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -347,7 +347,7 @@ struct spi_nor_flash_parameter; * @flags: flag options for the current SPI-NOR (SNOR_F_*) * @read_proto: the SPI protocol for read operations * @write_proto: the SPI protocol for write operations - * @reg_proto the SPI protocol for read_reg/write_reg/erase operations + * @reg_proto: the SPI protocol for read_reg/write_reg/erase operations * @controller_ops: SPI NOR controller driver specific operations. * @params: [FLASH-SPECIFIC] SPI-NOR flash parameters and settings. * The structure includes legacy flash parameters and -- cgit v1.2.3 From 80cb801144265866ce29fabe5ea7ac8588aa673c Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 3 Apr 2020 23:49:48 +0300 Subject: mtd: spi-nor: fix kernel-doc for spi_nor::info When adding the 'info' field to 'struct spi_nor', some acronyms were in lower case and some in upper case and the JEDEC acronym mistyped -- fix these issues. Fixes: 46dde01f6bab ("mtd: spi-nor: add spi_nor_init() function") Signed-off-by: Sergei Shtylyov Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 1b2143d921ac..3333103c519b 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -335,7 +335,7 @@ struct spi_nor_flash_parameter; * @bouncebuf: bounce buffer used when the buffer passed by the MTD * layer is not DMA-able * @bouncebuf_size: size of the bounce buffer - * @info: spi-nor part JDEC MFR id and other info + * @info: SPI NOR part JEDEC MFR ID and other info * @manufacturer: spi-nor manufacturer * @page_size: the page size of the SPI NOR * @addr_width: number of address bytes -- cgit v1.2.3 From 1f241ad2a093b889122bd6bfdce57551d21bba5b Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 3 Apr 2020 23:50:57 +0300 Subject: mtd: spi-nor: fix kernel-doc for spi_nor::spimem When adding the 'spimem' field to 'struct spi_nor', a grammar mistake ("point" instead of "pointer") was made -- fix it and convert the SPI acronym to uppercase and fully spell out "memory", while at it... Fixes: b35b9a10362 ("mtd: spi-nor: Move m25p80 code in spi-nor.c") Signed-off-by: Sergei Shtylyov Signed-off-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 3333103c519b..bebff2729c18 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -331,7 +331,7 @@ struct spi_nor_flash_parameter; * @mtd: an mtd_info structure * @lock: the lock for the read/write/erase/lock/unlock operations * @dev: pointer to an SPI device or an SPI NOR controller device - * @spimem: point to the spi mem device + * @spimem: pointer to the SPI memory device * @bouncebuf: bounce buffer used when the buffer passed by the MTD * layer is not DMA-able * @bouncebuf_size: size of the bounce buffer -- cgit v1.2.3 From 767dea211cd0c68d8116d8c3b5104e82454fb44b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 28 Apr 2020 07:17:03 +0200 Subject: x86/tboot: Mark tboot static This structure is only really used in tboot.c. The only exception is a single tboot_enabled check, but for that we don't need an inline function. Signed-off-by: Christoph Hellwig Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200428051703.1625952-1-hch@lst.de --- include/linux/tboot.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tboot.h b/include/linux/tboot.h index 5424bc6feac8..c7e424766360 100644 --- a/include/linux/tboot.h +++ b/include/linux/tboot.h @@ -121,13 +121,7 @@ struct tboot { #define TBOOT_UUID {0xff, 0x8d, 0x3c, 0x66, 0xb3, 0xe8, 0x82, 0x4b, 0xbf,\ 0xaa, 0x19, 0xea, 0x4d, 0x5, 0x7a, 0x8} -extern struct tboot *tboot; - -static inline int tboot_enabled(void) -{ - return tboot != NULL; -} - +bool tboot_enabled(void); extern void tboot_probe(void); extern void tboot_shutdown(u32 shutdown_type); extern struct acpi_table_header *tboot_get_dmar_table( -- cgit v1.2.3 From 0c6b20a1d720ad1d43a2aca0ffa1af07c201b55d Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Mon, 27 Apr 2020 13:28:27 +0530 Subject: bus: mhi: core: Add support for MHI suspend and resume Add support for MHI suspend and resume states. While at it, the mhi_notify() function needs to be exported as well. Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200427075829.9304-2-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index ad1996001965..a4288f4d656f 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -568,6 +568,13 @@ void mhi_driver_unregister(struct mhi_driver *mhi_drv); void mhi_set_mhi_state(struct mhi_controller *mhi_cntrl, enum mhi_state state); +/** + * mhi_notify - Notify the MHI client driver about client device status + * @mhi_dev: MHI device instance + * @cb_reason: MHI callback reason + */ +void mhi_notify(struct mhi_device *mhi_dev, enum mhi_callback cb_reason); + /** * mhi_prepare_for_power_up - Do pre-initialization before power up. * This is optional, call this before power up if @@ -604,6 +611,18 @@ void mhi_power_down(struct mhi_controller *mhi_cntrl, bool graceful); */ void mhi_unprepare_after_power_down(struct mhi_controller *mhi_cntrl); +/** + * mhi_pm_suspend - Move MHI into a suspended state + * @mhi_cntrl: MHI controller + */ +int mhi_pm_suspend(struct mhi_controller *mhi_cntrl); + +/** + * mhi_pm_resume - Resume MHI from suspended state + * @mhi_cntrl: MHI controller + */ +int mhi_pm_resume(struct mhi_controller *mhi_cntrl); + /** * mhi_download_rddm_img - Download ramdump image from device for * debugging purpose. -- cgit v1.2.3 From 7536ad8dbfcfd56cd04d005b76cd9ecf2036e220 Mon Sep 17 00:00:00 2001 From: Richard Gong Date: Tue, 14 Apr 2020 15:47:54 -0500 Subject: firmware: fpga: replace the error codes with the standard ones MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Intel service layer driver has defined error codes for the specific services, which started from FPGA configuration then RSU (Remote Status Update). Intel service layer driver should define the standard error codes rather than keep adding more error codes for the new services. The standard error codes will be used by all the clients of Intel service layer driver. Replace FPGA and RSU specific error codes with Intel service layer’s Common error codes. Signed-off-by: Richard Gong Link: https://lore.kernel.org/r/1586897274-307-2-git-send-email-richard.gong@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/intel/stratix10-smc.h | 49 +++++++-------- .../linux/firmware/intel/stratix10-svc-client.h | 71 +++++++++------------- 2 files changed, 51 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h index 013ae4819deb..682dbf694007 100644 --- a/include/linux/firmware/intel/stratix10-smc.h +++ b/include/linux/firmware/intel/stratix10-smc.h @@ -54,32 +54,25 @@ * Secure monitor software doesn't recognize the request. * * INTEL_SIP_SMC_STATUS_OK: - * FPGA configuration completed successfully, - * In case of FPGA configuration write operation, it means secure monitor - * software can accept the next chunk of FPGA configuration data. + * Secure monitor software accepts the service client's request. * - * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY: - * In case of FPGA configuration write operation, it means secure monitor - * software is still processing previous data & can't accept the next chunk - * of data. Service driver needs to issue - * INTEL_SIP_SMC_FPGA_CONFIG_COMPLETED_WRITE call to query the - * completed block(s). + * INTEL_SIP_SMC_STATUS_BUSY: + * Secure monitor software is still processing service client's request. * - * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR: - * There is error during the FPGA configuration process. + * INTEL_SIP_SMC_STATUS_REJECTED: + * Secure monitor software reject the service client's request. * - * INTEL_SIP_SMC_REG_ERROR: - * There is error during a read or write operation of the protected registers. + * INTEL_SIP_SMC_STATUS_ERROR: + * There is error during the process of service request. * * INTEL_SIP_SMC_RSU_ERROR: - * There is error during a remote status update. + * There is error during the process of remote status update request. */ #define INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION 0xFFFFFFFF #define INTEL_SIP_SMC_STATUS_OK 0x0 -#define INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY 0x1 -#define INTEL_SIP_SMC_FPGA_CONFIG_STATUS_REJECTED 0x2 -#define INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR 0x4 -#define INTEL_SIP_SMC_REG_ERROR 0x5 +#define INTEL_SIP_SMC_STATUS_BUSY 0x1 +#define INTEL_SIP_SMC_STATUS_REJECTED 0x2 +#define INTEL_SIP_SMC_STATUS_ERROR 0x4 #define INTEL_SIP_SMC_RSU_ERROR 0x7 /** @@ -95,7 +88,7 @@ * a2-7: not used. * * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK, or INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a0: INTEL_SIP_SMC_STATUS_OK, or INTEL_SIP_SMC_STATUS_ERROR. * a1-3: not used. */ #define INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_START 1 @@ -115,8 +108,8 @@ * a3-7: not used. * * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY or - * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_STATUS_BUSY or + * INTEL_SIP_SMC_STATUS_ERROR. * a1: 64bit physical address of 1st completed memory block if any completed * block, otherwise zero value. * a2: 64bit physical address of 2nd completed memory block if any completed @@ -133,15 +126,15 @@ * * Sync call used by service driver at EL1 to track the completed write * transactions. This request is called after INTEL_SIP_SMC_FPGA_CONFIG_WRITE - * call returns INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY. + * call returns INTEL_SIP_SMC_STATUS_BUSY. * * Call register usage: * a0: INTEL_SIP_SMC_FPGA_CONFIG_COMPLETED_WRITE. * a1-7: not used. * * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY or - * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FPGA_BUSY or + * INTEL_SIP_SMC_STATUS_ERROR. * a1: 64bit physical address of 1st completed memory block. * a2: 64bit physical address of 2nd completed memory block if * any completed block, otherwise zero value. @@ -164,8 +157,8 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) * a1-7: not used. * * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY or - * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_STATUS_BUSY or + * INTEL_SIP_SMC_STATUS_ERROR. * a1-3: not used. */ #define INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_ISDONE 4 @@ -183,7 +176,7 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) * a1-7: not used. * * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_STATUS_ERROR. * a1: start of physical address of reserved memory block. * a2: size of reserved memory block. * a3: not used. @@ -203,7 +196,7 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) * a1-7: not used. * * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_STATUS_ERROR. * a1-3: not used. */ #define INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_LOOPBACK 6 diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index 59bc6e2af693..64213c3e82f5 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -18,45 +18,37 @@ /** * Status of the sent command, in bit number * - * SVC_COMMAND_STATUS_RECONFIG_REQUEST_OK: - * Secure firmware accepts the request of FPGA reconfiguration. + * SVC_STATUS_OK: + * Secure firmware accepts the request issued by one of service clients. * - * SVC_STATUS_RECONFIG_BUFFER_SUBMITTED: - * Service client successfully submits FPGA configuration - * data buffer to secure firmware. + * SVC_STATUS_BUFFER_SUBMITTED: + * Service client successfully submits data buffer to secure firmware. * - * SVC_COMMAND_STATUS_RECONFIG_BUFFER_DONE: + * SVC_STATUS_BUFFER_DONE: * Secure firmware completes data process, ready to accept the * next WRITE transaction. * - * SVC_COMMAND_STATUS_RECONFIG_COMPLETED: - * Secure firmware completes FPGA configuration successfully, FPGA should - * be in user mode. + * SVC_STATUS_COMPLETED: + * Secure firmware completes service request successfully. In case of + * FPGA configuration, FPGA should be in user mode. * - * SVC_COMMAND_STATUS_RECONFIG_BUSY: - * FPGA configuration is still in process. + * SVC_COMMAND_STATUS_BUSY: + * Service request is still in process. * - * SVC_COMMAND_STATUS_RECONFIG_ERROR: - * Error encountered during FPGA configuration. + * SVC_COMMAND_STATUS_ERROR: + * Error encountered during the process of the service request. * - * SVC_STATUS_RSU_OK: - * Secure firmware accepts the request of remote status update (RSU). - * - * SVC_STATUS_RSU_ERROR: - * Error encountered during remote system update. - * - * SVC_STATUS_RSU_NO_SUPPORT: - * Secure firmware doesn't support RSU retry or notify feature. + * SVC_STATUS_NO_SUPPORT: + * Secure firmware doesn't support requested features such as RSU retry + * or RSU notify. */ -#define SVC_STATUS_RECONFIG_REQUEST_OK 0 -#define SVC_STATUS_RECONFIG_BUFFER_SUBMITTED 1 -#define SVC_STATUS_RECONFIG_BUFFER_DONE 2 -#define SVC_STATUS_RECONFIG_COMPLETED 3 -#define SVC_STATUS_RECONFIG_BUSY 4 -#define SVC_STATUS_RECONFIG_ERROR 5 -#define SVC_STATUS_RSU_OK 6 -#define SVC_STATUS_RSU_ERROR 7 -#define SVC_STATUS_RSU_NO_SUPPORT 8 +#define SVC_STATUS_OK 0 +#define SVC_STATUS_BUFFER_SUBMITTED 1 +#define SVC_STATUS_BUFFER_DONE 2 +#define SVC_STATUS_COMPLETED 3 +#define SVC_STATUS_BUSY 4 +#define SVC_STATUS_ERROR 5 +#define SVC_STATUS_NO_SUPPORT 6 /** * Flag bit for COMMAND_RECONFIG @@ -84,32 +76,29 @@ struct stratix10_svc_chan; * @COMMAND_NOOP: do 'dummy' request for integration/debug/trouble-shooting * * @COMMAND_RECONFIG: ask for FPGA configuration preparation, return status - * is SVC_STATUS_RECONFIG_REQUEST_OK + * is SVC_STATUS_OK * * @COMMAND_RECONFIG_DATA_SUBMIT: submit buffer(s) of bit-stream data for the - * FPGA configuration, return status is SVC_STATUS_RECONFIG_BUFFER_SUBMITTED, - * or SVC_STATUS_RECONFIG_ERROR + * FPGA configuration, return status is SVC_STATUS_SUBMITTED or SVC_STATUS_ERROR * * @COMMAND_RECONFIG_DATA_CLAIM: check the status of the configuration, return - * status is SVC_STATUS_RECONFIG_COMPLETED, or SVC_STATUS_RECONFIG_BUSY, or - * SVC_STATUS_RECONFIG_ERROR + * status is SVC_STATUS_COMPLETED, or SVC_STATUS_BUSY, or SVC_STATUS_ERROR * * @COMMAND_RECONFIG_STATUS: check the status of the configuration, return - * status is SVC_STATUS_RECONFIG_COMPLETED, or SVC_STATUS_RECONFIG_BUSY, or - * SVC_STATUS_RECONFIG_ERROR + * status is SVC_STATUS_COMPLETED, or SVC_STATUS_BUSY, or SVC_STATUS_ERROR * * @COMMAND_RSU_STATUS: request remote system update boot log, return status * is log data or SVC_STATUS_RSU_ERROR * * @COMMAND_RSU_UPDATE: set the offset of the bitstream to boot after reboot, - * return status is SVC_STATUS_RSU_OK or SVC_STATUS_RSU_ERROR + * return status is SVC_STATUS_OK or SVC_STATUS_ERROR * * @COMMAND_RSU_NOTIFY: report the status of hard processor system - * software to firmware, return status is SVC_STATUS_RSU_OK or - * SVC_STATUS_RSU_ERROR + * software to firmware, return status is SVC_STATUS_OK or + * SVC_STATUS_ERROR * * @COMMAND_RSU_RETRY: query firmware for the current image's retry counter, - * return status is SVC_STATUS_RSU_OK or SVC_STATUS_RSU_ERROR + * return status is SVC_STATUS_OK or SVC_STATUS_ERROR */ enum stratix10_svc_command_code { COMMAND_NOOP = 0, -- cgit v1.2.3 From b9b3a8be28b31a3dbcb0ced07aa0d869f45cdb69 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:43 -0700 Subject: firmware: xilinx: Remove eemi ops for get_api_version Use direct function calls instead of using eemi ops. So remove eemi ops for get_api_version and use direct function call. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-2-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 8efa5ac22d7e..a21abcdb1020 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -294,7 +294,6 @@ struct zynqmp_pm_query_data { }; struct zynqmp_eemi_ops { - int (*get_api_version)(u32 *version); int (*get_chipid)(u32 *idcode, u32 *version); int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); @@ -331,11 +330,16 @@ int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE) const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); +int zynqmp_pm_get_api_version(u32 *version); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { return ERR_PTR(-ENODEV); } +static inline int zynqmp_pm_get_api_version(u32 *version) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 21cd93bab92b2818c9391465123cd4be6431c69e Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:44 -0700 Subject: firmware: xilinx: Remove eemi ops for get_chipid Use direct function call instead of eemi ops for get_chipid. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-3-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index a21abcdb1020..89f6a5394a65 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -294,7 +294,6 @@ struct zynqmp_pm_query_data { }; struct zynqmp_eemi_ops { - int (*get_chipid)(u32 *idcode, u32 *version); int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); int (*query_data)(struct zynqmp_pm_query_data qdata, u32 *out); @@ -331,6 +330,7 @@ int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE) const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); int zynqmp_pm_get_api_version(u32 *version); +int zynqmp_pm_get_chipid(u32 *idcode, u32 *version); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -340,6 +340,10 @@ static inline int zynqmp_pm_get_api_version(u32 *version) { return -ENODEV; } +static inline int zynqmp_pm_get_chipid(u32 *idcode, u32 *version) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 6366c1bac3149c63752c03ea1c731d461d5349a7 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:45 -0700 Subject: firmware: xilinx: Remove eemi ops for query_data Use direct function call for query_data instead of using eemi ops. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-4-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 89f6a5394a65..fa1195c72976 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*query_data)(struct zynqmp_pm_query_data qdata, u32 *out); int (*clock_enable)(u32 clock_id); int (*clock_disable)(u32 clock_id); int (*clock_getstate)(u32 clock_id, u32 *state); @@ -331,6 +330,7 @@ int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); int zynqmp_pm_get_api_version(u32 *version); int zynqmp_pm_get_chipid(u32 *idcode, u32 *version); +int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -344,6 +344,11 @@ static inline int zynqmp_pm_get_chipid(u32 *idcode, u32 *version) { return -ENODEV; } +static inline int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, + u32 *out) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 3637e84cd2e910f84835fac9650316dce53218ef Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:46 -0700 Subject: firmware: xilinx: Remove eemi ops for clock_enable Use direct function call for clock_enable instead of eemi ops. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-5-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index fa1195c72976..77365d1d246c 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_enable)(u32 clock_id); int (*clock_disable)(u32 clock_id); int (*clock_getstate)(u32 clock_id, u32 *state); int (*clock_setdivider)(u32 clock_id, u32 divider); @@ -331,6 +330,7 @@ const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); int zynqmp_pm_get_api_version(u32 *version); int zynqmp_pm_get_chipid(u32 *idcode, u32 *version); int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out); +int zynqmp_pm_clock_enable(u32 clock_id); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -349,6 +349,10 @@ static inline int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, { return -ENODEV; } +static inline int zynqmp_pm_clock_enable(u32 clock_id) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From f5ccd54b67b3f029de9d3818efa70f210d189019 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:47 -0700 Subject: firmware: xilinx: Remove eemi ops for clock_disable Use direct function call for clock_disable instead using of eemi ops. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-6-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 77365d1d246c..f9a84d974b5c 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_disable)(u32 clock_id); int (*clock_getstate)(u32 clock_id, u32 *state); int (*clock_setdivider)(u32 clock_id, u32 divider); int (*clock_getdivider)(u32 clock_id, u32 *divider); @@ -331,6 +330,7 @@ int zynqmp_pm_get_api_version(u32 *version); int zynqmp_pm_get_chipid(u32 *idcode, u32 *version); int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out); int zynqmp_pm_clock_enable(u32 clock_id); +int zynqmp_pm_clock_disable(u32 clock_id); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -353,6 +353,10 @@ static inline int zynqmp_pm_clock_enable(u32 clock_id) { return -ENODEV; } +static inline int zynqmp_pm_clock_disable(u32 clock_id) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 5e76731dd370ca3217fceaa3e2e84e992e6b7b7f Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:48 -0700 Subject: firmware: xilinx: Remove eemi ops for clock_getstate Use direct function call instead of eemi ops for clock_getstate. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-7-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index f9a84d974b5c..e874f0c5e7ab 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_getstate)(u32 clock_id, u32 *state); int (*clock_setdivider)(u32 clock_id, u32 divider); int (*clock_getdivider)(u32 clock_id, u32 *divider); int (*clock_setrate)(u32 clock_id, u64 rate); @@ -331,6 +330,7 @@ int zynqmp_pm_get_chipid(u32 *idcode, u32 *version); int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out); int zynqmp_pm_clock_enable(u32 clock_id); int zynqmp_pm_clock_disable(u32 clock_id); +int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -357,6 +357,10 @@ static inline int zynqmp_pm_clock_disable(u32 clock_id) { return -ENODEV; } +static inline int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From fc9fb8fb985c092f9cf01c7c50269c132efc4d58 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:49 -0700 Subject: firmware: xilinx: Remove eemi ops for clock_setdivider Use direct function call instead of using eemi ops for clock_setdivider. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-8-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index e874f0c5e7ab..023f1f9807ed 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_setdivider)(u32 clock_id, u32 divider); int (*clock_getdivider)(u32 clock_id, u32 *divider); int (*clock_setrate)(u32 clock_id, u64 rate); int (*clock_getrate)(u32 clock_id, u64 *rate); @@ -331,6 +330,7 @@ int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out); int zynqmp_pm_clock_enable(u32 clock_id); int zynqmp_pm_clock_disable(u32 clock_id); int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state); +int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -361,6 +361,10 @@ static inline int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state) { return -ENODEV; } +static inline int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 0667a8d144bc830d0a752f079c9789735cd4f1f8 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:50 -0700 Subject: firmware: xilinx: Remove eemi ops for clock_getdivider Use direct function call instead of using eemi ops for clock_getdivider. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-9-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 023f1f9807ed..3bda22f5262b 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_getdivider)(u32 clock_id, u32 *divider); int (*clock_setrate)(u32 clock_id, u64 rate); int (*clock_getrate)(u32 clock_id, u64 *rate); int (*clock_setparent)(u32 clock_id, u32 parent_id); @@ -331,6 +330,7 @@ int zynqmp_pm_clock_enable(u32 clock_id); int zynqmp_pm_clock_disable(u32 clock_id); int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state); int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider); +int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -365,6 +365,10 @@ static inline int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider) { return -ENODEV; } +static inline int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 7a1e10621a215dad4727aaa82396c4c19ce6593f Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:51 -0700 Subject: firmware: xilinx: Remove eemi ops for clock set/get rate Use direct function call instead of eemi ops for clock set/get rate. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-10-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 3bda22f5262b..a71f52c6173e 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,8 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_setrate)(u32 clock_id, u64 rate); - int (*clock_getrate)(u32 clock_id, u64 *rate); int (*clock_setparent)(u32 clock_id, u32 parent_id); int (*clock_getparent)(u32 clock_id, u32 *parent_id); int (*ioctl)(u32 node_id, u32 ioctl_id, u32 arg1, u32 arg2, u32 *out); @@ -331,6 +329,8 @@ int zynqmp_pm_clock_disable(u32 clock_id); int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state); int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider); int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider); +int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate); +int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -369,6 +369,14 @@ static inline int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider) { return -ENODEV; } +static inline int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate) +{ + return -ENODEV; +} +static inline int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 70c0d36462ca5be8fc05176d11bec832dbb355b2 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:52 -0700 Subject: firmware: xilinx: Remove eemi ops for clock set/get parent Use direct function call instead of eemi ops for clock set/get parent. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-11-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index a71f52c6173e..7abb68311f17 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,8 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*clock_setparent)(u32 clock_id, u32 parent_id); - int (*clock_getparent)(u32 clock_id, u32 *parent_id); int (*ioctl)(u32 node_id, u32 ioctl_id, u32 arg1, u32 arg2, u32 *out); int (*reset_assert)(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); @@ -331,6 +329,8 @@ int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider); int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider); int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate); int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate); +int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id); +int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -377,6 +377,14 @@ static inline int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate) { return -ENODEV; } +static inline int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id) +{ + return -ENODEV; +} +static inline int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 426c8d85df7a7b8337e09eab2806e802311778fd Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:53 -0700 Subject: firmware: xilinx: Use APIs instead of IOCTLs Remove IOCTL API and use individual APIs for better readability. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-12-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 7abb68311f17..5aff8963c11a 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*ioctl)(u32 node_id, u32 ioctl_id, u32 arg1, u32 arg2, u32 *out); int (*reset_assert)(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); int (*reset_get_status)(const enum zynqmp_pm_reset reset, u32 *status); @@ -331,6 +330,12 @@ int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate); int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate); int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id); int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id); +int zynqmp_pm_set_pll_frac_mode(u32 clk_id, u32 mode); +int zynqmp_pm_get_pll_frac_mode(u32 clk_id, u32 *mode); +int zynqmp_pm_set_pll_frac_data(u32 clk_id, u32 data); +int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data); +int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value); +int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -385,6 +390,30 @@ static inline int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id) { return -ENODEV; } +static inline int zynqmp_pm_set_pll_frac_mode(u32 clk_id, u32 mode) +{ + return -ENODEV; +} +static inline int zynqmp_pm_get_pll_frac_mode(u32 clk_id, u32 *mode) +{ + return -ENODEV; +} +static inline int zynqmp_pm_set_pll_frac_data(u32 clk_id, u32 data) +{ + return -ENODEV; +} +static inline int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data) +{ + return -ENODEV; +} +static inline int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value) +{ + return -ENODEV; +} +static inline int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From cf23ec3531462376ef48237235daea577e1194e7 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:54 -0700 Subject: firmware: xilinx: Remove eemi ops for reset_assert Use direct function call instead of using eemi ops for reset_assert. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-13-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 5aff8963c11a..22b2bbe0faea 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,8 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*reset_assert)(const enum zynqmp_pm_reset reset, - const enum zynqmp_pm_reset_action assert_flag); int (*reset_get_status)(const enum zynqmp_pm_reset reset, u32 *status); int (*init_finalize)(void); int (*set_suspend_mode)(u32 mode); @@ -336,6 +334,8 @@ int zynqmp_pm_set_pll_frac_data(u32 clk_id, u32 data); int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data); int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value); int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); +int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, + const enum zynqmp_pm_reset_action assert_flag); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -414,6 +414,11 @@ static inline int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type) { return -ENODEV; } +static inline int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, + const enum zynqmp_pm_reset_action assert_flag) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 1b413581fe26404217a2160d444642440bb0e9e7 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:55 -0700 Subject: firmware: xilinx: Remove eemi ops for reset_get_status Use direct function call instead of using eemi ops for reset_get_status. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-14-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 22b2bbe0faea..200f9e0dc406 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*reset_get_status)(const enum zynqmp_pm_reset reset, u32 *status); int (*init_finalize)(void); int (*set_suspend_mode)(u32 mode); int (*request_node)(const u32 node, @@ -336,6 +335,7 @@ int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value); int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); +int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -419,6 +419,11 @@ static inline int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, { return -ENODEV; } +static inline int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, + u32 *status) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 9474da950d1e39f71cbfeaba87367fa146635a88 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:56 -0700 Subject: firmware: xilinx: Remove eemi ops for init_finalize Use direct function call instead of eemi ops for init_finalize. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-15-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 200f9e0dc406..9aa5fe8acbea 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*init_finalize)(void); int (*set_suspend_mode)(u32 mode); int (*request_node)(const u32 node, const u32 capabilities, @@ -336,6 +335,7 @@ int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); +int zynqmp_pm_init_finalize(void); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -424,6 +424,10 @@ static inline int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, { return -ENODEV; } +static inline int zynqmp_pm_init_finalize(void) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 951d0a97e41caff96c180ca416093276bfd9a4fd Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:57 -0700 Subject: firmware: xilinx: Remove eemi ops for set_suspend_mode Use direct function call instead of eemi ops for set_suspend_mode. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-16-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 9aa5fe8acbea..761caede5a51 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*set_suspend_mode)(u32 mode); int (*request_node)(const u32 node, const u32 capabilities, const u32 qos, @@ -336,6 +335,7 @@ int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); int zynqmp_pm_init_finalize(void); +int zynqmp_pm_set_suspend_mode(u32 mode); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -428,6 +428,10 @@ static inline int zynqmp_pm_init_finalize(void) { return -ENODEV; } +static inline int zynqmp_pm_set_suspend_mode(u32 mode) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From bf8b27ed2324b5108439593dcfb9ab264a745ee7 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:58 -0700 Subject: firmware: xilinx: Remove eemi ops for request_node Use direct function call instead of using eemi ops for request_node. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-17-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 761caede5a51..fb7e5c91c816 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,10 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*request_node)(const u32 node, - const u32 capabilities, - const u32 qos, - const enum zynqmp_pm_request_ack ack); int (*release_node)(const u32 node); int (*set_requirement)(const u32 node, const u32 capabilities, @@ -336,6 +332,8 @@ int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); int zynqmp_pm_init_finalize(void); int zynqmp_pm_set_suspend_mode(u32 mode); +int zynqmp_pm_request_node(const u32 node, const u32 capabilities, + const u32 qos, const enum zynqmp_pm_request_ack ack); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -432,6 +430,12 @@ static inline int zynqmp_pm_set_suspend_mode(u32 mode) { return -ENODEV; } +static inline int zynqmp_pm_request_node(const u32 node, const u32 capabilities, + const u32 qos, + const enum zynqmp_pm_request_ack ack) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 07fb1a4619fcb35f79d0adc13c8678f7726337ef Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:57:59 -0700 Subject: firmware: xilinx: Remove eemi ops for release_node Use direct function call instead of using eemi ops for release_node. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-18-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index fb7e5c91c816..bfa8cca64455 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*release_node)(const u32 node); int (*set_requirement)(const u32 node, const u32 capabilities, const u32 qos, @@ -334,6 +333,7 @@ int zynqmp_pm_init_finalize(void); int zynqmp_pm_set_suspend_mode(u32 mode); int zynqmp_pm_request_node(const u32 node, const u32 capabilities, const u32 qos, const enum zynqmp_pm_request_ack ack); +int zynqmp_pm_release_node(const u32 node); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -436,6 +436,10 @@ static inline int zynqmp_pm_request_node(const u32 node, const u32 capabilities, { return -ENODEV; } +static inline int zynqmp_pm_release_node(const u32 node) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From cbbbda71fe37fe70e610d5ec3977fc6a096280ed Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:00 -0700 Subject: firmware: xilinx: Remove eemi ops for set_requirement Use direct function call instead of using eemi ops for set_requirement. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-19-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index bfa8cca64455..5927f6f49980 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,10 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*set_requirement)(const u32 node, - const u32 capabilities, - const u32 qos, - const enum zynqmp_pm_request_ack ack); int (*aes)(const u64 address, u32 *out); }; @@ -334,6 +330,9 @@ int zynqmp_pm_set_suspend_mode(u32 mode); int zynqmp_pm_request_node(const u32 node, const u32 capabilities, const u32 qos, const enum zynqmp_pm_request_ack ack); int zynqmp_pm_release_node(const u32 node); +int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, + const u32 qos, + const enum zynqmp_pm_request_ack ack); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -440,6 +439,13 @@ static inline int zynqmp_pm_release_node(const u32 node) { return -ENODEV; } +static inline int zynqmp_pm_set_requirement(const u32 node, + const u32 capabilities, + const u32 qos, + const enum zynqmp_pm_request_ack ack) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From bc86f9c546160afce631fae223c3772d9375ee25 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:01 -0700 Subject: firmware: xilinx: Remove eemi ops for aes engine Use direct function call for aes engine instead of using eemi ops. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-20-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 5927f6f49980..11d7aef2cc3c 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -296,7 +296,6 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*fpga_load)(const u64 address, const u32 size, const u32 flags); int (*fpga_get_status)(u32 *value); - int (*aes)(const u64 address, u32 *out); }; int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, @@ -333,6 +332,7 @@ int zynqmp_pm_release_node(const u32 node); int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, const u32 qos, const enum zynqmp_pm_request_ack ack); +int zynqmp_pm_aes_engine(const u64 address, u32 *out); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -446,6 +446,10 @@ static inline int zynqmp_pm_set_requirement(const u32 node, { return -ENODEV; } +static inline int zynqmp_pm_aes_engine(const u64 address, u32 *out) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 4db8180ffe7c07bc4a602c82d6d9c1c04751583d Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:02 -0700 Subject: firmware: xilinx: Remove eemi ops for fpga related APIs Use direct function call instead of using eemi ops for fpga related APIs. Also remove eemi ops structure. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-21-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 11d7aef2cc3c..44ffb4f0d8be 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -293,16 +293,11 @@ struct zynqmp_pm_query_data { u32 arg3; }; -struct zynqmp_eemi_ops { - int (*fpga_load)(const u64 address, const u32 size, const u32 flags); - int (*fpga_get_status)(u32 *value); -}; int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 *ret_payload); #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE) -const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); int zynqmp_pm_get_api_version(u32 *version); int zynqmp_pm_get_chipid(u32 *idcode, u32 *version); int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out); @@ -333,6 +328,8 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, const u32 qos, const enum zynqmp_pm_request_ack ack); int zynqmp_pm_aes_engine(const u64 address, u32 *out); +int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags); +int zynqmp_pm_fpga_get_status(u32 *value); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -450,6 +447,15 @@ static inline int zynqmp_pm_aes_engine(const u64 address, u32 *out) { return -ENODEV; } +static inline int zynqmp_pm_fpga_load(const u64 address, const u32 size, + const u32 flags) +{ + return -ENODEV; +} +static inline int zynqmp_pm_fpga_get_status(u32 *value) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 4f680b72ea07a3e161ce1167a97ee09b1369f7de Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:03 -0700 Subject: firmware: xilinx: Add APIs to read/write GGS/PGGS registers Add APIs to read/write PGGS and GGS registers. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-22-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 44ffb4f0d8be..e23251d93176 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -107,6 +107,10 @@ enum pm_ioctl_id { IOCTL_GET_PLL_FRAC_MODE, IOCTL_SET_PLL_FRAC_DATA, IOCTL_GET_PLL_FRAC_DATA, + IOCTL_WRITE_GGS = 12, + IOCTL_READ_GGS = 13, + IOCTL_WRITE_PGGS = 14, + IOCTL_READ_PGGS = 15, }; enum pm_query_id { @@ -330,6 +334,10 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, int zynqmp_pm_aes_engine(const u64 address, u32 *out); int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_get_status(u32 *value); +int zynqmp_pm_write_ggs(u32 index, u32 value); +int zynqmp_pm_read_ggs(u32 index, u32 *value); +int zynqmp_pm_write_pggs(u32 index, u32 value); +int zynqmp_pm_read_pggs(u32 index, u32 *value); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -456,6 +464,22 @@ static inline int zynqmp_pm_fpga_get_status(u32 *value) { return -ENODEV; } +static inline int zynqmp_pm_write_ggs(u32 index, u32 value) +{ + return -ENODEV; +} +static inline int zynqmp_pm_read_ggs(u32 index, u32 *value) +{ + return -ENODEV; +} +static inline int zynqmp_pm_write_pggs(u32 index, u32 value) +{ + return -ENODEV; +} +static inline int zynqmp_pm_read_pggs(u32 index, u32 *value) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From ae5c961da6483b413dcb36d8bf6a881ffd2fb33f Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:04 -0700 Subject: firmware: xilinx: Add sysfs interface Add firmware-ggs sysfs interface which provides read/write interface to global storage registers. Signed-off-by: Rajan Vaja Signed-off-by: Michal Simek Signed-off-by: Tejas Patel Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-23-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index e23251d93176..c1356e93dcb2 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -42,6 +42,8 @@ #define ZYNQMP_PM_MAX_QOS 100U +#define GSS_NUM_REGS (4) + /* Node capabilities */ #define ZYNQMP_PM_CAPABILITY_ACCESS 0x1U #define ZYNQMP_PM_CAPABILITY_CONTEXT 0x2U -- cgit v1.2.3 From fdd2ed88ca971376669bce145f1a1bcf028d775e Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:05 -0700 Subject: firmware: xilinx: Add system shutdown API interface Add system shutdown API interface which asks firmware to perform system shutdown/restart. Signed-off-by: Rajan Vaja Signed-off-by: Michal Simek Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-24-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index c1356e93dcb2..2254c7cc3362 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -64,6 +64,7 @@ enum pm_api_id { PM_GET_API_VERSION = 1, + PM_SYSTEM_SHUTDOWN = 12, PM_REQUEST_NODE = 13, PM_RELEASE_NODE, PM_SET_REQUIREMENT, @@ -340,6 +341,7 @@ int zynqmp_pm_write_ggs(u32 index, u32 value); int zynqmp_pm_read_ggs(u32 index, u32 *value); int zynqmp_pm_write_pggs(u32 index, u32 value); int zynqmp_pm_read_pggs(u32 index, u32 *value); +int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -482,6 +484,10 @@ static inline int zynqmp_pm_read_pggs(u32 index, u32 *value) { return -ENODEV; } +static inline int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From b3ae24c44848c6403fb2333d7cbe494565058352 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:06 -0700 Subject: firmware: xilinx: Add sysfs to set shutdown scope The Linux shutdown functionality implemented via PSCI system_off does not include an option to set a scope, i.e. which parts of the system to shut down. This patch creates sysfs that allows to set the shutdown scope for the next shutdown request. When the next shutdown is performed, the platform specific portion of PSCI-system_off can use the chosen shutdown scope. Signed-off-by: Rajan Vaja Signed-off-by: Stefan Krsmanovic Signed-off-by: Michal Simek Signed-off-by: Tejas Patel Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-25-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 2254c7cc3362..c297333677d4 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -286,6 +286,18 @@ enum dll_reset_type { PM_DLL_RESET_PULSE, }; +enum zynqmp_pm_shutdown_type { + ZYNQMP_PM_SHUTDOWN_TYPE_SHUTDOWN, + ZYNQMP_PM_SHUTDOWN_TYPE_RESET, + ZYNQMP_PM_SHUTDOWN_TYPE_SETSCOPE_ONLY, +}; + +enum zynqmp_pm_shutdown_subtype { + ZYNQMP_PM_SHUTDOWN_SUBTYPE_SUBSYSTEM, + ZYNQMP_PM_SHUTDOWN_SUBTYPE_PS_ONLY, + ZYNQMP_PM_SHUTDOWN_SUBTYPE_SYSTEM, +}; + /** * struct zynqmp_pm_query_data - PM query data * @qid: query ID -- cgit v1.2.3 From a2cc220a9a9227b2c5c9b39f57340bce64f040fd Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Fri, 24 Apr 2020 13:58:07 -0700 Subject: firmware: xilinx: Add sysfs and API to set boot health status Add sysfs interface to set boot health status from user space. Add API used by this interface to communicate with firmware. If PMUFW is compiled with CHECK_HEALTHY_BOOT, it will check the healthy bit on FPD WDT expiration. If healthy bit is set by a user application running in Linux, PMUFW will do APU only restart. If healthy bit is not set during FPD WDT expiration, PMUFW will do system restart. Signed-off-by: Rajan Vaja Signed-off-by: Michal Simek Signed-off-by: Tejas Patel Signed-off-by: Jolly Shah Link: https://lore.kernel.org/r/1587761887-4279-26-git-send-email-jolly.shah@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index c297333677d4..5968df82b991 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -114,6 +114,8 @@ enum pm_ioctl_id { IOCTL_READ_GGS = 13, IOCTL_WRITE_PGGS = 14, IOCTL_READ_PGGS = 15, + /* Set healthy bit value */ + IOCTL_SET_BOOT_HEALTH_STATUS = 17, }; enum pm_query_id { @@ -354,6 +356,7 @@ int zynqmp_pm_read_ggs(u32 index, u32 *value); int zynqmp_pm_write_pggs(u32 index, u32 value); int zynqmp_pm_read_pggs(u32 index, u32 *value); int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype); +int zynqmp_pm_set_boot_health_status(u32 value); #else static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) { @@ -500,6 +503,10 @@ static inline int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype) { return -ENODEV; } +static inline int zynqmp_pm_set_boot_health_status(u32 value) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From d65dbedfd298344747033f17c1efd2afc8082bc7 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Fri, 24 Apr 2020 12:45:02 -0700 Subject: net/mlx5: Add support for COPY steering action Add COPY type to modify_header action. IPsec feature is the first feature that needs COPY steering action. Signed-off-by: Huy Nguyen Signed-off-by: Raed Salem Signed-off-by: Saeed Mahameed Acked-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6fa24918eade..3ad2c51ccde9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5670,9 +5670,9 @@ struct mlx5_ifc_copy_action_in_bits { u8 reserved_at_38[0x8]; }; -union mlx5_ifc_set_action_in_add_action_in_auto_bits { - struct mlx5_ifc_set_action_in_bits set_action_in; - struct mlx5_ifc_add_action_in_bits add_action_in; +union mlx5_ifc_set_add_copy_action_in_auto_bits { + struct mlx5_ifc_set_action_in_bits set_action_in; + struct mlx5_ifc_add_action_in_bits add_action_in; struct mlx5_ifc_copy_action_in_bits copy_action_in; u8 reserved_at_0[0x40]; }; @@ -5746,7 +5746,7 @@ struct mlx5_ifc_alloc_modify_header_context_in_bits { u8 reserved_at_68[0x10]; u8 num_of_actions[0x8]; - union mlx5_ifc_set_action_in_add_action_in_auto_bits actions[0]; + union mlx5_ifc_set_add_copy_action_in_auto_bits actions[0]; }; struct mlx5_ifc_dealloc_modify_header_context_out_bits { -- cgit v1.2.3 From 2b58f6d9df50f534fe465113b69de60a2ef0e74a Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Fri, 24 Apr 2020 12:45:03 -0700 Subject: net/mlx5: Introduce IPsec Connect-X offload hardware bits and structures Add IPsec offload related IFC structs, layouts and enumerations. Signed-off-by: Raed Salem Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 4 +++ include/linux/mlx5/mlx5_ifc.h | 78 +++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 79 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 2b90097a6cf9..7b57877e501e 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1107,6 +1107,7 @@ enum mlx5_cap_type { MLX5_CAP_TLS, MLX5_CAP_VDPA_EMULATION = 0x13, MLX5_CAP_DEV_EVENT = 0x14, + MLX5_CAP_IPSEC, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1324,6 +1325,9 @@ enum mlx5_qcam_feature_groups { MLX5_GET64(device_virtio_emulation_cap, \ (mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap) +#define MLX5_CAP_IPSEC(mdev, cap)\ + MLX5_GET(ipsec_cap, (mdev)->caps.hca_cur[MLX5_CAP_IPSEC], cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3ad2c51ccde9..cf971d341189 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -886,7 +886,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 tunnel_stateless_vxlan_gpe[0x1]; u8 tunnel_stateless_ipv4_over_vxlan[0x1]; u8 tunnel_stateless_ip_over_ip[0x1]; - u8 reserved_at_2a[0x6]; + u8 insert_trailer[0x1]; + u8 reserved_at_2b[0x5]; u8 max_vxlan_udp_ports[0x8]; u8 reserved_at_38[0x6]; u8 max_geneve_opt_len[0x1]; @@ -1100,6 +1101,23 @@ struct mlx5_ifc_tls_cap_bits { u8 reserved_at_20[0x7e0]; }; +struct mlx5_ifc_ipsec_cap_bits { + u8 ipsec_full_offload[0x1]; + u8 ipsec_crypto_offload[0x1]; + u8 ipsec_esn[0x1]; + u8 ipsec_crypto_esp_aes_gcm_256_encrypt[0x1]; + u8 ipsec_crypto_esp_aes_gcm_128_encrypt[0x1]; + u8 ipsec_crypto_esp_aes_gcm_256_decrypt[0x1]; + u8 ipsec_crypto_esp_aes_gcm_128_decrypt[0x1]; + u8 reserved_at_7[0x4]; + u8 log_max_ipsec_offload[0x5]; + u8 reserved_at_10[0x10]; + + u8 min_log_ipsec_full_replay_window[0x8]; + u8 max_log_ipsec_full_replay_window[0x8]; + u8 reserved_at_30[0x7d0]; +}; + enum { MLX5_WQ_TYPE_LINKED_LIST = 0x0, MLX5_WQ_TYPE_CYCLIC = 0x1, @@ -1464,7 +1482,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_460[0x3]; u8 log_max_uctx[0x5]; - u8 reserved_at_468[0x3]; + u8 reserved_at_468[0x2]; + u8 ipsec_offload[0x1]; u8 log_max_umem[0x5]; u8 max_num_eqs[0x10]; @@ -4143,7 +4162,8 @@ enum { MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION = 0x0, MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_TAG = 0x1, MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST = 0x2, - MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS = 0x3 + MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS = 0x3, + MLX5_SET_FTE_MODIFY_ENABLE_MASK_IPSEC_OBJ_ID = 0x4 }; struct mlx5_ifc_set_fte_out_bits { @@ -10468,10 +10488,62 @@ struct mlx5_ifc_affiliated_event_header_bits { enum { MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT(0xc), + MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT(0x13), }; enum { MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc, + MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13, +}; + +enum { + MLX5_IPSEC_OBJECT_ICV_LEN_16B, + MLX5_IPSEC_OBJECT_ICV_LEN_12B, + MLX5_IPSEC_OBJECT_ICV_LEN_8B, +}; + +struct mlx5_ifc_ipsec_obj_bits { + u8 modify_field_select[0x40]; + u8 full_offload[0x1]; + u8 reserved_at_41[0x1]; + u8 esn_en[0x1]; + u8 esn_overlap[0x1]; + u8 reserved_at_44[0x2]; + u8 icv_length[0x2]; + u8 reserved_at_48[0x4]; + u8 aso_return_reg[0x4]; + u8 reserved_at_50[0x10]; + + u8 esn_msb[0x20]; + + u8 reserved_at_80[0x8]; + u8 dekn[0x18]; + + u8 salt[0x20]; + + u8 implicit_iv[0x40]; + + u8 reserved_at_100[0x700]; +}; + +struct mlx5_ifc_create_ipsec_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_ipsec_obj_bits ipsec_object; +}; + +enum { + MLX5_MODIFY_IPSEC_BITMASK_ESN_OVERLAP = BIT(0), + MLX5_MODIFY_IPSEC_BITMASK_ESN_MSB = BIT(1), +}; + +struct mlx5_ifc_query_ipsec_obj_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; + struct mlx5_ifc_ipsec_obj_bits ipsec_object; +}; + +struct mlx5_ifc_modify_ipsec_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_ipsec_obj_bits ipsec_object; }; struct mlx5_ifc_encryption_key_obj_bits { -- cgit v1.2.3 From dff8e2d15283dd92582ddeec25ca86e4cf2618c7 Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Fri, 24 Apr 2020 12:45:04 -0700 Subject: net/mlx5: Use aligned variable while allocating ICM memory The alignment value is part of the input structure, so use it and spare extra memory allocation when is not needed. Now, using the new ability when allocating icm for Direct-Rule insertion. Signed-off-by: Ariel Levkovich Signed-off-by: Erez Shitrit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index b60e5ab7906b..b46537a81703 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1080,7 +1080,8 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, - u64 length, u16 uid, phys_addr_t *addr, u32 *obj_id); + u64 length, u32 log_alignment, u16 uid, + phys_addr_t *addr, u32 *obj_id); int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, u64 length, u16 uid, phys_addr_t addr, u32 obj_id); -- cgit v1.2.3 From 244faedfd4d8e8c8e9f3c628d29bb74196b49743 Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Fri, 24 Apr 2020 12:45:05 -0700 Subject: net/mlx5: Refactor imm_inval_pkey field in cqe struct The imm_inval_pkey field can hold four different types of data, depends on the usage, the data could be one of the below: - Immediate field of the received message - Invalidate rkey - Pkey of the packet - Flow table metadata Current implementation doesn't reflect the intended usage of the field at usage time. Reflect the different types by replace this field with a union, modify code where this field is used to reflect its intended usage. Signed-off-by: Raed Salem Reviewed-by: Huy Nguyen Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 7b57877e501e..746e17473d72 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -767,7 +767,12 @@ struct mlx5_cqe64 { u8 l4_l3_hdr_type; __be16 vlan_info; __be32 srqn; /* [31:24]: lro_num_seg, [23:0]: srqn */ - __be32 imm_inval_pkey; + union { + __be32 immediate; + __be32 inval_rkey; + __be32 pkey; + __be32 ft_metadata; + }; u8 rsvd40[4]; __be32 byte_cnt; __be32 timestamp_h; -- cgit v1.2.3 From 06939536263d684073a30543930622eede633af1 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Fri, 24 Apr 2020 12:45:06 -0700 Subject: net/mlx5: Add structure layout and defines for MFRL register Add needed structure layouts and defines for MFRL (Management Firmware Reset Level) register. This structure will be used for the firmware upgrade and reset flow in the downstream patches. Signed-off-by: Moshe Shemesh Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index b46537a81703..d82dbbab8179 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -130,6 +130,7 @@ enum { MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, MLX5_REG_MCIA = 0x9014, + MLX5_REG_MFRL = 0x9028, MLX5_REG_MLCR = 0x902b, MLX5_REG_MTRC_CAP = 0x9040, MLX5_REG_MTRC_CONF = 0x9041, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cf971d341189..9e6a3cec1e32 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9703,6 +9703,29 @@ struct mlx5_ifc_mcda_reg_bits { u8 data[0][0x20]; }; +enum { + MLX5_MFRL_REG_RESET_TYPE_FULL_CHIP = BIT(0), + MLX5_MFRL_REG_RESET_TYPE_NET_PORT_ALIVE = BIT(1), +}; + +enum { + MLX5_MFRL_REG_RESET_LEVEL0 = BIT(0), + MLX5_MFRL_REG_RESET_LEVEL3 = BIT(3), + MLX5_MFRL_REG_RESET_LEVEL6 = BIT(6), +}; + +struct mlx5_ifc_mfrl_reg_bits { + u8 reserved_at_0[0x20]; + + u8 reserved_at_20[0x2]; + u8 pci_sync_for_fw_update_start[0x1]; + u8 pci_sync_for_fw_update_resp[0x2]; + u8 rst_type_sel[0x3]; + u8 reserved_at_28[0x8]; + u8 reset_type[0x8]; + u8 reset_level[0x8]; +}; + struct mlx5_ifc_mirc_reg_bits { u8 reserved_at_0[0x18]; u8 status_code[0x8]; @@ -9766,6 +9789,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mcc_reg_bits mcc_reg; struct mlx5_ifc_mcda_reg_bits mcda_reg; struct mlx5_ifc_mirc_reg_bits mirc_reg; + struct mlx5_ifc_mfrl_reg_bits mfrl_reg; u8 reserved_at_0[0x60e0]; }; -- cgit v1.2.3 From 3df0107784ceb388039b1fe510a8c7b8816de8f0 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Fri, 24 Apr 2020 12:45:07 -0700 Subject: net/mlx5: Add structure and defines for pci sync for fw update event Add needed structure layouts and defines for pci sync for fw update event. The downstream patches will include event handlers for this event type. Signed-off-by: Moshe Shemesh Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 15 +++++++++++++++ include/linux/mlx5/mlx5_ifc.h | 4 +++- 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 746e17473d72..de93f0b67973 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -364,6 +364,7 @@ enum { enum { MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1, MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT = 0x5, + MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT = 0x8, }; enum { @@ -689,6 +690,19 @@ struct mlx5_eqe_temp_warning { __be64 sensor_warning_lsb; } __packed; +#define SYNC_RST_STATE_MASK 0xf + +enum sync_rst_state_type { + MLX5_SYNC_RST_STATE_RESET_REQUEST = 0x0, + MLX5_SYNC_RST_STATE_RESET_NOW = 0x1, + MLX5_SYNC_RST_STATE_RESET_ABORT = 0x2, +}; + +struct mlx5_eqe_sync_fw_update { + u8 reserved_at_0[3]; + u8 sync_rst_state; +}; + union ev_data { __be32 raw[7]; struct mlx5_eqe_cmd cmd; @@ -707,6 +721,7 @@ union ev_data { struct mlx5_eqe_dct dct; struct mlx5_eqe_temp_warning temp_warning; struct mlx5_eqe_xrq_err xrq_err; + struct mlx5_eqe_sync_fw_update sync_fw_update; } __packed; struct mlx5_eqe { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 9e6a3cec1e32..058ded202b65 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1317,7 +1317,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 wol_p[0x1]; u8 stat_rate_support[0x10]; - u8 reserved_at_1f0[0xc]; + u8 reserved_at_1f0[0x1]; + u8 pci_sync_for_fw_update_event[0x1]; + u8 reserved_at_1f2[0xa]; u8 cqe_version[0x4]; u8 compact_address_vector[0x1]; -- cgit v1.2.3 From ee5cdf7a5e8945372c7496e98de2b364e095b60b Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Fri, 24 Apr 2020 12:45:08 -0700 Subject: net/mlx5: Introduce TLS RX offload hardware bits Add TLS RX offload related IFC hardware fields and enumerations. Signed-off-by: Tariq Toukan Reviewed-by: Maxim Mikityanskiy Reviewed-by: Boris Pismenny Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 18 ++++++++++++++++-- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index de93f0b67973..1bc27aca648b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -450,10 +450,12 @@ enum { enum { MLX5_OPC_MOD_TLS_TIS_STATIC_PARAMS = 0x1, + MLX5_OPC_MOD_TLS_TIR_STATIC_PARAMS = 0x2, }; enum { MLX5_OPC_MOD_TLS_TIS_PROGRESS_PARAMS = 0x1, + MLX5_OPC_MOD_TLS_TIR_PROGRESS_PARAMS = 0x2, }; enum { @@ -764,7 +766,7 @@ struct mlx5_err_cqe { }; struct mlx5_cqe64 { - u8 outer_l3_tunneled; + u8 tls_outer_l3_tunneled; u8 rsvd0; __be16 wqe_id; u8 lro_tcppsh_abort_dupack; @@ -854,7 +856,12 @@ static inline u8 get_cqe_l3_hdr_type(struct mlx5_cqe64 *cqe) static inline bool cqe_is_tunneled(struct mlx5_cqe64 *cqe) { - return cqe->outer_l3_tunneled & 0x1; + return cqe->tls_outer_l3_tunneled & 0x1; +} + +static inline u8 get_cqe_tls_offload(struct mlx5_cqe64 *cqe) +{ + return (cqe->tls_outer_l3_tunneled >> 3) & 0x3; } static inline bool cqe_has_vlan(struct mlx5_cqe64 *cqe) @@ -942,6 +949,13 @@ enum { CQE_L4_OK = 1 << 2, }; +enum { + CQE_TLS_OFFLOAD_NOT_DECRYPTED = 0x0, + CQE_TLS_OFFLOAD_DECRYPTED = 0x1, + CQE_TLS_OFFLOAD_RESYNC = 0x2, + CQE_TLS_OFFLOAD_ERROR = 0x3, +}; + struct mlx5_sig_err_cqe { u8 rsvd0[16]; __be32 expected_trans_sig; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 058ded202b65..6a6bb5dc7916 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1491,7 +1491,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_480[0x1]; u8 tls_tx[0x1]; - u8 reserved_at_482[0x1]; + u8 tls_rx[0x1]; u8 log_max_l2_table[0x5]; u8 reserved_at_488[0x8]; u8 log_uar_page_sz[0x10]; @@ -3136,7 +3136,8 @@ struct mlx5_ifc_tirc_bits { u8 reserved_at_0[0x20]; u8 disp_type[0x4]; - u8 reserved_at_24[0x1c]; + u8 tls_en[0x1]; + u8 reserved_at_25[0x1b]; u8 reserved_at_40[0x40]; -- cgit v1.2.3 From 0e1533bb9cce2c6b2aecdfddfcc0de3beeaddc7b Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Fri, 24 Apr 2020 12:45:09 -0700 Subject: net/mlx5: Add release all pages capability bit Add a bit in HCA capabilities layout to indicate if release all pages is supported. Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6a6bb5dc7916..fb243848132d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1244,7 +1244,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_130[0xa]; u8 log_max_ra_res_dc[0x6]; - u8 reserved_at_140[0x9]; + u8 reserved_at_140[0x6]; + u8 release_all_pages[0x1]; + u8 reserved_at_147[0x2]; u8 roce_accl[0x1]; u8 log_max_ra_req_qp[0x6]; u8 reserved_at_150[0xa]; -- cgit v1.2.3 From 2dc8b5246d2c94f732c02e7a688d8a9c0c65361f Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Fri, 24 Apr 2020 12:45:10 -0700 Subject: net/mlx5: TX WQE Add trailer insertion field Add new TX WQE field for Connect-X6DX trailer insertion support, when set, the HW adds a trailer to the packet, the WQE trailer association flags are used to set to HW the header which the trailer belongs. Signed-off-by: Raed Salem Signed-off-by: Saeed Mahameed --- include/linux/mlx5/qp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index ef127a156a62..f23eb18526fe 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -229,6 +229,11 @@ enum { enum { MLX5_ETH_WQE_SVLAN = 1 << 0, + MLX5_ETH_WQE_TRAILER_HDR_OUTER_IP_ASSOC = 1 << 26, + MLX5_ETH_WQE_TRAILER_HDR_OUTER_L4_ASSOC = 1 << 27, + MLX5_ETH_WQE_TRAILER_HDR_INNER_IP_ASSOC = 3 << 26, + MLX5_ETH_WQE_TRAILER_HDR_INNER_L4_ASSOC = 1 << 28, + MLX5_ETH_WQE_INSERT_TRAILER = 1 << 30, MLX5_ETH_WQE_INSERT_VLAN = 1 << 15, }; @@ -257,6 +262,7 @@ struct mlx5_wqe_eth_seg { __be16 type; __be16 vlan_tci; } insert; + __be32 trailer; }; }; -- cgit v1.2.3 From 35fc0e3b0bd5be3b059e53ae90c4536ee4922330 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 24 Apr 2020 11:19:10 -0500 Subject: rculist: Add hlists_swap_heads_rcu Using the struct pid to refer to two tasks in de_thread was a clever idea and ultimately too clever, as it has lead to proc_flush_task being called inconsistently. To support rectifying this add hlists_swap_heads_rcu. An hlist primitive that just swaps the hlist heads of two lists. This is exactly what is needed for exchanging the pids of two tasks. Only consideration of correctness of the code has been given, as the caller is expected to be a slowpath. Link: https://lore.kernel.org/lkml/87mu6vajnq.fsf_-_@x220.int.ebiederm.org/ Acked-by: Linus Torvalds Acked-by: Oleg Nesterov Signed-off-by: "Eric W. Biederman" --- include/linux/rculist.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 8214cdc715f2..67867e0d4cec 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -506,6 +506,27 @@ static inline void hlist_replace_rcu(struct hlist_node *old, WRITE_ONCE(old->pprev, LIST_POISON2); } +/** + * hlists_swap_heads_rcu - swap the lists the hlist heads point to + * @left: The hlist head on the left + * @right: The hlist head on the right + * + * The lists start out as [@left ][node1 ... ] and + [@right ][node2 ... ] + * The lists end up as [@left ][node2 ... ] + * [@right ][node1 ... ] + */ +static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right) +{ + struct hlist_node *node1 = left->first; + struct hlist_node *node2 = right->first; + + rcu_assign_pointer(left->first, node2); + rcu_assign_pointer(right->first, node1); + WRITE_ONCE(node2->pprev, &left->first); + WRITE_ONCE(node1->pprev, &right->first); +} + /* * return the first or the next element in an RCU protected hlist */ -- cgit v1.2.3 From 6b03d1304a32dc8450c7516000a0fe07bef7c446 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 19 Apr 2020 06:35:02 -0500 Subject: proc: Ensure we see the exit of each process tid exactly once When the thread group leader changes during exec and the old leaders thread is reaped proc_flush_pid will flush the dentries for the entire process because the leader still has it's original pid. Fix this by exchanging the pids in an rcu safe manner, and wrapping the code to do that up in a helper exchange_tids. When I removed switch_exec_pids and introduced this behavior in d73d65293e3e ("[PATCH] pidhash: kill switch_exec_pids") there really was nothing that cared as flushing happened with the cached dentry and de_thread flushed both of them on exec. This lack of fully exchanging pids became a problem a few months later when I introduced 48e6484d4902 ("[PATCH] proc: Rewrite the proc dentry flush on exit optimization"). Which overlooked the de_thread case was no longer swapping pids, and I was looking up proc dentries by task->pid. The current behavior isn't properly a bug as everything in proc will continue to work correctly just a little bit less efficiently. Fix this just so there are no little surprise corner cases waiting to bite people. -- Oleg points out this could be an issue in next_tgid in proc where has_group_leader_pid is called, and reording some of the assignments should fix that. -- Oleg points out this will break the 10 year old hack in __exit_signal.c > /* > * This can only happen if the caller is de_thread(). > * FIXME: this is the temporary hack, we should teach > * posix-cpu-timers to handle this case correctly. > */ > if (unlikely(has_group_leader_pid(tsk))) > posix_cpu_timers_exit_group(tsk); The code in next_tgid has been changed to use PIDTYPE_TGID, and the posix cpu timers code has been fixed so it does not need the 10 year old hack, so this should be safe to merge now. Link: https://lore.kernel.org/lkml/87h7x3ajll.fsf_-_@x220.int.ebiederm.org/ Acked-by: Linus Torvalds Acked-by: Oleg Nesterov Fixes: 48e6484d4902 ("[PATCH] proc: Rewrite the proc dentry flush on exit optimization"). Signed-off-by: Eric W. Biederman --- include/linux/pid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index cc896f0fc4e3..2159ffca63fc 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -102,6 +102,7 @@ extern void attach_pid(struct task_struct *task, enum pid_type); extern void detach_pid(struct task_struct *task, enum pid_type); extern void change_pid(struct task_struct *task, enum pid_type, struct pid *pid); +extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); -- cgit v1.2.3 From c4dad0aab3fca0c1f0baa4cc84b6ec91b7ebf426 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 22 Apr 2020 17:39:28 -0400 Subject: audit: tidy and extend netfilter_cfg x_tables NETFILTER_CFG record generation was inconsistent for x_tables and ebtables configuration changes. The call was needlessly messy and there were supporting records missing at times while they were produced when not requested. Simplify the logging call into a new audit_log_nfcfg call. Honour the audit_enabled setting while more consistently recording information including supporting records by tidying up dummy checks. Add an op= field that indicates the operation being performed (register or replace). Here is the enhanced sample record: type=NETFILTER_CFG msg=audit(1580905834.919:82970): table=filter family=2 entries=83 op=replace Generate audit NETFILTER_CFG records on ebtables table registration. Previously this was being done for x_tables registration and replacement operations and ebtables table replacement only. See: https://github.com/linux-audit/audit-kernel/issues/25 See: https://github.com/linux-audit/audit-kernel/issues/35 See: https://github.com/linux-audit/audit-kernel/issues/43 Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index f9ceae57ca8d..5c7f07a9776d 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -94,6 +94,11 @@ struct audit_ntp_data { struct audit_ntp_data {}; #endif +enum audit_nfcfgop { + AUDIT_XT_OP_REGISTER, + AUDIT_XT_OP_REPLACE, +}; + extern int is_audit_feature_set(int which); extern int __init audit_register_class(int class, unsigned *list); @@ -379,6 +384,8 @@ extern void __audit_log_kern_module(char *name); extern void __audit_fanotify(unsigned int response); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); +extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, + enum audit_nfcfgop op); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { @@ -514,6 +521,14 @@ static inline void audit_ntp_log(const struct audit_ntp_data *ad) __audit_ntp_log(ad); } +static inline void audit_log_nfcfg(const char *name, u8 af, + unsigned int nentries, + enum audit_nfcfgop op) +{ + if (audit_enabled) + __audit_log_nfcfg(name, af, nentries, op); +} + extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ @@ -646,6 +661,12 @@ static inline void audit_ntp_log(const struct audit_ntp_data *ad) static inline void audit_ptrace(struct task_struct *t) { } + +static inline void audit_log_nfcfg(const char *name, u8 af, + unsigned int nentries, + enum audit_nfcfgop op) +{ } + #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ -- cgit v1.2.3 From bbd40fc4816d5329a89397206ece9f1763787a88 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 26 Apr 2020 07:59:55 -0500 Subject: signal: Remove has_group_leader_pid After the introduction of exchange_tids has_group_leader_pid is equivalent to thread_group_leader. After the last couple of cleanups has_group_leader_pid has no more callers. So remove the now unused and redundant has_group_leader_pid. Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3e5b090c16d4..0ee5e696c5d8 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -654,17 +654,6 @@ static inline bool thread_group_leader(struct task_struct *p) return p->exit_signal >= 0; } -/* Do to the insanities of de_thread it is possible for a process - * to have the pid of the thread group leader without actually being - * the thread group leader. For iteration through the pids in proc - * all we care about is that we have a task with the appropriate - * pid, we don't actually care if we have the right task. - */ -static inline bool has_group_leader_pid(struct task_struct *p) -{ - return task_pid(p) == task_tgid(p); -} - static inline bool same_thread_group(struct task_struct *p1, struct task_struct *p2) { -- cgit v1.2.3 From a45d88530b2552ad5ea0da18861600b4ecc9d0c7 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 22 Apr 2020 17:39:29 -0400 Subject: netfilter: add audit table unregister actions Audit the action of unregistering ebtables and x_tables. See: https://github.com/linux-audit/audit-kernel/issues/44 Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 5c7f07a9776d..1a2351508211 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -97,6 +97,7 @@ struct audit_ntp_data {}; enum audit_nfcfgop { AUDIT_XT_OP_REGISTER, AUDIT_XT_OP_REPLACE, + AUDIT_XT_OP_UNREGISTER, }; extern int is_audit_feature_set(int which); -- cgit v1.2.3 From f9d041271cf44ca02eed0cc82e1a6d8c814c53ed Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Apr 2020 17:16:05 -0700 Subject: bpf: Refactor bpf_link update handling Make bpf_link update support more generic by making it into another bpf_link_ops methods. This allows generic syscall handling code to be agnostic to various conditionally compiled features (e.g., the case of CONFIG_CGROUP_BPF). This also allows to keep link type-specific code to remain static within respective code base. Refactor existing bpf_cgroup_link code and take advantage of this. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200429001614.1544-2-andriin@fb.com --- include/linux/bpf-cgroup.h | 12 ------------ include/linux/bpf.h | 3 ++- 2 files changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 0b41fd5fc96b..a9cb9a5bf8e9 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -100,8 +100,6 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_cgroup_link *link, enum bpf_attach_type type); -int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link, - struct bpf_prog *new_prog); int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr); @@ -112,8 +110,6 @@ int cgroup_bpf_attach(struct cgroup *cgrp, u32 flags); int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type); -int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *old_prog, - struct bpf_prog *new_prog); int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr); @@ -353,7 +349,6 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, #else struct bpf_prog; -struct bpf_link; struct cgroup_bpf {}; static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } static inline void cgroup_bpf_offline(struct cgroup *cgrp) {} @@ -377,13 +372,6 @@ static inline int cgroup_bpf_link_attach(const union bpf_attr *attr, return -EINVAL; } -static inline int cgroup_bpf_replace(struct bpf_link *link, - struct bpf_prog *old_prog, - struct bpf_prog *new_prog) -{ - return -EINVAL; -} - static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 10960cfabea4..81c8620cb4c4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1093,7 +1093,8 @@ struct bpf_link { struct bpf_link_ops { void (*release)(struct bpf_link *link); void (*dealloc)(struct bpf_link *link); - + int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, + struct bpf_prog *old_prog); }; void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, -- cgit v1.2.3 From a3b80e1078943dc12553166fb08e258463dec013 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Apr 2020 17:16:06 -0700 Subject: bpf: Allocate ID for bpf_link Generate ID for each bpf_link using IDR, similarly to bpf_map and bpf_prog. bpf_link creation, initialization, attachment, and exposing to user-space through FD and ID is a complicated multi-step process, abstract it away through bpf_link_primer and bpf_link_prime(), bpf_link_settle(), and bpf_link_cleanup() internal API. They guarantee that until bpf_link is properly attached, user-space won't be able to access partially-initialized bpf_link either from FD or ID. All this allows to simplify bpf_link attachment and error handling code. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200429001614.1544-3-andriin@fb.com --- include/linux/bpf.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 81c8620cb4c4..875d1f0af803 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1085,11 +1085,19 @@ int bpf_prog_new_fd(struct bpf_prog *prog); struct bpf_link { atomic64_t refcnt; + u32 id; const struct bpf_link_ops *ops; struct bpf_prog *prog; struct work_struct work; }; +struct bpf_link_primer { + struct bpf_link *link; + struct file *file; + int fd; + u32 id; +}; + struct bpf_link_ops { void (*release)(struct bpf_link *link); void (*dealloc)(struct bpf_link *link); @@ -1097,10 +1105,11 @@ struct bpf_link_ops { struct bpf_prog *old_prog); }; -void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, - struct bpf_prog *prog); -void bpf_link_cleanup(struct bpf_link *link, struct file *link_file, - int link_fd); +void bpf_link_init(struct bpf_link *link, + const struct bpf_link_ops *ops, struct bpf_prog *prog); +int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); +int bpf_link_settle(struct bpf_link_primer *primer); +void bpf_link_cleanup(struct bpf_link_primer *primer); void bpf_link_inc(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); -- cgit v1.2.3 From f2e10bff16a0fdd41ba278c84da9813700e356af Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Apr 2020 17:16:08 -0700 Subject: bpf: Add support for BPF_OBJ_GET_INFO_BY_FD for bpf_link Add ability to fetch bpf_link details through BPF_OBJ_GET_INFO_BY_FD command. Also enhance show_fdinfo to potentially include bpf_link type-specific information (similarly to obj_info). Also introduce enum bpf_link_type stored in bpf_link itself and expose it in UAPI. bpf_link_tracing also now will store and return bpf_attach_type. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200429001614.1544-5-andriin@fb.com --- include/linux/bpf-cgroup.h | 2 -- include/linux/bpf.h | 8 +++++++- include/linux/bpf_types.h | 6 ++++++ 3 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a9cb9a5bf8e9..272626cc3fc9 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -57,8 +57,6 @@ struct bpf_cgroup_link { enum bpf_attach_type type; }; -extern const struct bpf_link_ops bpf_cgroup_link_lops; - struct bpf_prog_list { struct list_head node; struct bpf_prog *prog; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 875d1f0af803..c07b1d2f3824 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1026,9 +1026,11 @@ extern const struct file_operations bpf_prog_fops; extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; +#define BPF_LINK_TYPE(_id, _name) #include #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +#undef BPF_LINK_TYPE extern const struct bpf_prog_ops bpf_offload_prog_ops; extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; @@ -1086,6 +1088,7 @@ int bpf_prog_new_fd(struct bpf_prog *prog); struct bpf_link { atomic64_t refcnt; u32 id; + enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; struct work_struct work; @@ -1103,9 +1106,12 @@ struct bpf_link_ops { void (*dealloc)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); + void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); + int (*fill_link_info)(const struct bpf_link *link, + struct bpf_link_info *info); }; -void bpf_link_init(struct bpf_link *link, +void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog); int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); int bpf_link_settle(struct bpf_link_primer *primer); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index ba0c2d56f8a3..8345cdf553b8 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -118,3 +118,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) #if defined(CONFIG_BPF_JIT) BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) #endif + +BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) +BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) +#ifdef CONFIG_CGROUP_BPF +BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) +#endif -- cgit v1.2.3 From 61365ca7b24f1cb106a4c619c94610862bbec778 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 15 Apr 2020 14:14:49 +0200 Subject: backlight: l4f00242t03: Convert to GPIO descriptors This converts the l4f00242t03 backlight driver to use GPIO descriptors and switches the two Freescale i.MX boards over to passing descriptors instead of global GPIO numbers. We use the typical names "enable" and "reset" as found in the device tree bindings for panel GPIOs. This saves a lot of code in the driver and makes it possible to get rid of the platform data header altogether. Signed-off-by: Linus Walleij Reviewed-by: Daniel Thompson Acked-by: Shawn Guo Signed-off-by: Lee Jones --- include/linux/spi/l4f00242t03.h | 17 ----------------- 1 file changed, 17 deletions(-) delete mode 100644 include/linux/spi/l4f00242t03.h (limited to 'include/linux') diff --git a/include/linux/spi/l4f00242t03.h b/include/linux/spi/l4f00242t03.h deleted file mode 100644 index 831a5de7a0e2..000000000000 --- a/include/linux/spi/l4f00242t03.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * l4f00242t03.h -- Platform glue for Epson L4F00242T03 LCD - * - * Copyright (c) 2009 Alberto Panizzo - * Based on Marek Vasut work in lms283gf05.h -*/ - -#ifndef _INCLUDE_LINUX_SPI_L4F00242T03_H_ -#define _INCLUDE_LINUX_SPI_L4F00242T03_H_ - -struct l4f00242t03_pdata { - unsigned int reset_gpio; - unsigned int data_enable_gpio; -}; - -#endif /* _INCLUDE_LINUX_SPI_L4F00242T03_H_ */ -- cgit v1.2.3 From 36b5215436ad115551e12478ceb3be4a2279e415 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 28 Apr 2020 17:23:27 -0700 Subject: gpio: Document proper return value for gpio drivers The legacy defines GPIOF_DIR_XXX are only for consumers. Document the proper ones. Also: don't use "_XXX" since that's harder to find with "git grep". Just list both of the values. Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20200428172322.1.I396f351e364f3c09df7c7606e79abefb8682c092@changeid Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index b8fc92c177eb..7b5f5681b7e4 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -267,9 +267,9 @@ struct gpio_irq_chip { * @free: optional hook for chip-specific deactivation, such as * disabling module power and clock; may sleep * @get_direction: returns direction for signal "offset", 0=out, 1=in, - * (same as GPIOF_DIR_XXX), or negative error. - * It is recommended to always implement this function, even on - * input-only or output-only gpio chips. + * (same as GPIO_LINE_DIRECTION_OUT / GPIO_LINE_DIRECTION_IN), + * or negative error. It is recommended to always implement this + * function, even on input-only or output-only gpio chips. * @direction_input: configures signal "offset" as input, or returns error * This can be omitted on input-only or output-only gpio chips. * @direction_output: configures signal "offset" as output, or returns error -- cgit v1.2.3 From 8d0910121b070b4edf4239d91cf9a4523b33ca0c Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 28 Apr 2020 17:23:28 -0700 Subject: gpio: Make "offset" and "unsigned int", not just "unsigned" When I copied the function prototypes from the GPIO header file into my own driver, checkpatch yelled at me saying that I shouldn't use use "unsigned" but instead should say "unsigned int". Let's make the header file use "unsigned int" so others who copy like I did won't get yelled at. Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20200428172322.2.Iacb3c8152c3cf9015a91308678155a578b0cc050@changeid Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 7b5f5681b7e4..8c41ae41b6bb 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -349,30 +349,30 @@ struct gpio_chip { struct module *owner; int (*request)(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); void (*free)(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); int (*get_direction)(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); int (*direction_input)(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); int (*direction_output)(struct gpio_chip *gc, - unsigned offset, int value); + unsigned int offset, int value); int (*get)(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); int (*get_multiple)(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits); void (*set)(struct gpio_chip *gc, - unsigned offset, int value); + unsigned int offset, int value); void (*set_multiple)(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits); int (*set_config)(struct gpio_chip *gc, - unsigned offset, + unsigned int offset, unsigned long config); int (*to_irq)(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); void (*dbg_show)(struct seq_file *s, struct gpio_chip *gc); @@ -459,7 +459,7 @@ struct gpio_chip { }; extern const char *gpiochip_is_requested(struct gpio_chip *gc, - unsigned offset); + unsigned int offset); /* add/remove chips */ extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, @@ -657,9 +657,9 @@ static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gc, } #endif /* CONFIG_LOCKDEP */ -int gpiochip_generic_request(struct gpio_chip *gc, unsigned offset); -void gpiochip_generic_free(struct gpio_chip *gc, unsigned offset); -int gpiochip_generic_config(struct gpio_chip *gc, unsigned offset, +int gpiochip_generic_request(struct gpio_chip *gc, unsigned int offset); +void gpiochip_generic_free(struct gpio_chip *gc, unsigned int offset); +int gpiochip_generic_config(struct gpio_chip *gc, unsigned int offset, unsigned long config); /** -- cgit v1.2.3 From 0376e9efe18388bd486a65edbc16d34b84bddc8f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 28 Apr 2020 13:27:55 +0200 Subject: block: replace BIO_QUEUE_ENTERED with BIO_CGROUP_ACCT BIO_QUEUE_ENTERED is only used for cgroup accounting now, so rename the flag and move setting it into the cgroup code. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 10 ++++++---- include/linux/blk_types.h | 2 +- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 35f8ffe92b70..4deb8bb7b6af 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -607,12 +607,14 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, u64_stats_update_begin(&bis->sync); /* - * If the bio is flagged with BIO_QUEUE_ENTERED it means this - * is a split bio and we would have already accounted for the - * size of the bio. + * If the bio is flagged with BIO_CGROUP_ACCT it means this is a + * split bio and we would have already accounted for the size of + * the bio. */ - if (!bio_flagged(bio, BIO_QUEUE_ENTERED)) + if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { + bio_set_flag(bio, BIO_CGROUP_ACCT); bis->cur.bytes[rwd] += bio->bi_iter.bi_size; + } bis->cur.ios[rwd]++; u64_stats_update_end(&bis->sync); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 31eb92876be7..90895d594e64 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -220,7 +220,7 @@ enum { * throttling rules. Don't do it again. */ BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ - BIO_QUEUE_ENTERED, /* can use blk_queue_enter_live() */ + BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ BIO_TRACKED, /* set if bio goes through the rq_qos path */ BIO_FLAG_LAST }; -- cgit v1.2.3 From 3c2214b6027ff37945799de717c417212e1a8c54 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 21 Apr 2020 12:34:55 -0400 Subject: padata: add separate cpuhp node for CPUHP_PADATA_DEAD Removing the pcrypt module triggers this: general protection fault, probably for non-canonical address 0xdead000000000122 CPU: 5 PID: 264 Comm: modprobe Not tainted 5.6.0+ #2 Hardware name: QEMU Standard PC RIP: 0010:__cpuhp_state_remove_instance+0xcc/0x120 Call Trace: padata_sysfs_release+0x74/0xce kobject_put+0x81/0xd0 padata_free+0x12/0x20 pcrypt_exit+0x43/0x8ee [pcrypt] padata instances wrongly use the same hlist node for the online and dead states, so __padata_free()'s second cpuhp remove call chokes on the node that the first poisoned. cpuhp multi-instance callbacks only walk forward in cpuhp_step->list and the same node is linked in both the online and dead lists, so the list corruption that results from padata_alloc() adding the node to a second list without removing it from the first doesn't cause problems as long as no instances are freed. Avoid the issue by giving each state its own node. Fixes: 894c9ef9780c ("padata: validate cpumask without removed CPU during offline") Signed-off-by: Daniel Jordan Cc: Herbert Xu Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v5.4+ Signed-off-by: Herbert Xu --- include/linux/padata.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index a0d8b41850b2..693cae9bfe66 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -139,7 +139,8 @@ struct padata_shell { /** * struct padata_instance - The overall control structure. * - * @node: Used by CPU hotplug. + * @cpu_online_node: Linkage for CPU online callback. + * @cpu_dead_node: Linkage for CPU offline callback. * @parallel_wq: The workqueue used for parallel work. * @serial_wq: The workqueue used for serial work. * @pslist: List of padata_shell objects attached to this instance. @@ -150,7 +151,8 @@ struct padata_shell { * @flags: padata flags. */ struct padata_instance { - struct hlist_node node; + struct hlist_node cpu_online_node; + struct hlist_node cpu_dead_node; struct workqueue_struct *parallel_wq; struct workqueue_struct *serial_wq; struct list_head pslist; -- cgit v1.2.3 From 97f9ac3db6612f14ac0c509e1a63ce14fd4cc0eb Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Tue, 21 Apr 2020 12:44:49 -0500 Subject: crypto: ccp - Add support for SEV-ES to the PSP driver To provide support for SEV-ES, the hypervisor must provide an area of memory to the PSP. Once this Trusted Memory Region (TMR) is provided to the PSP, the contents of this area of memory are no longer available to the x86. Update the PSP driver to allocate a 1MB region for the TMR that is 1MB aligned and then provide it to the PSP through the SEV INIT command. Signed-off-by: Tom Lendacky Reviewed-by: Brijesh Singh Reviewed-by: Joerg Roedel Signed-off-by: Herbert Xu --- include/linux/psp-sev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 5167bf2bfc75..7fbc8679145c 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -100,6 +100,8 @@ struct sev_data_init { u32 tmr_len; /* In */ } __packed; +#define SEV_INIT_FLAGS_SEV_ES 0x01 + /** * struct sev_data_pek_csr - PEK_CSR command parameters * -- cgit v1.2.3 From 0da0e31600e8a42c6f1dfaa7a06211c8bb243ea7 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 3 Apr 2020 19:44:52 +0200 Subject: of: reserved-memory: Support lookup of regions by name Add support for looking up memory regions by name. This looks up the given name in the newly introduced memory-region-names property and returns the memory region at the corresponding index in the memory- region(s) property. Reviewed-by: Rob Herring Signed-off-by: Thierry Reding --- include/linux/of_reserved_mem.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h index 60f541912ccf..a1b427ac291b 100644 --- a/include/linux/of_reserved_mem.h +++ b/include/linux/of_reserved_mem.h @@ -33,6 +33,9 @@ typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem); int of_reserved_mem_device_init_by_idx(struct device *dev, struct device_node *np, int idx); +int of_reserved_mem_device_init_by_name(struct device *dev, + struct device_node *np, + const char *name); void of_reserved_mem_device_release(struct device *dev); void fdt_init_reserved_mem(void); @@ -45,6 +48,14 @@ static inline int of_reserved_mem_device_init_by_idx(struct device *dev, { return -ENOSYS; } + +static inline int of_reserved_mem_device_init_by_name(struct device *dev, + struct device_node *np, + const char *name) +{ + return -ENOSYS; +} + static inline void of_reserved_mem_device_release(struct device *pdev) { } static inline void fdt_init_reserved_mem(void) { } -- cgit v1.2.3 From 8aa8eb2a8f5b3305a95f39957dd2b715fa668e21 Mon Sep 17 00:00:00 2001 From: Alexandre Chartre Date: Tue, 14 Apr 2020 12:36:12 +0200 Subject: objtool: Add support for intra-function calls Change objtool to support intra-function calls. On x86, an intra-function call is represented in objtool as a push onto the stack (of the return address), and a jump to the destination address. That way the stack information is correctly updated and the call flow is still accurate. Signed-off-by: Alexandre Chartre Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Miroslav Benes Acked-by: Josh Poimboeuf Link: https://lkml.kernel.org/r/20200414103618.12657-4-alexandre.chartre@oracle.com --- include/linux/frame.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/frame.h b/include/linux/frame.h index 02d3ca2d9598..303cda600e56 100644 --- a/include/linux/frame.h +++ b/include/linux/frame.h @@ -15,9 +15,20 @@ static void __used __section(.discard.func_stack_frame_non_standard) \ *__func_stack_frame_non_standard_##func = func +/* + * This macro indicates that the following intra-function call is valid. + * Any non-annotated intra-function call will cause objtool to issue a warning. + */ +#define ANNOTATE_INTRA_FUNCTION_CALL \ + 999: \ + .pushsection .discard.intra_function_calls; \ + .long 999b; \ + .popsection; + #else /* !CONFIG_STACK_VALIDATION */ #define STACK_FRAME_NON_STANDARD(func) +#define ANNOTATE_INTRA_FUNCTION_CALL #endif /* CONFIG_STACK_VALIDATION */ -- cgit v1.2.3 From 36c5bdc4387056af3840adb4478c752faeb9d15e Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 15 Apr 2020 22:05:07 +0100 Subject: sched/topology: Kill SD_LOAD_BALANCE That flag is set unconditionally in sd_init(), and no one checks for it anymore. Remove it. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200415210512.805-5-valentin.schneider@arm.com --- include/linux/sched/topology.h | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 95253ad792b0..fb11091129b3 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -11,21 +11,20 @@ */ #ifdef CONFIG_SMP -#define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */ -#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */ -#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */ -#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */ -#define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */ -#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ -#define SD_ASYM_CPUCAPACITY 0x0040 /* Domain members have different CPU capacities */ -#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share CPU capacity */ -#define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */ -#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share CPU pkg resources */ -#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ -#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ -#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ -#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ -#define SD_NUMA 0x4000 /* cross-node balancing */ +#define SD_BALANCE_NEWIDLE 0x0001 /* Balance when about to become idle */ +#define SD_BALANCE_EXEC 0x0002 /* Balance on exec */ +#define SD_BALANCE_FORK 0x0004 /* Balance on fork, clone */ +#define SD_BALANCE_WAKE 0x0008 /* Balance on wakeup */ +#define SD_WAKE_AFFINE 0x0010 /* Wake task to waking CPU */ +#define SD_ASYM_CPUCAPACITY 0x0020 /* Domain members have different CPU capacities */ +#define SD_SHARE_CPUCAPACITY 0x0040 /* Domain members share CPU capacity */ +#define SD_SHARE_POWERDOMAIN 0x0080 /* Domain members share power domain */ +#define SD_SHARE_PKG_RESOURCES 0x0100 /* Domain members share CPU pkg resources */ +#define SD_SERIALIZE 0x0200 /* Only a single load balancing instance */ +#define SD_ASYM_PACKING 0x0400 /* Place busy groups earlier in the domain */ +#define SD_PREFER_SIBLING 0x0800 /* Prefer to place tasks in a sibling domain */ +#define SD_OVERLAP 0x1000 /* sched_domains of this level overlap */ +#define SD_NUMA 0x2000 /* cross-node balancing */ #ifdef CONFIG_SCHED_SMT static inline int cpu_smt_flags(void) -- cgit v1.2.3 From bf2c59fce4074e55d622089b34be3a6bc95484fb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 1 Apr 2020 17:40:33 -0400 Subject: sched/core: Fix illegal RCU from offline CPUs In the CPU-offline process, it calls mmdrop() after idle entry and the subsequent call to cpuhp_report_idle_dead(). Once execution passes the call to rcu_report_dead(), RCU is ignoring the CPU, which results in lockdep complaining when mmdrop() uses RCU from either memcg or debugobjects below. Fix it by cleaning up the active_mm state from BP instead. Every arch which has CONFIG_HOTPLUG_CPU should have already called idle_task_exit() from AP. The only exception is parisc because it switches them to &init_mm unconditionally (see smp_boot_one_cpu() and smp_cpu_init()), but the patch will still work there because it calls mmgrab(&init_mm) in smp_cpu_init() and then should call mmdrop(&init_mm) in finish_cpu(). WARNING: suspicious RCU usage ----------------------------- kernel/workqueue.c:710 RCU or wq_pool_mutex should be held! other info that might help us debug this: RCU used illegally from offline CPU! Call Trace: dump_stack+0xf4/0x164 (unreliable) lockdep_rcu_suspicious+0x140/0x164 get_work_pool+0x110/0x150 __queue_work+0x1bc/0xca0 queue_work_on+0x114/0x120 css_release+0x9c/0xc0 percpu_ref_put_many+0x204/0x230 free_pcp_prepare+0x264/0x570 free_unref_page+0x38/0xf0 __mmdrop+0x21c/0x2c0 idle_task_exit+0x170/0x1b0 pnv_smp_cpu_kill_self+0x38/0x2e0 cpu_die+0x48/0x64 arch_cpu_idle_dead+0x30/0x50 do_idle+0x2f4/0x470 cpu_startup_entry+0x38/0x40 start_secondary+0x7a8/0xa80 start_secondary_resume+0x10/0x14 Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Qian Cai Signed-off-by: Peter Zijlstra (Intel) Acked-by: Michael Ellerman (powerpc) Link: https://lkml.kernel.org/r/20200401214033.8448-1-cai@lca.pw --- include/linux/sched/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index c49257a3b510..a132d875d351 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,8 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +void mmdrop(struct mm_struct *mm); + /* * This has to be called after a get_task_mm()/mmget_not_zero() * followed by taking the mmap_sem for writing before modifying the -- cgit v1.2.3 From 12ac6782a40ad7636b6ef45680741825b64ab221 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 21 Apr 2020 21:07:39 -0700 Subject: sched/swait: Reword some of the main description With both the increased use of swait and kvm no longer using it, we can reword some of the comments. While removing Linus' valid rant, I've also cared to explicitly mention that swait is very different than regular wait. In addition it is mentioned against using swait in favor of the regular flavor. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200422040739.18601-6-dave@stgolabs.net --- include/linux/swait.h | 23 +++++------------------ 1 file changed, 5 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swait.h b/include/linux/swait.h index 73e06e9986d4..6a8c22b8c2a5 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -9,23 +9,10 @@ #include /* - * BROKEN wait-queues. - * - * These "simple" wait-queues are broken garbage, and should never be - * used. The comments below claim that they are "similar" to regular - * wait-queues, but the semantics are actually completely different, and - * every single user we have ever had has been buggy (or pointless). - * - * A "swake_up_one()" only wakes up _one_ waiter, which is not at all what - * "wake_up()" does, and has led to problems. In other cases, it has - * been fine, because there's only ever one waiter (kvm), but in that - * case gthe whole "simple" wait-queue is just pointless to begin with, - * since there is no "queue". Use "wake_up_process()" with a direct - * pointer instead. - * - * While these are very similar to regular wait queues (wait.h) the most - * important difference is that the simple waitqueue allows for deterministic - * behaviour -- IOW it has strictly bounded IRQ and lock hold times. + * Simple waitqueues are semantically very different to regular wait queues + * (wait.h). The most important difference is that the simple waitqueue allows + * for deterministic behaviour -- IOW it has strictly bounded IRQ and lock hold + * times. * * Mainly, this is accomplished by two things. Firstly not allowing swake_up_all * from IRQ disabled, and dropping the lock upon every wakeup, giving a higher @@ -39,7 +26,7 @@ * sleeper state. * * - the !exclusive mode; because that leads to O(n) wakeups, everything is - * exclusive. + * exclusive. As such swake_up_one will only ever awake _one_ waiter. * * - custom wake callback functions; because you cannot give any guarantees * about random code. This also allows swait to be used in RT, such that -- cgit v1.2.3 From 6e3a401fc8af01828bcdc92d713195d318b36e7e Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Thu, 30 Apr 2020 18:51:14 +0300 Subject: inet_diag: add cgroup id attribute This patch adds cgroup v2 ID to common inet diag message attributes. Cgroup v2 ID is kernfs ID (ino or ino+gen). This attribute allows filter inet diag output by cgroup ID obtained by name_to_handle_at() syscall. When net_cls or net_prio cgroup is activated this ID is equal to 1 (root cgroup ID) for newly created sockets. Some notes about this ID: 1) gets initialized in socket() syscall 2) incoming socket gets ID from listening socket (not during accept() syscall) 3) not changed when process get moved to another cgroup 4) can point to deleted cgroup (refcounting) v2: - use CONFIG_SOCK_CGROUP_DATA instead if CONFIG_CGROUPS v3: - fix attr size by using nla_total_size_64bit() (Eric Dumazet) - more detailed commit message (Konstantin Khlebnikov) Signed-off-by: Dmitry Yakunin Reviewed-by: Konstantin Khlebnikov Acked-By: Tejun Heo Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index ce9ed1c0602f..0ef2d800fda7 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -71,7 +71,11 @@ static inline size_t inet_diag_msg_attrs_size(void) + nla_total_size(1) /* INET_DIAG_SKV6ONLY */ #endif + nla_total_size(4) /* INET_DIAG_MARK */ - + nla_total_size(4); /* INET_DIAG_CLASS_ID */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ +#ifdef CONFIG_SOCK_CGROUP_DATA + + nla_total_size_64bit(sizeof(u64)) /* INET_DIAG_CGROUP_ID */ +#endif + ; } int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, -- cgit v1.2.3 From ea5bacaa2cec6967ed337f4d0ad6034123ca737b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 30 Apr 2020 18:04:03 +0200 Subject: docs: networking: convert netdev-features.txt to ReST Not much to be done here: - add SPDX header; - adjust titles and chapters, adding proper markups; - add to networking/index.rst. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 9d53c5ad272c..2cc3cf80b49a 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -89,7 +89,7 @@ enum { * Add your fresh new feature above and remember to update * netdev_features_strings[] in net/core/ethtool.c and maybe * some feature mask #defines below. Please also describe it - * in Documentation/networking/netdev-features.txt. + * in Documentation/networking/netdev-features.rst. */ /**/NETDEV_FEATURE_COUNT -- cgit v1.2.3 From 2b195850128f5bafde177b12489d9fa27962cc1e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 30 Apr 2020 10:35:41 -0700 Subject: tcp: add tp->dup_ack_counter In commit 86de5921a3d5 ("tcp: defer SACK compression after DupThresh") I added a TCP_FASTRETRANS_THRESH bias to tp->compressed_ack in order to enable sack compression only after 3 dupacks. Since we plan to relax this rule for flows that involve stacks not requiring this old rule, this patch adds a distinct tp->dup_ack_counter. This means the TCP_FASTRETRANS_THRESH value is now used in a single location that a future patch can adjust: if (tp->dup_ack_counter < TCP_FASTRETRANS_THRESH) { tp->dup_ack_counter++; goto send_now; } This patch also introduces tcp_sack_compress_send_ack() helper to ease following patch comprehension. This patch refines LINUX_MIB_TCPACKCOMPRESSED to not count the acks that we had to send if the timer expires or tcp_sack_compress_send_ack() is sending an ack. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 421c99c12291..2c6f87e9f0cf 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -268,6 +268,7 @@ struct tcp_sock { } rack; u16 advmss; /* Advertised MSS */ u8 compressed_ack; + u8 dup_ack_counter; u32 chrono_start; /* Start time in jiffies of a TCP chrono */ u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u8 chrono_type:2, /* current chronograph type */ -- cgit v1.2.3 From 54c52e10dc9b939084a7e6e3d32ce8fd8dee7898 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 13 Apr 2020 12:27:55 -0400 Subject: blk-iocost: switch to fixed non-auto-decaying use_delay The use_delay mechanism was introduced by blk-iolatency to hold memory allocators accountable for the reclaim and other shared IOs they cause. The duration of the delay is dynamically balanced between iolatency increasing the value on each target miss and it auto-decaying as time passes and threads get delayed on it. While this works well for iolatency, iocost's control model isn't compatible with it. There is no repeated "violation" events which can be balanced against auto-decaying. iocost instead knows how much a given cgroup is over budget and wants to prevent that cgroup from issuing IOs while over budget. Until now, iocost has been adding the cost of force-issued IOs. However, this doesn't reflect the amount which is already over budget and is simply not enough to counter the auto-decaying allowing anon-memory leaking low priority cgroup to go over its alloted share of IOs. As auto-decaying doesn't make much sense for iocost, this patch introduces a different mode of operation for use_delay - when blkcg_set_delay() are used insted of blkcg_add/use_delay(), the delay duration is not auto-decayed until it is explicitly cleared with blkcg_clear_delay(). iocost is updated to keep the delay duration synchronized to the budget overage amount. With this change, iocost can effectively police cgroups which generate significant amount of force-issued IOs. Signed-off-by: Tejun Heo Cc: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 43 +++++++++++++++++++++++++++++++++---------- 1 file changed, 33 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 4deb8bb7b6af..a57ebe2f00ab 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -631,6 +631,8 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, static inline void blkcg_use_delay(struct blkcg_gq *blkg) { + if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) + return; if (atomic_add_return(1, &blkg->use_delay) == 1) atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); } @@ -639,6 +641,8 @@ static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) { int old = atomic_read(&blkg->use_delay); + if (WARN_ON_ONCE(old < 0)) + return 0; if (old == 0) return 0; @@ -663,20 +667,39 @@ static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) return 1; } +/** + * blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount + * @blkg: target blkg + * @delay: delay duration in nsecs + * + * When enabled with this function, the delay is not decayed and must be + * explicitly cleared with blkcg_clear_delay(). Must not be mixed with + * blkcg_[un]use_delay() and blkcg_add_delay() usages. + */ +static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay) +{ + int old = atomic_read(&blkg->use_delay); + + /* We only want 1 person setting the congestion count for this blkg. */ + if (!old && atomic_cmpxchg(&blkg->use_delay, old, -1) == old) + atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); + + atomic64_set(&blkg->delay_nsec, delay); +} + +/** + * blkcg_clear_delay - Disable allocator delay mechanism + * @blkg: target blkg + * + * Disable use_delay mechanism. See blkcg_set_delay(). + */ static inline void blkcg_clear_delay(struct blkcg_gq *blkg) { int old = atomic_read(&blkg->use_delay); - if (!old) - return; + /* We only want 1 person clearing the congestion count for this blkg. */ - while (old) { - int cur = atomic_cmpxchg(&blkg->use_delay, old, 0); - if (cur == old) { - atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); - break; - } - old = cur; - } + if (old && atomic_cmpxchg(&blkg->use_delay, old, 0) == old) + atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); } void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); -- cgit v1.2.3 From c100beb9ccfb98e2474586a4006483cbf770c823 Mon Sep 17 00:00:00 2001 From: Alexandru Gagniuc Date: Mon, 27 Apr 2020 18:25:13 -0500 Subject: PCI/AER: Use only _OSC to determine AER ownership Per the PCI Firmware spec, r3.2, sec 4.5.1, the OS can request control of AER via bit 3 of the _OSC Control Field. In the returned value of the Control Field: The firmware sets [bit 3] to 1 to grant control over PCI Express Advanced Error Reporting. ... after control is transferred to the operating system, firmware must not modify the Advanced Error Reporting Capability. If control of this feature was requested and denied or was not requested, firmware returns this bit set to 0. Previously the pci_root driver looked at the HEST FIRMWARE_FIRST bit to determine whether to request ownership of the AER Capability. This was based on ACPI spec v6.3, sec 18.3.2.4, and similar sections, which say things like: Bit [0] - FIRMWARE_FIRST: If set, indicates that system firmware will handle errors from this source first. Bit [1] - GLOBAL: If set, indicates that the settings contained in this structure apply globally to all PCI Express Devices. These ACPI references don't say anything about ownership of the AER Capability. Remove use of the FIRMWARE_FIRST bit and rely only on the _OSC bit to determine whether we have control of the AER Capability. Link: https://lore.kernel.org/r/20181115231605.24352-1-mr.nuke.me@gmail.com/ v1 Link: https://lore.kernel.org/r/20190326172343.28946-1-mr.nuke.me@gmail.com/ v2 Link: https://lore.kernel.org/r/67af2931705bed9a588b5a39d369cb70b9942190.1587925636.git.sathyanarayanan.kuppuswamy@linux.intel.com [bhelgaas: commit log, note: Alex posted this identical patch 18 months ago, and I failed to apply it then, so I made him the author, added links to his postings, and added his Signed-off-by] Signed-off-by: Alexandru Gagniuc Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas Reviewed-by: Jon Derrick --- include/linux/pci-acpi.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 2d155bfb8fbf..11c98875538a 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -125,10 +125,4 @@ static inline void acpi_pci_add_bus(struct pci_bus *bus) { } static inline void acpi_pci_remove_bus(struct pci_bus *bus) { } #endif /* CONFIG_ACPI */ -#ifdef CONFIG_ACPI_APEI -extern bool aer_acpi_firmware_first(void); -#else -static inline bool aer_acpi_firmware_first(void) { return false; } -#endif - #endif /* _PCI_ACPI_H_ */ -- cgit v1.2.3 From 999a22890cb183b918e4372395d24426a755cef2 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 3 Apr 2020 07:20:50 +0000 Subject: uaccess: Add user_read_access_begin/end and user_write_access_begin/end Some architectures like powerpc64 have the capability to separate read access and write access protection. For get_user() and copy_from_user(), powerpc64 only open read access. For put_user() and copy_to_user(), powerpc64 only open write access. But when using unsafe_get_user() or unsafe_put_user(), user_access_begin open both read and write. Other architectures like powerpc book3s 32 bits only allow write access protection. And on this architecture protection is an heavy operation as it requires locking/unlocking per segment of 256Mbytes. On those architecture it is therefore desirable to do the unlocking only for write access. (Note that book3s/32 ranges from very old powermac from the 90's with powerpc 601 processor, till modern ADSL boxes with PowerQuicc II processors for instance so it is still worth considering.) In order to avoid any risk based of hacking some variable parameters passed to user_access_begin/end that would allow hacking and leaving user access open or opening too much, it is preferable to use dedicated static functions that can't be overridden. Add a user_read_access_begin and user_read_access_end to only open read access. Add a user_write_access_begin and user_write_access_end to only open write access. By default, when undefined, those new access helpers default on the existing user_access_begin and user_access_end. Signed-off-by: Christophe Leroy Reviewed-by: Kees Cook Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/36e43241c7f043a24b5069e78c6a7edd11043be5.1585898438.git.christophe.leroy@c-s.fr --- include/linux/uaccess.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 67f016010aad..9861c89f93be 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -378,6 +378,14 @@ extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif +#ifndef user_write_access_begin +#define user_write_access_begin user_access_begin +#define user_write_access_end user_access_end +#endif +#ifndef user_read_access_begin +#define user_read_access_begin user_access_begin +#define user_read_access_end user_access_end +#endif #ifdef CONFIG_HARDENED_USERCOPY void usercopy_warn(const char *name, const char *detail, bool to_user, -- cgit v1.2.3 From f256356f65e6449a9fcf6089ea25882c91768665 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Mon, 27 Apr 2020 11:39:03 +0800 Subject: ptp_qoriq: output PPS signal on FIPER2 in default Output PPS signal on FIPER2 (Fixed Period Interval Pulse) in default which is more desired by user. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- include/linux/fsl/ptp_qoriq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index 75884563059f..884b8f8ca06d 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -135,7 +135,7 @@ struct ptp_qoriq_registers { #define DEFAULT_CKSEL 1 #define DEFAULT_TMR_PRSC 2 #define DEFAULT_FIPER1_PERIOD 1000000000 -#define DEFAULT_FIPER2_PERIOD 100000 +#define DEFAULT_FIPER2_PERIOD 1000000000 struct ptp_qoriq { void __iomem *base; -- cgit v1.2.3 From e4e51da66dc812176cca16b0f8a5b87b173deb5d Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Wed, 29 Apr 2020 01:06:59 +0200 Subject: net: phy: bcm54140: add second PHY ID This PHY has two PHY IDs depending on its mode. Adjust the mask so that it includes both IDs. Signed-off-by: Michael Walle Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 8be150e69c7c..58d0150acc3e 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -25,7 +25,7 @@ #define PHY_ID_BCM5461 0x002060c0 #define PHY_ID_BCM54612E 0x03625e60 #define PHY_ID_BCM54616S 0x03625d10 -#define PHY_ID_BCM54140 0xae025019 +#define PHY_ID_BCM54140 0xae025009 #define PHY_ID_BCM57780 0x03625d90 #define PHY_ID_BCM89610 0x03625cd0 -- cgit v1.2.3 From 9ba2353b2cc58ba13f7a7369208107f133f6a27b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Fri, 3 Apr 2020 22:20:32 +0200 Subject: power: supply: core: allow to constify property lists MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since tables pointed to by power_supply_desc->properties and ->usb_types are not expected to change after registration, mark the pointers accordingly Signed-off-by: Michał Mirosław Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index dcd5a71e6c67..6a34df65d4d1 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -223,9 +223,9 @@ struct power_supply_config { struct power_supply_desc { const char *name; enum power_supply_type type; - enum power_supply_usb_type *usb_types; + const enum power_supply_usb_type *usb_types; size_t num_usb_types; - enum power_supply_property *properties; + const enum power_supply_property *properties; size_t num_properties; /* -- cgit v1.2.3 From 0b104773b4f72ccd8af98a2f1efe69b174c344d3 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 9 Apr 2020 17:49:21 -0600 Subject: PCI: Constify struct pci_ecam_ops struct pci_ecam_ops is typically DT match table data which is defined to be const. It's also best practice for ops structs to be const. Ideally, we'd make struct pci_ops const as well, but that becomes pretty invasive, so for now we just cast it where needed. Link: https://lore.kernel.org/r/20200409234923.21598-2-robh@kernel.org Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi Acked-by: Bjorn Helgaas Acked-by: Catalin Marinas Cc: Catalin Marinas Cc: Will Deacon Cc: Lorenzo Pieralisi Cc: Andrew Murray Cc: Bjorn Helgaas Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Jonathan Chocron Cc: Zhou Wang Cc: Robert Richter Cc: Toan Le Cc: Marc Gonzalez Cc: Mans Rullgard Cc: linux-acpi@vger.kernel.org --- include/linux/pci-acpi.h | 2 +- include/linux/pci-ecam.h | 22 +++++++++++----------- 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 2d155bfb8fbf..81f5535ca1b5 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -27,7 +27,7 @@ extern phys_addr_t acpi_pci_root_get_mcfg_addr(acpi_handle handle); struct pci_ecam_ops; extern int pci_mcfg_lookup(struct acpi_pci_root *root, struct resource *cfgres, - struct pci_ecam_ops **ecam_ops); + const struct pci_ecam_ops **ecam_ops); static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) { diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index a73164c85e78..6c21dd0901ab 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -29,7 +29,7 @@ struct pci_config_window { struct resource res; struct resource busr; void *priv; - struct pci_ecam_ops *ops; + const struct pci_ecam_ops *ops; union { void __iomem *win; /* 64-bit single mapping */ void __iomem **winp; /* 32-bit per-bus mapping */ @@ -40,29 +40,29 @@ struct pci_config_window { /* create and free pci_config_window */ struct pci_config_window *pci_ecam_create(struct device *dev, struct resource *cfgres, struct resource *busr, - struct pci_ecam_ops *ops); + const struct pci_ecam_ops *ops); void pci_ecam_free(struct pci_config_window *cfg); /* map_bus when ->sysdata is an instance of pci_config_window */ void __iomem *pci_ecam_map_bus(struct pci_bus *bus, unsigned int devfn, int where); /* default ECAM ops */ -extern struct pci_ecam_ops pci_generic_ecam_ops; +extern const struct pci_ecam_ops pci_generic_ecam_ops; #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) -extern struct pci_ecam_ops pci_32b_ops; /* 32-bit accesses only */ -extern struct pci_ecam_ops hisi_pcie_ops; /* HiSilicon */ -extern struct pci_ecam_ops thunder_pem_ecam_ops; /* Cavium ThunderX 1.x & 2.x */ -extern struct pci_ecam_ops pci_thunder_ecam_ops; /* Cavium ThunderX 1.x */ -extern struct pci_ecam_ops xgene_v1_pcie_ecam_ops; /* APM X-Gene PCIe v1 */ -extern struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x */ -extern struct pci_ecam_ops al_pcie_ops; /* Amazon Annapurna Labs PCIe */ +extern const struct pci_ecam_ops pci_32b_ops; /* 32-bit accesses only */ +extern const struct pci_ecam_ops hisi_pcie_ops; /* HiSilicon */ +extern const struct pci_ecam_ops thunder_pem_ecam_ops; /* Cavium ThunderX 1.x & 2.x */ +extern const struct pci_ecam_ops pci_thunder_ecam_ops; /* Cavium ThunderX 1.x */ +extern const struct pci_ecam_ops xgene_v1_pcie_ecam_ops; /* APM X-Gene PCIe v1 */ +extern const struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x */ +extern const struct pci_ecam_ops al_pcie_ops; /* Amazon Annapurna Labs PCIe */ #endif #ifdef CONFIG_PCI_HOST_COMMON /* for DT-based PCI controllers that support ECAM */ int pci_host_common_probe(struct platform_device *pdev, - struct pci_ecam_ops *ops); + const struct pci_ecam_ops *ops); int pci_host_common_remove(struct platform_device *pdev); #endif #endif -- cgit v1.2.3 From 0c59c06a7c90390c3985c9acd58a73320781c15e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 9 Apr 2020 17:49:22 -0600 Subject: PCI: host-generic: Support building as modules Enable building host-generic and its host-common dependency as a module. Link: https://lore.kernel.org/r/20200409234923.21598-3-robh@kernel.org Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi Acked-by: Will Deacon Acked-by: Bjorn Helgaas Cc: Lorenzo Pieralisi Cc: Andrew Murray Cc: Bjorn Helgaas Cc: Will Deacon Cc: linux-pci@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org --- include/linux/pci-ecam.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index 6c21dd0901ab..fd0edb8b8a00 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -59,7 +59,7 @@ extern const struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x extern const struct pci_ecam_ops al_pcie_ops; /* Amazon Annapurna Labs PCIe */ #endif -#ifdef CONFIG_PCI_HOST_COMMON +#if IS_ENABLED(CONFIG_PCI_HOST_COMMON) /* for DT-based PCI controllers that support ECAM */ int pci_host_common_probe(struct platform_device *pdev, const struct pci_ecam_ops *ops); -- cgit v1.2.3 From d46edd671a147032e22cfeb271a5734703093649 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 30 Apr 2020 00:15:04 -0700 Subject: bpf: Sharing bpf runtime stats with BPF_ENABLE_STATS Currently, sysctl kernel.bpf_stats_enabled controls BPF runtime stats. Typical userspace tools use kernel.bpf_stats_enabled as follows: 1. Enable kernel.bpf_stats_enabled; 2. Check program run_time_ns; 3. Sleep for the monitoring period; 4. Check program run_time_ns again, calculate the difference; 5. Disable kernel.bpf_stats_enabled. The problem with this approach is that only one userspace tool can toggle this sysctl. If multiple tools toggle the sysctl at the same time, the measurement may be inaccurate. To fix this problem while keep backward compatibility, introduce a new bpf command BPF_ENABLE_STATS. On success, this command enables stats and returns a valid fd. BPF_ENABLE_STATS takes argument "type". Currently, only one type, BPF_STATS_RUN_TIME, is supported. We can extend the command to support other types of stats in the future. With BPF_ENABLE_STATS, user space tool would have the following flow: 1. Get a fd with BPF_ENABLE_STATS, and make sure it is valid; 2. Check program run_time_ns; 3. Sleep for the monitoring period; 4. Check program run_time_ns again, calculate the difference; 5. Close the fd. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200430071506.1408910-2-songliubraving@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c07b1d2f3824..1262ec460ab3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -987,6 +987,7 @@ _out: \ #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); +extern struct mutex bpf_stats_enabled_mutex; /* * Block execution of BPF programs attached to instrumentation (perf, -- cgit v1.2.3 From cff9f12b18915d957a2130885a00f8ab15cff7e4 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 30 Apr 2020 22:21:31 +0300 Subject: net/core: Introduce netdev_get_xmit_slave Add new ndo to get the xmit slave of master device. The reference counters are not incremented so the caller must be careful with locks. User can ask to get the xmit slave assume all the slaves can transmit by set all_slaves arg to true. Signed-off-by: Maor Gottlieb Reviewed-by: Jiri Pirko Reviewed-by: David Ahern Acked-by: David S. Miller Signed-off-by: Saeed Mahameed --- include/linux/netdevice.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 130a668049ab..26bc0f11b7ad 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1146,6 +1146,12 @@ struct netdev_net_notifier { * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to release previously enslaved netdev. * + * struct net_device *(*ndo_get_xmit_slave)(struct net_device *dev, + * struct sk_buff *skb, + * bool all_slaves); + * Get the xmit slave of master device. If all_slaves is true, function + * assume all the slaves can transmit. + * * Feature/offload setting functions. * netdev_features_t (*ndo_fix_features)(struct net_device *dev, * netdev_features_t features); @@ -1389,6 +1395,9 @@ struct net_device_ops { struct netlink_ext_ack *extack); int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); + struct net_device* (*ndo_get_xmit_slave)(struct net_device *dev, + struct sk_buff *skb, + bool all_slaves); netdev_features_t (*ndo_fix_features)(struct net_device *dev, netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, @@ -2731,6 +2740,9 @@ void netdev_freemem(struct net_device *dev); void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); +struct net_device *netdev_get_xmit_slave(struct net_device *dev, + struct sk_buff *skb, + bool all_slaves); struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); -- cgit v1.2.3 From c6bc6041b10f70b617f2d13894311fe62027d292 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 30 Apr 2020 22:21:41 +0300 Subject: net/mlx5: Add support to get lag physical port Add function to get the device physical port of the lag slave. Signed-off-by: Maor Gottlieb Reviewed-by: Leon Romanovsky Acked-by: David S. Miller Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d82dbbab8179..267dfcc5493e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1074,6 +1074,8 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev); bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev); bool mlx5_lag_is_active(struct mlx5_core_dev *dev); struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev); +u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, + struct net_device *slave); int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, int num_counters, -- cgit v1.2.3 From cfc1a89e449c02207952c72a4c0394691fdedf43 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 30 Apr 2020 22:21:46 +0300 Subject: RDMA/mlx5: Set lag tx affinity according to slave The patch sets the lag tx affinity of the data QPs and the GSI QPs according to the LAG xmit slave. For GSI QPs, in case the link layer is Ethenet (RoCE) we create two GSI QPs, one for each physical port. When the driver selects the GSI QP, it will consider the port affinity result. For connected QPs, the driver sets the affinity of the xmit slave. The above, ensures that RC QP and it's corresponding GSI QP will transmit from the same physical port. Link: https://lore.kernel.org/r/20200430192146.12863-17-maorg@mellanox.com Signed-off-by: Maor Gottlieb Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/mlx5_ifc.h | 4 +++- include/linux/mlx5/qp.h | 2 ++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fb243848132d..c1ba89198335 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1321,7 +1321,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 stat_rate_support[0x10]; u8 reserved_at_1f0[0x1]; u8 pci_sync_for_fw_update_event[0x1]; - u8 reserved_at_1f2[0xa]; + u8 reserved_at_1f2[0x6]; + u8 init2_lag_tx_port_affinity[0x1]; + u8 reserved_at_1fa[0x3]; u8 cqe_version[0x4]; u8 compact_address_vector[0x1]; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index f23eb18526fe..b9facdb9b9bd 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -66,6 +66,7 @@ enum mlx5_qp_optpar { MLX5_QP_OPTPAR_RETRY_COUNT = 1 << 12, MLX5_QP_OPTPAR_RNR_RETRY = 1 << 13, MLX5_QP_OPTPAR_ACK_TIMEOUT = 1 << 14, + MLX5_QP_OPTPAR_LAG_TX_AFF = 1 << 15, MLX5_QP_OPTPAR_PRI_PORT = 1 << 16, MLX5_QP_OPTPAR_SRQN = 1 << 18, MLX5_QP_OPTPAR_CQN_RCV = 1 << 19, @@ -321,6 +322,7 @@ struct mlx5_av { struct mlx5_ib_ah { struct ib_ah ibah; struct mlx5_av av; + u8 xmit_port; }; static inline struct mlx5_ib_ah *to_mah(struct ib_ah *ibah) -- cgit v1.2.3 From 184ecc9eb260d5a3bcdddc5bebd18f285ac004e9 Mon Sep 17 00:00:00 2001 From: Vincent Cheng Date: Fri, 1 May 2020 23:35:36 -0400 Subject: ptp: Add adjphase function to support phase offset control. Adds adjust phase function to take advantage of a PHC clock's hardware filtering capability that uses phase offset control word instead of frequency offset control word. Signed-off-by: Vincent Cheng Reviewed-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 121a7eda4593..31144d954d89 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -36,7 +36,7 @@ struct ptp_system_timestamp { }; /** - * struct ptp_clock_info - decribes a PTP hardware clock + * struct ptp_clock_info - describes a PTP hardware clock * * @owner: The clock driver should set to THIS_MODULE. * @name: A short "friendly name" to identify the clock and to @@ -65,6 +65,9 @@ struct ptp_system_timestamp { * parameter delta: Desired frequency offset from nominal frequency * in parts per billion * + * @adjphase: Adjusts the phase offset of the hardware clock. + * parameter delta: Desired change in nanoseconds. + * * @adjtime: Shifts the time of the hardware clock. * parameter delta: Desired change in nanoseconds. * @@ -128,6 +131,7 @@ struct ptp_clock_info { struct ptp_pin_desc *pin_config; int (*adjfine)(struct ptp_clock_info *ptp, long scaled_ppm); int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta); + int (*adjphase)(struct ptp_clock_info *ptp, s32 phase); int (*adjtime)(struct ptp_clock_info *ptp, s64 delta); int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts); int (*gettimex64)(struct ptp_clock_info *ptp, struct timespec64 *ts, -- cgit v1.2.3 From efbe3c2493d2f7a1e1a753780fe727b34709ebd2 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 30 Apr 2020 07:41:33 -0700 Subject: fs: Remove unneeded IS_DAX() check in io_is_direct() Remove the check because DAX now has it's own read/write methods and file systems which support DAX check IS_DAX() prior to IOCB_DIRECT on their own. Therefore, it does not matter if the file state is DAX when the iocb flags are created. Also remove io_is_direct() as it is just a simple flag check. Reviewed-by: Dave Chinner Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Ira Weiny Signed-off-by: Darrick J. Wong --- include/linux/fs.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..a87cc5845a02 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3394,11 +3394,6 @@ extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); -static inline bool io_is_direct(struct file *filp) -{ - return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); -} - static inline bool vma_is_dax(const struct vm_area_struct *vma) { return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); @@ -3423,7 +3418,7 @@ static inline int iocb_flags(struct file *file) int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; - if (io_is_direct(file)) + if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host)) res |= IOCB_DSYNC; -- cgit v1.2.3 From a711d91cd97e6c9a554ccd1652527a7f36661857 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 25 Apr 2020 09:57:00 +0200 Subject: block: add a cdrom_device_info pointer to struct gendisk Add a pointer to the CDROM information structure to struct gendisk. This will allow various removable media file systems to call directly into the CDROM layer instead of abusing ioctls with kernel pointers. Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 2 +- include/linux/genhd.h | 9 +++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 528271c60018..4f74ce050253 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -104,7 +104,7 @@ extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi, unsigned int clearing); extern int cdrom_media_changed(struct cdrom_device_info *); -extern int register_cdrom(struct cdrom_device_info *cdi); +extern int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi); extern void unregister_cdrom(struct cdrom_device_info *cdi); typedef struct { diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 058d895544c7..f9c226f9546a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -217,11 +217,20 @@ struct gendisk { #ifdef CONFIG_BLK_DEV_INTEGRITY struct kobject integrity_kobj; #endif /* CONFIG_BLK_DEV_INTEGRITY */ +#if IS_ENABLED(CONFIG_CDROM) + struct cdrom_device_info *cdi; +#endif int node_id; struct badblocks *bb; struct lockdep_map lockdep_map; }; +#if IS_REACHABLE(CONFIG_CDROM) +#define disk_to_cdi(disk) ((disk)->cdi) +#else +#define disk_to_cdi(disk) NULL +#endif + static inline struct gendisk *part_to_disk(struct hd_struct *part) { if (likely(part)) { -- cgit v1.2.3 From 4c3cfcce45152309c2031b3b87bcf10e4f3899e1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 25 Apr 2020 09:57:02 +0200 Subject: cdrom: factor out a cdrom_read_tocentry helper Factor out a version of the CDROMREADTOCENTRY ioctl handler that can be called directly from kernel space. Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 4f74ce050253..008c4d79fa33 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -94,6 +94,9 @@ struct cdrom_device_ops { struct packet_command *); }; +int cdrom_read_tocentry(struct cdrom_device_info *cdi, + struct cdrom_tocentry *entry); + /* the general block_device operations structure: */ extern int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t mode); -- cgit v1.2.3 From eaf8e3e4b54a8b778257fc3921ad8f793c941882 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 25 Apr 2020 09:57:03 +0200 Subject: cdrom: factor out a cdrom_multisession helper Factor out a version of the CDROMMULTISESSION ioctl handler that can be called directly from kernel space. Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 008c4d79fa33..8543fa59da72 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -94,6 +94,8 @@ struct cdrom_device_ops { struct packet_command *); }; +int cdrom_multisession(struct cdrom_device_info *cdi, + struct cdrom_multisession *info); int cdrom_read_tocentry(struct cdrom_device_info *cdi, struct cdrom_tocentry *entry); -- cgit v1.2.3 From b86cd700edd3bfe27f631649727b7796067bb3fd Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 4 May 2020 19:27:00 +0200 Subject: net: add helper eth_hw_addr_crc Several drivers use the same code as basis for filter hashes. Therefore let's factor it out to a helper. This way drivers don't have to access struct netdev_hw_addr internals. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 8801f1f986e5..2e5debc0373c 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -265,6 +266,17 @@ static inline void eth_hw_addr_random(struct net_device *dev) eth_random_addr(dev->dev_addr); } +/** + * eth_hw_addr_crc - Calculate CRC from netdev_hw_addr + * @ha: pointer to hardware address + * + * Calculate CRC from a hardware address as basis for filter hashes. + */ +static inline u32 eth_hw_addr_crc(struct netdev_hw_addr *ha) +{ + return ether_crc(ETH_ALEN, ha->addr); +} + /** * ether_addr_copy - Copy an Ethernet address * @dst: Pointer to a six-byte array Ethernet address destination -- cgit v1.2.3 From 1a33e10e4a95cb109ff1145098175df3113313ef Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 2 May 2020 22:22:19 -0700 Subject: net: partially revert dynamic lockdep key changes This patch reverts the folowing commits: commit 064ff66e2bef84f1153087612032b5b9eab005bd "bonding: add missing netdev_update_lockdep_key()" commit 53d374979ef147ab51f5d632dfe20b14aebeccd0 "net: avoid updating qdisc_xmit_lock_key in netdev_update_lockdep_key()" commit 1f26c0d3d24125992ab0026b0dab16c08df947c7 "net: fix kernel-doc warning in " commit ab92d68fc22f9afab480153bd82a20f6e2533769 "net: core: add generic lockdep keys" but keeps the addr_list_lock_key because we still lock addr_list_lock nestedly on stack devices, unlikely xmit_lock this is safe because we don't take addr_list_lock on any fast path. Reported-and-tested-by: syzbot+aaa6fa4949cc5d9b7b25@syzkaller.appspotmail.com Cc: Dmitry Vyukov Cc: Taehee Yoo Signed-off-by: Cong Wang Acked-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5a8d40f1ffe2..7725efd6e48a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1805,13 +1805,11 @@ enum netdev_priv_flags { * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. - * @qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock - * spinlock - * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount - * @qdisc_xmit_lock_key: lockdep class annotating - * netdev_queue->_xmit_lock spinlock + * * @addr_list_lock_key: lockdep class annotating * net_device->addr_list_lock spinlock + * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock + * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount * * @proto_down: protocol port state information can be sent to the * switch driver and used to set the phys state of the @@ -2112,10 +2110,9 @@ struct net_device { #endif struct phy_device *phydev; struct sfp_bus *sfp_bus; - struct lock_class_key qdisc_tx_busylock_key; - struct lock_class_key qdisc_running_key; - struct lock_class_key qdisc_xmit_lock_key; struct lock_class_key addr_list_lock_key; + struct lock_class_key *qdisc_tx_busylock; + struct lock_class_key *qdisc_running_key; bool proto_down; unsigned wol_enabled:1; @@ -2200,6 +2197,20 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, f(dev, &dev->_tx[i], arg); } +#define netdev_lockdep_set_classes(dev) \ +{ \ + static struct lock_class_key qdisc_tx_busylock_key; \ + static struct lock_class_key qdisc_running_key; \ + static struct lock_class_key qdisc_xmit_lock_key; \ + unsigned int i; \ + \ + (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ + (dev)->qdisc_running_key = &qdisc_running_key; \ + for (i = 0; i < (dev)->num_tx_queues; i++) \ + lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ + &qdisc_xmit_lock_key); \ +} + u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, -- cgit v1.2.3 From d26c0cc53950464a24adfa76867f1d71f0cbbea6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 30 Apr 2020 23:30:47 +0200 Subject: bpf: Avoid gcc-10 stringop-overflow warning in struct bpf_prog gcc-10 warns about accesses to zero-length arrays: kernel/bpf/core.c: In function 'bpf_patch_insn_single': cc1: warning: writing 8 bytes into a region of size 0 [-Wstringop-overflow=] In file included from kernel/bpf/core.c:21: include/linux/filter.h:550:20: note: at offset 0 to object 'insnsi' with size 0 declared here 550 | struct bpf_insn insnsi[0]; | ^~~~~~ In this case, we really want to have two flexible-array members, but that is not possible. Removing the union to make insnsi a flexible-array member while leaving insns as a zero-length array fixes the warning, as nothing writes to the other one in that way. This trick only works on linux-3.18 or higher, as older versions had additional members in the union. Fixes: 60a3b2253c41 ("net: bpf: make eBPF interpreter images read-only") Signed-off-by: Arnd Bergmann Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200430213101.135134-6-arnd@arndb.de --- include/linux/filter.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index af37318bb1c5..73d06a39e2d6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -545,10 +545,8 @@ struct bpf_prog { unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); /* Instructions for interpreter */ - union { - struct sock_filter insns[0]; - struct bpf_insn insnsi[0]; - }; + struct sock_filter insns[0]; + struct bpf_insn insnsi[]; }; struct sk_filter { -- cgit v1.2.3 From d8e81bc3e87c9e7994f5bf24e215a607899ca470 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 15 Apr 2020 16:45:16 +0200 Subject: docs: dt: convert usage-model.txt to ReST - Add a SPDX header; - Adjust document title; - Use footnoote markups; - Some whitespace fixes and new line breaks; - Mark literal blocks as such; - Add it to devicetree/index.rst. Signed-off-by: Mauro Carvalho Chehab Acked-by: Lee Jones Signed-off-by: Rob Herring --- include/linux/mfd/core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index d01d1299e49d..21718c8b2b48 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -74,7 +74,7 @@ struct mfd_cell { /* * Device Tree compatible string - * See: Documentation/devicetree/usage-model.txt Chapter 2.2 for details + * See: Documentation/devicetree/usage-model.rst Chapter 2.2 for details */ const char *of_compatible; -- cgit v1.2.3 From 17309a6a43561bd7f4d4b51d7987225eb2b13d05 Mon Sep 17 00:00:00 2001 From: Tao Ren Date: Sun, 15 Mar 2020 12:16:28 -0700 Subject: usb: gadget: add "usb_validate_langid" function The USB LANGID validation code in "check_user_usb_string" function is moved to "usb_validate_langid" function which can be used by other usb gadget drivers. Signed-off-by: Tao Ren Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 9411c08a5c7e..e959c09a97c9 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -773,6 +773,9 @@ struct usb_gadget_string_container { /* put descriptor for string with that id into buf (buflen >= 256) */ int usb_gadget_get_string(const struct usb_gadget_strings *table, int id, u8 *buf); +/* check if the given language identifier is valid */ +bool usb_validate_langid(u16 langid); + /*-------------------------------------------------------------------------*/ /* utility to simplify managing config descriptors */ -- cgit v1.2.3 From 4cbf38511a007867def958872203ae8adb8e2351 Mon Sep 17 00:00:00 2001 From: Sai Praneeth Prakhya Date: Wed, 29 Apr 2020 15:36:40 +0200 Subject: iommu: Add def_domain_type() callback in iommu_ops Some devices are reqired to use a specific type (identity or dma) of default domain when they are used with a vendor iommu. When the system level default domain type is different from it, the vendor iommu driver has to request a new default domain with iommu_request_dma_domain_for_dev() and iommu_request_dm_for_dev() in the add_dev() callback. Unfortunately, these two helpers only work when the group hasn't been assigned to any other devices, hence, some vendor iommu driver has to use a private domain if it fails to request a new default one. This adds def_domain_type() callback in the iommu_ops, so that any special requirement of default domain for a device could be aware by the iommu generic layer. Signed-off-by: Sai Praneeth Prakhya Signed-off-by: Lu Baolu [ jroedel@suse.de: Added iommu_get_def_domain_type() function and use it to allocate the default domain ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Tested-by: Marek Szyprowski Acked-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200429133712.31431-3-joro@8bytes.org Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7ef8b0bda695..1f027b07e499 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -248,6 +248,10 @@ struct iommu_iotlb_gather { * @cache_invalidate: invalidate translation caches * @sva_bind_gpasid: bind guest pasid and mm * @sva_unbind_gpasid: unbind guest pasid and mm + * @def_domain_type: device default domain type, return value: + * - IOMMU_DOMAIN_IDENTITY: must use an identity domain + * - IOMMU_DOMAIN_DMA: must use a dma domain + * - 0: use the default setting * @pgsize_bitmap: bitmap of all possible supported page sizes * @owner: Driver module providing these ops */ @@ -318,6 +322,8 @@ struct iommu_ops { int (*sva_unbind_gpasid)(struct device *dev, int pasid); + int (*def_domain_type)(struct device *dev); + unsigned long pgsize_bitmap; struct module *owner; }; -- cgit v1.2.3 From a6a4c7e2c5b8b981d1c546a393ff21f2112468c3 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 29 Apr 2020 15:36:45 +0200 Subject: iommu: Add probe_device() and release_device() call-backs Add call-backs to 'struct iommu_ops' as an alternative to the add_device() and remove_device() call-backs, which will be removed when all drivers are converted. The new call-backs will not setup IOMMU groups and domains anymore, so also add a probe_finalize() call-back where the IOMMU driver can do per-device setup work which require the device to be set up with a group and a domain. Signed-off-by: Joerg Roedel Tested-by: Marek Szyprowski Acked-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200429133712.31431-8-joro@8bytes.org Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 1f027b07e499..30170d191e5e 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -225,6 +225,10 @@ struct iommu_iotlb_gather { * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping * @remove_device: remove device from iommu grouping + * @probe_device: Add device to iommu driver handling + * @release_device: Remove device from iommu driver handling + * @probe_finalize: Do final setup work after the device is added to an IOMMU + * group and attached to the groups domain * @device_group: find iommu group for a particular device * @domain_get_attr: Query domain attributes * @domain_set_attr: Change domain attributes @@ -275,6 +279,9 @@ struct iommu_ops { phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); int (*add_device)(struct device *dev); void (*remove_device)(struct device *dev); + struct iommu_device *(*probe_device)(struct device *dev); + void (*release_device)(struct device *dev); + void (*probe_finalize)(struct device *dev); struct iommu_group *(*device_group)(struct device *dev); int (*domain_get_attr)(struct iommu_domain *domain, enum iommu_attr attr, void *data); @@ -375,6 +382,7 @@ struct iommu_fault_param { * * @fault_param: IOMMU detected device fault reporting data * @fwspec: IOMMU fwspec data + * @iommu_dev: IOMMU device this device is linked to * @priv: IOMMU Driver private data * * TODO: migrate other per device data pointers under iommu_dev_data, e.g. @@ -384,6 +392,7 @@ struct dev_iommu { struct mutex lock; struct iommu_fault_param *fault_param; struct iommu_fwspec *fwspec; + struct iommu_device *iommu_dev; void *priv; }; -- cgit v1.2.3 From 5012c3968537e2ffecbdb2eba3479bf9fb9e5597 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 29 Apr 2020 15:36:51 +0200 Subject: iommu: Export bus_iommu_probe() and make is safe for re-probing Add a check to the bus_iommu_probe() call-path to make sure it ignores devices which have already been successfully probed. Then export the bus_iommu_probe() function so it can be used by IOMMU drivers. Signed-off-by: Joerg Roedel Tested-by: Marek Szyprowski Acked-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200429133712.31431-14-joro@8bytes.org Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 30170d191e5e..fea1622408ad 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -445,6 +445,7 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather) #define IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER 6 /* Post Driver unbind */ extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops); +extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); -- cgit v1.2.3 From 3eeeb45c6d0444b368cdeba9bdafa8bbcf5370d1 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 29 Apr 2020 15:37:10 +0200 Subject: iommu: Remove add_device()/remove_device() code-paths All drivers are converted to use the probe/release_device() call-backs, so the add_device/remove_device() pointers are unused and the code using them can be removed. Signed-off-by: Joerg Roedel Tested-by: Marek Szyprowski Acked-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200429133712.31431-33-joro@8bytes.org Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index fea1622408ad..dd076366383f 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -223,8 +223,6 @@ struct iommu_iotlb_gather { * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue * @iova_to_phys: translate iova to physical address - * @add_device: add device to iommu grouping - * @remove_device: remove device from iommu grouping * @probe_device: Add device to iommu driver handling * @release_device: Remove device from iommu driver handling * @probe_finalize: Do final setup work after the device is added to an IOMMU @@ -277,8 +275,6 @@ struct iommu_ops { void (*iotlb_sync)(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather); phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); - int (*add_device)(struct device *dev); - void (*remove_device)(struct device *dev); struct iommu_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); void (*probe_finalize)(struct device *dev); -- cgit v1.2.3 From 1b032ec1ecbce6047af7d11c9db432e237cb17d8 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 29 Apr 2020 15:37:12 +0200 Subject: iommu: Unexport iommu_group_get_for_dev() The function is now only used in IOMMU core code and shouldn't be used outside of it anyway, so remove the export for it. Signed-off-by: Joerg Roedel Tested-by: Marek Szyprowski Acked-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200429133712.31431-35-joro@8bytes.org Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index dd076366383f..7cfd2dddb49d 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -527,7 +527,6 @@ extern int iommu_page_response(struct device *dev, struct iommu_page_response *msg); extern int iommu_group_id(struct iommu_group *group); -extern struct iommu_group *iommu_group_get_for_dev(struct device *dev); extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *); extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr, -- cgit v1.2.3 From 79622f372b8679916bf4e38aabc6df2659d1e109 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 27 Apr 2020 19:49:12 +0100 Subject: i2c: pxa: move private definitions to i2c-pxa.c Move driver-private definitions out of the i2c-pxa.h platform data header file into the driver itself. Nothing outside of the driver makes use of these constants. Signed-off-by: Russell King Signed-off-by: Wolfram Sang --- include/linux/platform_data/i2c-pxa.h | 48 ----------------------------------- 1 file changed, 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/i2c-pxa.h b/include/linux/platform_data/i2c-pxa.h index 6a9b28399b39..24953981bd9f 100644 --- a/include/linux/platform_data/i2c-pxa.h +++ b/include/linux/platform_data/i2c-pxa.h @@ -7,54 +7,6 @@ #ifndef _I2C_PXA_H_ #define _I2C_PXA_H_ -#if 0 -#define DEF_TIMEOUT 3 -#else -/* need a longer timeout if we're dealing with the fact we may well be - * looking at a multi-master environment -*/ -#define DEF_TIMEOUT 32 -#endif - -#define BUS_ERROR (-EREMOTEIO) -#define XFER_NAKED (-ECONNREFUSED) -#define I2C_RETRY (-2000) /* an error has occurred retry transmit */ - -/* ICR initialize bit values -* -* 15. FM 0 (100 Khz operation) -* 14. UR 0 (No unit reset) -* 13. SADIE 0 (Disables the unit from interrupting on slave addresses -* matching its slave address) -* 12. ALDIE 0 (Disables the unit from interrupt when it loses arbitration -* in master mode) -* 11. SSDIE 0 (Disables interrupts from a slave stop detected, in slave mode) -* 10. BEIE 1 (Enable interrupts from detected bus errors, no ACK sent) -* 9. IRFIE 1 (Enable interrupts from full buffer received) -* 8. ITEIE 1 (Enables the I2C unit to interrupt when transmit buffer empty) -* 7. GCD 1 (Disables i2c unit response to general call messages as a slave) -* 6. IUE 0 (Disable unit until we change settings) -* 5. SCLE 1 (Enables the i2c clock output for master mode (drives SCL) -* 4. MA 0 (Only send stop with the ICR stop bit) -* 3. TB 0 (We are not transmitting a byte initially) -* 2. ACKNAK 0 (Send an ACK after the unit receives a byte) -* 1. STOP 0 (Do not send a STOP) -* 0. START 0 (Do not send a START) -* -*/ -#define I2C_ICR_INIT (ICR_BEIE | ICR_IRFIE | ICR_ITEIE | ICR_GCD | ICR_SCLE) - -/* I2C status register init values - * - * 10. BED 1 (Clear bus error detected) - * 9. SAD 1 (Clear slave address detected) - * 7. IRF 1 (Clear IDBR Receive Full) - * 6. ITE 1 (Clear IDBR Transmit Empty) - * 5. ALD 1 (Clear Arbitration Loss Detected) - * 4. SSD 1 (Clear Slave Stop Detected) - */ -#define I2C_ISR_INIT 0x7FF /* status register init */ - struct i2c_pxa_platform_data { unsigned int class; unsigned int use_pio :1; -- cgit v1.2.3 From 3d9231e69831551da3a78a618b31702ea4dedd5e Mon Sep 17 00:00:00 2001 From: Rajendra Nayak Date: Sun, 3 May 2020 17:34:24 +0530 Subject: tty: serial: qcom_geni_serial: Use OPP API to set clk/perf state geni serial needs to express a perforamnce state requirement on CX powerdomain depending on the frequency of the clock rates. Use OPP table from DT to register with OPP framework and use dev_pm_opp_set_rate() to set the clk/perf state. Signed-off-by: Rajendra Nayak Reviewed-by: Matthias Kaehlcke Cc: Greg Kroah-Hartman Cc: Akash Asthana Cc: linux-serial@vger.kernel.org Link: https://lore.kernel.org/r/1588507469-31889-2-git-send-email-rnayak@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- include/linux/qcom-geni-se.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index dd464943f717..6b78094a4e23 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -33,6 +33,8 @@ struct clk; * @clk: Handle to the core serial engine clock * @num_clk_levels: Number of valid clock levels in clk_perf_tbl * @clk_perf_tbl: Table of clock frequency input to serial engine clock + * @opp_table: Pointer to the OPP table + * @has_opp_table: Specifies if the SE has an OPP table */ struct geni_se { void __iomem *base; @@ -41,6 +43,8 @@ struct geni_se { struct clk *clk; unsigned int num_clk_levels; unsigned long *clk_perf_tbl; + struct opp_table *opp_table; + bool has_opp_table; }; /* Common SE registers */ -- cgit v1.2.3 From efc930fa1d844869eb65586f8cdd6a7837db3607 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 27 Apr 2020 23:16:55 +0200 Subject: docs: filesystems: caching/netfs-api.txt: convert it to ReST - Add a SPDX header; - Adjust document and section titles; - Some whitespace fixes and new line breaks; - Mark literal blocks as such; - Add it to filesystems/caching/index.rst. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/cfe4cb1bf8e1f0093d44c30801ec42e74721e543.1588021877.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/fscache.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index ad044c0cb1f3..a1c928fe98e7 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -6,7 +6,7 @@ * * NOTE!!! See: * - * Documentation/filesystems/caching/netfs-api.txt + * Documentation/filesystems/caching/netfs-api.rst * * for a description of the network filesystem interface declared here. */ @@ -233,7 +233,7 @@ extern void __fscache_enable_cookie(struct fscache_cookie *, const void *, loff_ * * Register a filesystem as desiring caching services if they're available. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -253,7 +253,7 @@ int fscache_register_netfs(struct fscache_netfs *netfs) * Indicate that a filesystem no longer desires caching services for the * moment. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -270,7 +270,7 @@ void fscache_unregister_netfs(struct fscache_netfs *netfs) * Acquire a specific cache referral tag that can be used to select a specific * cache in which to cache an index. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -288,7 +288,7 @@ struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name) * * Release a reference to a cache referral tag previously looked up. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -315,7 +315,7 @@ void fscache_release_cache_tag(struct fscache_cache_tag *tag) * that can be used to locate files. This is done by requesting a cookie for * each index in the path to the file. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -351,7 +351,7 @@ struct fscache_cookie *fscache_acquire_cookie( * provided to update the auxiliary data in the cache before the object is * disconnected. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -394,7 +394,7 @@ int fscache_check_consistency(struct fscache_cookie *cookie, * cookie. The auxiliary data on the cookie will be updated first if @aux_data * is set. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -410,7 +410,7 @@ void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data) * * Permit data-storage cache objects to be pinned in the cache. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -425,7 +425,7 @@ int fscache_pin_cookie(struct fscache_cookie *cookie) * * Permit data-storage cache objects to be unpinned from the cache. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -441,7 +441,7 @@ void fscache_unpin_cookie(struct fscache_cookie *cookie) * changed. This includes the data size. These attributes will be obtained * through the get_attr() cookie definition op. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -463,7 +463,7 @@ int fscache_attr_changed(struct fscache_cookie *cookie) * * This can be called with spinlocks held. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -479,7 +479,7 @@ void fscache_invalidate(struct fscache_cookie *cookie) * * Wait for the invalidation of an object to complete. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -498,7 +498,7 @@ void fscache_wait_on_invalidate(struct fscache_cookie *cookie) * cookie so that a write to that object within the space can always be * honoured. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -533,7 +533,7 @@ int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size) * Else, if the page is unbacked, -ENODATA is returned and a block may have * been allocated in the cache. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -582,7 +582,7 @@ int fscache_read_or_alloc_page(struct fscache_cookie *cookie, * regard to different pages, the return values are prioritised in that order. * Any pages submitted for reading are removed from the pages list. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -617,7 +617,7 @@ int fscache_read_or_alloc_pages(struct fscache_cookie *cookie, * Else, a block will be allocated if one wasn't already, and 0 will be * returned * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -667,7 +667,7 @@ void fscache_readpages_cancel(struct fscache_cookie *cookie, * be cleared at the completion of the write to indicate the success or failure * of the operation. Note that the completion may happen before the return. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -693,7 +693,7 @@ int fscache_write_page(struct fscache_cookie *cookie, * Note that this cannot cancel any outstanding I/O operations between this * page and the cache. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -711,7 +711,7 @@ void fscache_uncache_page(struct fscache_cookie *cookie, * * Ask the cache if a page is being written to the cache. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline @@ -731,7 +731,7 @@ bool fscache_check_page_write(struct fscache_cookie *cookie, * Ask the cache to wake us up when a page is no longer being written to the * cache. * - * See Documentation/filesystems/caching/netfs-api.txt for a complete + * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline -- cgit v1.2.3 From 0e822145b564204cd5e9dd67a7fd37d4a7b8253b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 27 Apr 2020 23:16:58 +0200 Subject: docs: filesystems: caching/backend-api.txt: convert it to ReST - Add a SPDX header; - Adjust document and section titles; - Some whitespace fixes and new line breaks; - Mark literal blocks as such; - Add table markups; - Add it to filesystems/caching/index.rst. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/5d0a61abaa87bfe913b9e2f321e74ef7af0f3dfc.1588021877.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/fscache-cache.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index d5ba431b5d63..ce0b5fbf239d 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -6,7 +6,7 @@ * * NOTE!!! See: * - * Documentation/filesystems/caching/backend-api.txt + * Documentation/filesystems/caching/backend-api.rst * * for a description of the cache backend interface declared here. */ @@ -454,7 +454,7 @@ static inline void fscache_object_lookup_error(struct fscache_object *object) * Set the maximum size an object is permitted to reach, implying the highest * byte that may be written. Intended to be called by the attr_changed() op. * - * See Documentation/filesystems/caching/backend-api.txt for a complete + * See Documentation/filesystems/caching/backend-api.rst for a complete * description. */ static inline -- cgit v1.2.3 From 791a17ee19736fc6d4e35c4bf9f8efd1001be77c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 27 Apr 2020 23:17:09 +0200 Subject: docs: filesystems: convert mount_api.txt to ReST - Add a SPDX header; - Adjust document and section titles; - Some whitespace fixes and new line breaks; - Mark literal blocks as such; - Add table markups; - Add lists markups; - Add it to filesystems/index.rst. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/32332c1659a28c22561cb5e64162c959856066b4.1588021877.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/fs_context.h | 2 +- include/linux/lsm_hooks.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index e6c3e4c61dad..5f24fcbfbfb4 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -85,7 +85,7 @@ struct p_log { * Superblock creation fills in ->root whereas reconfiguration begins with this * already set. * - * See Documentation/filesystems/mount_api.txt + * See Documentation/filesystems/mount_api.rst */ struct fs_context { const struct fs_context_operations *ops; diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 988ca0df7824..44d5422c18e4 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -77,7 +77,7 @@ * state. This is called immediately after commit_creds(). * * Security hooks for mount using fs_context. - * [See also Documentation/filesystems/mount_api.txt] + * [See also Documentation/filesystems/mount_api.rst] * * @fs_context_dup: * Allocate and attach a security structure to sc->security. This pointer -- cgit v1.2.3 From 982649915d626bba8753c04e994e5a6650523c64 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 27 Apr 2020 23:17:21 +0200 Subject: docs: filesystems: convert configfs.txt to ReST - Add a SPDX header; - Adjust document and section titles; - Use copyright symbol; - Some whitespace fixes and new line breaks; - Mark literal blocks as such; - Add it to filesystems/index.rst. Also, as this file is alone on its own dir, and it doesn't seem too likely that other documents will follow it, let's move it to the filesystems/ root documentation dir. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/c2424ec2ad4d735751434ff7f52144c44aa02d5a.1588021877.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/configfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/configfs.h b/include/linux/configfs.h index fa9490a8874c..2e8c69b43c64 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -13,7 +13,7 @@ * * configfs Copyright (C) 2005 Oracle. All rights reserved. * - * Please read Documentation/filesystems/configfs/configfs.txt before using + * Please read Documentation/filesystems/configfs.rst before using * the configfs interface, ESPECIALLY the parts about reference counts and * item destructors. */ -- cgit v1.2.3 From 9b06fc39084e161da84a399b6b5dc524e673f51e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Apr 2020 15:58:10 -0500 Subject: ARM: vexpress: Move vexpress_flags_set() into arch code vexpress_flags_set() is only used by the platform SMP related code and has nothing to do with the vexpress-sysreg MFD driver other than both access the same h/w block. It's also only needed for 32-bit systems and must be built-in for them. Let's move vexpress_flags_set() closer to where it is being used. This will allow for vexpress-sysreg to be built as a module. Cc: Lorenzo Pieralisi Cc: Linus Walleij Reviewed-by: Sudeep Holla Acked-by: Arnd Bergmann Acked-by: Liviu Dudau Acked-by: Lee Jones Signed-off-by: Rob Herring --- include/linux/vexpress.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h index 0e130b5077a5..2ec7992b054c 100644 --- a/include/linux/vexpress.h +++ b/include/linux/vexpress.h @@ -40,8 +40,4 @@ struct device *vexpress_config_bridge_register(struct device *parent, struct regmap *devm_regmap_init_vexpress_config(struct device *dev); -/* Platform control */ - -void vexpress_flags_set(u32 data); - #endif -- cgit v1.2.3 From c3b3f52476412a3899f2c65b220075aceb18dd2c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 5 May 2020 12:12:53 +0200 Subject: signal: refactor copy_siginfo_to_user32 Factor out a copy_siginfo_to_external32 helper from copy_siginfo_to_user32 that fills out the compat_siginfo, but does so on a kernel space data structure. With that we can let architectures override copy_siginfo_to_user32 with their own implementations using copy_siginfo_to_external32. That allows moving the x32 SIGCHLD purely to x86 architecture code. As a nice side effect copy_siginfo_to_external32 also comes in handy for avoiding a set_fs() call in the coredump code later on. Contains improvements from Eric W. Biederman and Arnd Bergmann . Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 0480ba4db592..e90100c0de72 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -402,8 +402,15 @@ long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size); long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, unsigned long bitmap_size); -int copy_siginfo_from_user32(kernel_siginfo_t *to, const struct compat_siginfo __user *from); -int copy_siginfo_to_user32(struct compat_siginfo __user *to, const kernel_siginfo_t *from); +void copy_siginfo_to_external32(struct compat_siginfo *to, + const struct kernel_siginfo *from); +int copy_siginfo_from_user32(kernel_siginfo_t *to, + const struct compat_siginfo __user *from); +int __copy_siginfo_to_user32(struct compat_siginfo __user *to, + const kernel_siginfo_t *from); +#ifndef copy_siginfo_to_user32 +#define copy_siginfo_to_user32 __copy_siginfo_to_user32 +#endif int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); -- cgit v1.2.3 From fa4751f454e6b51ef93babfd8b6c8b43a65c9db2 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 5 May 2020 12:12:54 +0200 Subject: binfmt_elf: remove the set_fs in fill_siginfo_note The code in binfmt_elf.c is differnt from the rest of the code that processes siginfo, as it sends siginfo from a kernel buffer to a file rather than from kernel memory to userspace buffers. To remove it's use of set_fs the code needs some different siginfo helpers. Add the helper copy_siginfo_to_external to copy from the kernel's internal siginfo layout to a buffer in the siginfo layout that userspace expects. Modify fill_siginfo_note to use copy_siginfo_to_external instead of set_fs and copy_siginfo_to_user. Update compat_binfmt_elf.c to use the previously added copy_siginfo_to_external32 to handle the compat case. Signed-off-by: "Eric W. Biederman" Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/signal.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 05bacd2ab135..6bb1a3f0258c 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -24,6 +24,14 @@ static inline void clear_siginfo(kernel_siginfo_t *info) #define SI_EXPANSION_SIZE (sizeof(struct siginfo) - sizeof(struct kernel_siginfo)) +static inline void copy_siginfo_to_external(siginfo_t *to, + const kernel_siginfo_t *from) +{ + memcpy(to, from, sizeof(*from)); + memset(((char *)to) + sizeof(struct kernel_siginfo), 0, + SI_EXPANSION_SIZE); +} + int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from); int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from); -- cgit v1.2.3 From d755cdb1b9d7e1b645e176b97eb137194bbe8cf9 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Thu, 23 Jan 2020 14:00:26 +0800 Subject: usb: chipidea: introduce CI_HDRC_CONTROLLER_VBUS_EVENT glue layer use Some vendors glue layer need to handle some events for vbus, eg, some i.mx platforms (imx7d, imx8mm, imx8mn, etc) needs vbus event to handle charger detection, its charger detection is finished at glue layer code, but not at USB PHY driver. Signed-off-by: Peter Chen --- include/linux/usb/chipidea.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index edd89b7c8f18..54167a2d28ea 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -67,6 +67,7 @@ struct ci_hdrc_platform_data { #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 #define CI_HDRC_IMX_HSIC_ACTIVE_EVENT 2 #define CI_HDRC_IMX_HSIC_SUSPEND_EVENT 3 +#define CI_HDRC_CONTROLLER_VBUS_EVENT 4 int (*notify_event) (struct ci_hdrc *ci, unsigned event); struct regulator *reg_vbus; struct usb_otg_caps ci_otg_caps; -- cgit v1.2.3 From 57a29df341466b5cca43ba3d2d7064426727d7c3 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Sat, 25 Apr 2020 02:49:14 +0800 Subject: iopoll: Introduce read_poll_timeout_atomic macro Like read_poll_timeout, an atomic variant for multiple parameter read function can be useful. Will be used by a later patch. Signed-off-by: Kai-Heng Feng Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20200424184918.30360-1-kai.heng.feng@canonical.com --- include/linux/iopoll.h | 62 ++++++++++++++++++++++++++++++++++---------------- 1 file changed, 43 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index cb20c733b15a..bc89ac625f26 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -57,6 +57,48 @@ (cond) ? 0 : -ETIMEDOUT; \ }) +/** + * read_poll_timeout_atomic - Periodically poll an address until a condition is + * met or a timeout occurs + * @op: accessor function (takes @addr as its only argument) + * @addr: Address to poll + * @val: Variable to read the value into + * @cond: Break condition (usually involving @val) + * @delay_us: Time to udelay between reads in us (0 tight-loops). Should + * be less than ~10us since udelay is used (see + * Documentation/timers/timers-howto.rst). + * @timeout_us: Timeout in us, 0 means never timeout + * @delay_before_read: if it is true, delay @delay_us before read. + * + * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @args is stored in @val. + * + * When available, you'll probably want to use one of the specialized + * macros defined below rather than this macro directly. + */ +#define read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, \ + delay_before_read, args...) \ +({ \ + u64 __timeout_us = (timeout_us); \ + unsigned long __delay_us = (delay_us); \ + ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \ + if (delay_before_read && __delay_us) \ + udelay(__delay_us); \ + for (;;) { \ + (val) = op(args); \ + if (cond) \ + break; \ + if (__timeout_us && \ + ktime_compare(ktime_get(), __timeout) > 0) { \ + (val) = op(args); \ + break; \ + } \ + if (__delay_us) \ + udelay(__delay_us); \ + } \ + (cond) ? 0 : -ETIMEDOUT; \ +}) + /** * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs * @op: accessor function (takes @addr as its only argument) @@ -96,25 +138,7 @@ * macros defined below rather than this macro directly. */ #define readx_poll_timeout_atomic(op, addr, val, cond, delay_us, timeout_us) \ -({ \ - u64 __timeout_us = (timeout_us); \ - unsigned long __delay_us = (delay_us); \ - ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \ - for (;;) { \ - (val) = op(addr); \ - if (cond) \ - break; \ - if (__timeout_us && \ - ktime_compare(ktime_get(), __timeout) > 0) { \ - (val) = op(addr); \ - break; \ - } \ - if (__delay_us) \ - udelay(__delay_us); \ - } \ - (cond) ? 0 : -ETIMEDOUT; \ -}) - + read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, false, addr) #define readb_poll_timeout(addr, val, cond, delay_us, timeout_us) \ readx_poll_timeout(readb, addr, val, cond, delay_us, timeout_us) -- cgit v1.2.3 From 0a64f38037cc230e2ad888a74263db6f6588cd90 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 6 May 2020 14:29:02 +0200 Subject: Revert "tty: serial: qcom_geni_serial: Use OPP API to set clk/perf state" This reverts commit 3d9231e69831551da3a78a618b31702ea4dedd5e Rajendra writes: Greg, there are other patches in the series which have a dependency on this patch [1] would it be possible for you to drop this patch and instead ack it so it can be taken via the msm tree? So dropping it from here. Reported-by: Rajendra Nayak Cc: Matthias Kaehlcke Cc: Akash Asthana Signed-off-by: Greg Kroah-Hartman --- include/linux/qcom-geni-se.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index 6b78094a4e23..dd464943f717 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -33,8 +33,6 @@ struct clk; * @clk: Handle to the core serial engine clock * @num_clk_levels: Number of valid clock levels in clk_perf_tbl * @clk_perf_tbl: Table of clock frequency input to serial engine clock - * @opp_table: Pointer to the OPP table - * @has_opp_table: Specifies if the SE has an OPP table */ struct geni_se { void __iomem *base; @@ -43,8 +41,6 @@ struct geni_se { struct clk *clk; unsigned int num_clk_levels; unsigned long *clk_perf_tbl; - struct opp_table *opp_table; - bool has_opp_table; }; /* Common SE registers */ -- cgit v1.2.3 From b720aaa347f227c416e8aed2f12ca62ea4f1cd4e Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 25 Mar 2020 01:43:34 +0300 Subject: firmware: tf: Different way of L2 cache enabling after LP2 suspend MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ASUS TF300T device may not work properly if firmware is asked to fully re-initialize L2 cache after resume from LP2 suspend. The downstream kernel of TF300T uses different opcode to enable cache after resuming from LP2, this opcode also works fine on Nexus 7 and Ouya devices. Supposedly, this may be needed by an older firmware versions. Reported-by: Michał Mirosław Tested-by: Michał Mirosław Tested-by: Jasper Korten Tested-by: David Heidelberg Tested-by: Peter Geis Signed-off-by: Dmitry Osipenko Signed-off-by: Thierry Reding --- include/linux/firmware/trusted_foundations.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firmware/trusted_foundations.h b/include/linux/firmware/trusted_foundations.h index 2549a2db56aa..be5984bda592 100644 --- a/include/linux/firmware/trusted_foundations.h +++ b/include/linux/firmware/trusted_foundations.h @@ -32,6 +32,7 @@ #define TF_PM_MODE_LP1_NO_MC_CLK 2 #define TF_PM_MODE_LP2 3 #define TF_PM_MODE_LP2_NOFLUSH_L2 4 +#define TF_PM_MODE_NONE 5 struct trusted_foundations_platform_data { unsigned int version_major; -- cgit v1.2.3 From 19acd03d95dad1f50d06f28179a1866fca431fed Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 24 Apr 2020 17:47:29 +0200 Subject: kcsan: Add __kcsan_{enable,disable}_current() variants The __kcsan_{enable,disable}_current() variants only call into KCSAN if KCSAN is enabled for the current compilation unit. Note: This is typically not what we want, as we usually want to ensure that even calls into other functions still have KCSAN disabled. These variants may safely be used in header files that are shared between regular kernel code and code that does not link the KCSAN runtime. Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/kcsan-checks.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index ef95ddc49182..7b0b9c44f5f3 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -49,6 +49,7 @@ void kcsan_disable_current(void); * Supports nesting. */ void kcsan_enable_current(void); +void kcsan_enable_current_nowarn(void); /* Safe in uaccess regions. */ /** * kcsan_nestable_atomic_begin - begin nestable atomic region @@ -149,6 +150,7 @@ static inline void __kcsan_check_access(const volatile void *ptr, size_t size, static inline void kcsan_disable_current(void) { } static inline void kcsan_enable_current(void) { } +static inline void kcsan_enable_current_nowarn(void) { } static inline void kcsan_nestable_atomic_begin(void) { } static inline void kcsan_nestable_atomic_end(void) { } static inline void kcsan_flat_atomic_begin(void) { } @@ -165,15 +167,24 @@ static inline void kcsan_end_scoped_access(struct kcsan_scoped_access *sa) { } #endif /* CONFIG_KCSAN */ +#ifdef __SANITIZE_THREAD__ /* - * kcsan_*: Only calls into the runtime when the particular compilation unit has - * KCSAN instrumentation enabled. May be used in header files. + * Only calls into the runtime when the particular compilation unit has KCSAN + * instrumentation enabled. May be used in header files. */ -#ifdef __SANITIZE_THREAD__ #define kcsan_check_access __kcsan_check_access + +/* + * Only use these to disable KCSAN for accesses in the current compilation unit; + * calls into libraries may still perform KCSAN checks. + */ +#define __kcsan_disable_current kcsan_disable_current +#define __kcsan_enable_current kcsan_enable_current_nowarn #else static inline void kcsan_check_access(const volatile void *ptr, size_t size, int type) { } +static inline void __kcsan_enable_current(void) { } +static inline void __kcsan_disable_current(void) { } #endif /** -- cgit v1.2.3 From 6349084746ff4f5f7ebc748e4b2a890f8c57b129 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Wed, 6 May 2020 16:53:13 +0200 Subject: net: phy: add concept of shared storage for PHYs There are packages which contain multiple PHY devices, eg. a quad PHY transceiver. Provide functions to allocate and free shared storage. Usually, a quad PHY contains global registers, which don't belong to any PHY. Provide convenience functions to access these registers. Signed-off-by: Michael Walle Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 89 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 89 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index e2bfb9240587..1d36ac608159 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -25,6 +25,7 @@ #include #include #include +#include #include @@ -227,6 +228,28 @@ struct mdio_bus_stats { struct u64_stats_sync syncp; }; +/* Represents a shared structure between different phydev's in the same + * package, for example a quad PHY. See phy_package_join() and + * phy_package_leave(). + */ +struct phy_package_shared { + int addr; + refcount_t refcnt; + unsigned long flags; + size_t priv_size; + + /* private data pointer */ + /* note that this pointer is shared between different phydevs and + * the user has to take care of appropriate locking. It is allocated + * and freed automatically by phy_package_join() and + * phy_package_leave(). + */ + void *priv; +}; + +/* used as bit number in atomic bitops */ +#define PHY_SHARED_F_INIT_DONE 0 + /* * The Bus class for PHYs. Devices which provide access to * PHYs should register using this structure @@ -278,6 +301,12 @@ struct mii_bus { int reset_delay_us; /* RESET GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; + + /* protect access to the shared element */ + struct mutex shared_lock; + + /* shared state across different PHYs */ + struct phy_package_shared *shared[PHY_MAX_ADDR]; }; #define to_mii_bus(d) container_of(d, struct mii_bus, dev) @@ -478,6 +507,10 @@ struct phy_device { /* For use by PHYs to maintain extra state */ void *priv; + /* shared data pointer */ + /* For use by PHYs inside the same package that need a shared state. */ + struct phy_package_shared *shared; + /* Interrupt and Polling infrastructure */ struct delayed_work state_queue; @@ -1354,6 +1387,10 @@ int phy_ethtool_get_link_ksettings(struct net_device *ndev, int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); +int phy_package_join(struct phy_device *phydev, int addr, size_t priv_size); +void phy_package_leave(struct phy_device *phydev); +int devm_phy_package_join(struct device *dev, struct phy_device *phydev, + int addr, size_t priv_size); #if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); @@ -1406,6 +1443,58 @@ static inline int phy_ethtool_get_stats(struct phy_device *phydev, return 0; } +static inline int phy_package_read(struct phy_device *phydev, u32 regnum) +{ + struct phy_package_shared *shared = phydev->shared; + + if (!shared) + return -EIO; + + return mdiobus_read(phydev->mdio.bus, shared->addr, regnum); +} + +static inline int __phy_package_read(struct phy_device *phydev, u32 regnum) +{ + struct phy_package_shared *shared = phydev->shared; + + if (!shared) + return -EIO; + + return __mdiobus_read(phydev->mdio.bus, shared->addr, regnum); +} + +static inline int phy_package_write(struct phy_device *phydev, + u32 regnum, u16 val) +{ + struct phy_package_shared *shared = phydev->shared; + + if (!shared) + return -EIO; + + return mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val); +} + +static inline int __phy_package_write(struct phy_device *phydev, + u32 regnum, u16 val) +{ + struct phy_package_shared *shared = phydev->shared; + + if (!shared) + return -EIO; + + return __mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val); +} + +static inline bool phy_package_init_once(struct phy_device *phydev) +{ + struct phy_package_shared *shared = phydev->shared; + + if (!shared) + return false; + + return !test_and_set_bit(PHY_SHARED_F_INIT_DONE, &shared->flags); +} + extern struct bus_type mdio_bus_type; struct mdio_board_info { -- cgit v1.2.3 From c6af13d334759c33c14b6fad4c676c6d1dbf9564 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 1 May 2020 23:27:21 +0200 Subject: timer: add fsleep for flexible sleeping Sleeping for a certain amount of time requires use of different functions, depending on the time period. Documentation/timers/timers-howto.rst explains when to use which function, and also checkpatch checks for some potentially problematic cases. So let's create a helper that automatically chooses the appropriate sleep function -> fsleep(), for flexible sleeping If the delay is a constant, then the compiler should be able to ensure that the new helper doesn't create overhead. If the delay is not constant, then the new helper can save some code. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/delay.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/delay.h b/include/linux/delay.h index 8e6828094c1e..5e016a4029d9 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -65,4 +65,15 @@ static inline void ssleep(unsigned int seconds) msleep(seconds * 1000); } +/* see Documentation/timers/timers-howto.rst for the thresholds */ +static inline void fsleep(unsigned long usecs) +{ + if (usecs <= 10) + udelay(usecs); + else if (usecs <= 20000) + usleep_range(usecs, 2 * usecs); + else + msleep(DIV_ROUND_UP(usecs, 1000)); +} + #endif /* defined(_LINUX_DELAY_H) */ -- cgit v1.2.3 From bdbdac7649fac05f88c9f7ab18121a17fb591687 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 5 May 2020 08:35:05 +0200 Subject: ethtool: provide UAPI for PHY master/slave configuration. This UAPI is needed for BroadR-Reach 100BASE-T1 devices. Due to lack of auto-negotiation support, we needed to be able to configure the MASTER-SLAVE role of the port manually or from an application in user space. The same UAPI can be used for 1000BASE-T or MultiGBASE-T devices to force MASTER or SLAVE role. See IEEE 802.3-2018: 22.2.4.3.7 MASTER-SLAVE control register (Register 9) 22.2.4.3.8 MASTER-SLAVE status register (Register 10) 40.5.2 MASTER-SLAVE configuration resolution 45.2.1.185.1 MASTER-SLAVE config value (1.2100.14) 45.2.7.10 MultiGBASE-T AN control 1 register (Register 7.32) The MASTER-SLAVE role affects the clock configuration: ------------------------------------------------------------------------------- When the PHY is configured as MASTER, the PMA Transmit function shall source TX_TCLK from a local clock source. When configured as SLAVE, the PMA Transmit function shall source TX_TCLK from the clock recovered from data stream provided by MASTER. iMX6Q KSZ9031 XXX ------\ /-----------\ /------------\ | | | | | MAC |<----RGMII----->| PHY Slave |<------>| PHY Master | |<--- 125 MHz ---+-<------/ | | \ | ------/ \-----------/ \------------/ ^ \-TX_TCLK ------------------------------------------------------------------------------- Since some clock or link related issues are only reproducible in a specific MASTER-SLAVE-role, MAC and PHY configuration, it is beneficial to provide generic (not 100BASE-T1 specific) interface to the user space for configuration flexibility and trouble shooting. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 1d36ac608159..a2b91b5f9d0a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -477,6 +477,9 @@ struct phy_device { int duplex; int pause; int asym_pause; + u8 master_slave_get; + u8 master_slave_set; + u8 master_slave_state; /* Union of PHY and Attached devices' supported link modes */ /* See ethtool.h for more info */ -- cgit v1.2.3 From b2f75a41eaa6bfc4aa6f6a1faefbf21c2c8d1588 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 9 Apr 2020 17:49:23 -0600 Subject: PCI: host-generic: Eliminate pci_host_common_probe wrappers Most ECAM host drivers are just different pci_ecam_ops which can be DT match table data. That's already the case in some cases, but let's do that for all the ECAM drivers. Then we can use of_device_get_match_data() in pci_host_common_probe() and eliminate the probe wrapper functions and use pci_host_common_probe() directly for probe. Link: https://lore.kernel.org/r/20200409234923.21598-4-robh@kernel.org Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi Acked-by: Bjorn Helgaas Cc: Zhou Wang Cc: Lorenzo Pieralisi Cc: Andrew Murray Cc: Bjorn Helgaas Cc: Will Deacon Cc: Robert Richter Cc: Marc Gonzalez Cc: Mans Rullgard Cc: linux-pci@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org --- include/linux/pci-ecam.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index fd0edb8b8a00..1af5cb02ef7f 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -61,8 +61,7 @@ extern const struct pci_ecam_ops al_pcie_ops; /* Amazon Annapurna Labs PCIe */ #if IS_ENABLED(CONFIG_PCI_HOST_COMMON) /* for DT-based PCI controllers that support ECAM */ -int pci_host_common_probe(struct platform_device *pdev, - const struct pci_ecam_ops *ops); +int pci_host_common_probe(struct platform_device *pdev); int pci_host_common_remove(struct platform_device *pdev); #endif #endif -- cgit v1.2.3 From 565558558985b1d7cd43b21f18c1ad6b232788d0 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Thu, 30 Apr 2020 12:40:03 +0100 Subject: cpu/hotplug: Remove disable_nonboot_cpus() The single user could have called freeze_secondary_cpus() directly. Since this function was a source of confusion, remove it as it's just a pointless wrapper. While at it, rename enable_nonboot_cpus() to thaw_secondary_cpus() to preserve the naming symmetry. Done automatically via: git grep -l enable_nonboot_cpus | xargs sed -i 's/enable_nonboot_cpus/thaw_secondary_cpus/g' Signed-off-by: Qais Yousef Signed-off-by: Thomas Gleixner Cc: "Rafael J. Wysocki" Link: https://lkml.kernel.org/r/20200430114004.17477-1-qais.yousef@arm.com --- include/linux/cpu.h | 12 +++--------- include/linux/smp.h | 4 ++-- 2 files changed, 5 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index beaed2dc269e..9d34dc3b859f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -150,12 +150,7 @@ static inline int freeze_secondary_cpus(int primary) return __freeze_secondary_cpus(primary, true); } -static inline int disable_nonboot_cpus(void) -{ - return __freeze_secondary_cpus(0, false); -} - -void enable_nonboot_cpus(void); +extern void thaw_secondary_cpus(void); static inline int suspend_disable_secondary_cpus(void) { @@ -168,12 +163,11 @@ static inline int suspend_disable_secondary_cpus(void) } static inline void suspend_enable_secondary_cpus(void) { - return enable_nonboot_cpus(); + return thaw_secondary_cpus(); } #else /* !CONFIG_PM_SLEEP_SMP */ -static inline int disable_nonboot_cpus(void) { return 0; } -static inline void enable_nonboot_cpus(void) {} +static inline void thaw_secondary_cpus(void) {} static inline int suspend_disable_secondary_cpus(void) { return 0; } static inline void suspend_enable_secondary_cpus(void) { } #endif /* !CONFIG_PM_SLEEP_SMP */ diff --git a/include/linux/smp.h b/include/linux/smp.h index cbc9162689d0..04019872c7bc 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -227,8 +227,8 @@ static inline int get_boot_cpu_id(void) */ extern void arch_disable_smp_support(void); -extern void arch_enable_nonboot_cpus_begin(void); -extern void arch_enable_nonboot_cpus_end(void); +extern void arch_thaw_secondary_cpus_begin(void); +extern void arch_thaw_secondary_cpus_end(void); void smp_setup_processor_id(void); -- cgit v1.2.3 From fb7fb84a0c4e8021ddecb157802d58241a3f1a40 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Thu, 30 Apr 2020 12:40:04 +0100 Subject: cpu/hotplug: Remove __freeze_secondary_cpus() The refactored function is no longer required as the codepaths that call freeze_secondary_cpus() are all suspend/resume related now. Signed-off-by: Qais Yousef Signed-off-by: Thomas Gleixner Cc: "Rafael J. Wysocki" Link: https://lkml.kernel.org/r/20200430114004.17477-2-qais.yousef@arm.com --- include/linux/cpu.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 9d34dc3b859f..52692587f7fe 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -144,12 +144,7 @@ static inline void get_online_cpus(void) { cpus_read_lock(); } static inline void put_online_cpus(void) { cpus_read_unlock(); } #ifdef CONFIG_PM_SLEEP_SMP -int __freeze_secondary_cpus(int primary, bool suspend); -static inline int freeze_secondary_cpus(int primary) -{ - return __freeze_secondary_cpus(primary, true); -} - +extern int freeze_secondary_cpus(int primary); extern void thaw_secondary_cpus(void); static inline int suspend_disable_secondary_cpus(void) -- cgit v1.2.3 From 3fec4aecb311995189217e64d725cfe84a568de3 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Wed, 6 May 2020 17:42:23 +0100 Subject: kgdb: Fix spurious true from in_dbg_master() Currently there is a small window where a badly timed migration could cause in_dbg_master() to spuriously return true. Specifically if we migrate to a new core after reading the processor id and the previous core takes a breakpoint then we will evaluate true if we read kgdb_active before we get the IPI to bring us to halt. Fix this by checking irqs_disabled() first. Interrupts are always disabled when we are executing the kgdb trap so this is an acceptable prerequisite. This also allows us to replace raw_smp_processor_id() with smp_processor_id() since the short circuit logic will prevent warnings from PREEMPT_DEBUG. Fixes: dcc7871128e9 ("kgdb: core changes to support kdb") Suggested-by: Will Deacon Link: https://lore.kernel.org/r/20200506164223.2875760-1-daniel.thompson@linaro.org Reviewed-by: Douglas Anderson Signed-off-by: Daniel Thompson --- include/linux/kgdb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index b072aeb1fd78..4d6fe87fd38f 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -323,7 +323,7 @@ extern void gdbstub_exit(int status); extern int kgdb_single_step; extern atomic_t kgdb_active; #define in_dbg_master() \ - (raw_smp_processor_id() == atomic_read(&kgdb_active)) + (irqs_disabled() && (smp_processor_id() == atomic_read(&kgdb_active))) extern bool dbg_is_early; extern void __init dbg_late_init(void); extern void kgdb_panic(const char *msg); -- cgit v1.2.3 From 1137a96f9b5a8615296bd319151896c859ead292 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Thu, 7 May 2020 19:06:49 +0800 Subject: kgdb: Return true in kgdb_nmi_poll_knock() Fix the following coccicheck warning: include/linux/kgdb.h:301:54-55: WARNING: return of 0/1 in function 'kgdb_nmi_poll_knock' with return type bool Signed-off-by: Jason Yan Link: https://lore.kernel.org/r/20200507110649.37426-1-yanaijie@huawei.com Signed-off-by: Daniel Thompson --- include/linux/kgdb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 4d6fe87fd38f..c2caee08e418 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -298,7 +298,7 @@ extern bool kgdb_nmi_poll_knock(void); #else static inline int kgdb_register_nmi_console(void) { return 0; } static inline int kgdb_unregister_nmi_console(void) { return 0; } -static inline bool kgdb_nmi_poll_knock(void) { return 1; } +static inline bool kgdb_nmi_poll_knock(void) { return true; } #endif extern int kgdb_register_io_module(struct kgdb_io *local_kgdb_io_ops); -- cgit v1.2.3 From 5d1f2e3c8090c0769ee4a1b920e82277613327fc Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 22 Apr 2020 17:37:34 -0700 Subject: soc: qcom: glink_ssr: Internalize ssr_notifiers Rather than carrying a special purpose blocking notifier for glink_ssr in remoteproc's qcom_common.c, move it into glink_ssr so allow wider reuse of the common one. The rpmsg glink header file is used in preparation for the next patch. Acked-by: Chris Lew Acked-by: Rishabh Bhatnagar Link: https://lore.kernel.org/r/20200423003736.2027371-3-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/rpmsg/qcom_glink.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rpmsg/qcom_glink.h b/include/linux/rpmsg/qcom_glink.h index 96e26d94719f..09daa0acde2c 100644 --- a/include/linux/rpmsg/qcom_glink.h +++ b/include/linux/rpmsg/qcom_glink.h @@ -26,4 +26,10 @@ static inline void qcom_glink_smem_unregister(struct qcom_glink *glink) {} #endif +#if IS_ENABLED(CONFIG_RPMSG_QCOM_GLINK_SSR) +void qcom_glink_ssr_notify(const char *ssr_name); +#else +static inline void qcom_glink_ssr_notify(const char *ssr_name) {} +#endif + #endif -- cgit v1.2.3 From 93bc3feee8bd5fbe29ad27779c5e7b369fd7c80b Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 22 Apr 2020 17:37:35 -0700 Subject: rpmsg: glink: Integrate glink_ssr in qcom_glink In all but the very special case of a system with _only_ glink_rpm, GLINK is dependent on glink_ssr, so move it to rpmsg and combine it with qcom_glink_native in the new qcom_glink kernel module. Acked-by: Chris Lew Acked-by: Rishabh Bhatnagar Link: https://lore.kernel.org/r/20200423003736.2027371-4-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/rpmsg/qcom_glink.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rpmsg/qcom_glink.h b/include/linux/rpmsg/qcom_glink.h index 09daa0acde2c..daded9fddf36 100644 --- a/include/linux/rpmsg/qcom_glink.h +++ b/include/linux/rpmsg/qcom_glink.h @@ -12,6 +12,7 @@ struct qcom_glink; struct qcom_glink *qcom_glink_smem_register(struct device *parent, struct device_node *node); void qcom_glink_smem_unregister(struct qcom_glink *glink); +void qcom_glink_ssr_notify(const char *ssr_name); #else @@ -23,12 +24,6 @@ qcom_glink_smem_register(struct device *parent, } static inline void qcom_glink_smem_unregister(struct qcom_glink *glink) {} - -#endif - -#if IS_ENABLED(CONFIG_RPMSG_QCOM_GLINK_SSR) -void qcom_glink_ssr_notify(const char *ssr_name); -#else static inline void qcom_glink_ssr_notify(const char *ssr_name) {} #endif -- cgit v1.2.3 From 89826cce37542f7950e8f4b9258284805e98430c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 2 Apr 2020 18:04:54 -0500 Subject: exec: Make unlocking exec_update_mutex explict With install_exec_creds updated to follow immediately after setup_new_exec, the failure of unshare_sighand is the only code path where exec_update_mutex is held but not explicitly unlocked. Update that code path to explicitly unlock exec_update_mutex. Remove the unlocking of exec_update_mutex from free_bprm. Reviewed-by: Kees Cook Reviewed-by: Greg Ungerer Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index a345d9fed3d8..6f564b9ad882 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -47,8 +47,7 @@ struct linux_binprm { secureexec:1, /* * Set by flush_old_exec, when exec_mmap has been called. - * This is past the point of no return, when the - * exec_update_mutex has been taken. + * This is past the point of no return. */ called_exec_mmap:1; #ifdef __alpha__ -- cgit v1.2.3 From 1507b7a30ad284a2a136ee79c214c0e86c62da64 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 2 Apr 2020 18:17:50 -0500 Subject: exec: Rename the flag called_exec_mmap point_of_no_return Update the comments and make the code easier to understand by renaming this flag. Reviewed-by: Kees Cook Reviewed-by: Greg Ungerer Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 6f564b9ad882..8f479dad7931 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -46,10 +46,10 @@ struct linux_binprm { */ secureexec:1, /* - * Set by flush_old_exec, when exec_mmap has been called. - * This is past the point of no return. + * Set when errors can no longer be returned to the + * original userspace. */ - called_exec_mmap:1; + point_of_no_return:1; #ifdef __alpha__ unsigned int taso:1; #endif -- cgit v1.2.3 From 96ecee29b0b560662ec082ee9b6f2049f2a79090 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 3 May 2020 06:48:17 -0500 Subject: exec: Merge install_exec_creds into setup_new_exec The two functions are now always called one right after the other so merge them together to make future maintenance easier. Reviewed-by: Kees Cook Reviewed-by: Greg Ungerer Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 8f479dad7931..2a8fddf3574a 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -145,7 +145,6 @@ extern int transfer_args_to_stack(struct linux_binprm *bprm, extern int bprm_change_interp(const char *interp, struct linux_binprm *bprm); extern int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm); -extern void install_exec_creds(struct linux_binprm *bprm); extern void set_binfmt(struct linux_binfmt *new); extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t); -- cgit v1.2.3 From 2388777a0a5957a10b3d78677216530a9b3bd09f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 3 May 2020 07:54:10 -0500 Subject: exec: Rename flush_old_exec begin_new_exec There is and has been for a very long time been a lot more going on in flush_old_exec than just flushing the old state. After the movement of code from setup_new_exec there is a whole lot more going on than just flushing the old executables state. Rename flush_old_exec to begin_new_exec to more accurately reflect what this function does. Reviewed-by: Kees Cook Reviewed-by: Greg Ungerer Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 2a8fddf3574a..1b48e2154766 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -125,7 +125,7 @@ extern void unregister_binfmt(struct linux_binfmt *); extern int prepare_binprm(struct linux_binprm *); extern int __must_check remove_arg_zero(struct linux_binprm *); extern int search_binary_handler(struct linux_binprm *); -extern int flush_old_exec(struct linux_binprm * bprm); +extern int begin_new_exec(struct linux_binprm * bprm); extern void setup_new_exec(struct linux_binprm * bprm); extern void finalize_exec(struct linux_binprm *bprm); extern void would_dump(struct linux_binprm *, struct file *); -- cgit v1.2.3 From 7c8e2bdd5f0d990e2398ee3deafc626dd469fc2d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 29 Apr 2020 10:24:44 -0500 Subject: livepatch: Apply vmlinux-specific KLP relocations early KLP relocations are livepatch-specific relocations which are applied to a KLP module's text or data. They exist for two reasons: 1) Unexported symbols: replacement functions often need to access unexported symbols (e.g. static functions), which "normal" relocations don't allow. 2) Late module patching: this is the ability for a KLP module to bypass normal module dependencies, such that the KLP module can be loaded *before* a to-be-patched module. This means that relocations which need to access symbols in the to-be-patched module might need to be applied to the KLP module well after it has been loaded. Non-late-patched KLP relocations are applied from the KLP module's init function. That usually works fine, unless the patched code wants to use alternatives, paravirt patching, jump tables, or some other special section which needs relocations. Then we run into ordering issues and crashes. In order for those special sections to work properly, the KLP relocations should be applied *before* the special section init code runs, such as apply_paravirt(), apply_alternatives(), or jump_label_apply_nops(). You might think the obvious solution would be to move the KLP relocation initialization earlier, but it's not necessarily that simple. The problem is the above-mentioned late module patching, for which KLP relocations can get applied well after the KLP module is loaded. To "fix" this issue in the past, we created .klp.arch sections: .klp.arch.{module}..altinstructions .klp.arch.{module}..parainstructions Those sections allow KLP late module patching code to call apply_paravirt() and apply_alternatives() after the module-specific KLP relocations (.klp.rela.{module}.{section}) have been applied. But that has a lot of drawbacks, including code complexity, the need for arch-specific code, and the (per-arch) danger that we missed some special section -- for example the __jump_table section which is used for jump labels. It turns out there's a simpler and more functional approach. There are two kinds of KLP relocation sections: 1) vmlinux-specific KLP relocation sections .klp.rela.vmlinux.{sec} These are relocations (applied to the KLP module) which reference unexported vmlinux symbols. 2) module-specific KLP relocation sections .klp.rela.{module}.{sec}: These are relocations (applied to the KLP module) which reference unexported or exported module symbols. Up until now, these have been treated the same. However, they're inherently different. Because of late module patching, module-specific KLP relocations can be applied very late, thus they can create the ordering headaches described above. But vmlinux-specific KLP relocations don't have that problem. There's nothing to prevent them from being applied earlier. So apply them at the same time as normal relocations, when the KLP module is being loaded. This means that for vmlinux-specific KLP relocations, we no longer have any ordering issues. vmlinux-referencing jump labels, alternatives, and paravirt patching will work automatically, without the need for the .klp.arch hacks. All that said, for module-specific KLP relocations, the ordering problems still exist and we *do* still need .klp.arch. Or do we? Stay tuned. Suggested-by: Peter Zijlstra Signed-off-by: Josh Poimboeuf Acked-by: Peter Zijlstra (Intel) Acked-by: Joe Lawrence Acked-by: Miroslav Benes Acked-by: Jessica Yu Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index e894e74905f3..c4302e9a5905 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -234,6 +234,11 @@ void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor); struct klp_state *klp_get_state(struct klp_patch *patch, unsigned long id); struct klp_state *klp_get_prev_state(unsigned long id); +int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, + const char *shstrtab, const char *strtab, + unsigned int symindex, unsigned int secindex, + const char *objname); + #else /* !CONFIG_LIVEPATCH */ static inline int klp_module_coming(struct module *mod) { return 0; } @@ -242,6 +247,15 @@ static inline bool klp_patch_pending(struct task_struct *task) { return false; } static inline void klp_update_patch_state(struct task_struct *task) {} static inline void klp_copy_process(struct task_struct *child) {} +static inline +int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, + const char *shstrtab, const char *strtab, + unsigned int symindex, unsigned int secindex, + const char *objname) +{ + return 0; +} + #endif /* CONFIG_LIVEPATCH */ #endif /* _LINUX_LIVEPATCH_H_ */ -- cgit v1.2.3 From 1d05334d2899bd3ecdf01beb53f0a70884a7f471 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 29 Apr 2020 10:24:45 -0500 Subject: livepatch: Remove .klp.arch After the previous patch, vmlinux-specific KLP relocations are now applied early during KLP module load. This means that .klp.arch sections are no longer needed for *vmlinux-specific* KLP relocations. One might think they're still needed for *module-specific* KLP relocations. If a to-be-patched module is loaded *after* its corresponding KLP module is loaded, any corresponding KLP relocations will be delayed until the to-be-patched module is loaded. If any special sections (.parainstructions, for example) rely on those relocations, their initializations (apply_paravirt) need to be done afterwards. Thus the apparent need for arch_klp_init_object_loaded() and its corresponding .klp.arch sections -- it allows some of the special section initializations to be done at a later time. But... if you look closer, that dependency between the special sections and the module-specific KLP relocations doesn't actually exist in reality. Looking at the contents of the .altinstructions and .parainstructions sections, there's not a realistic scenario in which a KLP module's .altinstructions or .parainstructions section needs to access a symbol in a to-be-patched module. It might need to access a local symbol or even a vmlinux symbol; but not another module's symbol. When a special section needs to reference a local or vmlinux symbol, a normal rela can be used instead of a KLP rela. Since the special section initializations don't actually have any real dependency on module-specific KLP relocations, .klp.arch and arch_klp_init_object_loaded() no longer have a reason to exist. So remove them. As Peter said much more succinctly: So the reason for .klp.arch was that .klp.rela.* stuff would overwrite paravirt instructions. If that happens you're doing it wrong. Those RELAs are core kernel, not module, and thus should've happened in .rela.* sections at patch-module loading time. Reverting this removes the two apply_{paravirt,alternatives}() calls from the late patching path, and means we don't have to worry about them when removing module_disable_ro(). [ jpoimboe: Rewrote patch description. Tweaked klp_init_object_loaded() error path. ] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Josh Poimboeuf Acked-by: Peter Zijlstra (Intel) Acked-by: Joe Lawrence Acked-by: Miroslav Benes Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index c4302e9a5905..2614247a9781 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -195,9 +195,6 @@ struct klp_patch { int klp_enable_patch(struct klp_patch *); -void arch_klp_init_object_loaded(struct klp_patch *patch, - struct klp_object *obj); - /* Called from the module loader during module coming/going states */ int klp_module_coming(struct module *mod); void klp_module_going(struct module *mod); -- cgit v1.2.3 From 0d9fbf78fefb421a3af97394ce80bba0db4f046a Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 29 Apr 2020 10:24:51 -0500 Subject: module: Remove module_disable_ro() module_disable_ro() has no more users. Remove it. Signed-off-by: Josh Poimboeuf Acked-by: Peter Zijlstra (Intel) Acked-by: Joe Lawrence Acked-by: Miroslav Benes Acked-by: Jessica Yu Signed-off-by: Jiri Kosina --- include/linux/module.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 1ad393e62bef..e4ef7b36feda 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -860,10 +860,8 @@ extern int module_sysfs_initialized; #ifdef CONFIG_STRICT_MODULE_RWX extern void module_enable_ro(const struct module *mod, bool after_init); -extern void module_disable_ro(const struct module *mod); #else static inline void module_enable_ro(const struct module *mod, bool after_init) { } -static inline void module_disable_ro(const struct module *mod) { } #endif #ifdef CONFIG_GENERIC_BUG -- cgit v1.2.3 From e6eff4376e2897c2e14b70d87bf7284cdb093830 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 29 Apr 2020 10:24:53 -0500 Subject: module: Make module_enable_ro() static again Now that module_enable_ro() has no more external users, make it static again. Suggested-by: Jessica Yu Signed-off-by: Josh Poimboeuf Acked-by: Jessica Yu Signed-off-by: Jiri Kosina --- include/linux/module.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index e4ef7b36feda..2c2e988bcf10 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -858,12 +858,6 @@ extern int module_sysfs_initialized; #define __MODULE_STRING(x) __stringify(x) -#ifdef CONFIG_STRICT_MODULE_RWX -extern void module_enable_ro(const struct module *mod, bool after_init); -#else -static inline void module_enable_ro(const struct module *mod, bool after_init) { } -#endif - #ifdef CONFIG_GENERIC_BUG void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, struct module *); -- cgit v1.2.3 From 307f660d056b5eb8f5bb2328fac3915ab75b5007 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 May 2020 09:32:18 -0700 Subject: netpoll: remove dev argument from netpoll_send_skb_on_dev() netpoll_send_skb_on_dev() can get the device pointer directly from np->dev Rename it to __netpoll_send_skb() Following patch will move netpoll_send_skb() out-of-line. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netpoll.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 676f1ff161a9..00e0bae3d402 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -63,13 +63,12 @@ int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); -void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, - struct net_device *dev); +void __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) { unsigned long flags; local_irq_save(flags); - netpoll_send_skb_on_dev(np, skb, np->dev); + __netpoll_send_skb(np, skb); local_irq_restore(flags); } -- cgit v1.2.3 From fb1eee476b0d3be3e58dac1a3a96f726c6278bed Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 May 2020 09:32:19 -0700 Subject: netpoll: move netpoll_send_skb() out of line There is no need to inline this helper, as we intend to add more code in this function. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netpoll.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 00e0bae3d402..e466ddffef61 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -63,14 +63,7 @@ int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); -void __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); -static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) -{ - unsigned long flags; - local_irq_save(flags); - __netpoll_send_skb(np, skb); - local_irq_restore(flags); -} +void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); #ifdef CONFIG_NETPOLL static inline void *netpoll_poll_lock(struct napi_struct *napi) -- cgit v1.2.3 From 1ddabdfaf70c202b88925edd74c66f4707dbd92e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 May 2020 09:32:20 -0700 Subject: netpoll: netpoll_send_skb() returns transmit status Some callers want to know if the packet has been sent or dropped, to inform upper stacks. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netpoll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index e466ddffef61..f47af135bd56 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -63,7 +63,7 @@ int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); -void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); +netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); #ifdef CONFIG_NETPOLL static inline void *netpoll_poll_lock(struct napi_struct *napi) -- cgit v1.2.3 From f78ed2204db9fc35b545d693865bddbe0149aa1f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 May 2020 09:32:21 -0700 Subject: netpoll: accept NULL np argument in netpoll_send_skb() netpoll_send_skb() callers seem to leak skb if the np pointer is NULL. While this should not happen, we can make the code more robust. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/if_team.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index ec7e4bd07f82..537dc2b8c879 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -102,10 +102,7 @@ static inline bool team_port_dev_txable(const struct net_device *port_dev) static inline void team_netpoll_send_skb(struct team_port *port, struct sk_buff *skb) { - struct netpoll *np = port->np; - - if (np) - netpoll_send_skb(np, skb); + netpoll_send_skb(port->np, skb); } #else static inline void team_netpoll_send_skb(struct team_port *port, -- cgit v1.2.3 From 0090c1edebf464f34629e14ae03d764cca7e0a3b Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:50:41 -0500 Subject: audit: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Reviewed-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 1a2351508211..3fcd9ee49734 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -19,7 +19,7 @@ struct audit_sig_info { uid_t uid; pid_t pid; - char ctx[0]; + char ctx[]; }; struct audit_buffer; -- cgit v1.2.3 From 6b0b0fa2bce61db790efc8070ae6e5696435b0a8 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sat, 2 May 2020 11:24:25 -0700 Subject: crypto: lib/sha1 - rename "sha" to "sha1" The library implementation of the SHA-1 compression function is confusingly called just "sha_transform()". Alongside it are some "SHA_" constants and "sha_init()". Presumably these are left over from a time when SHA just meant SHA-1. But now there are also SHA-2 and SHA-3, and moreover SHA-1 is now considered insecure and thus shouldn't be used. Therefore, rename these functions and constants to make it very clear that they are for SHA-1. Also add a comment to make it clear that these shouldn't be used. For the extra-misleadingly named "SHA_MESSAGE_BYTES", rename it to SHA1_BLOCK_SIZE and define it to just '64' rather than '(512/8)' so that it matches the same definition in . This prepares for merging into . Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/cryptohash.h | 16 ++++++++++------ include/linux/filter.h | 2 +- 2 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h index f6ba4c3e60d7..c324ffca96e0 100644 --- a/include/linux/cryptohash.h +++ b/include/linux/cryptohash.h @@ -4,11 +4,15 @@ #include -#define SHA_DIGEST_WORDS 5 -#define SHA_MESSAGE_BYTES (512 /*bits*/ / 8) -#define SHA_WORKSPACE_WORDS 16 - -void sha_init(__u32 *buf); -void sha_transform(__u32 *digest, const char *data, __u32 *W); +/* + * An implementation of SHA-1's compression function. Don't use in new code! + * You shouldn't be using SHA-1, and even if you *have* to use SHA-1, this isn't + * the correct way to hash something with SHA-1 (use crypto_shash instead). + */ +#define SHA1_DIGEST_WORDS 5 +#define SHA1_BLOCK_SIZE 64 +#define SHA1_WORKSPACE_WORDS 16 +void sha1_init(__u32 *buf); +void sha1_transform(__u32 *digest, const char *data, __u32 *W); #endif diff --git a/include/linux/filter.h b/include/linux/filter.h index 9b5aa5c483cc..f42662adffe4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -746,7 +746,7 @@ static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog) { return round_up(bpf_prog_insn_size(prog) + - sizeof(__be64) + 1, SHA_MESSAGE_BYTES); + sizeof(__be64) + 1, SHA1_BLOCK_SIZE); } static inline unsigned int bpf_prog_size(unsigned int proglen) -- cgit v1.2.3 From 228c4f265c6eb60eaa4ed0edb3bf7c113173576c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sat, 2 May 2020 11:24:27 -0700 Subject: crypto: lib/sha1 - fold linux/cryptohash.h into crypto/sha.h sounds very generic and important, like it's the header to include if you're doing cryptographic hashing in the kernel. But actually it only includes the library implementation of the SHA-1 compression function (not even the full SHA-1). This should basically never be used anymore; SHA-1 is no longer considered secure, and there are much better ways to do cryptographic hashing in the kernel. Remove this header and fold it into which already contains constants and functions for SHA-1 (along with SHA-2). Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/cryptohash.h | 18 ------------------ include/linux/filter.h | 2 +- 2 files changed, 1 insertion(+), 19 deletions(-) delete mode 100644 include/linux/cryptohash.h (limited to 'include/linux') diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h deleted file mode 100644 index c324ffca96e0..000000000000 --- a/include/linux/cryptohash.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __CRYPTOHASH_H -#define __CRYPTOHASH_H - -#include - -/* - * An implementation of SHA-1's compression function. Don't use in new code! - * You shouldn't be using SHA-1, and even if you *have* to use SHA-1, this isn't - * the correct way to hash something with SHA-1 (use crypto_shash instead). - */ -#define SHA1_DIGEST_WORDS 5 -#define SHA1_BLOCK_SIZE 64 -#define SHA1_WORKSPACE_WORDS 16 -void sha1_init(__u32 *buf); -void sha1_transform(__u32 *digest, const char *data, __u32 *W); - -#endif diff --git a/include/linux/filter.h b/include/linux/filter.h index f42662adffe4..ec45fd7992c9 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -16,11 +16,11 @@ #include #include #include -#include #include #include #include #include +#include #include -- cgit v1.2.3 From d2218d4e4a65f25bd2d38489567012c7db50233c Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 8 May 2020 18:39:35 +0300 Subject: lib: add linear ranges helpers Many devices have control registers which control some measurable property. Often a register contains control field so that change in this field causes linear change in the controlled property. It is not a rare case that user wants to give 'meaningful' control values and driver needs to convert them to register field values. Even more often user wants to 'see' the currently set value - again in meaningful units - and driver needs to convert the values it reads from register to these meaningful units. Examples of this include: - regulators, voltage/current configurations - power, voltage/current configurations - clk(?) NCOs and maybe others I can't think of right now. Provide a linear_range helper which can do conversion from user value to register value 'selector'. The idea here is stolen from regulator framework and patches refactoring the regulator helpers to use this are following. Current implementation does not support inversely proportional ranges but it might be useful if we could support also inversely proportional ranges? Signed-off-by: Matti Vaittinen Reviewed-by: Mark Brown Reviewed-by: Linus Walleij Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/59259bc475e0c800eb4bb163f02528c7c01f7b3a.1588944082.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/linear_range.h | 48 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 include/linux/linear_range.h (limited to 'include/linux') diff --git a/include/linux/linear_range.h b/include/linux/linear_range.h new file mode 100644 index 000000000000..17b5943727d5 --- /dev/null +++ b/include/linux/linear_range.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2020 ROHM Semiconductors */ + +#ifndef LINEAR_RANGE_H +#define LINEAR_RANGE_H + +#include + +/** + * struct linear_range - table of selector - value pairs + * + * Define a lookup-table for range of values. Intended to help when looking + * for a register value matching certaing physical measure (like voltage). + * Usable when increment of one in register always results a constant increment + * of the physical measure (like voltage). + * + * @min: Lowest value in range + * @min_sel: Lowest selector for range + * @max_sel: Highest selector for range + * @step: Value step size + */ +struct linear_range { + unsigned int min; + unsigned int min_sel; + unsigned int max_sel; + unsigned int step; +}; + +unsigned int linear_range_values_in_range(const struct linear_range *r); +unsigned int linear_range_values_in_range_array(const struct linear_range *r, + int ranges); +unsigned int linear_range_get_max_value(const struct linear_range *r); + +int linear_range_get_value(const struct linear_range *r, unsigned int selector, + unsigned int *val); +int linear_range_get_value_array(const struct linear_range *r, int ranges, + unsigned int selector, unsigned int *val); +int linear_range_get_selector_low(const struct linear_range *r, + unsigned int val, unsigned int *selector, + bool *found); +int linear_range_get_selector_high(const struct linear_range *r, + unsigned int val, unsigned int *selector, + bool *found); +int linear_range_get_selector_low_array(const struct linear_range *r, + int ranges, unsigned int val, + unsigned int *selector, bool *found); + +#endif -- cgit v1.2.3 From 60ab7f4153b6af461c90d572c31104086b44639f Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 8 May 2020 18:43:36 +0300 Subject: regulator: use linear_ranges helper Change the regulator helpers to use common linear_ranges code. Signed-off-by: Matti Vaittinen Reviewed-by: Mark Brown Acked-by: Charles Keepax Acked-by: Adam Thomson Link: https://lore.kernel.org/r/64f01d5e381b8631a271616b7790f9d5640974fb.1588944082.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 27 +++++---------------------- 1 file changed, 5 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 29d920516e0b..7eb9fea8e482 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -13,6 +13,7 @@ #define __LINUX_REGULATOR_DRIVER_H_ #include +#include #include #include #include @@ -39,31 +40,13 @@ enum regulator_status { REGULATOR_STATUS_UNDEFINED, }; -/** - * struct regulator_linear_range - specify linear voltage ranges - * - * Specify a range of voltages for regulator_map_linear_range() and - * regulator_list_linear_range(). - * - * @min_uV: Lowest voltage in range - * @min_sel: Lowest selector for range - * @max_sel: Highest selector for range - * @uV_step: Step size - */ -struct regulator_linear_range { - unsigned int min_uV; - unsigned int min_sel; - unsigned int max_sel; - unsigned int uV_step; -}; - -/* Initialize struct regulator_linear_range */ +/* Initialize struct linear_range for regulators */ #define REGULATOR_LINEAR_RANGE(_min_uV, _min_sel, _max_sel, _step_uV) \ { \ - .min_uV = _min_uV, \ + .min = _min_uV, \ .min_sel = _min_sel, \ .max_sel = _max_sel, \ - .uV_step = _step_uV, \ + .step = _step_uV, \ } /** @@ -348,7 +331,7 @@ struct regulator_desc { unsigned int ramp_delay; int min_dropout_uV; - const struct regulator_linear_range *linear_ranges; + const struct linear_range *linear_ranges; const unsigned int *linear_range_selectors; int n_linear_ranges; -- cgit v1.2.3 From 62a7f3009a460001eb46984395280dd900bc4ef4 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 8 May 2020 14:53:40 +0800 Subject: serial: 8250_pci: Move Pericom IDs to pci_ids.h Move the IDs to pci_ids.h so it can be used by next patch. Link: https://lore.kernel.org/r/20200508065343.32751-1-kai.heng.feng@canonical.com Signed-off-by: Kai-Heng Feng Signed-off-by: Bjorn Helgaas Acked-by: Greg Kroah-Hartman Cc: stable@vger.kernel.org --- include/linux/pci_ids.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 1dfc4e1dcb94..9a57e6717e5c 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1832,6 +1832,12 @@ #define PCI_VENDOR_ID_NVIDIA_SGS 0x12d2 #define PCI_DEVICE_ID_NVIDIA_SGS_RIVA128 0x0018 +#define PCI_VENDOR_ID_PERICOM 0x12D8 +#define PCI_DEVICE_ID_PERICOM_PI7C9X7951 0x7951 +#define PCI_DEVICE_ID_PERICOM_PI7C9X7952 0x7952 +#define PCI_DEVICE_ID_PERICOM_PI7C9X7954 0x7954 +#define PCI_DEVICE_ID_PERICOM_PI7C9X7958 0x7958 + #define PCI_SUBVENDOR_ID_CHASE_PCIFAST 0x12E0 #define PCI_SUBDEVICE_ID_CHASE_PCIFAST4 0x0031 #define PCI_SUBDEVICE_ID_CHASE_PCIFAST8 0x0021 -- cgit v1.2.3 From 52782c92ac85c4e393eb4a903a62e6c24afa633f Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Wed, 6 May 2020 12:09:34 -0400 Subject: kthread: save thread function It's handy to keep the kthread_fn just as a unique cookie to identify classes of kthreads. E.g. if you can verify that a given task is running your thread_fn, then you may know what sort of type kthread_data points to. We'll use this in nfsd to pass some information into the vfs. Note it will need kthread_data() exported too. Original-patch-by: Tejun Heo Signed-off-by: J. Bruce Fields --- include/linux/kthread.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 8bbcaad7ef0f..c2a274b79c42 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -57,6 +57,7 @@ bool kthread_should_stop(void); bool kthread_should_park(void); bool __kthread_should_park(struct task_struct *k); bool kthread_freezable_should_stop(bool *was_frozen); +void *kthread_func(struct task_struct *k); void *kthread_data(struct task_struct *k); void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); -- cgit v1.2.3 From 28df3d1539de5090f7916f6fff03891b67f366f4 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 28 Jul 2017 16:35:15 -0400 Subject: nfsd: clients don't need to break their own delegations We currently revoke read delegations on any write open or any operation that modifies file data or metadata (including rename, link, and unlink). But if the delegation in question is the only read delegation and is held by the client performing the operation, that's not really necessary. It's not always possible to prevent this in the NFSv4.0 case, because there's not always a way to determine which client an NFSv4.0 delegation came from. (In theory we could try to guess this from the transport layer, e.g., by assuming all traffic on a given TCP connection comes from the same client. But that's not really correct.) In the NFSv4.1 case the session layer always tells us the client. This patch should remove such self-conflicts in all cases where we can reliably determine the client from the compound. To do that we need to track "who" is performing a given (possibly lease-breaking) file operation. We're doing that by storing the information in the svc_rqst and using kthread_data() to map the current task back to a svc_rqst. Signed-off-by: J. Bruce Fields --- include/linux/fs.h | 1 + include/linux/sunrpc/svc.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..4b784560ffaf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1045,6 +1045,7 @@ struct lock_manager_operations { bool (*lm_break)(struct file_lock *); int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); + bool (*lm_breaker_owns_lease)(struct file_lock *); }; struct lock_manager { diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index fd390894a584..abf4a57ce4a7 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -299,6 +299,7 @@ struct svc_rqst { struct net *rq_bc_net; /* pointer to backchannel's * net namespace */ + void ** rq_lease_breaker; /* The v4 client breaking a lease */ }; #define SVC_NET(rqst) (rqst->rq_xprt ? rqst->rq_xprt->xpt_net : rqst->rq_bc_net) -- cgit v1.2.3 From f2a8d52e0a4db968c346c4332630a71cba377567 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 5 May 2020 16:04:30 +0200 Subject: nsproxy: add struct nsset Add a simple struct nsset. It holds all necessary pieces to switch to a new set of namespaces without leaving a task in a half-switched state which we will make use of in the next patch. This patch switches the existing setns logic over without causing a change in setns() behavior. This brings setns() closer to how unshare() works(). The prepare_ns() function is responsible to prepare all necessary information. This has two reasons. First it minimizes dependencies between individual namespaces, i.e. all install handler can expect that all fields are properly initialized independent in what order they are called in. Second, this makes the code easier to maintain and easier to follow if it needs to be changed. The prepare_ns() helper will only be switched over to use a flags argument in the next patch. Here it will still use nstype as a simple integer argument which was argued would be clearer. I'm not particularly opinionated about this if it really helps or not. The struct nsset itself already contains the flags field since its name already indicates that it can contain information required by different namespaces. None of this should have functional consequences. Signed-off-by: Christian Brauner Reviewed-by: Serge Hallyn Cc: Eric W. Biederman Cc: Serge Hallyn Cc: Jann Horn Cc: Michael Kerrisk Cc: Aleksa Sarai Link: https://lore.kernel.org/r/20200505140432.181565-2-christian.brauner@ubuntu.com --- include/linux/mnt_namespace.h | 1 + include/linux/nsproxy.h | 24 ++++++++++++++++++++++++ include/linux/proc_ns.h | 4 ++-- 3 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 35942084cd40..007cfa52efb2 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -6,6 +6,7 @@ struct mnt_namespace; struct fs_struct; struct user_namespace; +struct ns_common; extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, struct user_namespace *, struct fs_struct *); diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 074f395b9ad2..cdb171efc7cb 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -41,6 +41,30 @@ struct nsproxy { }; extern struct nsproxy init_nsproxy; +/* + * A structure to encompass all bits needed to install + * a partial or complete new set of namespaces. + * + * If a new user namespace is requested cred will + * point to a modifiable set of credentials. If a pointer + * to a modifiable set is needed nsset_cred() must be + * used and tested. + */ +struct nsset { + unsigned flags; + struct nsproxy *nsproxy; + struct fs_struct *fs; + const struct cred *cred; +}; + +static inline struct cred *nsset_cred(struct nsset *set) +{ + if (set->flags & CLONE_NEWUSER) + return (struct cred *)set->cred; + + return NULL; +} + /* * the namespaces access rules are: * diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 6abe85c34681..75807ecef880 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -8,7 +8,7 @@ #include struct pid_namespace; -struct nsproxy; +struct nsset; struct path; struct task_struct; struct inode; @@ -19,7 +19,7 @@ struct proc_ns_operations { int type; struct ns_common *(*get)(struct task_struct *task); void (*put)(struct ns_common *ns); - int (*install)(struct nsproxy *nsproxy, struct ns_common *ns); + int (*install)(struct nsset *nsset, struct ns_common *ns); struct user_namespace *(*owner)(struct ns_common *ns); struct ns_common *(*get_parent)(struct ns_common *ns); } __randomize_layout; -- cgit v1.2.3 From 4c74746625dedb62ce00ac86ac4faedb640536d0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 May 2020 14:47:57 +0200 Subject: driver core: remove device_create_vargs All external users of device_create_vargs are gone, so remove it and open code it in the only caller. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/device.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index ac8e37cd716a..15460a5ac024 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -884,10 +884,6 @@ extern bool device_is_bound(struct device *dev); /* * Easy functions for dynamically creating devices on the fly */ -extern __printf(5, 0) -struct device *device_create_vargs(struct class *cls, struct device *parent, - dev_t devt, void *drvdata, - const char *fmt, va_list vargs); extern __printf(5, 6) struct device *device_create(struct class *cls, struct device *parent, dev_t devt, void *drvdata, -- cgit v1.2.3 From 3c5d202b55d3fa9106607f99cdd5044b02b5929b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 May 2020 14:47:59 +0200 Subject: bdi: remove bdi_register_owner Split out a new bdi_set_owner helper to set the owner, and move the policy for creating the bdi name back into genhd.c, where it belongs. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Greg Kroah-Hartman Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index c9ad5c3b7b4b..4098ed6ba6b4 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -33,7 +33,7 @@ int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...); __printf(2, 0) int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args); -int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner); +void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id); -- cgit v1.2.3 From aef33c2ff8aa5e24f3f7d93806aa84ca1c2b6832 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 May 2020 14:48:00 +0200 Subject: bdi: simplify bdi_alloc Merge the _node vs normal version and drop the superflous gfp_t argument. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Greg Kroah-Hartman Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 4098ed6ba6b4..6b3504bf7a42 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -36,11 +36,7 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); -struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id); -static inline struct backing_dev_info *bdi_alloc(gfp_t gfp_mask) -{ - return bdi_alloc_node(gfp_mask, NUMA_NO_NODE); -} +struct backing_dev_info *bdi_alloc(int node_id); void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); -- cgit v1.2.3 From 1cd925d583857ee3ead6cfbf1e4b1cd067d28591 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 May 2020 14:48:01 +0200 Subject: bdi: remove the name field in struct backing_dev_info The name is only printed for a not registered bdi in writeback. Use the device name there as is more useful anyway for the unlike case that the warning triggers. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Greg Kroah-Hartman Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 7367150f962a..90a7e844a098 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -193,8 +193,6 @@ struct backing_dev_info { congested_fn *congested_fn; /* Function pointer if device is md/dm */ void *congested_data; /* Pointer to aux data for congested func */ - const char *name; - struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ unsigned int min_ratio; -- cgit v1.2.3 From 615399896ca3787728c56c499c99be79e40ac125 Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 31 Mar 2020 09:49:46 -0700 Subject: nvme-fc: Sync header to FC-NVME-2 rev 1.08 A couple of minor changes occurred between 1.06 and 1.08: - Addition of NVME_SR_RSP opcode - change of SR_RSP status code 1 to Reserved Signed-off-by: James Smart Reviewed-by: Sagi Grimberg Reviewed-by: Himanshu Madhani Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme-fc.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h index e8c30b39bb27..51fe44e0328b 100644 --- a/include/linux/nvme-fc.h +++ b/include/linux/nvme-fc.h @@ -4,8 +4,8 @@ */ /* - * This file contains definitions relative to FC-NVME-2 r1.06 - * (T11-2019-00210-v001). + * This file contains definitions relative to FC-NVME-2 r1.08 + * (T11-2019-00210-v004). */ #ifndef _NVME_FC_H @@ -81,7 +81,8 @@ struct nvme_fc_ersp_iu { }; -#define FCNVME_NVME_SR_OPCODE 0x01 +#define FCNVME_NVME_SR_OPCODE 0x01 +#define FCNVME_NVME_SR_RSP_OPCODE 0x02 struct nvme_fc_nvme_sr_iu { __u8 fc_id; @@ -94,7 +95,7 @@ struct nvme_fc_nvme_sr_iu { enum { FCNVME_SRSTAT_ACC = 0x0, - FCNVME_SRSTAT_INV_FCID = 0x1, + /* reserved 0x1 */ /* reserved 0x2 */ FCNVME_SRSTAT_LOGICAL_ERR = 0x3, FCNVME_SRSTAT_INV_QUALIF = 0x4, @@ -397,7 +398,7 @@ struct fcnvme_ls_disconnect_conn_rqst { struct fcnvme_ls_rqst_w0 w0; __be32 desc_list_len; struct fcnvme_lsdesc_assoc_id associd; - struct fcnvme_lsdesc_disconn_cmd connectid; + struct fcnvme_lsdesc_conn_id connectid; }; struct fcnvme_ls_disconnect_conn_acc { -- cgit v1.2.3 From 72e6329f86c714785ac195d293cb19dd24507880 Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 31 Mar 2020 09:49:47 -0700 Subject: nvme-fc and nvmet-fc: revise LLDD api for LS reception and LS request The current LLDD api has: nvme-fc: contains api for transport to do LS requests (and aborts of them). However, there is no interface for reception of LS's and sending responses for them. nvmet-fc: contains api for transport to do reception of LS's and sending of responses for them. However, there is no interface for doing LS requests. Revise the api's so that both nvme-fc and nvmet-fc can send LS's, as well as receiving LS's and sending their responses. Change name of the rcv_ls_req struct to better reflect generic use as a context to used to send an ls rsp. Specifically: nvmefc_tgt_ls_req -> nvmefc_ls_rsp nvmefc_tgt_ls_req.nvmet_fc_private -> nvmefc_ls_rsp.nvme_fc_private Change nvmet_fc_rcv_ls_req() calling sequence to provide handle that can be used by transport in later LS request sequences for an association. nvme-fc nvmet_fc nvme_fcloop: Revise to adapt to changed names in api header. Change calling sequence to nvmet_fc_rcv_ls_req() for hosthandle. Add stubs for new interfaces: host/fc.c: nvme_fc_rcv_ls_req() target/fc.c: nvmet_fc_invalidate_host() lpfc: Revise to adapt code to changed names in api header. Change calling sequence to nvmet_fc_rcv_ls_req() for hosthandle. Signed-off-by: James Smart Reviewed-by: Sagi Grimberg Reviewed-by: Himanshu Madhani Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme-fc-driver.h | 368 ++++++++++++++++++++++++++++++----------- 1 file changed, 270 insertions(+), 98 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 10f81629b9ce..41e7795a3ee4 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -10,47 +10,26 @@ /* - * ********************** LLDD FC-NVME Host API ******************** + * ********************** FC-NVME LS API ******************** * - * For FC LLDD's that are the NVME Host role. + * Data structures used by both FC-NVME hosts and FC-NVME + * targets to perform FC-NVME LS requests or transmit + * responses. * - * ****************************************************************** + * *********************************************************** */ - - /** - * struct nvme_fc_port_info - port-specific ids and FC connection-specific - * data element used during NVME Host role - * registrations - * - * Static fields describing the port being registered: - * @node_name: FC WWNN for the port - * @port_name: FC WWPN for the port - * @port_role: What NVME roles are supported (see FC_PORT_ROLE_xxx) - * @dev_loss_tmo: maximum delay for reconnects to an association on - * this device. Used only on a remoteport. + * struct nvmefc_ls_req - Request structure passed from the transport + * to the LLDD to perform a NVME-FC LS request and obtain + * a response. + * Used by nvme-fc transport (host) to send LS's such as + * Create Association, Create Connection and Disconnect + * Association. + * Used by the nvmet-fc transport (controller) to send + * LS's such as Disconnect Association. * - * Initialization values for dynamic port fields: - * @port_id: FC N_Port_ID currently assigned the port. Upper 8 bits must - * be set to 0. - */ -struct nvme_fc_port_info { - u64 node_name; - u64 port_name; - u32 port_role; - u32 port_id; - u32 dev_loss_tmo; -}; - - -/** - * struct nvmefc_ls_req - Request structure passed from NVME-FC transport - * to LLDD in order to perform a NVME FC-4 LS - * request and obtain a response. - * - * Values set by the NVME-FC layer prior to calling the LLDD ls_req - * entrypoint. + * Values set by the requestor prior to calling the LLDD ls_req entrypoint: * @rqstaddr: pointer to request buffer * @rqstdma: PCI DMA address of request buffer * @rqstlen: Length, in bytes, of request buffer @@ -63,8 +42,8 @@ struct nvme_fc_port_info { * @private: pointer to memory allocated alongside the ls request structure * that is specifically for the LLDD to use while processing the * request. The length of the buffer corresponds to the - * lsrqst_priv_sz value specified in the nvme_fc_port_template - * supplied by the LLDD. + * lsrqst_priv_sz value specified in the xxx_template supplied + * by the LLDD. * @done: The callback routine the LLDD is to invoke upon completion of * the LS request. req argument is the pointer to the original LS * request structure. Status argument must be 0 upon success, a @@ -86,6 +65,101 @@ struct nvmefc_ls_req { } __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ +/** + * struct nvmefc_ls_rsp - Structure passed from the transport to the LLDD + * to request the transmit the NVME-FC LS response to a + * NVME-FC LS request. The structure originates in the LLDD + * and is given to the transport via the xxx_rcv_ls_req() + * transport routine. As such, the structure represents the + * FC exchange context for the NVME-FC LS request that was + * received and which the response is to be sent for. + * Used by the LLDD to pass the nvmet-fc transport (controller) + * received LS's such as Create Association, Create Connection + * and Disconnect Association. + * Used by the LLDD to pass the nvme-fc transport (host) + * received LS's such as Disconnect Association or Disconnect + * Connection. + * + * The structure is allocated by the LLDD whenever a LS Request is received + * from the FC link. The address of the structure is passed to the nvmet-fc + * or nvme-fc layer via the xxx_rcv_ls_req() transport routines. + * + * The address of the structure is to be passed back to the LLDD + * when the response is to be transmit. The LLDD will use the address to + * map back to the LLDD exchange structure which maintains information such + * the remote N_Port that sent the LS as well as any FC exchange context. + * Upon completion of the LS response transmit, the LLDD will pass the + * address of the structure back to the transport LS rsp done() routine, + * allowing the transport release dma resources. Upon completion of + * the done() routine, no further access to the structure will be made by + * the transport and the LLDD can de-allocate the structure. + * + * Field initialization: + * At the time of the xxx_rcv_ls_req() call, there is no content that + * is valid in the structure. + * + * When the structure is used for the LLDD->xmt_ls_rsp() call, the + * transport layer will fully set the fields in order to specify the + * response payload buffer and its length as well as the done routine + * to be called upon completion of the transmit. The transport layer + * will also set a private pointer for its own use in the done routine. + * + * Values set by the transport layer prior to calling the LLDD xmt_ls_rsp + * entrypoint: + * @rspbuf: pointer to the LS response buffer + * @rspdma: PCI DMA address of the LS response buffer + * @rsplen: Length, in bytes, of the LS response buffer + * @done: The callback routine the LLDD is to invoke upon completion of + * transmitting the LS response. req argument is the pointer to + * the original ls request. + * @nvme_fc_private: pointer to an internal transport-specific structure + * used as part of the transport done() processing. The LLDD is + * not to access this pointer. + */ +struct nvmefc_ls_rsp { + void *rspbuf; + dma_addr_t rspdma; + u16 rsplen; + + void (*done)(struct nvmefc_ls_rsp *rsp); + void *nvme_fc_private; /* LLDD is not to access !! */ +}; + + + +/* + * ********************** LLDD FC-NVME Host API ******************** + * + * For FC LLDD's that are the NVME Host role. + * + * ****************************************************************** + */ + + +/** + * struct nvme_fc_port_info - port-specific ids and FC connection-specific + * data element used during NVME Host role + * registrations + * + * Static fields describing the port being registered: + * @node_name: FC WWNN for the port + * @port_name: FC WWPN for the port + * @port_role: What NVME roles are supported (see FC_PORT_ROLE_xxx) + * @dev_loss_tmo: maximum delay for reconnects to an association on + * this device. Used only on a remoteport. + * + * Initialization values for dynamic port fields: + * @port_id: FC N_Port_ID currently assigned the port. Upper 8 bits must + * be set to 0. + */ +struct nvme_fc_port_info { + u64 node_name; + u64 port_name; + u32 port_role; + u32 port_id; + u32 dev_loss_tmo; +}; + enum nvmefc_fcp_datadir { NVMEFC_FCP_NODATA, /* payload_length and sg_cnt will be zero */ NVMEFC_FCP_WRITE, @@ -337,6 +411,21 @@ struct nvme_fc_remote_port { * indicating an FC transport Aborted status. * Entrypoint is Mandatory. * + * @xmt_ls_rsp: Called to transmit the response to a FC-NVME FC-4 LS service. + * The nvmefc_ls_rsp structure is the same LLDD-supplied exchange + * structure specified in the nvme_fc_rcv_ls_req() call made when + * the LS request was received. The structure will fully describe + * the buffers for the response payload and the dma address of the + * payload. The LLDD is to transmit the response (or return a + * non-zero errno status), and upon completion of the transmit, call + * the "done" routine specified in the nvmefc_ls_rsp structure + * (argument to done is the address of the nvmefc_ls_rsp structure + * itself). Upon the completion of the done routine, the LLDD shall + * consider the LS handling complete and the nvmefc_ls_rsp structure + * may be freed/released. + * Entrypoint is mandatory if the LLDD calls the nvme_fc_rcv_ls_req() + * entrypoint. + * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -371,7 +460,7 @@ struct nvme_fc_remote_port { * @lsrqst_priv_sz: The LLDD sets this field to the amount of additional * memory that it would like fc nvme layer to allocate on the LLDD's * behalf whenever a ls request structure is allocated. The additional - * memory area solely for the of the LLDD and its location is + * memory area is solely for use by the LLDD and its location is * specified by the ls_request->private pointer. * Value is Mandatory. Allowed to be zero. * @@ -405,6 +494,9 @@ struct nvme_fc_port_template { struct nvme_fc_remote_port *, void *hw_queue_handle, struct nvmefc_fcp_req *); + int (*xmt_ls_rsp)(struct nvme_fc_local_port *localport, + struct nvme_fc_remote_port *rport, + struct nvmefc_ls_rsp *ls_rsp); u32 max_hw_queues; u16 max_sgl_segments; @@ -441,6 +533,34 @@ void nvme_fc_rescan_remoteport(struct nvme_fc_remote_port *remoteport); int nvme_fc_set_remoteport_devloss(struct nvme_fc_remote_port *remoteport, u32 dev_loss_tmo); +/* + * Routine called to pass a NVME-FC LS request, received by the lldd, + * to the nvme-fc transport. + * + * If the return value is zero: the LS was successfully accepted by the + * transport. + * If the return value is non-zero: the transport has not accepted the + * LS. The lldd should ABTS-LS the LS. + * + * Note: if the LLDD receives and ABTS for the LS prior to the transport + * calling the ops->xmt_ls_rsp() routine to transmit a response, the LLDD + * shall mark the LS as aborted, and when the xmt_ls_rsp() is called: the + * response shall not be transmit and the struct nvmefc_ls_rsp() done + * routine shall be called. The LLDD may transmit the ABTS response as + * soon as the LS was marked or can delay until the xmt_ls_rsp() call is + * made. + * Note: if an RCV LS was successfully posted to the transport and the + * remoteport is then unregistered before xmt_ls_rsp() was called for + * the lsrsp structure, the transport will still call xmt_ls_rsp() + * afterward to cleanup the outstanding lsrsp structure. The LLDD should + * noop the transmission of the rsp and call the lsrsp->done() routine + * to allow the lsrsp structure to be released. + */ +int nvme_fc_rcv_ls_req(struct nvme_fc_remote_port *remoteport, + struct nvmefc_ls_rsp *lsrsp, + void *lsreqbuf, u32 lsreqbuf_len); + + /* * *************** LLDD FC-NVME Target/Subsystem API *************** @@ -470,55 +590,6 @@ struct nvmet_fc_port_info { }; -/** - * struct nvmefc_tgt_ls_req - Structure used between LLDD and NVMET-FC - * layer to represent the exchange context for - * a FC-NVME Link Service (LS). - * - * The structure is allocated by the LLDD whenever a LS Request is received - * from the FC link. The address of the structure is passed to the nvmet-fc - * layer via the nvmet_fc_rcv_ls_req() call. The address of the structure - * will be passed back to the LLDD when the response is to be transmit. - * The LLDD is to use the address to map back to the LLDD exchange structure - * which maintains information such as the targetport the LS was received - * on, the remote FC NVME initiator that sent the LS, and any FC exchange - * context. Upon completion of the LS response transmit, the address of the - * structure will be passed back to the LS rsp done() routine, allowing the - * nvmet-fc layer to release dma resources. Upon completion of the done() - * routine, no further access will be made by the nvmet-fc layer and the - * LLDD can de-allocate the structure. - * - * Field initialization: - * At the time of the nvmet_fc_rcv_ls_req() call, there is no content that - * is valid in the structure. - * - * When the structure is used for the LLDD->xmt_ls_rsp() call, the nvmet-fc - * layer will fully set the fields in order to specify the response - * payload buffer and its length as well as the done routine to be called - * upon compeletion of the transmit. The nvmet-fc layer will also set a - * private pointer for its own use in the done routine. - * - * Values set by the NVMET-FC layer prior to calling the LLDD xmt_ls_rsp - * entrypoint. - * @rspbuf: pointer to the LS response buffer - * @rspdma: PCI DMA address of the LS response buffer - * @rsplen: Length, in bytes, of the LS response buffer - * @done: The callback routine the LLDD is to invoke upon completion of - * transmitting the LS response. req argument is the pointer to - * the original ls request. - * @nvmet_fc_private: pointer to an internal NVMET-FC layer structure used - * as part of the NVMET-FC processing. The LLDD is not to access - * this pointer. - */ -struct nvmefc_tgt_ls_req { - void *rspbuf; - dma_addr_t rspdma; - u16 rsplen; - - void (*done)(struct nvmefc_tgt_ls_req *req); - void *nvmet_fc_private; /* LLDD is not to access !! */ -}; - /* Operations that NVME-FC layer may request the LLDD to perform for FCP */ enum { NVMET_FCOP_READDATA = 1, /* xmt data to initiator */ @@ -693,17 +764,19 @@ struct nvmet_fc_target_port { * Entrypoint is Mandatory. * * @xmt_ls_rsp: Called to transmit the response to a FC-NVME FC-4 LS service. - * The nvmefc_tgt_ls_req structure is the same LLDD-supplied exchange + * The nvmefc_ls_rsp structure is the same LLDD-supplied exchange * structure specified in the nvmet_fc_rcv_ls_req() call made when - * the LS request was received. The structure will fully describe + * the LS request was received. The structure will fully describe * the buffers for the response payload and the dma address of the - * payload. The LLDD is to transmit the response (or return a non-zero - * errno status), and upon completion of the transmit, call the - * "done" routine specified in the nvmefc_tgt_ls_req structure - * (argument to done is the ls reqwuest structure itself). - * After calling the done routine, the LLDD shall consider the - * LS handling complete and the nvmefc_tgt_ls_req structure may - * be freed/released. + * payload. The LLDD is to transmit the response (or return a + * non-zero errno status), and upon completion of the transmit, call + * the "done" routine specified in the nvmefc_ls_rsp structure + * (argument to done is the address of the nvmefc_ls_rsp structure + * itself). Upon the completion of the done() routine, the LLDD shall + * consider the LS handling complete and the nvmefc_ls_rsp structure + * may be freed/released. + * The transport will always call the xmt_ls_rsp() routine for any + * LS received. * Entrypoint is Mandatory. * * @fcp_op: Called to perform a data transfer or transmit a response. @@ -798,6 +871,39 @@ struct nvmet_fc_target_port { * should cause the initiator to rescan the discovery controller * on the targetport. * + * @ls_req: Called to issue a FC-NVME FC-4 LS service request. + * The nvme_fc_ls_req structure will fully describe the buffers for + * the request payload and where to place the response payload. + * The targetport that is to issue the LS request is identified by + * the targetport argument. The remote port that is to receive the + * LS request is identified by the hosthandle argument. The nvmet-fc + * transport is only allowed to issue FC-NVME LS's on behalf of an + * association that was created prior by a Create Association LS. + * The hosthandle will originate from the LLDD in the struct + * nvmefc_ls_rsp structure for the Create Association LS that + * was delivered to the transport. The transport will save the + * hosthandle as an attribute of the association. If the LLDD + * loses connectivity with the remote port, it must call the + * nvmet_fc_invalidate_host() routine to remove any references to + * the remote port in the transport. + * The LLDD is to allocate an exchange, issue the LS request, obtain + * the LS response, and call the "done" routine specified in the + * request structure (argument to done is the ls request structure + * itself). + * Entrypoint is Optional - but highly recommended. + * + * @ls_abort: called to request the LLDD to abort the indicated ls request. + * The call may return before the abort has completed. After aborting + * the request, the LLDD must still call the ls request done routine + * indicating an FC transport Aborted status. + * Entrypoint is Mandatory if the ls_req entry point is specified. + * + * @host_release: called to inform the LLDD that the request to invalidate + * the host port indicated by the hosthandle has been fully completed. + * No associations exist with the host port and there will be no + * further references to hosthandle. + * Entrypoint is Mandatory if the lldd calls nvmet_fc_invalidate_host(). + * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -826,11 +932,19 @@ struct nvmet_fc_target_port { * area solely for the of the LLDD and its location is specified by * the targetport->private pointer. * Value is Mandatory. Allowed to be zero. + * + * @lsrqst_priv_sz: The LLDD sets this field to the amount of additional + * memory that it would like nvmet-fc layer to allocate on the LLDD's + * behalf whenever a ls request structure is allocated. The additional + * memory area is solely for use by the LLDD and its location is + * specified by the ls_request->private pointer. + * Value is Mandatory. Allowed to be zero. + * */ struct nvmet_fc_target_template { void (*targetport_delete)(struct nvmet_fc_target_port *tgtport); int (*xmt_ls_rsp)(struct nvmet_fc_target_port *tgtport, - struct nvmefc_tgt_ls_req *tls_req); + struct nvmefc_ls_rsp *ls_rsp); int (*fcp_op)(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq); void (*fcp_abort)(struct nvmet_fc_target_port *tgtport, @@ -840,6 +954,11 @@ struct nvmet_fc_target_template { void (*defer_rcv)(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq); void (*discovery_event)(struct nvmet_fc_target_port *tgtport); + int (*ls_req)(struct nvmet_fc_target_port *targetport, + void *hosthandle, struct nvmefc_ls_req *lsreq); + void (*ls_abort)(struct nvmet_fc_target_port *targetport, + void *hosthandle, struct nvmefc_ls_req *lsreq); + void (*host_release)(void *hosthandle); u32 max_hw_queues; u16 max_sgl_segments; @@ -848,7 +967,9 @@ struct nvmet_fc_target_template { u32 target_features; + /* sizes of additional private data for data structures */ u32 target_priv_sz; + u32 lsrqst_priv_sz; }; @@ -859,10 +980,61 @@ int nvmet_fc_register_targetport(struct nvmet_fc_port_info *portinfo, int nvmet_fc_unregister_targetport(struct nvmet_fc_target_port *tgtport); +/* + * Routine called to pass a NVME-FC LS request, received by the lldd, + * to the nvmet-fc transport. + * + * If the return value is zero: the LS was successfully accepted by the + * transport. + * If the return value is non-zero: the transport has not accepted the + * LS. The lldd should ABTS-LS the LS. + * + * Note: if the LLDD receives and ABTS for the LS prior to the transport + * calling the ops->xmt_ls_rsp() routine to transmit a response, the LLDD + * shall mark the LS as aborted, and when the xmt_ls_rsp() is called: the + * response shall not be transmit and the struct nvmefc_ls_rsp() done + * routine shall be called. The LLDD may transmit the ABTS response as + * soon as the LS was marked or can delay until the xmt_ls_rsp() call is + * made. + * Note: if an RCV LS was successfully posted to the transport and the + * targetport is then unregistered before xmt_ls_rsp() was called for + * the lsrsp structure, the transport will still call xmt_ls_rsp() + * afterward to cleanup the outstanding lsrsp structure. The LLDD should + * noop the transmission of the rsp and call the lsrsp->done() routine + * to allow the lsrsp structure to be released. + */ int nvmet_fc_rcv_ls_req(struct nvmet_fc_target_port *tgtport, - struct nvmefc_tgt_ls_req *lsreq, + void *hosthandle, + struct nvmefc_ls_rsp *rsp, void *lsreqbuf, u32 lsreqbuf_len); +/* + * Routine called by the LLDD whenever it has a logout or loss of + * connectivity to a NVME-FC host port which there had been active + * NVMe controllers for. The host port is indicated by the + * hosthandle. The hosthandle is given to the nvmet-fc transport + * when a NVME LS was received, typically to create a new association. + * The nvmet-fc transport will cache the hostport value with the + * association for use in LS requests for the association. + * When the LLDD calls this routine, the nvmet-fc transport will + * immediately terminate all associations that were created with + * the hosthandle host port. + * The LLDD, after calling this routine and having control returned, + * must assume the transport may subsequently utilize hosthandle as + * part of sending LS's to terminate the association. The LLDD + * should reject the LS's if they are attempted. + * Once the last association has terminated for the hosthandle host + * port, the nvmet-fc transport will call the ops->host_release() + * callback. As of the callback, the nvmet-fc transport will no + * longer reference hosthandle. + */ +void nvmet_fc_invalidate_host(struct nvmet_fc_target_port *tgtport, + void *hosthandle); + +/* + * If nvmet_fc_rcv_fcp_req returns non-zero, the transport has not accepted + * the FCP cmd. The lldd should ABTS-LS the cmd. + */ int nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq, void *cmdiubuf, u32 cmdiubuf_len); -- cgit v1.2.3 From d02abd198633a4c40411b9a5994111452720470d Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Mon, 4 May 2020 01:56:48 -0700 Subject: nvmet: align addrfam list to spec With reference to the NVMeOF Specification (page 44, Figure 38) discovery log page entry provides address family field. We do set the transport type field but the adrfam field is not set when using loop transport and also it doesn't have support in the nvme-cli. So when reading discovery log page with a loop transport it leads to confusing output. As per the spec for adrfam value 254 is reserved for Intra Host Transport i.e. loopback), we add a required macro in the protocol header file, set default port disc addr entry's adrfam to NVMF_ADDR_FAMILY_MAX, and update nvmet_addr_family configfs array for show/store attribute. Without this patch, setting adrfam to (ipv4/ipv6/ib/fc/loop/" ") we get following output for nvme discover command from nvme-cli which is confusing. trtype: loop adrfam: ipv4 trtype: loop adrfam: ipv6 trtype: loop adrfam: infiniband trtype: loop adrfam: fibre-channel trtype: loop # ${CFGFS_HOME}/nvmet/ports/1/addr_adrfam = loop adrfam: pci # <----- pci for loop trtype: loop # ${CFGFS_HOME}/nvmet/ports/1/addr_adrfam = " " adrfam: pci # <----- pci for unrecognized This patch fixes above output :- trtype: loop adrfam: ipv4 trtype: loop adrfam: ipv6 trtype: loop adrfam: infiniband trtype: loop adrfam: fibre-channel trtype: loop # ${CFGFS_HOME}/nvmet/ports/1/addr_adrfam = loop adrfam: loop # <----- loop for loop trtype: loop # ${CFGFS_HOME}/config/nvmet/ports/adrfam = " " adrfam: unrecognized # <----- unrecognized when invalid value Signed-off-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 3d5189f46cb1..2d978d0cbde6 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -38,6 +38,8 @@ enum { NVMF_ADDR_FAMILY_IP6 = 2, /* IP6 */ NVMF_ADDR_FAMILY_IB = 3, /* InfiniBand */ NVMF_ADDR_FAMILY_FC = 4, /* Fibre Channel */ + NVMF_ADDR_FAMILY_LOOP = 254, /* Reserved for host usage */ + NVMF_ADDR_FAMILY_MAX, }; /* Transport Type codes for Discovery Log Page entry TRTYPE field */ -- cgit v1.2.3 From 92decf118f1da4c866515f80387f9cf4d48611d6 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 3 Apr 2020 10:53:46 -0700 Subject: nvme: define constants for identification values Improve code readability by defining the specification's constants that the driver is using when decoding identification payloads. Signed-off-by: Keith Busch Reviewed-by: Bart van Assche Reviewed-by: Chaitanya Kulkarni Acked-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 2d978d0cbde6..b235a48eac8c 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -301,6 +301,8 @@ struct nvme_id_ctrl { }; enum { + NVME_CTRL_CMIC_MULTI_CTRL = 1 << 1, + NVME_CTRL_CMIC_ANA = 1 << 3, NVME_CTRL_ONCS_COMPARE = 1 << 0, NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, NVME_CTRL_ONCS_DSM = 1 << 2, @@ -396,8 +398,12 @@ enum { enum { NVME_NS_FEAT_THIN = 1 << 0, + NVME_NS_FEAT_ATOMICS = 1 << 1, + NVME_NS_FEAT_IO_OPT = 1 << 4, + NVME_NS_ATTR_RO = 1 << 0, NVME_NS_FLBAS_LBA_MASK = 0xf, NVME_NS_FLBAS_META_EXT = 0x10, + NVME_NS_NMIC_SHARED = 1 << 0, NVME_LBAF_RP_BEST = 0, NVME_LBAF_RP_BETTER = 1, NVME_LBAF_RP_GOOD = 2, -- cgit v1.2.3 From ae24345da54e452880808b011fa2d8a0bbd191ba Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:58:59 -0700 Subject: bpf: Implement an interface to register bpf_iter targets The target can call bpf_iter_reg_target() to register itself. The needed information: target: target name seq_ops: the seq_file operations for the target init_seq_private target callback to initialize seq_priv during file open fini_seq_private target callback to clean up seq_priv during file release seq_priv_size: the private_data size needed by the seq_file operations The target name represents a target which provides a seq_ops for iterating objects. The target can provide two callback functions, init_seq_private and fini_seq_private, called during file open/release time. For example, /proc/net/{tcp6, ipv6_route, netlink, ...}, net name space needs to be setup properly during file open and released properly during file release. Function bpf_iter_unreg_target() is also implemented to unregister a particular target. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175859.2474669-1-yhs@fb.com --- include/linux/bpf.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1262ec460ab3..40c78b86fe38 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -31,6 +31,7 @@ struct seq_file; struct btf; struct btf_type; struct exception_table_entry; +struct seq_operations; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -1126,6 +1127,20 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); +typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); +typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); + +struct bpf_iter_reg { + const char *target; + const struct seq_operations *seq_ops; + bpf_iter_init_seq_priv_t init_seq_private; + bpf_iter_fini_seq_priv_t fini_seq_private; + u32 seq_priv_size; +}; + +int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); +void bpf_iter_unreg_target(const char *target); + int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, -- cgit v1.2.3 From 15d83c4d7cef5c067a8b075ce59e97df4f60706e Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:00 -0700 Subject: bpf: Allow loading of a bpf_iter program A bpf_iter program is a tracing program with attach type BPF_TRACE_ITER. The load attribute attach_btf_id is used by the verifier against a particular kernel function, which represents a target, e.g., __bpf_iter__bpf_map for target bpf_map which is implemented later. The program return value must be 0 or 1 for now. 0 : successful, except potential seq_file buffer overflow which is handled by seq_file reader. 1 : request to restart the same object In the future, other return values may be used for filtering or teminating the iterator. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175900.2474947-1-yhs@fb.com --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 40c78b86fe38..f28bdd714754 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1127,6 +1127,8 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); +#define BPF_ITER_FUNC_PREFIX "__bpf_iter__" + typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); @@ -1140,6 +1142,7 @@ struct bpf_iter_reg { int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); +bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); -- cgit v1.2.3 From de4e05cac46d206f9090051ef09930514bff73e4 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:01 -0700 Subject: bpf: Support bpf tracing/iter programs for BPF_LINK_CREATE Given a bpf program, the step to create an anonymous bpf iterator is: - create a bpf_iter_link, which combines bpf program and the target. In the future, there could be more information recorded in the link. A link_fd will be returned to the user space. - create an anonymous bpf iterator with the given link_fd. The bpf_iter_link can be pinned to bpffs mount file system to create a file based bpf iterator as well. The benefit to use of bpf_iter_link: - using bpf link simplifies design and implementation as bpf link is used for other tracing bpf programs. - for file based bpf iterator, bpf_iter_link provides a standard way to replace underlying bpf programs. - for both anonymous and free based iterators, bpf link query capability can be leveraged. The patch added support of tracing/iter programs for BPF_LINK_CREATE. A new link type BPF_LINK_TYPE_ITER is added to facilitate link querying. Currently, only prog_id is needed, so there is no additional in-kernel show_fdinfo() and fill_link_info() hook is needed for BPF_LINK_TYPE_ITER link. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175901.2475084-1-yhs@fb.com --- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f28bdd714754..e93d2d33c82c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1143,6 +1143,7 @@ struct bpf_iter_reg { int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); +int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 8345cdf553b8..29d22752fc87 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -124,3 +124,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) #ifdef CONFIG_CGROUP_BPF BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) #endif +BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) -- cgit v1.2.3 From ac51d99bf81caac8d8881fe52098948110d0de68 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:05 -0700 Subject: bpf: Create anonymous bpf iterator A new bpf command BPF_ITER_CREATE is added. The anonymous bpf iterator is seq_file based. The seq_file private data are referenced by targets. The bpf_iter infrastructure allocated additional space at seq_file->private before the space used by targets to store some meta data, e.g., prog: prog to run session_id: an unique id for each opened seq_file seq_num: how many times bpf programs are queried in this session done_stop: an internal state to decide whether bpf program should be called in seq_ops->stop() or not The seq_num will start from 0 for valid objects. The bpf program may see the same seq_num more than once if - seq_file buffer overflow happens and the same object is retried by bpf_seq_read(), or - the bpf program explicitly requests a retry of the same object Since module is not supported for bpf_iter, all target registeration happens at __init time, so there is no need to change bpf_iter_unreg_target() as it is used mostly in error path of the init function at which time no bpf iterators have been created yet. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175905.2475770-1-yhs@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e93d2d33c82c..80b1b9d8a638 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1144,6 +1144,7 @@ int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int bpf_iter_new_fd(struct bpf_link *link); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); -- cgit v1.2.3 From 367ec3e4834cbd611401c2c40a23c22c825474f1 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:06 -0700 Subject: bpf: Create file bpf iterator To produce a file bpf iterator, the fd must be corresponding to a link_fd assocciated with a trace/iter program. When the pinned file is opened, a seq_file will be generated. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175906.2475893-1-yhs@fb.com --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 80b1b9d8a638..b06653ab3476 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1022,6 +1022,7 @@ static inline void bpf_enable_instrumentation(void) extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; +extern const struct file_operations bpf_iter_fops; #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ extern const struct bpf_prog_ops _name ## _prog_ops; \ @@ -1145,6 +1146,7 @@ void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); +bool bpf_link_is_iter(struct bpf_link *link); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); -- cgit v1.2.3 From e5158d987b72c3f318b4b52a01ac6f3997bd0c00 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:07 -0700 Subject: bpf: Implement common macros/helpers for target iterators Macro DEFINE_BPF_ITER_FUNC is implemented so target can define an init function to capture the BTF type which represents the target. The bpf_iter_meta is a structure holding meta data, common to all targets in the bpf program. Additional marker functions are called before or after bpf_seq_read() show()/next()/stop() callback functions to help calculate precise seq_num and whether call bpf_prog inside stop(). Two functions, bpf_iter_get_info() and bpf_iter_run_prog(), are implemented so target can get needed information from bpf_iter infrastructure and can run the program. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175907.2475956-1-yhs@fb.com --- include/linux/bpf.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b06653ab3476..ffe0b9b669bf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1129,6 +1129,9 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); #define BPF_ITER_FUNC_PREFIX "__bpf_iter__" +#define DEFINE_BPF_ITER_FUNC(target, args...) \ + extern int __bpf_iter__ ## target(args); \ + int __init __bpf_iter__ ## target(args) { return 0; } typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); @@ -1141,12 +1144,20 @@ struct bpf_iter_reg { u32 seq_priv_size; }; +struct bpf_iter_meta { + __bpf_md_ptr(struct seq_file *, seq); + u64 session_id; + u64 seq_num; +}; + int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); +struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); +int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); -- cgit v1.2.3 From 6086d29def80edd78f9832ea6eafa74e3818f6a7 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:09 -0700 Subject: bpf: Add bpf_map iterator Implement seq_file operations to traverse all bpf_maps. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175909.2476096-1-yhs@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ffe0b9b669bf..363ab0751967 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1082,6 +1082,7 @@ int generic_map_update_batch(struct bpf_map *map, int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); +struct bpf_map *bpf_map_get_curr_or_next(u32 *id); extern int sysctl_unprivileged_bpf_disabled; -- cgit v1.2.3 From 138d0be35b141e09f6b267c6ae4094318d4e4491 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:10 -0700 Subject: net: bpf: Add netlink and ipv6_route bpf_iter targets This patch added netlink and ipv6_route targets, using the same seq_ops (except show() and minor changes for stop()) for /proc/net/{netlink,ipv6_route}. The net namespace for these targets are the current net namespace at file open stage, similar to /proc/net/{netlink,ipv6_route} reference counting the net namespace at seq_file open stage. Since module is not supported for now, ipv6_route is supported only if the IPV6 is built-in, i.e., not compiled as a module. The restriction can be lifted once module is properly supported for bpf_iter. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175910.2476329-1-yhs@fb.com --- include/linux/proc_fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 45c05fd9c99d..03953c59807d 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -105,6 +105,9 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo void *data); extern struct pid *tgid_pidfd_to_pid(const struct file *file); +extern int bpf_iter_init_seq_net(void *priv_data); +extern void bpf_iter_fini_seq_net(void *priv_data); + #ifdef CONFIG_PROC_PID_ARCH_STATUS /* * The architecture which selects CONFIG_PROC_PID_ARCH_STATUS must -- cgit v1.2.3 From b121b341e5983bdccf7a5d6cf9236a45c965a31f Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:12 -0700 Subject: bpf: Add PTR_TO_BTF_ID_OR_NULL support Add bpf_reg_type PTR_TO_BTF_ID_OR_NULL support. For tracing/iter program, the bpf program context definition, e.g., for previous bpf_map target, looks like struct bpf_iter__bpf_map { struct bpf_iter_meta *meta; struct bpf_map *map; }; The kernel guarantees that meta is not NULL, but map pointer maybe NULL. The NULL map indicates that all objects have been traversed, so bpf program can take proper action, e.g., do final aggregation and/or send final report to user space. Add btf_id_or_null_non0_off to prog->aux structure, to indicate that if the context access offset is not 0, set to PTR_TO_BTF_ID_OR_NULL instead of PTR_TO_BTF_ID. This bit is set for tracing/iter program. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175912.2476576-1-yhs@fb.com --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 363ab0751967..cf4b6e44f2bc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -320,6 +320,7 @@ enum bpf_reg_type { PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ PTR_TO_BTF_ID, /* reg points to kernel struct */ + PTR_TO_BTF_ID_OR_NULL, /* reg points to kernel struct or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -658,6 +659,7 @@ struct bpf_prog_aux { bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool func_proto_unreliable; + bool btf_id_or_null_non0_off; enum bpf_tramp_prog_type trampoline_prog_type; struct bpf_trampoline *trampoline; struct hlist_node tramp_hlist; -- cgit v1.2.3 From 5a63b7ba50fd6b7a897bf9353dbf31d579cfe116 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 8 May 2020 18:47:20 +0300 Subject: power: supply: add battery parameters Add parsing of new device-tree battery bindings. - trickle-charge-current-microamp - precharge-upper-limit-microvolt - re-charge-voltage-microvolt - over-voltage-threshold-microvolt Signed-off-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 6a34df65d4d1..1f60731ec7fe 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -346,8 +346,12 @@ struct power_supply_battery_info { int charge_full_design_uah; /* microAmp-hours */ int voltage_min_design_uv; /* microVolts */ int voltage_max_design_uv; /* microVolts */ + int tricklecharge_current_ua; /* microAmps */ int precharge_current_ua; /* microAmps */ + int precharge_voltage_max_uv; /* microVolts */ int charge_term_current_ua; /* microAmps */ + int charge_restart_voltage_uv; /* microVolts */ + int overvoltage_limit_uv; /* microVolts */ int constant_charge_current_max_ua; /* microAmps */ int constant_charge_voltage_max_uv; /* microVolts */ int factory_internal_resistance_uohm; /* microOhms */ -- cgit v1.2.3 From e7bb7ecefa817543e11fa3c1c3e55deb90b02e6c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:59:21 -0500 Subject: IB/mlx4: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Jakub Kicinski --- include/linux/mlx4/qp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 8e2828d48d7f..9db93e487496 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -362,7 +362,7 @@ struct mlx4_wqe_datagram_seg { struct mlx4_wqe_lso_seg { __be32 mss_hdr_size; - __be32 header[0]; + __be32 header[]; }; enum mlx4_wqe_bind_seg_flags2 { -- cgit v1.2.3 From 7d374b20908338c9fbb03ea8022a11f3b3e0e55f Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Sun, 10 May 2020 18:30:37 +0300 Subject: interconnect: Add helpers for enabling/disabling a path There is a repeated pattern in multiple drivers where they want to switch the bandwidth between zero and some other value. This is happening often in the suspend/resume callbacks. Let's add helper functions to enable and disable the path, so that callers don't have to take care of remembering the bandwidth values and handle this in the framework instead. With this patch the users can call icc_disable() and icc_enable() to lower their bandwidth request to zero and then restore it back to it's previous value. Suggested-by: Evan Green Suggested-by: Bjorn Andersson Signed-off-by: Georgi Djakov Reviewed-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/20200507120846.8354-1-georgi.djakov@linaro.org Signed-off-by: Georgi Djakov --- include/linux/interconnect.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index 770692421f4c..e56a95e3cf25 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -30,6 +30,8 @@ struct icc_path *icc_get(struct device *dev, const int src_id, struct icc_path *of_icc_get(struct device *dev, const char *name); struct icc_path *devm_of_icc_get(struct device *dev, const char *name); void icc_put(struct icc_path *path); +int icc_enable(struct icc_path *path); +int icc_disable(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); void icc_set_tag(struct icc_path *path, u32 tag); @@ -57,6 +59,16 @@ static inline void icc_put(struct icc_path *path) { } +static inline int icc_enable(struct icc_path *path) +{ + return 0; +} + +static inline int icc_disable(struct icc_path *path) +{ + return 0; +} + static inline int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw) { return 0; -- cgit v1.2.3 From a68a813836e12b15715d9101309899123c250302 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 10 May 2020 21:12:30 +0200 Subject: net: phy: Add cable test support to state machine Running a cable test is desruptive to normal operation of the PHY and can take a 5 to 10 seconds to complete. The RTNL lock cannot be held for this amount of time, and add a new state to the state machine for running a cable test. The driver is expected to implement two functions. The first is used to start a cable test. Once the test has started, it should return. The second function is called once per second, or on interrupt to check if the cable test is complete, and to allow the PHY to report the status. v2: Rename phy_cable_test_abort to phy_abort_cable_test Return different extack when already running test Use phy_init_hw() to reset the PHY Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index a2b91b5f9d0a..632403fc34f4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -372,6 +373,12 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); * - irq or timer will set NOLINK if link goes down * - phy_stop moves to HALTED * + * CABLETEST: PHY is performing a cable test. Packet reception/sending + * is not expected to work, carrier will be indicated as down. PHY will be + * poll once per second, or on interrupt for it current state. + * Once complete, move to UP to restart the PHY. + * - phy_stop aborts the running test and moves to HALTED + * * HALTED: PHY is up, but no polling or interrupts are done. Or * PHY is in an error state. * - phy_start moves to UP @@ -383,6 +390,7 @@ enum phy_state { PHY_UP, PHY_RUNNING, PHY_NOLINK, + PHY_CABLETEST, }; /** @@ -689,6 +697,13 @@ struct phy_driver { int (*module_eeprom)(struct phy_device *dev, struct ethtool_eeprom *ee, u8 *data); + /* Start a cable test */ + int (*cable_test_start)(struct phy_device *dev); + /* Once per second, or on interrupt, request the status of the + * test. + */ + int (*cable_test_get_status)(struct phy_device *dev, bool *finished); + /* Get statistics from the phy using ethtool */ int (*get_sset_count)(struct phy_device *dev); void (*get_strings)(struct phy_device *dev, u8 *data); @@ -1227,6 +1242,19 @@ int phy_speed_up(struct phy_device *phydev); int phy_restart_aneg(struct phy_device *phydev); int phy_reset_after_clk_enable(struct phy_device *phydev); +#if IS_ENABLED(CONFIG_PHYLIB) +int phy_start_cable_test(struct phy_device *phydev, + struct netlink_ext_ack *extack); +#else +static inline +int phy_start_cable_test(struct phy_device *phydev, + struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); + return -EOPNOTSUPP; +} +#endif + static inline void phy_device_reset(struct phy_device *phydev, int value) { mdio_device_reset(&phydev->mdio, value); -- cgit v1.2.3 From 97c22438963a7484c05c59ab6654e30f0a3e9288 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 10 May 2020 21:12:32 +0200 Subject: net: phy: Add support for polling cable test Some PHYs are not capable of generating interrupts when a cable test finished. They do however support interrupts for normal operations, like link up/down. As such, the PHY state machine would normally not poll the PHY. Add support for indicating the PHY state machine must poll the PHY when performing a cable test. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 632403fc34f4..f58eee735a45 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -79,6 +79,7 @@ extern const int phy_10gbit_features_array[1]; #define PHY_IS_INTERNAL 0x00000001 #define PHY_RST_AFTER_CLK_EN 0x00000002 +#define PHY_POLL_CABLE_TEST 0x00000004 #define MDIO_DEVICE_IS_PHY 0x80000000 /* Interface Mode definitions */ @@ -1061,6 +1062,10 @@ static inline bool phy_interrupt_is_valid(struct phy_device *phydev) */ static inline bool phy_polling_mode(struct phy_device *phydev) { + if (phydev->state == PHY_CABLETEST) + if (phydev->drv->flags & PHY_POLL_CABLE_TEST) + return true; + return phydev->irq == PHY_POLL; } -- cgit v1.2.3 From 1dd3f212af30b42c90ba252c165f2f6d2ddf5230 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 10 May 2020 21:12:36 +0200 Subject: net: ethtool: Add infrastructure for reporting cable test results Provide infrastructure for PHY drivers to report the cable test results. A netlink skb is associated to the phydev. Helpers will be added which can add results to this skb. Once the test has finished the results are sent to user space. When netlink ethtool is not part of the kernel configuration stubs are provided. It is also impossible to trigger a cable test, so the error code returned by the alloc function is of no consequence. v2: Include the status complete in the netlink notification message v4: Replace -EINVAL with -EMSGSIZE Signed-off-by: Andrew Lunn Reviewed-by: Michal Kubecek Signed-off-by: Jakub Kicinski --- include/linux/ethtool_netlink.h | 20 ++++++++++++++++++++ include/linux/phy.h | 5 +++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index d01b77887f82..7d763ba22f6f 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -14,4 +14,24 @@ enum ethtool_multicast_groups { ETHNL_MCGRP_MONITOR, }; +struct phy_device; + +#if IS_ENABLED(CONFIG_ETHTOOL_NETLINK) +int ethnl_cable_test_alloc(struct phy_device *phydev); +void ethnl_cable_test_free(struct phy_device *phydev); +void ethnl_cable_test_finished(struct phy_device *phydev); +#else +static inline int ethnl_cable_test_alloc(struct phy_device *phydev) +{ + return -ENOTSUPP; +} + +static inline void ethnl_cable_test_free(struct phy_device *phydev) +{ +} + +static inline void ethnl_cable_test_finished(struct phy_device *phydev) +{ +} +#endif /* IS_ENABLED(ETHTOOL_NETLINK) */ #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ diff --git a/include/linux/phy.h b/include/linux/phy.h index f58eee735a45..169fae4249a9 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -523,6 +523,11 @@ struct phy_device { /* For use by PHYs inside the same package that need a shared state. */ struct phy_package_shared *shared; + /* Reporting cable test results */ + struct sk_buff *skb; + void *ehdr; + struct nlattr *nest; + /* Interrupt and Polling infrastructure */ struct delayed_work state_queue; -- cgit v1.2.3 From 1e2dc14509fd072739e4bab98ac42317267dbad6 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 10 May 2020 21:12:37 +0200 Subject: net: ethtool: Add helpers for reporting test results The PHY drivers can use these helpers for reporting the results. The results get translated into netlink attributes which are added to the pre-allocated skbuf. v3: Poison phydev->skb Return -EMSGSIZE when ethnl_bcastmsg_put() fails Return valid error code when nla_nest_start() fails Use u8 for results Actually put u32 length into message v4: s/ENOTSUPP/EOPNOTSUPP/g Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Michal Kubecek Signed-off-by: Jakub Kicinski --- include/linux/ethtool_netlink.h | 15 ++++++++++++++- include/linux/phy.h | 4 ++++ 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 7d763ba22f6f..e317fc99565e 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -20,10 +20,12 @@ struct phy_device; int ethnl_cable_test_alloc(struct phy_device *phydev); void ethnl_cable_test_free(struct phy_device *phydev); void ethnl_cable_test_finished(struct phy_device *phydev); +int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result); +int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm); #else static inline int ethnl_cable_test_alloc(struct phy_device *phydev) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline void ethnl_cable_test_free(struct phy_device *phydev) @@ -33,5 +35,16 @@ static inline void ethnl_cable_test_free(struct phy_device *phydev) static inline void ethnl_cable_test_finished(struct phy_device *phydev) { } +static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, + u8 result) +{ + return -EOPNOTSUPP; +} + +static inline int ethnl_cable_test_fault_length(struct phy_device *phydev, + u8 pair, u32 cm) +{ + return -EOPNOTSUPP; +} #endif /* IS_ENABLED(ETHTOOL_NETLINK) */ #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ diff --git a/include/linux/phy.h b/include/linux/phy.h index 169fae4249a9..5d8ff5428010 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1265,6 +1265,10 @@ int phy_start_cable_test(struct phy_device *phydev, } #endif +int phy_cable_test_result(struct phy_device *phydev, u8 pair, u16 result); +int phy_cable_test_fault_length(struct phy_device *phydev, u8 pair, + u16 cm); + static inline void phy_device_reset(struct phy_device *phydev, int value) { mdio_device_reset(&phydev->mdio, value); -- cgit v1.2.3 From b6ca09cb156d349e6fdde8a8466ec15b902d1419 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:59:35 -0500 Subject: net/mlx5: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- include/linux/mlx5/mlx5_ifc.h | 66 +++++++++++++++++++++---------------------- include/linux/mlx5/qp.h | 2 +- 3 files changed, 35 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 267dfcc5493e..24e04901f92e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -201,7 +201,7 @@ struct mlx5_rsc_debug { void *object; enum dbg_rsc_type type; struct dentry *root; - struct mlx5_field_desc fields[0]; + struct mlx5_field_desc fields[]; }; enum mlx5_dev_event { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fb243848132d..c9dd6e99ad56 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1703,7 +1703,7 @@ struct mlx5_ifc_wq_bits { u8 reserved_at_140[0x4c0]; - struct mlx5_ifc_cmd_pas_bits pas[0]; + struct mlx5_ifc_cmd_pas_bits pas[]; }; struct mlx5_ifc_rq_num_bits { @@ -1921,7 +1921,7 @@ struct mlx5_ifc_resource_dump_menu_segment_bits { u8 reserved_at_20[0x10]; u8 num_of_records[0x10]; - struct mlx5_ifc_resource_dump_menu_record_bits record[0]; + struct mlx5_ifc_resource_dump_menu_record_bits record[]; }; struct mlx5_ifc_resource_dump_resource_segment_bits { @@ -1933,7 +1933,7 @@ struct mlx5_ifc_resource_dump_resource_segment_bits { u8 index2[0x20]; - u8 payload[0][0x20]; + u8 payload[][0x20]; }; struct mlx5_ifc_resource_dump_terminate_segment_bits { @@ -3010,7 +3010,7 @@ struct mlx5_ifc_flow_context_bits { u8 reserved_at_1200[0x600]; - union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[0]; + union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[]; }; enum { @@ -3303,7 +3303,7 @@ struct mlx5_ifc_rqtc_bits { u8 reserved_at_e0[0x6a0]; - struct mlx5_ifc_rq_num_bits rq_num[0]; + struct mlx5_ifc_rq_num_bits rq_num[]; }; enum { @@ -3415,7 +3415,7 @@ struct mlx5_ifc_nic_vport_context_bits { u8 reserved_at_7e0[0x20]; - u8 current_uc_mac_address[0][0x40]; + u8 current_uc_mac_address[][0x40]; }; enum { @@ -4338,7 +4338,7 @@ struct mlx5_ifc_query_xrc_srq_out_bits { u8 reserved_at_280[0x600]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_query_xrc_srq_in_bits { @@ -4616,7 +4616,7 @@ struct mlx5_ifc_query_srq_out_bits { u8 reserved_at_280[0x600]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_query_srq_in_bits { @@ -4827,7 +4827,7 @@ struct mlx5_ifc_query_qp_out_bits { u8 reserved_at_800[0x80]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_query_qp_in_bits { @@ -5160,7 +5160,7 @@ struct mlx5_ifc_query_hca_vport_pkey_out_bits { u8 reserved_at_40[0x40]; - struct mlx5_ifc_pkey_bits pkey[0]; + struct mlx5_ifc_pkey_bits pkey[]; }; struct mlx5_ifc_query_hca_vport_pkey_in_bits { @@ -5196,7 +5196,7 @@ struct mlx5_ifc_query_hca_vport_gid_out_bits { u8 gids_num[0x10]; u8 reserved_at_70[0x10]; - struct mlx5_ifc_array128_auto_bits gid[0]; + struct mlx5_ifc_array128_auto_bits gid[]; }; struct mlx5_ifc_query_hca_vport_gid_in_bits { @@ -5464,7 +5464,7 @@ struct mlx5_ifc_query_flow_counter_out_bits { u8 reserved_at_40[0x40]; - struct mlx5_ifc_traffic_counter_bits flow_statistics[0]; + struct mlx5_ifc_traffic_counter_bits flow_statistics[]; }; struct mlx5_ifc_query_flow_counter_in_bits { @@ -5558,7 +5558,7 @@ struct mlx5_ifc_query_eq_out_bits { u8 reserved_at_300[0x580]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_query_eq_in_bits { @@ -5583,7 +5583,7 @@ struct mlx5_ifc_packet_reformat_context_in_bits { u8 reserved_at_20[0x10]; u8 reformat_data[2][0x8]; - u8 more_reformat_data[0][0x8]; + u8 more_reformat_data[][0x8]; }; struct mlx5_ifc_query_packet_reformat_context_out_bits { @@ -5594,7 +5594,7 @@ struct mlx5_ifc_query_packet_reformat_context_out_bits { u8 reserved_at_40[0xa0]; - struct mlx5_ifc_packet_reformat_context_in_bits packet_reformat_context[0]; + struct mlx5_ifc_packet_reformat_context_in_bits packet_reformat_context[]; }; struct mlx5_ifc_query_packet_reformat_context_in_bits { @@ -5833,7 +5833,7 @@ struct mlx5_ifc_query_cq_out_bits { u8 reserved_at_280[0x600]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_query_cq_in_bits { @@ -6440,7 +6440,7 @@ struct mlx5_ifc_modify_cq_in_bits { u8 reserved_at_300[0x580]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_modify_cong_status_out_bits { @@ -6504,7 +6504,7 @@ struct mlx5_ifc_manage_pages_out_bits { u8 reserved_at_60[0x20]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; enum { @@ -6526,7 +6526,7 @@ struct mlx5_ifc_manage_pages_in_bits { u8 input_num_entries[0x20]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_mad_ifc_out_bits { @@ -7481,7 +7481,7 @@ struct mlx5_ifc_create_xrc_srq_in_bits { u8 reserved_at_300[0x580]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_create_tis_out_bits { @@ -7557,7 +7557,7 @@ struct mlx5_ifc_create_srq_in_bits { u8 reserved_at_280[0x600]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_create_sq_out_bits { @@ -7718,7 +7718,7 @@ struct mlx5_ifc_create_qp_in_bits { u8 wq_umem_valid[0x1]; u8 reserved_at_861[0x1f]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_create_psv_out_bits { @@ -7789,7 +7789,7 @@ struct mlx5_ifc_create_mkey_in_bits { u8 reserved_at_320[0x560]; - u8 klm_pas_mtt[0][0x20]; + u8 klm_pas_mtt[][0x20]; }; enum { @@ -7922,7 +7922,7 @@ struct mlx5_ifc_create_eq_in_bits { u8 reserved_at_3c0[0x4c0]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_create_dct_out_bits { @@ -7979,7 +7979,7 @@ struct mlx5_ifc_create_cq_in_bits { u8 cq_umem_valid[0x1]; u8 reserved_at_2e1[0x59f]; - u8 pas[0][0x40]; + u8 pas[][0x40]; }; struct mlx5_ifc_config_int_moderation_out_bits { @@ -8335,7 +8335,7 @@ struct mlx5_ifc_access_register_out_bits { u8 reserved_at_40[0x40]; - u8 register_data[0][0x20]; + u8 register_data[][0x20]; }; enum { @@ -8355,7 +8355,7 @@ struct mlx5_ifc_access_register_in_bits { u8 argument[0x20]; - u8 register_data[0][0x20]; + u8 register_data[][0x20]; }; struct mlx5_ifc_sltp_reg_bits { @@ -9372,7 +9372,7 @@ struct mlx5_ifc_cmd_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 command[0][0x20]; + u8 command[][0x20]; }; struct mlx5_ifc_cmd_if_box_bits { @@ -9666,7 +9666,7 @@ struct mlx5_ifc_mcqi_reg_bits { u8 reserved_at_a0[0x10]; u8 data_size[0x10]; - union mlx5_ifc_mcqi_reg_data_bits data[0]; + union mlx5_ifc_mcqi_reg_data_bits data[]; }; struct mlx5_ifc_mcc_reg_bits { @@ -10252,7 +10252,7 @@ struct mlx5_ifc_umem_bits { u8 num_of_mtt[0x40]; - struct mlx5_ifc_mtt_bits mtt[0]; + struct mlx5_ifc_mtt_bits mtt[]; }; struct mlx5_ifc_uctx_bits { @@ -10377,7 +10377,7 @@ struct mlx5_ifc_mtrc_stdb_bits { u8 reserved_at_4[0x4]; u8 read_size[0x18]; u8 start_offset[0x20]; - u8 string_db_data[0]; + u8 string_db_data[]; }; struct mlx5_ifc_mtrc_ctrl_bits { @@ -10431,7 +10431,7 @@ struct mlx5_ifc_query_esw_functions_out_bits { struct mlx5_ifc_host_params_context_bits host_params_context; u8 reserved_at_280[0x180]; - u8 host_sf_enable[0][0x40]; + u8 host_sf_enable[][0x40]; }; struct mlx5_ifc_sf_partition_bits { @@ -10451,7 +10451,7 @@ struct mlx5_ifc_query_sf_partitions_out_bits { u8 reserved_at_60[0x20]; - struct mlx5_ifc_sf_partition_bits sf_partition[0]; + struct mlx5_ifc_sf_partition_bits sf_partition[]; }; struct mlx5_ifc_query_sf_partitions_in_bits { diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index f23eb18526fe..1af5e460b5f6 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -408,7 +408,7 @@ struct mlx5_wqe_signature_seg { struct mlx5_wqe_inline_seg { __be32 byte_count; - __be32 data[0]; + __be32 data[]; }; enum mlx5_sig_type { -- cgit v1.2.3 From ac02a451a6148bb9c395b39783ce7299eddf4f31 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 10 May 2020 19:37:43 +0300 Subject: net: dsa: sja1105: implement cross-chip bridging operations sja1105 uses dsa_8021q for DSA tagging, a format which is VLAN at heart and which is compatible with cascading. A complete description of this tagging format is in net/dsa/tag_8021q.c, but a quick summary is that each external-facing port tags incoming frames with a unique pvid, and this special VLAN is transmitted as tagged towards the inside of the system, and as untagged towards the exterior. The tag encodes the switch id and the source port index. This means that cross-chip bridging for dsa_8021q only entails adding the dsa_8021q pvids of one switch to the RX filter of the other switches. Everything else falls naturally into place, as long as the bottom-end of ports (the leaves in the tree) is comprised exclusively of dsa_8021q-compatible (i.e. sja1105 switches). Otherwise, there would be a chance that a front-panel switch transmits a packet tagged with a dsa_8021q header, header which it wouldn't be able to remove, and which would hence "leak" out. The only use case I tested (due to lack of board availability) was when the sja1105 switches are part of disjoint trees (however, this doesn't change the fact that multiple sja1105 switches still need unique switch identifiers in such a system). But in principle, even "true" single-tree setups (with DSA links) should work just as fine, except for a small change which I can't test: dsa_towards_port should be used instead of dsa_upstream_port (I made the assumption that the routing port that any sja1105 should use towards its neighbours is the CPU port. That might not hold true in other setups). Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/linux/dsa/8021q.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index c620d9139c28..b8daaec0896e 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -12,11 +12,33 @@ struct sk_buff; struct net_device; struct packet_type; +struct dsa_8021q_crosschip_link { + struct list_head list; + int port; + struct dsa_switch *other_ds; + int other_port; + refcount_t refcount; +}; + #if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, bool enabled); +int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, + int other_port, bool enabled); + +int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, + int other_port, struct net_device *br, + struct list_head *crosschip_links); + +int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, + int other_port, struct net_device *br, + struct list_head *crosschip_links); + struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); @@ -36,6 +58,29 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, return 0; } +int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, + int other_port, bool enabled) +{ + return 0; +} + +int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, + int other_port, struct net_device *br, + struct list_head *crosschip_links) +{ + return 0; +} + +int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, + int other_port, struct net_device *br, + struct list_head *crosschip_links) +{ + return 0; +} + struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci) { -- cgit v1.2.3 From 479da1f538a2f3547e15f9d5922c611b69ec2fbc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Noralf=20Tr=C3=B8nnes?= Date: Sat, 9 May 2020 16:16:10 +0200 Subject: backlight: Add backlight_device_get_by_name() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a way to lookup a backlight device based on its name. Will be used by a USB display gadget getting the name from configfs. Signed-off-by: Noralf Trønnes Reviewed-by: Sam Ravnborg Reviewed-by: Daniel Thompson Acked-by: Jingoo Han Signed-off-by: Lee Jones --- include/linux/backlight.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index c7d6b2e8c3b5..56e4580d4f55 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -190,6 +190,7 @@ extern void backlight_force_update(struct backlight_device *bd, extern int backlight_register_notifier(struct notifier_block *nb); extern int backlight_unregister_notifier(struct notifier_block *nb); extern struct backlight_device *backlight_device_get_by_type(enum backlight_type type); +struct backlight_device *backlight_device_get_by_name(const char *name); extern int backlight_device_set_brightness(struct backlight_device *bd, unsigned long brightness); #define to_backlight_device(obj) container_of(obj, struct backlight_device, dev) -- cgit v1.2.3 From 83c411c29b90b7de505a2fe1d655293c95f8ba90 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 28 Apr 2020 11:42:54 +0200 Subject: mtd: rawnand: timings: Add mode information to the timings structure Convert the timings union into a structure containing the mode and the actual values. The values are still a union in prevision of the addition of the NVDDR modes. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200428094302.14624-2-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 1e76196f9829..21873168ba4d 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -491,13 +491,17 @@ enum nand_data_interface_type { /** * struct nand_data_interface - NAND interface timing * @type: type of the timing - * @timings: The timing, type according to @type + * @timings: The timing information + * @timings.mode: Timing mode as defined in the specification * @timings.sdr: Use it when @type is %NAND_SDR_IFACE. */ struct nand_data_interface { enum nand_data_interface_type type; - union { - struct nand_sdr_timings sdr; + struct nand_timings { + unsigned int mode; + union { + struct nand_sdr_timings sdr; + }; } timings; }; -- cgit v1.2.3 From 9e3307a169537a6adc30b13bf9063e94990a5493 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 3 May 2020 17:53:37 +0200 Subject: mtd: Add support for emulated SLC mode on MLC NANDs MLC NANDs can be made a bit more reliable if we only program the lower page of each pair. At least, this solves the paired-pages corruption issue. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200503155341.16712-5-miquel.raynal@bootlin.com --- include/linux/mtd/mtd.h | 7 ++++++- include/linux/mtd/partitions.h | 2 ++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 2d1f4a61f4ac..157357ec1441 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -200,6 +200,8 @@ struct mtd_debug_info { * * @node: list node used to add an MTD partition to the parent partition list * @offset: offset of the partition relatively to the parent offset + * @size: partition size. Should be equal to mtd->size unless + * MTD_SLC_ON_MLC_EMULATION is set * @flags: original flags (before the mtdpart logic decided to tweak them based * on flash constraints, like eraseblock/pagesize alignment) * @@ -209,6 +211,7 @@ struct mtd_debug_info { struct mtd_part { struct list_head node; u64 offset; + u64 size; u32 flags; }; @@ -622,7 +625,9 @@ static inline uint32_t mtd_mod_by_ws(uint64_t sz, struct mtd_info *mtd) static inline int mtd_wunit_per_eb(struct mtd_info *mtd) { - return mtd->erasesize / mtd->writesize; + struct mtd_info *master = mtd_get_master(mtd); + + return master->erasesize / mtd->writesize; } static inline int mtd_offset_to_wunit(struct mtd_info *mtd, loff_t offs) diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index e545c050d3e8..b74a539ec581 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -37,6 +37,7 @@ * master MTD flag set for the corresponding MTD partition. * For example, to force a read-only partition, simply adding * MTD_WRITEABLE to the mask_flags will do the trick. + * add_flags: contains flags to add to the parent flags * * Note: writeable partitions require their size and offset be * erasesize aligned (e.g. use MTDPART_OFS_NEXTBLK). @@ -48,6 +49,7 @@ struct mtd_partition { uint64_t size; /* partition size */ uint64_t offset; /* offset within the master MTD space */ uint32_t mask_flags; /* master MTD flags to mask out for this partition */ + uint32_t add_flags; /* flags to add to the partition */ struct device_node *of_node; }; -- cgit v1.2.3 From dd6ed5c9890b759ba1b56697b9f3f50e71909e43 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 May 2020 12:52:29 +0200 Subject: mtd: rawnand: Translate obscure bitfields into readable macros Use the BIT() macro instead of defining a 8-digit value. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200507105241.14299-2-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 21873168ba4d..4b58de842340 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -129,36 +129,36 @@ enum nand_ecc_algo { * features. */ /* Buswidth is 16 bit */ -#define NAND_BUSWIDTH_16 0x00000002 +#define NAND_BUSWIDTH_16 BIT(1) /* Chip has cache program function */ -#define NAND_CACHEPRG 0x00000008 +#define NAND_CACHEPRG BIT(3) /* * Chip requires ready check on read (for auto-incremented sequential read). * True only for small page devices; large page devices do not support * autoincrement. */ -#define NAND_NEED_READRDY 0x00000100 +#define NAND_NEED_READRDY BIT(8) /* Chip does not allow subpage writes */ -#define NAND_NO_SUBPAGE_WRITE 0x00000200 +#define NAND_NO_SUBPAGE_WRITE BIT(9) /* Device is one of 'new' xD cards that expose fake nand command set */ -#define NAND_BROKEN_XD 0x00000400 +#define NAND_BROKEN_XD BIT(10) /* Device behaves just like nand, but is readonly */ -#define NAND_ROM 0x00000800 +#define NAND_ROM BIT(11) /* Device supports subpage reads */ -#define NAND_SUBPAGE_READ 0x00001000 +#define NAND_SUBPAGE_READ BIT(12) /* * Some MLC NANDs need data scrambling to limit bitflips caused by repeated * patterns. */ -#define NAND_NEED_SCRAMBLING 0x00002000 +#define NAND_NEED_SCRAMBLING BIT(13) /* Device needs 3rd row address cycle */ -#define NAND_ROW_ADDR_3 0x00004000 +#define NAND_ROW_ADDR_3 BIT(14) /* Options valid for Samsung large page devices */ #define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG @@ -173,9 +173,9 @@ enum nand_ecc_algo { * Position within the block: Each of these pages needs to be checked for a * bad block marking pattern. */ -#define NAND_BBM_FIRSTPAGE 0x01000000 -#define NAND_BBM_SECONDPAGE 0x02000000 -#define NAND_BBM_LASTPAGE 0x04000000 +#define NAND_BBM_FIRSTPAGE BIT(24) +#define NAND_BBM_SECONDPAGE BIT(25) +#define NAND_BBM_LASTPAGE BIT(26) /* Position within the OOB data of the page */ #define NAND_BBM_POS_SMALL 5 @@ -183,21 +183,21 @@ enum nand_ecc_algo { /* Non chip related options */ /* This option skips the bbt scan during initialization. */ -#define NAND_SKIP_BBTSCAN 0x00010000 +#define NAND_SKIP_BBTSCAN BIT(16) /* Chip may not exist, so silence any errors in scan */ -#define NAND_SCAN_SILENT_NODEV 0x00040000 +#define NAND_SCAN_SILENT_NODEV BIT(18) /* * Autodetect nand buswidth with readid/onfi. * This suppose the driver will configure the hardware in 8 bits mode * when calling nand_scan_ident, and update its configuration * before calling nand_scan_tail. */ -#define NAND_BUSWIDTH_AUTO 0x00080000 +#define NAND_BUSWIDTH_AUTO BIT(19) /* * This option could be defined by controller drivers to protect against * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers */ -#define NAND_USE_BOUNCE_BUFFER 0x00100000 +#define NAND_USE_BOUNCE_BUFFER BIT(20) /* * In case your controller is implementing ->legacy.cmd_ctrl() and is relying @@ -207,20 +207,20 @@ enum nand_ecc_algo { * If your controller already takes care of this delay, you don't need to set * this flag. */ -#define NAND_WAIT_TCCS 0x00200000 +#define NAND_WAIT_TCCS BIT(21) /* * Whether the NAND chip is a boot medium. Drivers might use this information * to select ECC algorithms supported by the boot ROM or similar restrictions. */ -#define NAND_IS_BOOT_MEDIUM 0x00400000 +#define NAND_IS_BOOT_MEDIUM BIT(22) /* * Do not try to tweak the timings at runtime. This is needed when the * controller initializes the timings on itself or when it relies on * configuration done by the bootloader. */ -#define NAND_KEEP_TIMINGS 0x00800000 +#define NAND_KEEP_TIMINGS BIT(23) /* Cell info constants */ #define NAND_CI_CHIPNR_MSK 0x03 -- cgit v1.2.3 From 96d627bdf112d116a79c86435550cd18b9a9d82b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 May 2020 12:52:30 +0200 Subject: mtd: rawnand: Reorder the nand_chip->options flags These flags are in a strange order, reorder the list, add spaces when it is relevant, pack definitions that are related. There is no functional change. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200507105241.14299-3-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 57 ++++++++++++++++++++++++--------------------- 1 file changed, 30 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 4b58de842340..e70fea67030b 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -118,20 +118,25 @@ enum nand_ecc_algo { #define NAND_ECC_GENERIC_ERASED_CHECK BIT(0) #define NAND_ECC_MAXIMIZE BIT(1) -/* - * When using software implementation of Hamming, we can specify which byte - * ordering should be used. - */ -#define NAND_ECC_SOFT_HAMMING_SM_ORDER BIT(2) - /* * Option constants for bizarre disfunctionality and real * features. */ + /* Buswidth is 16 bit */ #define NAND_BUSWIDTH_16 BIT(1) + +/* + * When using software implementation of Hamming, we can specify which byte + * ordering should be used. + */ +#define NAND_ECC_SOFT_HAMMING_SM_ORDER BIT(2) + /* Chip has cache program function */ #define NAND_CACHEPRG BIT(3) +/* Options valid for Samsung large page devices */ +#define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG + /* * Chip requires ready check on read (for auto-incremented sequential read). * True only for small page devices; large page devices do not support @@ -150,6 +155,8 @@ enum nand_ecc_algo { /* Device supports subpage reads */ #define NAND_SUBPAGE_READ BIT(12) +/* Macros to identify the above */ +#define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) /* * Some MLC NANDs need data scrambling to limit bitflips caused by repeated @@ -160,32 +167,12 @@ enum nand_ecc_algo { /* Device needs 3rd row address cycle */ #define NAND_ROW_ADDR_3 BIT(14) -/* Options valid for Samsung large page devices */ -#define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG - -/* Macros to identify the above */ -#define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) - -/* - * There are different places where the manufacturer stores the factory bad - * block markers. - * - * Position within the block: Each of these pages needs to be checked for a - * bad block marking pattern. - */ -#define NAND_BBM_FIRSTPAGE BIT(24) -#define NAND_BBM_SECONDPAGE BIT(25) -#define NAND_BBM_LASTPAGE BIT(26) - -/* Position within the OOB data of the page */ -#define NAND_BBM_POS_SMALL 5 -#define NAND_BBM_POS_LARGE 0 - /* Non chip related options */ /* This option skips the bbt scan during initialization. */ #define NAND_SKIP_BBTSCAN BIT(16) /* Chip may not exist, so silence any errors in scan */ #define NAND_SCAN_SILENT_NODEV BIT(18) + /* * Autodetect nand buswidth with readid/onfi. * This suppose the driver will configure the hardware in 8 bits mode @@ -193,6 +180,7 @@ enum nand_ecc_algo { * before calling nand_scan_tail. */ #define NAND_BUSWIDTH_AUTO BIT(19) + /* * This option could be defined by controller drivers to protect against * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers @@ -222,11 +210,26 @@ enum nand_ecc_algo { */ #define NAND_KEEP_TIMINGS BIT(23) +/* + * There are different places where the manufacturer stores the factory bad + * block markers. + * + * Position within the block: Each of these pages needs to be checked for a + * bad block marking pattern. + */ +#define NAND_BBM_FIRSTPAGE BIT(24) +#define NAND_BBM_SECONDPAGE BIT(25) +#define NAND_BBM_LASTPAGE BIT(26) + /* Cell info constants */ #define NAND_CI_CHIPNR_MSK 0x03 #define NAND_CI_CELLTYPE_MSK 0x0C #define NAND_CI_CELLTYPE_SHIFT 2 +/* Position within the OOB data of the page */ +#define NAND_BBM_POS_SMALL 5 +#define NAND_BBM_POS_LARGE 0 + /** * struct nand_parameters - NAND generic parameters from the parameter page * @model: Model name -- cgit v1.2.3 From ce8148d7b8f204a18188e3cd7386c8dddbb461a1 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 May 2020 12:52:31 +0200 Subject: mtd: rawnand: Rename a NAND chip option NAND controller drivers can set the NAND_USE_BOUNCE_BUFFER flag to a chip 'option' field. With this flag, the core is responsible of providing DMA-able buffers. The current behavior is to not force the use of a bounce buffer when the core thinks this is not needed. So in the end the name is a bit misleading, because in theory we will always have a DMA buffer but in practice it will not always be a bounce buffer. Rename this flag NAND_USES_DMA to be more accurate. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200507105241.14299-4-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index e70fea67030b..d1f5c5258e35 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -185,7 +185,7 @@ enum nand_ecc_algo { * This option could be defined by controller drivers to protect against * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers */ -#define NAND_USE_BOUNCE_BUFFER BIT(20) +#define NAND_USES_DMA BIT(20) /* * In case your controller is implementing ->legacy.cmd_ctrl() and is relying -- cgit v1.2.3 From b451f5beece3f5556920992e7498d23f6da6ef6e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 May 2020 12:52:36 +0200 Subject: mtd: rawnand: Give the possibility to verify a read operation is supported This can be used to discriminate between two path in the parameter page detection: use data_in cycles (like before) if supported, use the CHANGE READ COLUMN command otherwise. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200507105241.14299-9-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index d1f5c5258e35..70380c91731c 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1363,7 +1363,7 @@ int nand_change_write_column_op(struct nand_chip *chip, unsigned int offset_in_page, const void *buf, unsigned int len, bool force_8bit); int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len, - bool force_8bit); + bool force_8bit, bool check_only); int nand_write_data_op(struct nand_chip *chip, const void *buf, unsigned int len, bool force_8bit); -- cgit v1.2.3 From 658beb6639606268bd48eb7de7cf308d6b10600f Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 May 2020 12:52:39 +0200 Subject: mtd: rawnand: Expose monolithic read/write_page_raw() helpers The current nand_read/write_page_raw() helpers are already widely used but do not fit the purpose of "constrained" controllers which cannot, for instance, separate command/address cycles with data cycles. Workaround this issue by proposing alternative helpers that can be used by these controller drivers instead. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200507105241.14299-12-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 70380c91731c..406e9ff0f45c 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1328,13 +1328,17 @@ int nand_read_oob_std(struct nand_chip *chip, int page); int nand_get_set_features_notsupp(struct nand_chip *chip, int addr, u8 *subfeature_param); -/* Default read_page_raw implementation */ +/* read_page_raw implementations */ int nand_read_page_raw(struct nand_chip *chip, uint8_t *buf, int oob_required, int page); +int nand_monolithic_read_page_raw(struct nand_chip *chip, uint8_t *buf, + int oob_required, int page); -/* Default write_page_raw implementation */ +/* write_page_raw implementations */ int nand_write_page_raw(struct nand_chip *chip, const uint8_t *buf, int oob_required, int page); +int nand_monolithic_write_page_raw(struct nand_chip *chip, const uint8_t *buf, + int oob_required, int page); /* Reset and initialize a NAND device */ int nand_reset(struct nand_chip *chip, int chipnr); -- cgit v1.2.3 From ec7cfc3d763c761ff1ad5a4e66c4f94098d7e161 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 11 May 2020 08:49:15 +0200 Subject: mtd: rawnand: Add a NAND_NO_BBM_QUIRK flag Some controllers with embedded ECC engines override the BBM marker with data or ECC bytes, thus making bad block detection through bad block marker impossible. Let's flag those chips so the core knows it shouldn't check the BBM and consider all blocks good. This should allow us to get rid of two implementers of the legacy.block_bad() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200511064917.6255-1-boris.brezillon@collabora.com --- include/linux/mtd/rawnand.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 406e9ff0f45c..0f45b6984ad1 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -221,6 +221,14 @@ enum nand_ecc_algo { #define NAND_BBM_SECONDPAGE BIT(25) #define NAND_BBM_LASTPAGE BIT(26) +/* + * Some controllers with pipelined ECC engines override the BBM marker with + * data or ECC bytes, thus making bad block detection through bad block marker + * impossible. Let's flag those chips so the core knows it shouldn't check the + * BBM and consider all blocks good. + */ +#define NAND_NO_BBM_QUIRK BIT(27) + /* Cell info constants */ #define NAND_CI_CHIPNR_MSK 0x03 #define NAND_CI_CELLTYPE_MSK 0x0C -- cgit v1.2.3 From 913b99f70feb1cd9fb4bbcb302a029b4b9bee454 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:25:24 -0500 Subject: thunderbolt: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Mika Westerberg --- include/linux/thunderbolt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index ece782ef5466..ff397c0d5c07 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -80,7 +80,7 @@ struct tb { int index; enum tb_security_level security_level; size_t nboot_acl; - unsigned long privdata[0]; + unsigned long privdata[]; }; extern struct bus_type tb_bus_type; -- cgit v1.2.3 From 975cf23e3aa89588cbfc9ad6f2b23bd32af4edc7 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Thu, 7 May 2020 13:33:15 +0100 Subject: PCI: endpoint: Pass page size as argument to pci_epc_mem_init() pci_epc_mem_init() internally used page size equal to *PAGE_SIZE* to manage the address space so instead just pass the page size as a argument to pci_epc_mem_init(). Also make pci_epc_mem_init() as a C function instead of a macro function in preparation for adding support for pci-epc-mem core to handle multiple windows. Link: https://lore.kernel.org/r/1588854799-13710-5-git-send-email-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Lad Prabhakar Signed-off-by: Lorenzo Pieralisi Reviewed-by: Yoshihiro Shimoda Acked-by: Kishon Vijay Abraham I --- include/linux/pci-epc.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index e0ed9d01f6e5..5bc1de65849e 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -137,9 +137,6 @@ struct pci_epc_features { #define devm_pci_epc_create(dev, ops) \ __devm_pci_epc_create((dev), (ops), THIS_MODULE) -#define pci_epc_mem_init(epc, phys_addr, size) \ - __pci_epc_mem_init((epc), (phys_addr), (size), PAGE_SIZE) - static inline void epc_set_drvdata(struct pci_epc *epc, void *data) { dev_set_drvdata(&epc->dev, data); @@ -195,6 +192,8 @@ unsigned int pci_epc_get_first_free_bar(const struct pci_epc_features struct pci_epc *pci_epc_get(const char *epc_name); void pci_epc_put(struct pci_epc *epc); +int pci_epc_mem_init(struct pci_epc *epc, phys_addr_t base, + size_t size, size_t page_size); int __pci_epc_mem_init(struct pci_epc *epc, phys_addr_t phys_addr, size_t size, size_t page_size); void pci_epc_mem_exit(struct pci_epc *epc); -- cgit v1.2.3 From e33bcbab16d1c0dd85d72bec275308369ad901f5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Vesa=20J=C3=A4=C3=A4skel=C3=A4inen?= Date: Thu, 30 Apr 2020 15:37:09 +0300 Subject: tee: add support for session's client UUID generation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit TEE Client API defines that from user space only information needed for specified login operations is group identifier for group based logins. REE kernel is expected to formulate trustworthy client UUID and pass that to TEE environment. REE kernel is required to verify that provided group identifier for group based logins matches calling processes group memberships. TEE specification only defines that the information passed from REE environment to TEE environment is encoded into on UUID. In order to guarantee trustworthiness of client UUID user space is not allowed to freely pass client UUID. UUIDv5 form is used encode variable amount of information needed for different login types. Signed-off-by: Vesa Jääskeläinen [jw: remove unused variable application_id] Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 1412e9cc79ce..8471b790e858 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -165,6 +165,22 @@ int tee_device_register(struct tee_device *teedev); */ void tee_device_unregister(struct tee_device *teedev); +/** + * tee_session_calc_client_uuid() - Calculates client UUID for session + * @uuid: Resulting UUID + * @connection_method: Connection method for session (TEE_IOCTL_LOGIN_*) + * @connectuon_data: Connection data for opening session + * + * Based on connection method calculates UUIDv5 based client UUID. + * + * For group based logins verifies that calling process has specified + * credentials. + * + * @return < 0 on failure + */ +int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, + const u8 connection_data[TEE_IOCTL_UUID_LEN]); + /** * struct tee_shm - shared memory object * @ctx: context using the object -- cgit v1.2.3 From be957c886d92aa9caf0f63aee2c77d1497217d93 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 1 May 2020 15:20:45 -0300 Subject: mm/hmm: make hmm_range_fault return 0 or -1 hmm_vma_walk->last is supposed to be updated after every write to the pfns, so that it can be returned by hmm_range_fault(). However, this is not done consistently. Fortunately nothing checks the return code of hmm_range_fault() for anything other than error. More importantly last must be set before returning -EBUSY as it is used to prevent reading an output pfn as an input flags when the loop restarts. For clarity and simplicity make hmm_range_fault() return 0 or -ERRNO. Only set last when returning -EBUSY. Link: https://lore.kernel.org/r/2-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.com Acked-by: Felix Kuehling Tested-by: Ralph Campbell Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 7475051100c7..0df27dd03d53 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -120,7 +120,7 @@ static inline struct page *hmm_device_entry_to_page(const struct hmm_range *rang /* * Please see Documentation/vm/hmm.rst for how to use the range API. */ -long hmm_range_fault(struct hmm_range *range); +int hmm_range_fault(struct hmm_range *range); /* * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range -- cgit v1.2.3 From 5c8f3c4cf18ad007242bc370da54d45d4d4293dc Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 1 May 2020 15:20:47 -0300 Subject: mm/hmm: remove HMM_PFN_SPECIAL This is just an alias for HMM_PFN_ERROR, nothing cares that the error was because of a special page vs any other error case. Link: https://lore.kernel.org/r/4-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.com Acked-by: Felix Kuehling Reviewed-by: Christoph Hellwig Reviewed-by: John Hubbard Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 0df27dd03d53..81c302c884c0 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -44,10 +44,6 @@ enum hmm_pfn_flag_e { * Flags: * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory * HMM_PFN_NONE: corresponding CPU page table entry is pte_none() - * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the - * result of vmf_insert_pfn() or vm_insert_page(). Therefore, it should not - * be mirrored by a device, because the entry will never have HMM_PFN_VALID - * set and the pfn value is undefined. * * Driver provides values for none entry, error entry, and special entry. * Driver can alias (i.e., use same value) error and special, but @@ -56,12 +52,10 @@ enum hmm_pfn_flag_e { * HMM pfn value returned by hmm_vma_get_pfns() or hmm_vma_fault() will be: * hmm_range.values[HMM_PFN_ERROR] if CPU page table entry is poisonous, * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table entry, - * hmm_range.values[HMM_PFN_SPECIAL] if CPU page table entry is a special one */ enum hmm_pfn_value_e { HMM_PFN_ERROR, HMM_PFN_NONE, - HMM_PFN_SPECIAL, HMM_PFN_VALUE_MAX }; @@ -110,8 +104,6 @@ static inline struct page *hmm_device_entry_to_page(const struct hmm_range *rang return NULL; if (entry == range->values[HMM_PFN_ERROR]) return NULL; - if (entry == range->values[HMM_PFN_SPECIAL]) - return NULL; if (!(entry & range->flags[HMM_PFN_VALID])) return NULL; return pfn_to_page(entry >> range->pfn_shift); -- cgit v1.2.3 From 2733ea144dcce789de20988c1056e228a07b1bff Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 1 May 2020 15:20:48 -0300 Subject: mm/hmm: remove the customizable pfn format from hmm_range_fault Presumably the intent here was that hmm_range_fault() could put the data into some HW specific format and thus avoid some work. However, nothing actually does that, and it isn't clear how anything actually could do that as hmm_range_fault() provides CPU addresses which must be DMA mapped. Perhaps there is some special HW that does not need DMA mapping, but we don't have any examples of this, and the theoretical performance win of avoiding an extra scan over the pfns array doesn't seem worth the complexity. Plus pfns needs to be scanned anyhow to sort out any DEVICE_PRIVATE pages. This version replaces the uint64_t with an usigned long containing a pfn and fixed flags. On input flags is filled with the HMM_PFN_REQ_* values, on successful output it is filled with HMM_PFN_* values, describing the state of the pages. amdgpu is simple to convert, it doesn't use snapshot and doesn't use per-page flags. nouveau uses only 16 hmm_pte entries at most (ie fits in a few cache lines), and it sweeps over its pfns array a couple of times anyhow. It also has a nasty call chain before it reaches the dma map and hardware suggesting performance isn't important: nouveau_svm_fault(): args.i.m.method = NVIF_VMM_V0_PFNMAP nouveau_range_fault() nvif_object_ioctl() client->driver->ioctl() struct nvif_driver nvif_driver_nvkm: .ioctl = nvkm_client_ioctl nvkm_ioctl() nvkm_ioctl_path() nvkm_ioctl_v0[type].func(..) nvkm_ioctl_mthd() nvkm_object_mthd() struct nvkm_object_func nvkm_uvmm: .mthd = nvkm_uvmm_mthd nvkm_uvmm_mthd() nvkm_uvmm_mthd_pfnmap() nvkm_vmm_pfn_map() nvkm_vmm_ptes_get_map() func == gp100_vmm_pgt_pfn struct nvkm_vmm_desc_func gp100_vmm_desc_spt: .pfn = gp100_vmm_pgt_pfn nvkm_vmm_iter() REF_PTES == func == gp100_vmm_pgt_pfn() dma_map_page() Link: https://lore.kernel.org/r/5-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.com Acked-by: Felix Kuehling Tested-by: Ralph Campbell Signed-off-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 101 ++++++++++++++++++++-------------------------------- 1 file changed, 38 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 81c302c884c0..e912b9dc4633 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -19,45 +19,47 @@ #include /* - * hmm_pfn_flag_e - HMM flag enums + * On output: + * 0 - The page is faultable and a future call with + * HMM_PFN_REQ_FAULT could succeed. + * HMM_PFN_VALID - the pfn field points to a valid PFN. This PFN is at + * least readable. If dev_private_owner is !NULL then this could + * point at a DEVICE_PRIVATE page. + * HMM_PFN_WRITE - if the page memory can be written to (requires HMM_PFN_VALID) + * HMM_PFN_ERROR - accessing the pfn is impossible and the device should + * fail. ie poisoned memory, special pages, no vma, etc * - * Flags: - * HMM_PFN_VALID: pfn is valid. It has, at least, read permission. - * HMM_PFN_WRITE: CPU page table has write permission set - * - * The driver provides a flags array for mapping page protections to device - * PTE bits. If the driver valid bit for an entry is bit 3, - * i.e., (entry & (1 << 3)), then the driver must provide - * an array in hmm_range.flags with hmm_range.flags[HMM_PFN_VALID] == 1 << 3. - * Same logic apply to all flags. This is the same idea as vm_page_prot in vma - * except that this is per device driver rather than per architecture. + * On input: + * 0 - Return the current state of the page, do not fault it. + * HMM_PFN_REQ_FAULT - The output must have HMM_PFN_VALID or hmm_range_fault() + * will fail + * HMM_PFN_REQ_WRITE - The output must have HMM_PFN_WRITE or hmm_range_fault() + * will fail. Must be combined with HMM_PFN_REQ_FAULT. */ -enum hmm_pfn_flag_e { - HMM_PFN_VALID = 0, - HMM_PFN_WRITE, - HMM_PFN_FLAG_MAX +enum hmm_pfn_flags { + /* Output flags */ + HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1), + HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2), + HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3), + + /* Input flags */ + HMM_PFN_REQ_FAULT = HMM_PFN_VALID, + HMM_PFN_REQ_WRITE = HMM_PFN_WRITE, + + HMM_PFN_FLAGS = HMM_PFN_VALID | HMM_PFN_WRITE | HMM_PFN_ERROR, }; /* - * hmm_pfn_value_e - HMM pfn special value - * - * Flags: - * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory - * HMM_PFN_NONE: corresponding CPU page table entry is pte_none() + * hmm_pfn_to_page() - return struct page pointed to by a device entry * - * Driver provides values for none entry, error entry, and special entry. - * Driver can alias (i.e., use same value) error and special, but - * it should not alias none with error or special. - * - * HMM pfn value returned by hmm_vma_get_pfns() or hmm_vma_fault() will be: - * hmm_range.values[HMM_PFN_ERROR] if CPU page table entry is poisonous, - * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table entry, + * This must be called under the caller 'user_lock' after a successful + * mmu_interval_read_begin(). The caller must have tested for HMM_PFN_VALID + * already. */ -enum hmm_pfn_value_e { - HMM_PFN_ERROR, - HMM_PFN_NONE, - HMM_PFN_VALUE_MAX -}; +static inline struct page *hmm_pfn_to_page(unsigned long hmm_pfn) +{ + return pfn_to_page(hmm_pfn & ~HMM_PFN_FLAGS); +} /* * struct hmm_range - track invalidation lock on virtual address range @@ -66,12 +68,9 @@ enum hmm_pfn_value_e { * @notifier_seq: result of mmu_interval_read_begin() * @start: range virtual start address (inclusive) * @end: range virtual end address (exclusive) - * @pfns: array of pfns (big enough for the range) - * @flags: pfn flags to match device driver page table - * @values: pfn value for some special case (none, special, error, ...) + * @hmm_pfns: array of pfns (big enough for the range) * @default_flags: default flags for the range (write, read, ... see hmm doc) * @pfn_flags_mask: allows to mask pfn flags so that only default_flags matter - * @pfn_shift: pfn shift value (should be <= PAGE_SHIFT) * @dev_private_owner: owner of device private pages */ struct hmm_range { @@ -79,36 +78,12 @@ struct hmm_range { unsigned long notifier_seq; unsigned long start; unsigned long end; - uint64_t *pfns; - const uint64_t *flags; - const uint64_t *values; - uint64_t default_flags; - uint64_t pfn_flags_mask; - uint8_t pfn_shift; + unsigned long *hmm_pfns; + unsigned long default_flags; + unsigned long pfn_flags_mask; void *dev_private_owner; }; -/* - * hmm_device_entry_to_page() - return struct page pointed to by a device entry - * @range: range use to decode device entry value - * @entry: device entry value to get corresponding struct page from - * Return: struct page pointer if entry is a valid, NULL otherwise - * - * If the device entry is valid (ie valid flag set) then return the struct page - * matching the entry value. Otherwise return NULL. - */ -static inline struct page *hmm_device_entry_to_page(const struct hmm_range *range, - uint64_t entry) -{ - if (entry == range->values[HMM_PFN_NONE]) - return NULL; - if (entry == range->values[HMM_PFN_ERROR]) - return NULL; - if (!(entry & range->flags[HMM_PFN_VALID])) - return NULL; - return pfn_to_page(entry >> range->pfn_shift); -} - /* * Please see Documentation/vm/hmm.rst for how to use the range API. */ -- cgit v1.2.3 From 9c8255c888bac9221739c822132b405d4196bdd8 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:25:07 -0500 Subject: team: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- include/linux/if_team.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 537dc2b8c879..add607943c95 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -67,7 +67,7 @@ struct team_port { u16 queue_id; struct list_head qom_list; /* node in queue override mapping list */ struct rcu_head rcu; - long mode_priv[0]; + long mode_priv[]; }; static inline struct team_port *team_port_get_rcu(const struct net_device *dev) -- cgit v1.2.3 From 0462b6bdb6445b887b8896f28be92e0d94c92e7b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 11 May 2020 13:59:11 +0200 Subject: net: add a CMSG_USER_DATA macro Add a variant of CMSG_DATA that operates on user pointer to avoid sparse warnings about casting to/from user pointers. Also fix up CMSG_DATA to rely on the gcc extension that allows void pointer arithmetics to cut down on the amount of casts. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/socket.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 54338fac45cb..4cc64d611cf4 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -94,7 +94,10 @@ struct cmsghdr { #define CMSG_ALIGN(len) ( ((len)+sizeof(long)-1) & ~(sizeof(long)-1) ) -#define CMSG_DATA(cmsg) ((void *)((char *)(cmsg) + sizeof(struct cmsghdr))) +#define CMSG_DATA(cmsg) \ + ((void *)(cmsg) + sizeof(struct cmsghdr)) +#define CMSG_USER_DATA(cmsg) \ + ((void __user *)(cmsg) + sizeof(struct cmsghdr)) #define CMSG_SPACE(len) (sizeof(struct cmsghdr) + CMSG_ALIGN(len)) #define CMSG_LEN(len) (sizeof(struct cmsghdr) + (len)) -- cgit v1.2.3 From 1f466e1f15cf1dac7c86798d694649fc42cd868a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 11 May 2020 13:59:13 +0200 Subject: net: cleanly handle kernel vs user buffers for ->msg_control The msg_control field in struct msghdr can either contain a user pointer when used with the recvmsg system call, or a kernel pointer when used with sendmsg. To complicate things further kernel_recvmsg can stuff a kernel pointer in and then use set_fs to make the uaccess helpers accept it. Replace it with a union of a kernel pointer msg_control field, and a user pointer msg_control_user one, and allow kernel_recvmsg operate on a proper kernel pointer using a bitfield to override the normal choice of a user pointer for recvmsg. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/socket.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 4cc64d611cf4..04d2bc97f497 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -50,7 +50,17 @@ struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ struct iov_iter msg_iter; /* data */ - void *msg_control; /* ancillary data */ + + /* + * Ancillary data. msg_control_user is the user buffer used for the + * recv* side when msg_control_is_user is set, msg_control is the kernel + * buffer used for all other cases. + */ + union { + void *msg_control; + void __user *msg_control_user; + }; + bool msg_control_is_user : 1; __kernel_size_t msg_controllen; /* ancillary data buffer length */ unsigned int msg_flags; /* flags on received message */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ -- cgit v1.2.3 From 8b59cd81dc5e724eaea283fa6006985891c7bff4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 23 Apr 2020 23:23:52 +0900 Subject: kbuild: ensure full rebuild when the compiler is updated Commit 21c54b774744 ("kconfig: show compiler version text in the top comment") added the environment variable, CC_VERSION_TEXT in the comment of the top Kconfig file. It can detect the compiler update, and invoke the syncconfig because all environment variables referenced in Kconfig files are recorded in include/config/auto.conf.cmd This commit makes it a CONFIG option in order to ensure the full rebuild when the compiler is updated. This works like follows: include/config/kconfig.h contains "CONFIG_CC_VERSION_TEXT" in the comment block. The top Makefile specifies "-include $(srctree)/include/linux/kconfig.h" to guarantee it is included from all kernel source files. fixdep parses every source file and all headers included from it, searching for words prefixed with "CONFIG_". Then, fixdep finds CONFIG_CC_VERSION_TEXT in include/config/kconfig.h and adds include/config/cc/version/text.h into every .*.cmd file. When the compiler is updated, syncconfig is invoked because init/Kconfig contains the reference to the environment variable CC_VERTION_TEXT. CONFIG_CC_VERSION_TEXT is updated to the new version string, and include/config/cc/version/text.h is touched. In the next rebuild, Make will rebuild every files since the timestamp of include/config/cc/version/text.h is newer than that of target. Signed-off-by: Masahiro Yamada --- include/linux/kconfig.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index cc8fa109cfa3..9d12c970f18f 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -2,6 +2,8 @@ #ifndef __LINUX_KCONFIG_H #define __LINUX_KCONFIG_H +/* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */ + #include #ifdef CONFIG_CPU_BIG_ENDIAN -- cgit v1.2.3 From 914a1951d88968371c7d43400c9d936382cd7d69 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:05:44 -0500 Subject: PCI: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these as a flexible array member [1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that dynamic memory allocations won't be affected by this change: Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero. [1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type [1]. There are some instances of code in which the sizeof() operator is being incorrectly/erroneously applied to zero-length arrays, and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Link: https://lore.kernel.org/r/20200507190544.GA15633@embeddedor Signed-off-by: Gustavo A. R. Silva Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 83ce1cdf5676..0453ee458ab1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -279,7 +279,7 @@ struct pci_cap_saved_data { u16 cap_nr; bool cap_extended; unsigned int size; - u32 data[0]; + u32 data[]; }; struct pci_cap_saved_state { @@ -532,7 +532,7 @@ struct pci_host_bridge { resource_size_t start, resource_size_t size, resource_size_t align); - unsigned long private[0] ____cacheline_aligned; + unsigned long private[] ____cacheline_aligned; }; #define to_pci_host_bridge(n) container_of(n, struct pci_host_bridge, dev) -- cgit v1.2.3 From b0dbd97de1f1fd6b3c9a7bb8f7c795bba7e169d8 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 10 May 2020 14:24:31 +0200 Subject: platform/x86: asus-wmi: Add support for SW_TABLET_MODE On Asus 2-in-1s with a detachable keyboard the Asus WMI interface reports if the tablet is attached to the keyboard or not. Report if the 2-in-1 is in tablet or clamshell mode to userspace by reporting SW_TABLET_MODE events to userspace. This has been tested on a T100TA, T100CHI, T100HA and T200TA. Signed-off-by: Hans de Goede Signed-off-by: Andy Shevchenko --- include/linux/platform_data/x86/asus-wmi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index d39fc658c320..897b8332a39f 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -85,6 +85,9 @@ /* Maximum charging percentage */ #define ASUS_WMI_DEVID_RSOC 0x00120057 +/* Keyboard dock */ +#define ASUS_WMI_DEVID_KBD_DOCK 0x00120063 + /* DSTS masks */ #define ASUS_WMI_DSTS_STATUS_BIT 0x00000001 #define ASUS_WMI_DSTS_UNKNOWN_BIT 0x00000002 -- cgit v1.2.3 From 2a0a24ebb499c9d499eea948d3fc108f936e36d4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 27 Mar 2020 12:42:00 +0100 Subject: sched: Make scheduler_ipi inline Now that the scheduler IPI is trivial and simple again there is no point to have the little function out of line. This simplifies the effort of constraining the instrumentation nicely. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134058.453581595@linutronix.de --- include/linux/sched.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4418f5cb8324..d4ea4407cd6d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1715,7 +1715,15 @@ extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk); }) #ifdef CONFIG_SMP -void scheduler_ipi(void); +static __always_inline void scheduler_ipi(void) +{ + /* + * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting + * TIF_NEED_RESCHED remotely (for the first time) will also send + * this IPI. + */ + preempt_fold_need_resched(); +} extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else static inline void scheduler_ipi(void) { } -- cgit v1.2.3 From 1e6769b0aece51ea7a3dc3117c37d4a5669e4a21 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 26 Mar 2020 23:49:48 +0900 Subject: kprobes: Support __kprobes blacklist in modules Support __kprobes attribute for blacklist functions in modules. The __kprobes attribute functions are stored in .kprobes.text section. Signed-off-by: Masami Hiramatsu Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134059.678201813@linutronix.de --- include/linux/module.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 1ad393e62bef..369c354f9207 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -489,6 +489,10 @@ struct module { unsigned int num_ftrace_callsites; unsigned long *ftrace_callsites; #endif +#ifdef CONFIG_KPROBES + void *kprobes_text_start; + unsigned int kprobes_text_size; +#endif #ifdef CONFIG_LIVEPATCH bool klp; /* Is this a livepatch module? */ -- cgit v1.2.3 From 16db6264c93d2d7df9eb8be5d9eb717ab30105fe Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 26 Mar 2020 23:50:00 +0900 Subject: kprobes: Support NOKPROBE_SYMBOL() in modules Support NOKPROBE_SYMBOL() in modules. NOKPROBE_SYMBOL() records only symbol address in "_kprobe_blacklist" section in the module. Signed-off-by: Masami Hiramatsu Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134059.771170126@linutronix.de --- include/linux/module.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 369c354f9207..1192097c9a69 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -492,6 +492,8 @@ struct module { #ifdef CONFIG_KPROBES void *kprobes_text_start; unsigned int kprobes_text_size; + unsigned long *kprobe_blacklist; + unsigned int num_kprobe_blacklist; #endif #ifdef CONFIG_LIVEPATCH -- cgit v1.2.3 From 1f66b0f0aec671f8fbc86d75b2efdf7c7e0f7880 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 May 2020 20:20:26 +0300 Subject: net: dsa: tag_8021q: introduce a vid_is_dsa_8021q helper This function returns a boolean denoting whether the VLAN passed as argument is part of the 1024-3071 range that the dsa_8021q tagging scheme uses. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index b8daaec0896e..ebc245ff838a 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -50,6 +50,8 @@ int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); +bool vid_is_dsa_8021q(u16 vid); + #else int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, @@ -107,6 +109,11 @@ int dsa_8021q_rx_source_port(u16 vid) return 0; } +bool vid_is_dsa_8021q(u16 vid) +{ + return false; +} + #endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */ #endif /* _NET_DSA_8021Q_H */ -- cgit v1.2.3 From ec5ae61076d07be986df19773662506220757c9f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 May 2020 20:20:29 +0300 Subject: net: dsa: sja1105: save/restore VLANs using a delta commit method Managing the VLAN table that is present in hardware will become very difficult once we add a third operating state (best_effort_vlan_filtering). That is because correct cleanup (not too little, not too much) becomes virtually impossible, when VLANs can be added from the bridge layer, from dsa_8021q for basic tagging, for cross-chip bridging, as well as retagging rules for sub-VLANs and cross-chip sub-VLANs. So we need to rethink VLAN interaction with the switch in a more scalable way. In preparation for that, use the priv->expect_dsa_8021q boolean to classify any VLAN request received through .port_vlan_add or .port_vlan_del towards either one of 2 internal lists: bridge VLANs and dsa_8021q VLANs. Then, implement a central sja1105_build_vlan_table method that creates a VLAN configuration from scratch based on the 2 lists of VLANs kept by the driver, and based on the VLAN awareness state. Currently, if we are VLAN-unaware, install the dsa_8021q VLANs, otherwise the bridge VLANs. Then, implement a delta commit procedure that identifies which VLANs from this new configuration are actually different from the config previously committed to hardware. We apply the delta through the dynamic configuration interface (we don't reset the switch). The result is that the hardware should see the exact sequence of operations as before this patch. This also helps remove the "br" argument passed to dsa_8021q_crosschip_bridge_join, which it was only using to figure out whether it should commit the configuration back to us or not, based on the VLAN awareness state of the bridge. We can simplify that, by always allowing those VLANs inside of our dsa_8021q_vlans list, and committing those to hardware when necessary. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index ebc245ff838a..404bd2cce642 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -25,18 +25,14 @@ struct dsa_8021q_crosschip_link { int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, bool enabled); -int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, bool enabled); - int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, struct dsa_switch *other_ds, - int other_port, struct net_device *br, + int other_port, struct list_head *crosschip_links); int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, struct dsa_switch *other_ds, - int other_port, struct net_device *br, + int other_port, struct list_head *crosschip_links); struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, @@ -60,16 +56,9 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, return 0; } -int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, bool enabled) -{ - return 0; -} - int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, struct dsa_switch *other_ds, - int other_port, struct net_device *br, + int other_port, struct list_head *crosschip_links) { return 0; @@ -77,7 +66,7 @@ int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, struct dsa_switch *other_ds, - int other_port, struct net_device *br, + int other_port, struct list_head *crosschip_links) { return 0; -- cgit v1.2.3 From 38b5beeae7a4cde87edabb0196fac1f55ae668ee Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 May 2020 20:20:32 +0300 Subject: net: dsa: sja1105: prepare tagger for handling DSA tags and VLAN simultaneously In VLAN-unaware mode, sja1105 uses VLAN tags with a custom TPID of 0xdadb. While in the yet-to-be introduced best_effort_vlan_filtering mode, it needs to work with normal VLAN TPID values. A complication arises when we must transmit a VLAN-tagged packet to the switch when it's in VLAN-aware mode. We need to construct a packet with 2 VLAN tags, and the switch will use the outer header for routing and pop it on egress. But sadly, here the 2 hardware generations don't behave the same: - E/T switches won't pop an ETH_P_8021AD tag on egress, it seems (packets will remain double-tagged). - P/Q/R/S switches will drop a packet with 2 ETH_P_8021Q tags (it looks like it tries to prevent VLAN hopping). But looks like the reverse is also true: - E/T switches have no problem popping the outer tag from packets with 2 ETH_P_8021Q tags. - P/Q/R/S will have no problem popping a single tag even if that is ETH_P_8021AD. So it is clear that if we want the hardware to work with dsa_8021q tagging in VLAN-aware mode, we need to send different TPIDs depending on revision. Keep that information in priv->info->qinq_tpid. The per-port tagger structure will hold an xmit_tpid value that depends not only upon the qinq_tpid, but also upon the VLAN awareness state itself (in case we must transmit using 0xdadb). Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index fa5735c353cd..f821d08b1b5f 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -59,6 +59,7 @@ struct sja1105_port { struct sja1105_tagger_data *data; struct dsa_port *dp; bool hwts_tx_en; + u16 xmit_tpid; }; #endif /* _NET_DSA_SJA1105_H */ -- cgit v1.2.3 From 3eaae1d05f2b5be1be834bfad64f8fc2ad39a56d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 May 2020 20:20:33 +0300 Subject: net: dsa: tag_8021q: support up to 8 VLANs per port using sub-VLANs For switches that support VLAN retagging, such as sja1105, we extend dsa_8021q by encoding a "sub-VLAN" into the remaining 3 free bits in the dsa_8021q tag. A sub-VLAN is nothing more than a number in the range 0-7, which serves as an index into a per-port driver lookup table. The sub-VLAN value of zero means that traffic is untagged (this is also backwards-compatible with dsa_8021q without retagging). The switch should be configured to retag VLAN-tagged traffic that gets transmitted towards the CPU port (and towards the CPU only). Example: bridge vlan add dev sw1p0 vid 100 The switch retags frames received on port 0, going to the CPU, and having VID 100, to the VID of 1104 (0x0450). In dsa_8021q language: | 11 | 10 | 9 | 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 | +-----------+-----+-----------------+-----------+-----------------------+ | DIR | SVL | SWITCH_ID | SUBVLAN | PORT | +-----------+-----+-----------------+-----------+-----------------------+ 0x0450 means: - DIR = 0b01: this is an RX VLAN - SUBVLAN = 0b001: this is subvlan #1 - SWITCH_ID = 0b001: this is switch 1 (see the name "sw1p0") - PORT = 0b0000: this is port 0 (see the name "sw1p0") The driver also remembers the "1 -> 100" mapping. In the hotpath, if the sub-VLAN from the tag encodes a non-untagged frame, this mapping is used to create a VLAN hwaccel tag, with the value of 100. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 404bd2cce642..311aa04e7520 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -20,6 +20,8 @@ struct dsa_8021q_crosschip_link { refcount_t refcount; }; +#define DSA_8021Q_N_SUBVLAN 8 + #if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, @@ -42,10 +44,14 @@ u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); +u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan); + int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); +u16 dsa_8021q_rx_subvlan(u16 vid); + bool vid_is_dsa_8021q(u16 vid); #else @@ -88,6 +94,11 @@ u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) return 0; } +u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan) +{ + return 0; +} + int dsa_8021q_rx_switch_id(u16 vid) { return 0; @@ -98,6 +109,11 @@ int dsa_8021q_rx_source_port(u16 vid) return 0; } +u16 dsa_8021q_rx_subvlan(u16 vid) +{ + return 0; +} + bool vid_is_dsa_8021q(u16 vid) { return false; -- cgit v1.2.3 From 84eeb5d460e399795e9a92a0cd44999254886150 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 May 2020 20:20:34 +0300 Subject: net: dsa: tag_sja1105: implement sub-VLAN decoding Create a subvlan_map as part of each port's tagger private structure. This keeps reverse mappings of bridge-to-dsa_8021q VLAN retagging rules. Note that as of this patch, this piece of code is never engaged, due to the fact that the driver hasn't installed any retagging rule, so we'll always see packets with a subvlan code of 0 (untagged). Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index f821d08b1b5f..dd93735ae228 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -9,6 +9,7 @@ #include #include +#include #include #define ETH_P_SJA1105 ETH_P_DSA_8021Q @@ -53,6 +54,7 @@ struct sja1105_skb_cb { ((struct sja1105_skb_cb *)DSA_SKB_CB_PRIV(skb)) struct sja1105_port { + u16 subvlan_map[DSA_8021Q_N_SUBVLAN]; struct kthread_worker *xmit_worker; struct kthread_work xmit_work; struct sk_buff_head xmit_queue; -- cgit v1.2.3 From 4a470f00e10e3336350ab60ec6c3206177093019 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 6 May 2020 14:32:35 +0200 Subject: of: Make self-contained is not self-contained, as it uses _OF_DECLARE() to define RESERVEDMEM_OF_DECLARE(), but does not include . Fix this by adding the missing include. Signed-off-by: Geert Uytterhoeven Reviewed-by: Thierry Reding Acked-by: Rob Herring Signed-off-by: Thierry Reding --- include/linux/of_reserved_mem.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h index a1b427ac291b..8216a4156263 100644 --- a/include/linux/of_reserved_mem.h +++ b/include/linux/of_reserved_mem.h @@ -3,6 +3,7 @@ #define __OF_RESERVED_MEM_H #include +#include struct of_phandle_args; struct reserved_mem_ops; -- cgit v1.2.3 From a3cba697a2a09e6769996d5265991a3228004d92 Mon Sep 17 00:00:00 2001 From: Joseph Lo Date: Wed, 29 May 2019 16:21:34 +0800 Subject: clk: tegra: Export functions for EMC clock scaling Export functions to allow accessing the CAR register required by EMC clock scaling. These functions will be used to access the CAR register as part of the scaling sequence. Signed-off-by: Joseph Lo Signed-off-by: Thierry Reding --- include/linux/clk/tegra.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index 2b1b35240074..5b0bdb413460 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -131,6 +131,9 @@ extern void tegra210_set_sata_pll_seq_sw(bool state); extern void tegra210_put_utmipll_in_iddq(void); extern void tegra210_put_utmipll_out_iddq(void); extern int tegra210_clk_handle_mbist_war(unsigned int id); +extern void tegra210_clk_emc_dll_enable(bool flag); +extern void tegra210_clk_emc_dll_update_setting(u32 emc_dll_src_value); +extern void tegra210_clk_emc_update_setting(u32 emc_src_value); struct clk; -- cgit v1.2.3 From 0ac65fc946d3a15ff30cea28b38a00b9ba98217b Mon Sep 17 00:00:00 2001 From: Joseph Lo Date: Wed, 29 May 2019 16:21:35 +0800 Subject: clk: tegra: Implement Tegra210 EMC clock The EMC clock needs to carefully coordinate with the EMC controller programming to make sure external memory can be properly clocked. Do so by hooking up the EMC clock with an EMC provider that will specify which rates are supported by the EMC and provide a callback to use for setting the clock rate at the EMC. Based on work by Peter De Schrijver . Signed-off-by: Joseph Lo Signed-off-by: Thierry Reding --- include/linux/clk/tegra.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index 5b0bdb413460..3f01d43f0598 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -146,4 +146,28 @@ void tegra20_clk_set_emc_round_callback(tegra20_clk_emc_round_cb *round_cb, void *cb_arg); int tegra20_clk_prepare_emc_mc_same_freq(struct clk *emc_clk, bool same); +struct tegra210_clk_emc_config { + unsigned long rate; + bool same_freq; + u32 value; + + unsigned long parent_rate; + u8 parent; +}; + +struct tegra210_clk_emc_provider { + struct module *owner; + struct device *dev; + + struct tegra210_clk_emc_config *configs; + unsigned int num_configs; + + int (*set_rate)(struct device *dev, + const struct tegra210_clk_emc_config *config); +}; + +int tegra210_clk_emc_attach(struct clk *clk, + struct tegra210_clk_emc_provider *provider); +void tegra210_clk_emc_detach(struct clk *clk); + #endif /* __LINUX_CLK_TEGRA_H_ */ -- cgit v1.2.3 From 529798bae7c155d38eec211436df736349dca2ee Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:19:43 -0500 Subject: remoteproc: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200507191943.GA16033@embeddedor Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 0468be4d02f4..e7b7bab8b235 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -73,7 +73,7 @@ struct resource_table { u32 ver; u32 num; u32 reserved[2]; - u32 offset[0]; + u32 offset[]; } __packed; /** @@ -87,7 +87,7 @@ struct resource_table { */ struct fw_rsc_hdr { u32 type; - u8 data[0]; + u8 data[]; } __packed; /** @@ -306,7 +306,7 @@ struct fw_rsc_vdev { u8 status; u8 num_of_vrings; u8 reserved[2]; - struct fw_rsc_vdev_vring vring[0]; + struct fw_rsc_vdev_vring vring[]; } __packed; struct rproc; -- cgit v1.2.3 From d2fe97545a1e2d01c0ca0105bdc59002a0d0b130 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:13:56 -0700 Subject: fscrypt: fix all kerneldoc warnings Fix all kerneldoc warnings in fs/crypto/ and include/linux/fscrypt.h. Most of these were due to missing documentation for function parameters. Detected with: scripts/kernel-doc -v -none fs/crypto/*.{c,h} include/linux/fscrypt.h This cleanup makes it possible to check new patches for kerneldoc warnings without having to filter out all the existing ones. For consistency, also adjust some function "brief descriptions" to include the parentheses and to wrap at 80 characters. (The latter matches the checkpatch expectation.) Link: https://lore.kernel.org/r/20200511191358.53096-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index e3c2d2a15525..cb2c41f8dfde 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -75,6 +75,7 @@ static inline bool fscrypt_has_encryption_key(const struct inode *inode) /** * fscrypt_needs_contents_encryption() - check whether an inode needs * contents encryption + * @inode: the inode to check * * Return: %true iff the inode is an encrypted regular file and the kernel was * built with fscrypt support. @@ -504,7 +505,7 @@ static inline void fscrypt_set_ops(struct super_block *sb, #endif /* !CONFIG_FS_ENCRYPTION */ /** - * fscrypt_require_key - require an inode's encryption key + * fscrypt_require_key() - require an inode's encryption key * @inode: the inode we need the key for * * If the inode is encrypted, set up its encryption key if not already done. @@ -530,7 +531,8 @@ static inline int fscrypt_require_key(struct inode *inode) } /** - * fscrypt_prepare_link - prepare to link an inode into a possibly-encrypted directory + * fscrypt_prepare_link() - prepare to link an inode into a possibly-encrypted + * directory * @old_dentry: an existing dentry for the inode being linked * @dir: the target directory * @dentry: negative dentry for the target filename @@ -557,7 +559,8 @@ static inline int fscrypt_prepare_link(struct dentry *old_dentry, } /** - * fscrypt_prepare_rename - prepare for a rename between possibly-encrypted directories + * fscrypt_prepare_rename() - prepare for a rename between possibly-encrypted + * directories * @old_dir: source directory * @old_dentry: dentry for source file * @new_dir: target directory @@ -590,7 +593,8 @@ static inline int fscrypt_prepare_rename(struct inode *old_dir, } /** - * fscrypt_prepare_lookup - prepare to lookup a name in a possibly-encrypted directory + * fscrypt_prepare_lookup() - prepare to lookup a name in a possibly-encrypted + * directory * @dir: directory being searched * @dentry: filename being looked up * @fname: (output) the name to use to search the on-disk directory @@ -623,7 +627,8 @@ static inline int fscrypt_prepare_lookup(struct inode *dir, } /** - * fscrypt_prepare_setattr - prepare to change a possibly-encrypted inode's attributes + * fscrypt_prepare_setattr() - prepare to change a possibly-encrypted inode's + * attributes * @dentry: dentry through which the inode is being changed * @attr: attributes to change * @@ -648,7 +653,7 @@ static inline int fscrypt_prepare_setattr(struct dentry *dentry, } /** - * fscrypt_prepare_symlink - prepare to create a possibly-encrypted symlink + * fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink * @dir: directory in which the symlink is being created * @target: plaintext symlink target * @len: length of @target excluding null terminator @@ -687,7 +692,7 @@ static inline int fscrypt_prepare_symlink(struct inode *dir, } /** - * fscrypt_encrypt_symlink - encrypt the symlink target if needed + * fscrypt_encrypt_symlink() - encrypt the symlink target if needed * @inode: symlink inode * @target: plaintext symlink target * @len: length of @target excluding null terminator -- cgit v1.2.3 From fe015a78e5d0139cb126e8dbfc46a80be2bd27ad Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:13:57 -0700 Subject: fscrypt: name all function parameters Name all the function parameters. This makes it so that we don't have a mix of both styles, so it won't be ambiguous what to use in new fscrypt patches. This also matches the checkpatch expectation. Link: https://lore.kernel.org/r/20200511191358.53096-3-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 46 +++++++++++++++++++++++++--------------------- 1 file changed, 25 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index cb2c41f8dfde..210a05dd9ecd 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -56,10 +56,11 @@ struct fscrypt_name { struct fscrypt_operations { unsigned int flags; const char *key_prefix; - int (*get_context)(struct inode *, void *, size_t); - int (*set_context)(struct inode *, const void *, size_t, void *); - bool (*dummy_context)(struct inode *); - bool (*empty_dir)(struct inode *); + int (*get_context)(struct inode *inode, void *ctx, size_t len); + int (*set_context)(struct inode *inode, const void *ctx, size_t len, + void *fs_data); + bool (*dummy_context)(struct inode *inode); + bool (*empty_dir)(struct inode *inode); unsigned int max_namelen; bool (*has_stable_inodes)(struct super_block *sb); void (*get_ino_and_lblk_bits)(struct super_block *sb, @@ -137,13 +138,15 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) extern void fscrypt_free_bounce_page(struct page *bounce_page); /* policy.c */ -extern int fscrypt_ioctl_set_policy(struct file *, const void __user *); -extern int fscrypt_ioctl_get_policy(struct file *, void __user *); -extern int fscrypt_ioctl_get_policy_ex(struct file *, void __user *); +extern int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg); +extern int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg); +extern int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg); extern int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); -extern int fscrypt_has_permitted_context(struct inode *, struct inode *); -extern int fscrypt_inherit_context(struct inode *, struct inode *, - void *, bool); +extern int fscrypt_has_permitted_context(struct inode *parent, + struct inode *child); +extern int fscrypt_inherit_context(struct inode *parent, struct inode *child, + void *fs_data, bool preload); + /* keyring.c */ extern void fscrypt_sb_free(struct super_block *sb); extern int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); @@ -153,23 +156,24 @@ extern int fscrypt_ioctl_remove_key_all_users(struct file *filp, extern int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); /* keysetup.c */ -extern int fscrypt_get_encryption_info(struct inode *); -extern void fscrypt_put_encryption_info(struct inode *); -extern void fscrypt_free_inode(struct inode *); +extern int fscrypt_get_encryption_info(struct inode *inode); +extern void fscrypt_put_encryption_info(struct inode *inode); +extern void fscrypt_free_inode(struct inode *inode); extern int fscrypt_drop_inode(struct inode *inode); /* fname.c */ -extern int fscrypt_setup_filename(struct inode *, const struct qstr *, - int lookup, struct fscrypt_name *); +extern int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname, + int lookup, struct fscrypt_name *fname); static inline void fscrypt_free_filename(struct fscrypt_name *fname) { kfree(fname->crypto_buf.name); } -extern int fscrypt_fname_alloc_buffer(const struct inode *, u32, - struct fscrypt_str *); -extern void fscrypt_fname_free_buffer(struct fscrypt_str *); +extern int fscrypt_fname_alloc_buffer(const struct inode *inode, + u32 max_encrypted_len, + struct fscrypt_str *crypto_str); +extern void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str); extern int fscrypt_fname_disk_to_usr(const struct inode *inode, u32 hash, u32 minor_hash, const struct fscrypt_str *iname, @@ -180,9 +184,9 @@ extern u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name); /* bio.c */ -extern void fscrypt_decrypt_bio(struct bio *); -extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, - unsigned int); +extern void fscrypt_decrypt_bio(struct bio *bio); +extern int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, + sector_t pblk, unsigned int len); /* hooks.c */ extern int fscrypt_file_open(struct inode *inode, struct file *filp); -- cgit v1.2.3 From 607009020a5e7fd9353fb2dd4cdcc73e26f3350f Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:13:58 -0700 Subject: fscrypt: remove unnecessary extern keywords Remove the unnecessary 'extern' keywords from function declarations. This makes it so that we don't have a mix of both styles, so it won't be ambiguous what to use in new fscrypt patches. This also makes the code shorter and matches the 'checkpatch --strict' expectation. Link: https://lore.kernel.org/r/20200511191358.53096-4-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 138 +++++++++++++++++++++++------------------------- 1 file changed, 65 insertions(+), 73 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 210a05dd9ecd..0e0c7ad19383 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -108,22 +108,21 @@ static inline void fscrypt_handle_d_move(struct dentry *dentry) } /* crypto.c */ -extern void fscrypt_enqueue_decrypt_work(struct work_struct *); - -extern struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, - unsigned int len, - unsigned int offs, - gfp_t gfp_flags); -extern int fscrypt_encrypt_block_inplace(const struct inode *inode, - struct page *page, unsigned int len, - unsigned int offs, u64 lblk_num, - gfp_t gfp_flags); - -extern int fscrypt_decrypt_pagecache_blocks(struct page *page, unsigned int len, - unsigned int offs); -extern int fscrypt_decrypt_block_inplace(const struct inode *inode, - struct page *page, unsigned int len, - unsigned int offs, u64 lblk_num); +void fscrypt_enqueue_decrypt_work(struct work_struct *); + +struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, + unsigned int len, + unsigned int offs, + gfp_t gfp_flags); +int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page, + unsigned int len, unsigned int offs, + u64 lblk_num, gfp_t gfp_flags); + +int fscrypt_decrypt_pagecache_blocks(struct page *page, unsigned int len, + unsigned int offs); +int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page, + unsigned int len, unsigned int offs, + u64 lblk_num); static inline bool fscrypt_is_bounce_page(struct page *page) { @@ -135,81 +134,74 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) return (struct page *)page_private(bounce_page); } -extern void fscrypt_free_bounce_page(struct page *bounce_page); +void fscrypt_free_bounce_page(struct page *bounce_page); /* policy.c */ -extern int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg); -extern int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg); -extern int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg); -extern int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); -extern int fscrypt_has_permitted_context(struct inode *parent, - struct inode *child); -extern int fscrypt_inherit_context(struct inode *parent, struct inode *child, - void *fs_data, bool preload); +int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg); +int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg); +int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg); +int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg); +int fscrypt_has_permitted_context(struct inode *parent, struct inode *child); +int fscrypt_inherit_context(struct inode *parent, struct inode *child, + void *fs_data, bool preload); /* keyring.c */ -extern void fscrypt_sb_free(struct super_block *sb); -extern int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); -extern int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); -extern int fscrypt_ioctl_remove_key_all_users(struct file *filp, - void __user *arg); -extern int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); +void fscrypt_sb_free(struct super_block *sb); +int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); +int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); +int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); +int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); /* keysetup.c */ -extern int fscrypt_get_encryption_info(struct inode *inode); -extern void fscrypt_put_encryption_info(struct inode *inode); -extern void fscrypt_free_inode(struct inode *inode); -extern int fscrypt_drop_inode(struct inode *inode); +int fscrypt_get_encryption_info(struct inode *inode); +void fscrypt_put_encryption_info(struct inode *inode); +void fscrypt_free_inode(struct inode *inode); +int fscrypt_drop_inode(struct inode *inode); /* fname.c */ -extern int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname, - int lookup, struct fscrypt_name *fname); +int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname, + int lookup, struct fscrypt_name *fname); static inline void fscrypt_free_filename(struct fscrypt_name *fname) { kfree(fname->crypto_buf.name); } -extern int fscrypt_fname_alloc_buffer(const struct inode *inode, - u32 max_encrypted_len, - struct fscrypt_str *crypto_str); -extern void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str); -extern int fscrypt_fname_disk_to_usr(const struct inode *inode, - u32 hash, u32 minor_hash, - const struct fscrypt_str *iname, - struct fscrypt_str *oname); -extern bool fscrypt_match_name(const struct fscrypt_name *fname, - const u8 *de_name, u32 de_name_len); -extern u64 fscrypt_fname_siphash(const struct inode *dir, - const struct qstr *name); +int fscrypt_fname_alloc_buffer(const struct inode *inode, u32 max_encrypted_len, + struct fscrypt_str *crypto_str); +void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str); +int fscrypt_fname_disk_to_usr(const struct inode *inode, + u32 hash, u32 minor_hash, + const struct fscrypt_str *iname, + struct fscrypt_str *oname); +bool fscrypt_match_name(const struct fscrypt_name *fname, + const u8 *de_name, u32 de_name_len); +u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name); /* bio.c */ -extern void fscrypt_decrypt_bio(struct bio *bio); -extern int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, - sector_t pblk, unsigned int len); +void fscrypt_decrypt_bio(struct bio *bio); +int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, + sector_t pblk, unsigned int len); /* hooks.c */ -extern int fscrypt_file_open(struct inode *inode, struct file *filp); -extern int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, - struct dentry *dentry); -extern int __fscrypt_prepare_rename(struct inode *old_dir, - struct dentry *old_dentry, - struct inode *new_dir, - struct dentry *new_dentry, - unsigned int flags); -extern int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, - struct fscrypt_name *fname); -extern int fscrypt_prepare_setflags(struct inode *inode, - unsigned int oldflags, unsigned int flags); -extern int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len, - unsigned int max_len, - struct fscrypt_str *disk_link); -extern int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, - unsigned int len, - struct fscrypt_str *disk_link); -extern const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, - unsigned int max_size, - struct delayed_call *done); +int fscrypt_file_open(struct inode *inode, struct file *filp); +int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, + struct dentry *dentry); +int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags); +int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, + struct fscrypt_name *fname); +int fscrypt_prepare_setflags(struct inode *inode, + unsigned int oldflags, unsigned int flags); +int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len, + unsigned int max_len, + struct fscrypt_str *disk_link); +int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, + unsigned int len, struct fscrypt_str *disk_link); +const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, + unsigned int max_size, + struct delayed_call *done); static inline void fscrypt_set_ops(struct super_block *sb, const struct fscrypt_operations *s_cop) { -- cgit v1.2.3 From 6377a38bd345b7f3b664c43ebb647ae55c1166e4 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:21:17 -0700 Subject: fs-verity: fix all kerneldoc warnings Fix all kerneldoc warnings in fs/verity/ and include/linux/fsverity.h. Most of these were due to missing documentation for function parameters. Detected with: scripts/kernel-doc -v -none fs/verity/*.{c,h} include/linux/fsverity.h This cleanup makes it possible to check new patches for kerneldoc warnings without having to filter out all the existing ones. Link: https://lore.kernel.org/r/20200511192118.71427-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fsverity.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index ecc604e61d61..5ac30198e032 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -200,6 +200,7 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work) /** * fsverity_active() - do reads from the inode need to go through fs-verity? + * @inode: inode to check * * This checks whether ->i_verity_info has been set. * @@ -207,6 +208,8 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work) * be verified or not. Don't use IS_VERITY() for this purpose; it's subject to * a race condition where the file is being read concurrently with * FS_IOC_ENABLE_VERITY completing. (S_VERITY is set before ->i_verity_info.) + * + * Return: true if reads need to go through fs-verity, otherwise false */ static inline bool fsverity_active(const struct inode *inode) { -- cgit v1.2.3 From 9cd6b593cfc9eaa476c9a3fa768b08bca73213d0 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 11 May 2020 12:21:18 -0700 Subject: fs-verity: remove unnecessary extern keywords Remove the unnecessary 'extern' keywords from function declarations. This makes it so that we don't have a mix of both styles, so it won't be ambiguous what to use in new fs-verity patches. This also makes the code shorter and matches the 'checkpatch --strict' expectation. Link: https://lore.kernel.org/r/20200511192118.71427-3-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fsverity.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 5ac30198e032..78201a6d35f6 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -121,23 +121,23 @@ static inline struct fsverity_info *fsverity_get_info(const struct inode *inode) /* enable.c */ -extern int fsverity_ioctl_enable(struct file *filp, const void __user *arg); +int fsverity_ioctl_enable(struct file *filp, const void __user *arg); /* measure.c */ -extern int fsverity_ioctl_measure(struct file *filp, void __user *arg); +int fsverity_ioctl_measure(struct file *filp, void __user *arg); /* open.c */ -extern int fsverity_file_open(struct inode *inode, struct file *filp); -extern int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); -extern void fsverity_cleanup_inode(struct inode *inode); +int fsverity_file_open(struct inode *inode, struct file *filp); +int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); +void fsverity_cleanup_inode(struct inode *inode); /* verify.c */ -extern bool fsverity_verify_page(struct page *page); -extern void fsverity_verify_bio(struct bio *bio); -extern void fsverity_enqueue_verify_work(struct work_struct *work); +bool fsverity_verify_page(struct page *page); +void fsverity_verify_bio(struct bio *bio); +void fsverity_enqueue_verify_work(struct work_struct *work); #else /* !CONFIG_FS_VERITY */ -- cgit v1.2.3 From 07c4e1e834f8e7c991aa6dcb5ee0b7f2842e495d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 8 May 2020 16:17:56 +0800 Subject: block: only define 'nr_sects_seq' in hd_part for 32bit SMP The seqcount of 'nr_sects_seq' is only needed in case of 32bit SMP, so define it just for 32bit SMP. Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Cc: Yufen Yu Cc: Christoph Hellwig Cc: Hou Tao Signed-off-by: Jens Axboe --- include/linux/genhd.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index f9c226f9546a..b4744035ae58 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -68,7 +68,9 @@ struct hd_struct { * can be non-atomic on 32bit machines with 64bit sector_t. */ sector_t nr_sects; +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) seqcount_t nr_sects_seq; +#endif sector_t alignment_offset; unsigned int discard_alignment; struct device __dev; @@ -274,6 +276,13 @@ static inline void disk_put_part(struct hd_struct *part) put_device(part_to_dev(part)); } +static inline void hd_sects_seq_init(struct hd_struct *p) +{ +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + seqcount_init(&p->nr_sects_seq); +#endif +} + /* * Smarter partition iterator without context limits. */ -- cgit v1.2.3 From 520138c3b9425c615d1417687947d86821003319 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 8 May 2020 16:17:57 +0800 Subject: block: re-organize fields of 'struct hd_part' Put all fields accessed in IO path together at the beginning of the struct, so that all can be fetched in single cacheline. Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Cc: Yufen Yu Cc: Christoph Hellwig Cc: Hou Tao Signed-off-by: Jens Axboe --- include/linux/genhd.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index b4744035ae58..a9384449465a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -71,6 +71,14 @@ struct hd_struct { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) seqcount_t nr_sects_seq; #endif + unsigned long stamp; +#ifdef CONFIG_SMP + struct disk_stats __percpu *dkstats; +#else + struct disk_stats dkstats; +#endif + struct percpu_ref ref; + sector_t alignment_offset; unsigned int discard_alignment; struct device __dev; @@ -80,13 +88,6 @@ struct hd_struct { #ifdef CONFIG_FAIL_MAKE_REQUEST int make_it_fail; #endif - unsigned long stamp; -#ifdef CONFIG_SMP - struct disk_stats __percpu *dkstats; -#else - struct disk_stats dkstats; -#endif - struct percpu_ref ref; struct rcu_work rcu_work; }; -- cgit v1.2.3 From e6249cdd46e43a7d3bdb8cce5fe24565d6c11e94 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sun, 3 May 2020 09:54:22 +0800 Subject: block: add blk_io_schedule() for avoiding task hung in sync dio Sync dio could be big, or may take long time in discard or in case of IO failure. We have prevented task hung in submit_bio_wait() and blk_execute_rq(), so apply the same trick for prevent task hung from happening in sync dio. Add helper of blk_io_schedule() and use io_schedule_timeout() to prevent task hung warning. Signed-off-by: Ming Lei Reviewed-by: Bart Van Assche Cc: Salman Qazi Cc: Jesse Barnes Cc: Christoph Hellwig Cc: Bart Van Assche Cc: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f00bd4042295..222eb5f32279 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -27,6 +27,7 @@ #include #include #include +#include struct module; struct scsi_ioctl_command; @@ -1827,4 +1828,15 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } +static inline void blk_io_schedule(void) +{ + /* Prevent hang_check timer from firing at us during very long I/O */ + unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; + + if (timeout) + io_schedule_timeout(timeout); + else + io_schedule(); +} + #endif -- cgit v1.2.3 From 02992df822e7e36685593aad10721a5a9f8d3402 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 12 May 2020 17:55:45 +0900 Subject: block: provide fallbacks for blk_queue_zone_is_seq and blk_queue_zone_no blk_queue_zone_is_seq() and blk_queue_zone_no() have not been called with CONFIG_BLK_DEV_ZONED disabled until now. The introduction of REQ_OP_ZONE_APPEND will change this, so we need to provide noop fallbacks for the !CONFIG_BLK_DEV_ZONED case. Signed-off-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 222eb5f32279..d736acf7f564 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -722,6 +722,16 @@ static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { return 0; } +static inline bool blk_queue_zone_is_seq(struct request_queue *q, + sector_t sector) +{ + return false; +} +static inline unsigned int blk_queue_zone_no(struct request_queue *q, + sector_t sector) +{ + return 0; +} #endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) -- cgit v1.2.3 From 0512a75b98f847c2e9a4b664013424e603e202f7 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 12 May 2020 17:55:47 +0900 Subject: block: Introduce REQ_OP_ZONE_APPEND Define REQ_OP_ZONE_APPEND to append-write sectors to a zone of a zoned block device. This is a no-merge write operation. A zone append write BIO must: * Target a zoned block device * Have a sector position indicating the start sector of the target zone * The target zone must be a sequential write zone * The BIO must not cross a zone boundary * The BIO size must not be split to ensure that a single range of LBAs is written with a single command. Implement these checks in generic_make_request_checks() using the helper function blk_check_zone_append(). To avoid write append BIO splitting, introduce the new max_zone_append_sectors queue limit attribute and ensure that a BIO size is always lower than this limit. Export this new limit through sysfs and check these limits in bio_full(). Also when a LLDD can't dispatch a request to a specific zone, it will return BLK_STS_ZONE_RESOURCE indicating this request needs to be delayed, e.g. because the zone it will be dispatched to is still write-locked. If this happens set the request aside in a local list to continue trying dispatching requests such as READ requests or a WRITE/ZONE_APPEND requests targetting other zones. This way we can still keep a high queue depth without starving other requests even if one request can't be served due to zone write-locking. Finally, make sure that the bio sector position indicates the actual write position as indicated by the device on completion. Signed-off-by: Keith Busch [ jth: added zone-append specific add_page and merge_page helpers ] Signed-off-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 14 ++++++++++++++ include/linux/blkdev.h | 11 +++++++++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 90895d594e64..b90dca1fa430 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -63,6 +63,18 @@ typedef u8 __bitwise blk_status_t; */ #define BLK_STS_DEV_RESOURCE ((__force blk_status_t)13) +/* + * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone + * related resources are unavailable, but the driver can guarantee the queue + * will be rerun in the future once the resources become available again. + * + * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references + * a zone specific resource and IO to a different zone on the same device could + * still be served. Examples of that are zones that are write-locked, but a read + * to the same zone could be served. + */ +#define BLK_STS_ZONE_RESOURCE ((__force blk_status_t)14) + /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with @@ -296,6 +308,8 @@ enum req_opf { REQ_OP_ZONE_CLOSE = 11, /* Transition a zone to full */ REQ_OP_ZONE_FINISH = 12, + /* write data at the current zone write pointer */ + REQ_OP_ZONE_APPEND = 13, /* SCSI passthrough using struct scsi_request */ REQ_OP_SCSI_IN = 32, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d736acf7f564..5647c78bb876 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -332,6 +332,7 @@ struct queue_limits { unsigned int max_hw_discard_sectors; unsigned int max_write_same_sectors; unsigned int max_write_zeroes_sectors; + unsigned int max_zone_append_sectors; unsigned int discard_granularity; unsigned int discard_alignment; @@ -750,6 +751,9 @@ static inline bool rq_mergeable(struct request *rq) if (req_op(rq) == REQ_OP_WRITE_ZEROES) return false; + if (req_op(rq) == REQ_OP_ZONE_APPEND) + return false; + if (rq->cmd_flags & REQ_NOMERGE_FLAGS) return false; if (rq->rq_flags & RQF_NOMERGE_FLAGS) @@ -1084,6 +1088,8 @@ extern void blk_queue_max_write_same_sectors(struct request_queue *q, extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); +extern void blk_queue_max_zone_append_sectors(struct request_queue *q, + unsigned int max_zone_append_sectors); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); @@ -1301,6 +1307,11 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } +static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q) +{ + return q->limits.max_zone_append_sectors; +} + static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; -- cgit v1.2.3 From 1392d37018d4f68c5bb2c98dae9a018b73926865 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 12 May 2020 17:55:48 +0900 Subject: block: introduce blk_req_zone_write_trylock Introduce blk_req_zone_write_trylock(), which either grabs the write-lock for a sequential zone or returns false, if the zone is already locked. Signed-off-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5647c78bb876..73f4f4f1df92 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1738,6 +1738,7 @@ extern int bdev_write_page(struct block_device *, sector_t, struct page *, #ifdef CONFIG_BLK_DEV_ZONED bool blk_req_needs_zone_write_lock(struct request *rq); +bool blk_req_zone_write_trylock(struct request *rq); void __blk_req_zone_write_lock(struct request *rq); void __blk_req_zone_write_unlock(struct request *rq); -- cgit v1.2.3 From e732671aa5f67232cf760666a15242dead003362 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 12 May 2020 17:55:49 +0900 Subject: block: Modify revalidate zones Modify the interface of blk_revalidate_disk_zones() to add an optional driver callback function that a driver can use to extend processing done during zone revalidation. The callback, if defined, is executed with the device request queue frozen, after all zones have been inspected. Signed-off-by: Damien Le Moal Signed-off-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 73f4f4f1df92..5360696d85ff 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -358,7 +358,8 @@ unsigned int blkdev_nr_zones(struct gendisk *disk); extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); -extern int blk_revalidate_disk_zones(struct gendisk *disk); +int blk_revalidate_disk_zones(struct gendisk *disk, + void (*update_driver_data)(struct gendisk *disk)); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); -- cgit v1.2.3 From 755a7397947e21123d8162eaf7477b614732ff22 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Sun, 26 Apr 2020 16:11:43 +0800 Subject: dt-bindings: firmware: imx: Move system control into dt-binding headfile i.MX8 SoCs DTS file needs system control macro definitions, so move them into dt-binding headfile, then include/linux/firmware/imx/types.h can be removed and those drivers using it should be changed accordingly. Signed-off-by: Dong Aisheng Signed-off-by: Jacky Bai Signed-off-by: Anson Huang Signed-off-by: Shawn Guo --- include/linux/firmware/imx/sci.h | 1 - include/linux/firmware/imx/types.h | 65 -------------------------------------- 2 files changed, 66 deletions(-) delete mode 100644 include/linux/firmware/imx/types.h (limited to 'include/linux') diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h index 17ba4e405129..3fa418a4ca67 100644 --- a/include/linux/firmware/imx/sci.h +++ b/include/linux/firmware/imx/sci.h @@ -11,7 +11,6 @@ #define _SC_SCI_H #include -#include #include #include diff --git a/include/linux/firmware/imx/types.h b/include/linux/firmware/imx/types.h deleted file mode 100644 index 80821100e85f..000000000000 --- a/include/linux/firmware/imx/types.h +++ /dev/null @@ -1,65 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * Copyright (C) 2016 Freescale Semiconductor, Inc. - * Copyright 2017~2018 NXP - * - * Header file containing types used across multiple service APIs. - */ - -#ifndef _SC_TYPES_H -#define _SC_TYPES_H - -/* - * This type is used to indicate a control. - */ -enum imx_sc_ctrl { - IMX_SC_C_TEMP = 0, - IMX_SC_C_TEMP_HI = 1, - IMX_SC_C_TEMP_LOW = 2, - IMX_SC_C_PXL_LINK_MST1_ADDR = 3, - IMX_SC_C_PXL_LINK_MST2_ADDR = 4, - IMX_SC_C_PXL_LINK_MST_ENB = 5, - IMX_SC_C_PXL_LINK_MST1_ENB = 6, - IMX_SC_C_PXL_LINK_MST2_ENB = 7, - IMX_SC_C_PXL_LINK_SLV1_ADDR = 8, - IMX_SC_C_PXL_LINK_SLV2_ADDR = 9, - IMX_SC_C_PXL_LINK_MST_VLD = 10, - IMX_SC_C_PXL_LINK_MST1_VLD = 11, - IMX_SC_C_PXL_LINK_MST2_VLD = 12, - IMX_SC_C_SINGLE_MODE = 13, - IMX_SC_C_ID = 14, - IMX_SC_C_PXL_CLK_POLARITY = 15, - IMX_SC_C_LINESTATE = 16, - IMX_SC_C_PCIE_G_RST = 17, - IMX_SC_C_PCIE_BUTTON_RST = 18, - IMX_SC_C_PCIE_PERST = 19, - IMX_SC_C_PHY_RESET = 20, - IMX_SC_C_PXL_LINK_RATE_CORRECTION = 21, - IMX_SC_C_PANIC = 22, - IMX_SC_C_PRIORITY_GROUP = 23, - IMX_SC_C_TXCLK = 24, - IMX_SC_C_CLKDIV = 25, - IMX_SC_C_DISABLE_50 = 26, - IMX_SC_C_DISABLE_125 = 27, - IMX_SC_C_SEL_125 = 28, - IMX_SC_C_MODE = 29, - IMX_SC_C_SYNC_CTRL0 = 30, - IMX_SC_C_KACHUNK_CNT = 31, - IMX_SC_C_KACHUNK_SEL = 32, - IMX_SC_C_SYNC_CTRL1 = 33, - IMX_SC_C_DPI_RESET = 34, - IMX_SC_C_MIPI_RESET = 35, - IMX_SC_C_DUAL_MODE = 36, - IMX_SC_C_VOLTAGE = 37, - IMX_SC_C_PXL_LINK_SEL = 38, - IMX_SC_C_OFS_SEL = 39, - IMX_SC_C_OFS_AUDIO = 40, - IMX_SC_C_OFS_PERIPH = 41, - IMX_SC_C_OFS_IRQ = 42, - IMX_SC_C_RST0 = 43, - IMX_SC_C_RST1 = 44, - IMX_SC_C_SEL0 = 45, - IMX_SC_C_LAST -}; - -#endif /* _SC_TYPES_H */ -- cgit v1.2.3 From 32b1924b210a70dcacdf65abd687c5ef86a67541 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 9 Apr 2020 11:29:47 +0300 Subject: ovl: skip overlayfs superblocks at global sync Stacked filesystems like overlayfs has no own writeback, but they have to forward syncfs() requests to backend for keeping data integrity. During global sync() each overlayfs instance calls method ->sync_fs() for backend although it itself is in global list of superblocks too. As a result one syscall sync() could write one superblock several times and send multiple disk barriers. This patch adds flag SB_I_SKIP_SYNC into sb->sb_iflags to avoid that. Reported-by: Dmitry Monakhov Signed-off-by: Konstantin Khlebnikov Reviewed-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..f186a966a36c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1409,6 +1409,8 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 +#define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ + /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ -- cgit v1.2.3 From 303cc571d107b3641d6487061b748e70ffe15ce4 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 5 May 2020 16:04:31 +0200 Subject: nsproxy: attach to namespaces via pidfds For quite a while we have been thinking about using pidfds to attach to namespaces. This patchset has existed for about a year already but we've wanted to wait to see how the general api would be received and adopted. Now that more and more programs in userspace have started using pidfds for process management it's time to send this one out. This patch makes it possible to use pidfds to attach to the namespaces of another process, i.e. they can be passed as the first argument to the setns() syscall. When only a single namespace type is specified the semantics are equivalent to passing an nsfd. That means setns(nsfd, CLONE_NEWNET) equals setns(pidfd, CLONE_NEWNET). However, when a pidfd is passed, multiple namespace flags can be specified in the second setns() argument and setns() will attach the caller to all the specified namespaces all at once or to none of them. Specifying 0 is not valid together with a pidfd. Here are just two obvious examples: setns(pidfd, CLONE_NEWPID | CLONE_NEWNS | CLONE_NEWNET); setns(pidfd, CLONE_NEWUSER); Allowing to also attach subsets of namespaces supports various use-cases where callers setns to a subset of namespaces to retain privilege, perform an action and then re-attach another subset of namespaces. If the need arises, as Eric suggested, we can extend this patchset to assume even more context than just attaching all namespaces. His suggestion specifically was about assuming the process' root directory when setns(pidfd, 0) or setns(pidfd, SETNS_PIDFD) is specified. For now, just keep it flexible in terms of supporting subsets of namespaces but let's wait until we have users asking for even more context to be assumed. At that point we can add an extension. The obvious example where this is useful is a standard container manager interacting with a running container: pushing and pulling files or directories, injecting mounts, attaching/execing any kind of process, managing network devices all these operations require attaching to all or at least multiple namespaces at the same time. Given that nowadays most containers are spawned with all namespaces enabled we're currently looking at at least 14 syscalls, 7 to open the /proc//ns/ nsfds, another 7 to actually perform the namespace switch. With time namespaces we're looking at about 16 syscalls. (We could amortize the first 7 or 8 syscalls for opening the nsfds by stashing them in each container's monitor process but that would mean we need to send around those file descriptors through unix sockets everytime we want to interact with the container or keep on-disk state. Even in scenarios where a caller wants to join a particular namespace in a particular order callers still profit from batching other namespaces. That mostly applies to the user namespace but all container runtimes I found join the user namespace first no matter if it privileges or deprivileges the container similar to how unshare behaves.) With pidfds this becomes a single syscall no matter how many namespaces are supposed to be attached to. A decently designed, large-scale container manager usually isn't the parent of any of the containers it spawns so the containers don't die when it crashes or needs to update or reinitialize. This means that for the manager to interact with containers through pids is inherently racy especially on systems where the maximum pid number is not significicantly bumped. This is even more problematic since we often spawn and manage thousands or ten-thousands of containers. Interacting with a container through a pid thus can become risky quite quickly. Especially since we allow for an administrator to enable advanced features such as syscall interception where we're performing syscalls in lieu of the container. In all of those cases we use pidfds if they are available and we pass them around as stable references. Using them to setns() to the target process' namespaces is as reliable as using nsfds. Either the target process is already dead and we get ESRCH or we manage to attach to its namespaces but we can't accidently attach to another process' namespaces. So pidfds lend themselves to be used with this api. The other main advantage is that with this change the pidfd becomes the only relevant token for most container interactions and it's the only token we need to create and send around. Apart from significiantly reducing the number of syscalls from double digit to single digit which is a decent reason post-spectre/meltdown this also allows to switch to a set of namespaces atomically, i.e. either attaching to all the specified namespaces succeeds or we fail. If we fail we haven't changed a single namespace. There are currently three namespaces that can fail (other than for ENOMEM which really is not very interesting since we then have other problems anyway) for non-trivial reasons, user, mount, and pid namespaces. We can fail to attach to a pid namespace if it is not our current active pid namespace or a descendant of it. We can fail to attach to a user namespace because we are multi-threaded or because our current mount namespace shares filesystem state with other tasks, or because we're trying to setns() to the same user namespace, i.e. the target task has the same user namespace as we do. We can fail to attach to a mount namespace because it shares filesystem state with other tasks or because we fail to lookup the new root for the new mount namespace. In most non-pathological scenarios these issues can be somewhat mitigated. But there are cases where we're half-attached to some namespace and failing to attach to another one. I've talked about some of these problem during the hallway track (something only the pre-COVID-19 generation will remember) of Plumbers in Los Angeles in 2018(?). Even if all these issues could be avoided with super careful userspace coding it would be nicer to have this done in-kernel. Pidfds seem to lend themselves nicely for this. The other neat thing about this is that setns() becomes an actual counterpart to the namespace bits of unshare(). Signed-off-by: Christian Brauner Reviewed-by: Serge Hallyn Cc: Eric W. Biederman Cc: Serge Hallyn Cc: Jann Horn Cc: Michael Kerrisk Cc: Aleksa Sarai Link: https://lore.kernel.org/r/20200505140432.181565-3-christian.brauner@ubuntu.com --- include/linux/mnt_namespace.h | 1 + include/linux/proc_fs.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 007cfa52efb2..8f882f5881e8 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -11,6 +11,7 @@ struct ns_common; extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, struct user_namespace *, struct fs_struct *); extern void put_mnt_ns(struct mnt_namespace *ns); +extern struct ns_common *from_mnt_ns(struct mnt_namespace *); extern const struct file_operations proc_mounts_operations; extern const struct file_operations proc_mountinfo_operations; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 45c05fd9c99d..0cfc44d7ac74 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -179,4 +179,6 @@ static inline struct pid_namespace *proc_pid_ns(const struct inode *inode) return inode->i_sb->s_fs_info; } +bool proc_ns_file(const struct file *file); + #endif /* _LINUX_PROC_FS_H */ -- cgit v1.2.3 From 1597d453289b385237628cd96d57d147632ab105 Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Tue, 12 May 2020 15:53:20 +0300 Subject: interconnect: Add of_icc_get_by_index() helper function This is the same as the traditional of_icc_get() function, but the difference is that it takes index as an argument, instead of name. Reviewed-by: Matthias Kaehlcke Reviewed-by: Sibi Sankar Link: https://lore.kernel.org/r/20200512125327.1868-4-georgi.djakov@linaro.org Signed-off-by: Georgi Djakov --- include/linux/interconnect.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index d70a914cba11..34e97231a6ab 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -28,6 +28,7 @@ struct device; struct icc_path *icc_get(struct device *dev, const int src_id, const int dst_id); struct icc_path *of_icc_get(struct device *dev, const char *name); +struct icc_path *of_icc_get_by_index(struct device *dev, int idx); void icc_put(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); void icc_set_tag(struct icc_path *path, u32 tag); @@ -46,6 +47,11 @@ static inline struct icc_path *of_icc_get(struct device *dev, return NULL; } +static inline struct icc_path *of_icc_get_by_index(struct device *dev, int idx) +{ + return NULL; +} + static inline void icc_put(struct icc_path *path) { } -- cgit v1.2.3 From 84c1e51d7df85332705ffebc40ef135205492036 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:53:18 -0500 Subject: greybus: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200507185318.GA14393@embeddedor Signed-off-by: Greg Kroah-Hartman --- include/linux/greybus/greybus_protocols.h | 44 +++++++++++++++---------------- 1 file changed, 22 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/greybus/greybus_protocols.h b/include/linux/greybus/greybus_protocols.h index dfbc6c39a74b..aeb8f9243545 100644 --- a/include/linux/greybus/greybus_protocols.h +++ b/include/linux/greybus/greybus_protocols.h @@ -345,7 +345,7 @@ struct gb_cap_get_ims_certificate_request { struct gb_cap_get_ims_certificate_response { __u8 result_code; - __u8 certificate[0]; + __u8 certificate[]; } __packed; /* CAP authenticate request/response */ @@ -358,7 +358,7 @@ struct gb_cap_authenticate_request { struct gb_cap_authenticate_response { __u8 result_code; __u8 response[64]; - __u8 signature[0]; + __u8 signature[]; } __packed; @@ -642,7 +642,7 @@ struct gb_hid_get_report_request { struct gb_hid_set_report_request { __u8 report_type; __u8 report_id; - __u8 report[0]; + __u8 report[]; } __packed; /* HID input report request, via interrupt pipe */ @@ -680,7 +680,7 @@ struct gb_i2c_transfer_op { struct gb_i2c_transfer_request { __le16 op_count; - struct gb_i2c_transfer_op ops[0]; /* op_count of these */ + struct gb_i2c_transfer_op ops[]; /* op_count of these */ } __packed; struct gb_i2c_transfer_response { __u8 data[0]; /* inbound data */ @@ -908,7 +908,7 @@ struct gb_spi_transfer_request { __u8 chip_select; /* of the spi device */ __u8 mode; /* of the spi device */ __le16 count; - struct gb_spi_transfer transfers[0]; /* count of these */ + struct gb_spi_transfer transfers[]; /* count of these */ } __packed; struct gb_spi_transfer_response { @@ -1188,7 +1188,7 @@ struct gb_svc_pwrmon_rail_count_get_response { struct gb_svc_pwrmon_rail_names_get_response { __u8 status; - __u8 name[0][GB_SVC_PWRMON_RAIL_NAME_BUFSIZE]; + __u8 name[][GB_SVC_PWRMON_RAIL_NAME_BUFSIZE]; } __packed; #define GB_SVC_PWRMON_TYPE_CURR 0x01 @@ -1281,7 +1281,7 @@ struct gb_svc_intf_oops_request { struct gb_raw_send_request { __le32 len; - __u8 data[0]; + __u8 data[]; } __packed; @@ -1300,7 +1300,7 @@ struct gb_raw_send_request { /* Represents data from AP -> Module */ struct gb_uart_send_data_request { __le16 size; - __u8 data[0]; + __u8 data[]; } __packed; /* recv-data-request flags */ @@ -1313,7 +1313,7 @@ struct gb_uart_send_data_request { struct gb_uart_recv_data_request { __le16 size; __u8 flags; - __u8 data[0]; + __u8 data[]; } __packed; struct gb_uart_receive_credits_request { @@ -1382,14 +1382,14 @@ struct gb_loopback_transfer_request { __le32 len; __le32 reserved0; __le32 reserved1; - __u8 data[0]; + __u8 data[]; } __packed; struct gb_loopback_transfer_response { __le32 len; __le32 reserved0; __le32 reserved1; - __u8 data[0]; + __u8 data[]; } __packed; /* SDIO */ @@ -1530,13 +1530,13 @@ struct gb_sdio_transfer_request { __le16 data_blocks; __le16 data_blksz; - __u8 data[0]; + __u8 data[]; } __packed; struct gb_sdio_transfer_response { __le16 data_blocks; __le16 data_blksz; - __u8 data[0]; + __u8 data[]; } __packed; /* event request: generated by module and is defined as unidirectional */ @@ -1572,7 +1572,7 @@ struct gb_camera_configure_streams_request { __u8 flags; #define GB_CAMERA_CONFIGURE_STREAMS_TEST_ONLY 0x01 __le16 padding; - struct gb_camera_stream_config_request config[0]; + struct gb_camera_stream_config_request config[]; } __packed; /* Greybus Camera Configure Streams response payload */ @@ -1593,7 +1593,7 @@ struct gb_camera_configure_streams_response { __u8 flags; __u8 padding[2]; __le32 data_rate; - struct gb_camera_stream_config_response config[0]; + struct gb_camera_stream_config_response config[]; }; /* Greybus Camera Capture request payload - response has no payload */ @@ -1602,7 +1602,7 @@ struct gb_camera_capture_request { __u8 streams; __u8 padding; __le16 num_frames; - __u8 settings[0]; + __u8 settings[]; } __packed; /* Greybus Camera Flush response payload - request has no payload */ @@ -1616,7 +1616,7 @@ struct gb_camera_metadata_request { __le16 frame_number; __u8 stream; __u8 padding; - __u8 metadata[0]; + __u8 metadata[]; } __packed; /* Lights */ @@ -1993,7 +1993,7 @@ struct gb_audio_integer64 { struct gb_audio_enumerated { __le32 items; __le16 names_length; - __u8 names[0]; + __u8 names[]; } __packed; struct gb_audio_ctl_elem_info { /* See snd_ctl_elem_info in Linux source */ @@ -2033,7 +2033,7 @@ struct gb_audio_widget { __u8 type; /* GB_AUDIO_WIDGET_TYPE_* */ __u8 state; /* GB_AUDIO_WIDGET_STATE_* */ __u8 ncontrols; - struct gb_audio_control ctl[0]; /* 'ncontrols' entries */ + struct gb_audio_control ctl[]; /* 'ncontrols' entries */ } __packed; struct gb_audio_route { @@ -2059,7 +2059,7 @@ struct gb_audio_topology { * struct gb_audio_widget widgets[num_widgets]; * struct gb_audio_route routes[num_routes]; */ - __u8 data[0]; + __u8 data[]; } __packed; struct gb_audio_get_topology_size_response { @@ -2157,7 +2157,7 @@ struct gb_audio_streaming_event_request { struct gb_audio_send_data_request { __le64 timestamp; - __u8 data[0]; + __u8 data[]; } __packed; @@ -2171,7 +2171,7 @@ struct gb_audio_send_data_request { struct gb_log_send_log_request { __le16 len; - __u8 msg[0]; + __u8 msg[]; } __packed; #endif /* __GREYBUS_PROTOCOLS_H */ -- cgit v1.2.3 From 8c49c9ee4a91c158d28c583862718b348881cb16 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Thu, 7 May 2020 18:08:57 +0300 Subject: usb: typec: Add typec_find_orientation() Function that converts orientation string into orientation value. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20200507150900.12102-2-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index b00a2642a9cd..5daa1c49761c 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -254,6 +254,7 @@ int typec_set_mode(struct typec_port *port, int mode); void *typec_get_drvdata(struct typec_port *port); +int typec_find_orientation(const char *name); int typec_find_port_power_role(const char *name); int typec_find_power_role(const char *name); int typec_find_port_data_role(const char *name); -- cgit v1.2.3 From d9d200bcebc1f6e56f0178cbb8db9953e8cc9a11 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 13 May 2020 15:32:08 +0200 Subject: dma-mapping: add generic helpers for mapping sgtable objects struct sg_table is a common structure used for describing a memory buffer. It consists of a scatterlist with memory pages and DMA addresses (sgl entry), as well as the number of scatterlist entries: CPU pages (orig_nents entry) and DMA mapped pages (nents entry). It turned out that it was a common mistake to misuse nents and orig_nents entries, calling DMA-mapping functions with a wrong number of entries or ignoring the number of mapped entries returned by the dma_map_sg function. To avoid such issues, let's introduce a common wrappers operating directly on the struct sg_table objects, which take care of the proper use of the nents and orig_nents entries. Signed-off-by: Marek Szyprowski Reviewed-by: Robin Murphy Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 80 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 330ad58fbf4d..936e30b86cd3 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -609,6 +609,86 @@ static inline void dma_sync_single_range_for_device(struct device *dev, return dma_sync_single_for_device(dev, addr + offset, size, dir); } +/** + * dma_map_sgtable - Map the given buffer for DMA + * @dev: The device for which to perform the DMA operation + * @sgt: The sg_table object describing the buffer + * @dir: DMA direction + * @attrs: Optional DMA attributes for the map operation + * + * Maps a buffer described by a scatterlist stored in the given sg_table + * object for the @dir DMA operation by the @dev device. After success the + * ownership for the buffer is transferred to the DMA domain. One has to + * call dma_sync_sgtable_for_cpu() or dma_unmap_sgtable() to move the + * ownership of the buffer back to the CPU domain before touching the + * buffer by the CPU. + * + * Returns 0 on success or -EINVAL on error during mapping the buffer. + */ +static inline int dma_map_sgtable(struct device *dev, struct sg_table *sgt, + enum dma_data_direction dir, unsigned long attrs) +{ + int nents; + + nents = dma_map_sg_attrs(dev, sgt->sgl, sgt->orig_nents, dir, attrs); + if (nents <= 0) + return -EINVAL; + sgt->nents = nents; + return 0; +} + +/** + * dma_unmap_sgtable - Unmap the given buffer for DMA + * @dev: The device for which to perform the DMA operation + * @sgt: The sg_table object describing the buffer + * @dir: DMA direction + * @attrs: Optional DMA attributes for the unmap operation + * + * Unmaps a buffer described by a scatterlist stored in the given sg_table + * object for the @dir DMA operation by the @dev device. After this function + * the ownership of the buffer is transferred back to the CPU domain. + */ +static inline void dma_unmap_sgtable(struct device *dev, struct sg_table *sgt, + enum dma_data_direction dir, unsigned long attrs) +{ + dma_unmap_sg_attrs(dev, sgt->sgl, sgt->orig_nents, dir, attrs); +} + +/** + * dma_sync_sgtable_for_cpu - Synchronize the given buffer for CPU access + * @dev: The device for which to perform the DMA operation + * @sgt: The sg_table object describing the buffer + * @dir: DMA direction + * + * Performs the needed cache synchronization and moves the ownership of the + * buffer back to the CPU domain, so it is safe to perform any access to it + * by the CPU. Before doing any further DMA operations, one has to transfer + * the ownership of the buffer back to the DMA domain by calling the + * dma_sync_sgtable_for_device(). + */ +static inline void dma_sync_sgtable_for_cpu(struct device *dev, + struct sg_table *sgt, enum dma_data_direction dir) +{ + dma_sync_sg_for_cpu(dev, sgt->sgl, sgt->orig_nents, dir); +} + +/** + * dma_sync_sgtable_for_device - Synchronize the given buffer for DMA + * @dev: The device for which to perform the DMA operation + * @sgt: The sg_table object describing the buffer + * @dir: DMA direction + * + * Performs the needed cache synchronization and moves the ownership of the + * buffer back to the DMA domain, so it is safe to perform the DMA operation. + * Once finished, one has to call dma_sync_sgtable_for_cpu() or + * dma_unmap_sgtable(). + */ +static inline void dma_sync_sgtable_for_device(struct device *dev, + struct sg_table *sgt, enum dma_data_direction dir) +{ + dma_sync_sg_for_device(dev, sgt->sgl, sgt->orig_nents, dir); +} + #define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, 0) #define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, 0) #define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, 0) -- cgit v1.2.3 From 709d6d73c756107fb8a292a9f957d630097425fa Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 13 May 2020 15:32:09 +0200 Subject: scatterlist: add generic wrappers for iterating over sgtable objects struct sg_table is a common structure used for describing a memory buffer. It consists of a scatterlist with memory pages and DMA addresses (sgl entry), as well as the number of scatterlist entries: CPU pages (orig_nents entry) and DMA mapped pages (nents entry). It turned out that it was a common mistake to misuse nents and orig_nents entries, calling the scatterlist iterating functions with a wrong number of the entries. To avoid such issues, lets introduce a common wrappers operating directly on the struct sg_table objects, which take care of the proper use of the nents and orig_nents entries. While touching this, lets clarify some ambiguities in the comments for the existing for_each helpers. Signed-off-by: Marek Szyprowski Reviewed-by: Robin Murphy Signed-off-by: Christoph Hellwig --- include/linux/scatterlist.h | 50 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 47 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 6eec50fb36c8..4f922afb607a 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -151,6 +151,20 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, #define for_each_sg(sglist, sg, nr, __i) \ for (__i = 0, sg = (sglist); __i < (nr); __i++, sg = sg_next(sg)) +/* + * Loop over each sg element in the given sg_table object. + */ +#define for_each_sgtable_sg(sgt, sg, i) \ + for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) + +/* + * Loop over each sg element in the given *DMA mapped* sg_table object. + * Please use sg_dma_address(sg) and sg_dma_len(sg) to extract DMA addresses + * of the each element. + */ +#define for_each_sgtable_dma_sg(sgt, sg, i) \ + for_each_sg(sgt->sgl, sg, sgt->nents, i) + /** * sg_chain - Chain two sglists together * @prv: First scatterlist @@ -401,9 +415,10 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter) * @sglist: sglist to iterate over * @piter: page iterator to hold current page, sg, sg_pgoffset * @nents: maximum number of sg entries to iterate over - * @pgoffset: starting page offset + * @pgoffset: starting page offset (in pages) * * Callers may use sg_page_iter_page() to get each page pointer. + * In each loop it operates on PAGE_SIZE unit. */ #define for_each_sg_page(sglist, piter, nents, pgoffset) \ for (__sg_page_iter_start((piter), (sglist), (nents), (pgoffset)); \ @@ -412,18 +427,47 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter) /** * for_each_sg_dma_page - iterate over the pages of the given sg list * @sglist: sglist to iterate over - * @dma_iter: page iterator to hold current page + * @dma_iter: DMA page iterator to hold current page * @dma_nents: maximum number of sg entries to iterate over, this is the value * returned from dma_map_sg - * @pgoffset: starting page offset + * @pgoffset: starting page offset (in pages) * * Callers may use sg_page_iter_dma_address() to get each page's DMA address. + * In each loop it operates on PAGE_SIZE unit. */ #define for_each_sg_dma_page(sglist, dma_iter, dma_nents, pgoffset) \ for (__sg_page_iter_start(&(dma_iter)->base, sglist, dma_nents, \ pgoffset); \ __sg_page_iter_dma_next(dma_iter);) +/** + * for_each_sgtable_page - iterate over all pages in the sg_table object + * @sgt: sg_table object to iterate over + * @piter: page iterator to hold current page + * @pgoffset: starting page offset (in pages) + * + * Iterates over the all memory pages in the buffer described by + * a scatterlist stored in the given sg_table object. + * See also for_each_sg_page(). In each loop it operates on PAGE_SIZE unit. + */ +#define for_each_sgtable_page(sgt, piter, pgoffset) \ + for_each_sg_page(sgt->sgl, piter, sgt->orig_nents, pgoffset) + +/** + * for_each_sgtable_dma_page - iterate over the DMA mapped sg_table object + * @sgt: sg_table object to iterate over + * @dma_iter: DMA page iterator to hold current page + * @pgoffset: starting page offset (in pages) + * + * Iterates over the all DMA mapped pages in the buffer described by + * a scatterlist stored in the given sg_table object. + * See also for_each_sg_dma_page(). In each loop it operates on PAGE_SIZE + * unit. + */ +#define for_each_sgtable_dma_page(sgt, dma_iter, pgoffset) \ + for_each_sg_dma_page(sgt->sgl, dma_iter, sgt->nents, pgoffset) + + /* * Mapping sg iterator * -- cgit v1.2.3 From 48530d9fab0d3bf08827f9167be54acf66d4d457 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 13 May 2020 15:32:10 +0200 Subject: iommu: add generic helper for mapping sgtable objects struct sg_table is a common structure used for describing a memory buffer. It consists of a scatterlist with memory pages and DMA addresses (sgl entry), as well as the number of scatterlist entries: CPU pages (orig_nents entry) and DMA mapped pages (nents entry). It turned out that it was a common mistake to misuse nents and orig_nents entries, calling mapping functions with a wrong number of entries. To avoid such issues, lets introduce a common wrapper operating directly on the struct sg_table objects, which take care of the proper use of the nents and orig_nents entries. Signed-off-by: Marek Szyprowski Acked-by: Joerg Roedel Reviewed-by: Robin Murphy Signed-off-by: Christoph Hellwig --- include/linux/iommu.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7ef8b0bda695..b1bfbe6dff42 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -466,6 +466,22 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t io extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); +/** + * iommu_map_sgtable - Map the given buffer to the IOMMU domain + * @domain: The IOMMU domain to perform the mapping + * @iova: The start address to map the buffer + * @sgt: The sg_table object describing the buffer + * @prot: IOMMU protection bits + * + * Creates a mapping at @iova for the buffer described by a scatterlist + * stored in the given sg_table object in the provided IOMMU domain. + */ +static inline size_t iommu_map_sgtable(struct iommu_domain *domain, + unsigned long iova, struct sg_table *sgt, int prot) +{ + return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot); +} + extern void iommu_get_resv_regions(struct device *dev, struct list_head *list); extern void iommu_put_resv_regions(struct device *dev, struct list_head *list); extern void generic_iommu_put_resv_regions(struct device *dev, -- cgit v1.2.3 From dae2f8ed7992e88c8d62c54e8295ffc8475b4a80 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 30 Apr 2020 07:41:37 -0700 Subject: fs: Lift XFS_IDONTCACHE to the VFS layer DAX effective mode (S_DAX) changes requires inode eviction. XFS has an advisory flag (XFS_IDONTCACHE) to prevent caching of the inode if no other additional references are taken. We lift this flag to the VFS layer and change the behavior slightly by allowing the flag to remain even if multiple references are taken. This will expedite the eviction of inodes to change S_DAX. Cc: Al Viro Reviewed-by: Dave Chinner Reviewed-by: Jan Kara Signed-off-by: Ira Weiny Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/fs.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index a87cc5845a02..44bd45af760f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2156,6 +2156,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_CREATING New object's inode in the middle of setting up. * + * I_DONTCACHE Evict inode as soon as it is not used anymore. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2178,6 +2180,7 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) #define I_CREATING (1 << 15) +#define I_DONTCACHE (1 << 16) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) @@ -3049,7 +3052,8 @@ extern int inode_needs_sync(struct inode *inode); extern int generic_delete_inode(struct inode *inode); static inline int generic_drop_inode(struct inode *inode) { - return !inode->i_nlink || inode_unhashed(inode); + return !inode->i_nlink || inode_unhashed(inode) || + (inode->i_state & I_DONTCACHE); } extern struct inode *ilookup5_nowait(struct super_block *sb, -- cgit v1.2.3 From 2c567af418e3f9380c2051aada58b4e5a4b5c2ad Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 30 Apr 2020 07:41:37 -0700 Subject: fs: Introduce DCACHE_DONTCACHE DCACHE_DONTCACHE indicates a dentry should not be cached on final dput(). Also add a helper function to mark DCACHE_DONTCACHE on all dentries pointing to a specific inode when that inode is being set I_DONTCACHE. This facilitates dropping dentry references to inodes sooner which require eviction to swap S_DAX mode. Cc: Al Viro Signed-off-by: Ira Weiny Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/dcache.h | 2 ++ include/linux/fs.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c1488cc84fd9..a81f0c3cf352 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -177,6 +177,8 @@ struct dentry_operations { #define DCACHE_REFERENCED 0x00000040 /* Recently used, don't discard. */ +#define DCACHE_DONTCACHE 0x00000080 /* Purge from memory on final dput() */ + #define DCACHE_CANT_MOUNT 0x00000100 #define DCACHE_GENOCIDE 0x00000200 #define DCACHE_SHRINK_LIST 0x00000400 diff --git a/include/linux/fs.h b/include/linux/fs.h index 44bd45af760f..7c3e8c0306e0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3055,6 +3055,7 @@ static inline int generic_drop_inode(struct inode *inode) return !inode->i_nlink || inode_unhashed(inode) || (inode->i_state & I_DONTCACHE); } +extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), -- cgit v1.2.3 From 9254f8ed15b6dcc9b04b9ad32863a7518cc5a5b1 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 4 May 2020 08:30:10 +0300 Subject: net/mlx5: Add support in forward to namespace Currently, fs_core supports rule of forward the traffic to continue matching in the next priority, now we add support to forward the traffic matching in the next namespace. Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Reviewed-by: Mark Zhang Signed-off-by: Leon Romanovsky --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index e2d13e074067..6c5aa0a21425 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -42,6 +42,7 @@ enum { MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO = 1 << 16, MLX5_FLOW_CONTEXT_ACTION_ENCRYPT = 1 << 17, MLX5_FLOW_CONTEXT_ACTION_DECRYPT = 1 << 18, + MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS = 1 << 19, }; enum { -- cgit v1.2.3 From 9d9a6ebfea329cadeda87544dceae01e9c27aaef Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 23 Apr 2020 22:48:34 -0700 Subject: rcuwait: Let rcuwait_wake_up() return whether or not a task was awoken Propagating the return value of wake_up_process() back to the caller can come in handy for future users, such as for statistics or accounting purposes. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Davidlohr Bueso Message-Id: <20200424054837.5138-3-dave@stgolabs.net> Signed-off-by: Paolo Bonzini --- include/linux/rcuwait.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 2ffe1ee6d482..6ebb23258a27 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -25,7 +25,7 @@ static inline void rcuwait_init(struct rcuwait *w) w->task = NULL; } -extern void rcuwait_wake_up(struct rcuwait *w); +extern int rcuwait_wake_up(struct rcuwait *w); /* * The caller is responsible for locking around rcuwait_wait_event(), -- cgit v1.2.3 From 5c21f7b322cb9fcb97f2e22f5976a0ae8dd71354 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 23 Apr 2020 22:48:35 -0700 Subject: rcuwait: Introduce prepare_to and finish_rcuwait This allows further flexibility for some callers to implement ad-hoc versions of the generic rcuwait_wait_event(). For example, kvm will need this to maintain tracing semantics. The naming is of course similar to what waitqueue apis offer. Also go ahead and make use of rcu_assign_pointer() for both task writes as it will make the __rcu sparse people happy - this will be the special nil case, thus no added serialization. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Davidlohr Bueso Message-Id: <20200424054837.5138-4-dave@stgolabs.net> Signed-off-by: Paolo Bonzini --- include/linux/rcuwait.h | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 6ebb23258a27..45bc6604e9b1 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -29,12 +29,25 @@ extern int rcuwait_wake_up(struct rcuwait *w); /* * The caller is responsible for locking around rcuwait_wait_event(), - * such that writes to @task are properly serialized. + * and [prepare_to/finish]_rcuwait() such that writes to @task are + * properly serialized. */ + +static inline void prepare_to_rcuwait(struct rcuwait *w) +{ + rcu_assign_pointer(w->task, current); +} + +static inline void finish_rcuwait(struct rcuwait *w) +{ + rcu_assign_pointer(w->task, NULL); + __set_current_state(TASK_RUNNING); +} + #define rcuwait_wait_event(w, condition, state) \ ({ \ int __ret = 0; \ - rcu_assign_pointer((w)->task, current); \ + prepare_to_rcuwait(w); \ for (;;) { \ /* \ * Implicit barrier (A) pairs with (B) in \ @@ -51,9 +64,7 @@ extern int rcuwait_wake_up(struct rcuwait *w); \ schedule(); \ } \ - \ - WRITE_ONCE((w)->task, NULL); \ - __set_current_state(TASK_RUNNING); \ + finish_rcuwait(w); \ __ret; \ }) -- cgit v1.2.3 From 191a43be61d6791fd4a9098a35c1a09e73f55228 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 23 Apr 2020 22:48:36 -0700 Subject: rcuwait: Introduce rcuwait_active() This call is lockless and thus should not be trusted blindly. For example, the return value of rcuwait_wakeup() should be used to track whether a process was woken up. Signed-off-by: Davidlohr Bueso Message-Id: <20200424054837.5138-5-dave@stgolabs.net> Acked-by: Peter Zijlstra (Intel) Signed-off-by: Paolo Bonzini --- include/linux/rcuwait.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 45bc6604e9b1..c1414ce44abc 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -25,6 +25,15 @@ static inline void rcuwait_init(struct rcuwait *w) w->task = NULL; } +/* + * Note: this provides no serialization and, just as with waitqueues, + * requires care to estimate as to whether or not the wait is active. + */ +static inline int rcuwait_active(struct rcuwait *w) +{ + return !!rcu_dereference(w->task); +} + extern int rcuwait_wake_up(struct rcuwait *w); /* -- cgit v1.2.3 From da4ad88cab5867ee240dfd0585e9d115a8cc47db Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 23 Apr 2020 22:48:37 -0700 Subject: kvm: Replace vcpu->swait with rcuwait The use of any sort of waitqueue (simple or regular) for wait/waking vcpus has always been an overkill and semantically wrong. Because this is per-vcpu (which is blocked) there is only ever a single waiting vcpu, thus no need for any sort of queue. As such, make use of the rcuwait primitive, with the following considerations: - rcuwait already provides the proper barriers that serialize concurrent waiter and waker. - Task wakeup is done in rcu read critical region, with a stable task pointer. - Because there is no concurrency among waiters, we need not worry about rcuwait_wait_event() calls corrupting the wait->task. As a consequence, this saves the locking done in swait when modifying the queue. This also applies to per-vcore wait for powerpc kvm-hv. The x86 tscdeadline_latency test mentioned in 8577370fb0cb ("KVM: Use simple waitqueue for vcpu->wq") shows that, on avg, latency is reduced by around 15-20% with this change. Cc: Paul Mackerras Cc: kvmarm@lists.cs.columbia.edu Cc: linux-mips@vger.kernel.org Reviewed-by: Marc Zyngier Signed-off-by: Davidlohr Bueso Message-Id: <20200424054837.5138-6-dave@stgolabs.net> [Avoid extra logic changes. - Paolo] Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index abfa71cb5d2d..161684696610 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include @@ -277,7 +277,7 @@ struct kvm_vcpu { struct mutex mutex; struct kvm_run *run; - struct swait_queue_head wq; + struct rcuwait wait; struct pid __rcu *pid; int sigset_active; sigset_t sigset; @@ -960,12 +960,12 @@ static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) } #endif -static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) +static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) { #ifdef __KVM_HAVE_ARCH_WQP - return vcpu->arch.wqp; + return vcpu->arch.waitp; #else - return &vcpu->wq; + return &vcpu->wait; #endif } -- cgit v1.2.3 From d06cfe3f123c50449a0c3ece21bc16668289c50f Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Apr 2020 15:58:21 -0500 Subject: bus: vexpress-config: Merge vexpress-syscfg into vexpress-config The only thing that vexpress-syscfg does is provide a regmap to vexpress-config bus child devices. There's little reason to have 2 components for this. The current structure with initcall ordering requirements makes turning these components into modules more difficult. So let's start to simplify things and merge vexpress-syscfg into vexpress-config. There's no functional change in this commit and it's still separate components until subsequent commits. Cc: Lorenzo Pieralisi Cc: Linus Walleij Cc: Arnd Bergmann Reviewed-by: Sudeep Holla Acked-by: Greg Kroah-Hartman Acked-by: Liviu Dudau Signed-off-by: Rob Herring --- include/linux/vexpress.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h index 2ec7992b054c..65096c792d57 100644 --- a/include/linux/vexpress.h +++ b/include/linux/vexpress.h @@ -18,23 +18,6 @@ /* Config infrastructure */ void vexpress_config_set_master(u32 site); -u32 vexpress_config_get_master(void); - -void vexpress_config_lock(void *arg); -void vexpress_config_unlock(void *arg); - -int vexpress_config_get_topo(struct device_node *node, u32 *site, - u32 *position, u32 *dcc); - -/* Config bridge API */ - -struct vexpress_config_bridge_ops { - struct regmap * (*regmap_init)(struct device *dev, void *context); - void (*regmap_exit)(struct regmap *regmap, void *context); -}; - -struct device *vexpress_config_bridge_register(struct device *parent, - struct vexpress_config_bridge_ops *ops, void *context); /* Config regmap API */ -- cgit v1.2.3 From 310f80d61717425fbf799ef0ff0926e64cd57d9c Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Apr 2020 15:58:23 -0500 Subject: vexpress: Move setting master site to vexpress-config bus There's only a single caller of vexpress_config_set_master() from vexpress-sysreg.c. Let's just make the registers needed available to vexpress-config and move all the code there. The registers needed aren't used anywhere else either. With this, we can get rid of the private API between these 2 drivers. Cc: Lorenzo Pieralisi Cc: Linus Walleij Cc: Greg Kroah-Hartman Acked-by: Liviu Dudau Acked-by: Sudeep Holla Acked-by: Lee Jones Signed-off-by: Rob Herring --- include/linux/vexpress.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h index 65096c792d57..2f9dd072f11f 100644 --- a/include/linux/vexpress.h +++ b/include/linux/vexpress.h @@ -10,15 +10,6 @@ #include #include -#define VEXPRESS_SITE_MB 0 -#define VEXPRESS_SITE_DB1 1 -#define VEXPRESS_SITE_DB2 2 -#define VEXPRESS_SITE_MASTER 0xf - -/* Config infrastructure */ - -void vexpress_config_set_master(u32 site); - /* Config regmap API */ struct regmap *devm_regmap_init_vexpress_config(struct device *dev); -- cgit v1.2.3 From 21aef70eade22a656297c28d5da93301915d2ac2 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 13 May 2020 11:02:16 -0700 Subject: bpf: Change btf_iter func proto prefix to "bpf_iter_" This is to be consistent with tracing and lsm programs which have prefix "bpf_trace_" and "bpf_lsm_" respectively. Suggested-by: Alexei Starovoitov Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200513180216.2949387-1-yhs@fb.com --- include/linux/bpf.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cf4b6e44f2bc..ab94dfd8826f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1131,10 +1131,10 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); -#define BPF_ITER_FUNC_PREFIX "__bpf_iter__" +#define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ - extern int __bpf_iter__ ## target(args); \ - int __init __bpf_iter__ ## target(args) { return 0; } + extern int bpf_iter_ ## target(args); \ + int __init bpf_iter_ ## target(args) { return 0; } typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); -- cgit v1.2.3 From 15172a46fa2796c1a1358a36babd31274716ed41 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 13 May 2020 11:02:19 -0700 Subject: bpf: net: Refactor bpf_iter target registration Currently bpf_iter_reg_target takes parameters from target and allocates memory to save them. This is really not necessary, esp. in the future we may grow information passed from targets to bpf_iter manager. The patch refactors the code so target reg_info becomes static and bpf_iter manager can just take a reference to it. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200513180219.2949605-1-yhs@fb.com --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ab94dfd8826f..6fa773e2d1bf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1153,7 +1153,7 @@ struct bpf_iter_meta { u64 seq_num; }; -int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); +int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); -- cgit v1.2.3 From ab2ee4fcb9d61fd57db70db694adbcf54662bd80 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 13 May 2020 11:02:20 -0700 Subject: bpf: Change func bpf_iter_unreg_target() signature Change func bpf_iter_unreg_target() parameter from target name to target reg_info, similar to bpf_iter_reg_target(). Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200513180220.2949737-1-yhs@fb.com --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6fa773e2d1bf..534174eca86b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1154,7 +1154,7 @@ struct bpf_iter_meta { }; int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); -void bpf_iter_unreg_target(const char *target); +void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); -- cgit v1.2.3 From 3c32cc1bceba8a1755dc35cd97516f6c67856844 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 13 May 2020 11:02:21 -0700 Subject: bpf: Enable bpf_iter targets registering ctx argument types Commit b121b341e598 ("bpf: Add PTR_TO_BTF_ID_OR_NULL support") adds a field btf_id_or_null_non0_off to bpf_prog->aux structure to indicate that the first ctx argument is PTR_TO_BTF_ID reg_type and all others are PTR_TO_BTF_ID_OR_NULL. This approach does not really scale if we have other different reg types in the future, e.g., a pointer to a buffer. This patch enables bpf_iter targets registering ctx argument reg types which may be different from the default one. For example, for pointers to structures, the default reg_type is PTR_TO_BTF_ID for tracing program. The target can register a particular pointer type as PTR_TO_BTF_ID_OR_NULL which can be used by the verifier to enforce accesses. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200513180221.2949882-1-yhs@fb.com --- include/linux/bpf.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 534174eca86b..c45d198ac38c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -643,6 +643,12 @@ struct bpf_jit_poke_descriptor { u16 reason; }; +/* reg_type info for ctx arguments */ +struct bpf_ctx_arg_aux { + u32 offset; + enum bpf_reg_type reg_type; +}; + struct bpf_prog_aux { atomic64_t refcnt; u32 used_map_cnt; @@ -654,12 +660,13 @@ struct bpf_prog_aux { u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ + u32 ctx_arg_info_size; + const struct bpf_ctx_arg_aux *ctx_arg_info; struct bpf_prog *linked_prog; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool func_proto_unreliable; - bool btf_id_or_null_non0_off; enum bpf_tramp_prog_type trampoline_prog_type; struct bpf_trampoline *trampoline; struct hlist_node tramp_hlist; @@ -1139,12 +1146,15 @@ int bpf_obj_get_user(const char __user *pathname, int flags); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); +#define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; const struct seq_operations *seq_ops; bpf_iter_init_seq_priv_t init_seq_private; bpf_iter_fini_seq_priv_t fini_seq_private; u32 seq_priv_size; + u32 ctx_arg_info_size; + struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; }; struct bpf_iter_meta { -- cgit v1.2.3 From 11ecf8c55b91806e4dc6a1b9fe7cbf68cdc9b006 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Wed, 13 May 2020 18:35:23 +0200 Subject: net: phy: broadcom: add cable test support Most modern broadcom PHYs support ECD (enhanced cable diagnostics). Add support for it in the bcm-phy-lib so they can easily be used in the PHY driver. There are two access methods for ECD: legacy by expansion registers and via the new RDB registers which are exclusive. Provide functions in two variants where the PHY driver can choose from. To keep things simple for now, we just switch the register access to expansion registers in the RDB variant for now. On the flipside, we have to keep a bus lock to prevent any other non-legacy access on the PHY. The results of the intra-pair tests are inconclusive (at least for the BCM54140). Most of the times half the length is reported but sometimes the length is correct. Signed-off-by: Michael Walle Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 58d0150acc3e..d41624db6de2 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -119,6 +119,11 @@ #define MII_BCM54XX_RDB_ADDR 0x1e #define MII_BCM54XX_RDB_DATA 0x1f +/* legacy access control via rdb/expansion register */ +#define BCM54XX_RDB_REG0087 0x0087 +#define BCM54XX_EXP_REG7E (MII_BCM54XX_EXP_SEL_ER + 0x7E) +#define BCM54XX_ACCESS_MODE_LEGACY_EN BIT(15) + /* * AUXILIARY CONTROL SHADOW ACCESS REGISTERS. (PHY REG 0x18) */ @@ -294,4 +299,51 @@ #define MII_BRCM_CORE_EXPB0 0xB0 #define MII_BRCM_CORE_EXPB1 0xB1 +/* Enhanced Cable Diagnostics */ +#define BCM54XX_RDB_ECD_CTRL 0x2a0 +#define BCM54XX_EXP_ECD_CTRL (MII_BCM54XX_EXP_SEL_ER + 0xc0) + +#define BCM54XX_ECD_CTRL_CABLE_TYPE_CAT3 1 /* CAT3 or worse */ +#define BCM54XX_ECD_CTRL_CABLE_TYPE_CAT5 0 /* CAT5 or better */ +#define BCM54XX_ECD_CTRL_CABLE_TYPE_MASK BIT(0) /* cable type */ +#define BCM54XX_ECD_CTRL_INVALID BIT(3) /* invalid result */ +#define BCM54XX_ECD_CTRL_UNIT_CM 0 /* centimeters */ +#define BCM54XX_ECD_CTRL_UNIT_M 1 /* meters */ +#define BCM54XX_ECD_CTRL_UNIT_MASK BIT(10) /* cable length unit */ +#define BCM54XX_ECD_CTRL_IN_PROGRESS BIT(11) /* test in progress */ +#define BCM54XX_ECD_CTRL_BREAK_LINK BIT(12) /* unconnect link + * during test + */ +#define BCM54XX_ECD_CTRL_CROSS_SHORT_DIS BIT(13) /* disable inter-pair + * short check + */ +#define BCM54XX_ECD_CTRL_RUN BIT(15) /* run immediate */ + +#define BCM54XX_RDB_ECD_FAULT_TYPE 0x2a1 +#define BCM54XX_EXP_ECD_FAULT_TYPE (MII_BCM54XX_EXP_SEL_ER + 0xc1) +#define BCM54XX_ECD_FAULT_TYPE_INVALID 0x0 +#define BCM54XX_ECD_FAULT_TYPE_OK 0x1 +#define BCM54XX_ECD_FAULT_TYPE_OPEN 0x2 +#define BCM54XX_ECD_FAULT_TYPE_SAME_SHORT 0x3 /* short same pair */ +#define BCM54XX_ECD_FAULT_TYPE_CROSS_SHORT 0x4 /* short different pairs */ +#define BCM54XX_ECD_FAULT_TYPE_BUSY 0x9 +#define BCM54XX_ECD_FAULT_TYPE_PAIR_D_MASK GENMASK(3, 0) +#define BCM54XX_ECD_FAULT_TYPE_PAIR_C_MASK GENMASK(7, 4) +#define BCM54XX_ECD_FAULT_TYPE_PAIR_B_MASK GENMASK(11, 8) +#define BCM54XX_ECD_FAULT_TYPE_PAIR_A_MASK GENMASK(15, 12) +#define BCM54XX_ECD_PAIR_A_LENGTH_RESULTS 0x2a2 +#define BCM54XX_ECD_PAIR_B_LENGTH_RESULTS 0x2a3 +#define BCM54XX_ECD_PAIR_C_LENGTH_RESULTS 0x2a4 +#define BCM54XX_ECD_PAIR_D_LENGTH_RESULTS 0x2a5 + +#define BCM54XX_RDB_ECD_PAIR_A_LENGTH_RESULTS 0x2a2 +#define BCM54XX_EXP_ECD_PAIR_A_LENGTH_RESULTS (MII_BCM54XX_EXP_SEL_ER + 0xc2) +#define BCM54XX_RDB_ECD_PAIR_B_LENGTH_RESULTS 0x2a3 +#define BCM54XX_EXP_ECD_PAIR_B_LENGTH_RESULTS (MII_BCM54XX_EXP_SEL_ER + 0xc3) +#define BCM54XX_RDB_ECD_PAIR_C_LENGTH_RESULTS 0x2a4 +#define BCM54XX_EXP_ECD_PAIR_C_LENGTH_RESULTS (MII_BCM54XX_EXP_SEL_ER + 0xc4) +#define BCM54XX_RDB_ECD_PAIR_D_LENGTH_RESULTS 0x2a5 +#define BCM54XX_EXP_ECD_PAIR_D_LENGTH_RESULTS (MII_BCM54XX_EXP_SEL_ER + 0xc5) +#define BCM54XX_ECD_LENGTH_RESULTS_INVALID 0xffff + #endif /* _LINUX_BRCMPHY_H */ -- cgit v1.2.3 From f45ce9336ff0640e491c642a84ea02f21daac3a4 Mon Sep 17 00:00:00 2001 From: Gwan-gyeong Mun Date: Thu, 14 May 2020 09:07:19 +0300 Subject: video/hdmi: Add Unpack only function for DRM infoframe It adds an unpack only function for DRM infoframe for dynamic range and mastering infoframe readout. It unpacks the information data block contained in the binary buffer into a structured frame of the HDMI Dynamic Range and Mastering (DRM) information frame. In contrast to hdmi_drm_infoframe_unpack() function, it does not verify a checksum. It can be used for unpacking a DP HDR Metadata Infoframe SDP case. DP HDR Metadata Infoframe SDP uses the same Dynamic Range and Mastering (DRM) information (CTA-861-G spec.) such as HDMI DRM infoframe. But DP SDP header and payload structure are different from HDMI DRM Infoframe. Therefore unpacking DRM infoframe for DP requires skipping of a verifying checksum. v9: Add clear comments to hdmi_drm_infoframe_unpack_only() and hdmi_drm_infoframe_unpack() (Laurent Pinchart) Signed-off-by: Gwan-gyeong Mun Reviewed-by: Uma Shankar Cc: Laurent Pinchart Cc: Ville Syrjala Acked-by: Daniel Vetter Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20200514060732.3378396-2-gwan-gyeong.mun@intel.com --- include/linux/hdmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 9613d796cfb1..50c31f1a0a2d 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -219,6 +219,8 @@ ssize_t hdmi_drm_infoframe_pack(struct hdmi_drm_infoframe *frame, void *buffer, ssize_t hdmi_drm_infoframe_pack_only(const struct hdmi_drm_infoframe *frame, void *buffer, size_t size); int hdmi_drm_infoframe_check(struct hdmi_drm_infoframe *frame); +int hdmi_drm_infoframe_unpack_only(struct hdmi_drm_infoframe *frame, + const void *buffer, size_t size); enum hdmi_spd_sdi { HDMI_SPD_SDI_UNKNOWN, -- cgit v1.2.3 From 2909438d4d62681f392c57df4cd6b7183d19dde0 Mon Sep 17 00:00:00 2001 From: Wang Wenhu Date: Wed, 13 May 2020 07:18:54 -0700 Subject: cpufreq: fix minor typo in struct cpufreq_driver doc comment Delete the duplicate "to", possibly double-typed. Signed-off-by: Wang Wenhu Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index f7240251a949..67d5950bd878 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -330,7 +330,7 @@ struct cpufreq_driver { * * get_intermediate should return a stable intermediate frequency * platform wants to switch to and target_intermediate() should set CPU - * to to that frequency, before jumping to the frequency corresponding + * to that frequency, before jumping to the frequency corresponding * to 'index'. Core will take care of sending notifications and driver * doesn't have to handle them in target_intermediate() or * target_index(). -- cgit v1.2.3 From 71ac860af824ce9ebbbe8de20044e777c0fc33b9 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 14 May 2020 16:45:09 +0800 Subject: block: move blk_io_schedule() out of header file blk_io_schedule() isn't called from performance sensitive code path, and it is easier to maintain by exporting it as symbol. Also blk_io_schedule() is only called by CONFIG_BLOCK code, so it is safe to do this way. Meantime fixes build failure when CONFIG_BLOCK is off. Cc: Christoph Hellwig Fixes: e6249cdd46e4 ("block: add blk_io_schedule() for avoiding task hung in sync dio") Reported-by: Satya Tangirala Tested-by: Satya Tangirala Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5360696d85ff..f9e4b21b051b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -27,7 +27,6 @@ #include #include #include -#include struct module; struct scsi_ioctl_command; @@ -1221,6 +1220,8 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) !list_empty(&plug->cb_list)); } +extern void blk_io_schedule(void); + extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); @@ -1851,15 +1852,4 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -static inline void blk_io_schedule(void) -{ - /* Prevent hang_check timer from firing at us during very long I/O */ - unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; - - if (timeout) - io_schedule_timeout(timeout); - else - io_schedule(); -} - #endif -- cgit v1.2.3 From a3c751a50fe6bbe50eb7622a14b18b361804ee0c Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 14 May 2020 16:44:23 +0200 Subject: vfs: allow unprivileged whiteout creation Whiteouts, unlike real device node should not require privileges to create. The general concern with device nodes is that opening them can have side effects. The kernel already avoids zero major (see Documentation/admin-guide/devices.txt). To be on the safe side the patch explicitly forbids registering a char device with 0/0 number (see cdev_add()). This guarantees that a non-O_PATH open on a whiteout will fail with ENODEV; i.e. it won't have any side effect. Signed-off-by: Miklos Szeredi --- include/linux/device_cgroup.h | 3 +++ include/linux/fs.h | 6 +++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index fa35b52e0002..57e63bd63370 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -51,6 +51,9 @@ static inline int devcgroup_inode_mknod(int mode, dev_t dev) if (!S_ISBLK(mode) && !S_ISCHR(mode)) return 0; + if (S_ISCHR(mode) && dev == WHITEOUT_DEV) + return 0; + if (S_ISBLK(mode)) type = DEVCG_DEV_BLOCK; else diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..15665ef1ef90 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1721,7 +1721,11 @@ extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct ino extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); -extern int vfs_whiteout(struct inode *, struct dentry *); + +static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry) +{ + return vfs_mknod(dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); +} extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag); -- cgit v1.2.3 From 9f6c61f96f2d97cbb5f7fa85607bc398f843ff0f Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 14 May 2020 16:44:24 +0200 Subject: proc/mounts: add cursor If mounts are deleted after a read(2) call on /proc/self/mounts (or its kin), the subsequent read(2) could miss a mount that comes after the deleted one in the list. This is because the file position is interpreted as the number mount entries from the start of the list. E.g. first read gets entries #0 to #9; the seq file index will be 10. Then entry #5 is deleted, resulting in #10 becoming #9 and #11 becoming #10, etc... The next read will continue from entry #10, and #9 is missed. Solve this by adding a cursor entry for each open instance. Taking the global namespace_sem for write seems excessive, since we are only dealing with a per-namespace list. Instead add a per-namespace spinlock and use that together with namespace_sem taken for read to protect against concurrent modification of the mount list. This may reduce parallelism of is_local_mountpoint(), but it's hardly a big contention point. We could also use RCU freeing of cursors to make traversal not need additional locks, if that turns out to be neceesary. Only move the cursor once for each read (cursor is not added on open) to minimize cacheline invalidation. When EOF is reached, the cursor is taken off the list, in order to prevent an excessive number of cursors due to inactive open file descriptors. Reported-by: Karel Zak Signed-off-by: Miklos Szeredi --- include/linux/mount.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index bf8cc4108b8f..7edac8c7a9c1 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -50,7 +50,8 @@ struct fs_context; #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ - MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED) + MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | \ + MNT_CURSOR) #define MNT_INTERNAL 0x4000 @@ -64,6 +65,7 @@ struct fs_context; #define MNT_SYNC_UMOUNT 0x2000000 #define MNT_MARKED 0x4000000 #define MNT_UMOUNT 0x8000000 +#define MNT_CURSOR 0x10000000 struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ -- cgit v1.2.3 From fa2fcf4f1df1559a0a4ee0f46915b496cc2ebf60 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 14 May 2020 16:44:24 +0200 Subject: statx: add mount ID Systemd is hacking around to get it and it's trivial to add to statx, so... Cc: linux-api@vger.kernel.org Cc: linux-man@vger.kernel.org Signed-off-by: Miklos Szeredi Reviewed-by: Christoph Hellwig --- include/linux/stat.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stat.h b/include/linux/stat.h index 528c4baad091..56614af83d4a 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -47,6 +47,7 @@ struct kstat { struct timespec64 ctime; struct timespec64 btime; /* File creation time */ u64 blocks; + u64 mnt_id; }; #endif -- cgit v1.2.3 From c8ffd8bcdd28296a198f237cc595148a8d4adfbe Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 14 May 2020 16:44:25 +0200 Subject: vfs: add faccessat2 syscall POSIX defines faccessat() as having a fourth "flags" argument, while the linux syscall doesn't have it. Glibc tries to emulate AT_EACCESS and AT_SYMLINK_NOFOLLOW, but AT_EACCESS emulation is broken. Add a new faccessat(2) syscall with the added flags argument and implement both flags. The value of AT_EACCESS is defined in glibc headers to be the same as AT_REMOVEDIR. Use this value for the kernel interface as well, together with the explanatory comment. Also add AT_EMPTY_PATH support, which is not documented by POSIX, but can be useful and is trivial to implement. Signed-off-by: Miklos Szeredi --- include/linux/syscalls.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1815065d52f3..7c354c2955f5 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -428,6 +428,8 @@ asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length); #endif asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode); +asmlinkage long sys_faccessat2(int dfd, const char __user *filename, int mode, + int flags); asmlinkage long sys_chdir(const char __user *filename); asmlinkage long sys_fchdir(unsigned int fd); asmlinkage long sys_chroot(const char __user *filename); @@ -1333,11 +1335,11 @@ static inline int ksys_chmod(const char __user *filename, umode_t mode) return do_fchmodat(AT_FDCWD, filename, mode); } -extern long do_faccessat(int dfd, const char __user *filename, int mode); +long do_faccessat(int dfd, const char __user *filename, int mode, int flags); static inline long ksys_access(const char __user *filename, int mode) { - return do_faccessat(AT_FDCWD, filename, mode); + return do_faccessat(AT_FDCWD, filename, mode, 0); } extern int do_fchownat(int dfd, const char __user *filename, uid_t user, -- cgit v1.2.3 From 1b2628397058ebce7277480960b29c788138de90 Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Thu, 14 May 2020 00:37:17 +0000 Subject: block: Keyslot Manager for Inline Encryption Inline Encryption hardware allows software to specify an encryption context (an encryption key, crypto algorithm, data unit num, data unit size) along with a data transfer request to a storage device, and the inline encryption hardware will use that context to en/decrypt the data. The inline encryption hardware is part of the storage device, and it conceptually sits on the data path between system memory and the storage device. Inline Encryption hardware implementations often function around the concept of "keyslots". These implementations often have a limited number of "keyslots", each of which can hold a key (we say that a key can be "programmed" into a keyslot). Requests made to the storage device may have a keyslot and a data unit number associated with them, and the inline encryption hardware will en/decrypt the data in the requests using the key programmed into that associated keyslot and the data unit number specified with the request. As keyslots are limited, and programming keys may be expensive in many implementations, and multiple requests may use exactly the same encryption contexts, we introduce a Keyslot Manager to efficiently manage keyslots. We also introduce a blk_crypto_key, which will represent the key that's programmed into keyslots managed by keyslot managers. The keyslot manager also functions as the interface that upper layers will use to program keys into inline encryption hardware. For more information on the Keyslot Manager, refer to documentation found in block/keyslot-manager.c and linux/keyslot-manager.h. Co-developed-by: Eric Biggers Signed-off-by: Eric Biggers Signed-off-by: Satya Tangirala Reviewed-by: Eric Biggers Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-crypto.h | 52 ++++++++++++++++++++ include/linux/blkdev.h | 6 +++ include/linux/keyslot-manager.h | 106 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 164 insertions(+) create mode 100644 include/linux/blk-crypto.h create mode 100644 include/linux/keyslot-manager.h (limited to 'include/linux') diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h new file mode 100644 index 000000000000..4e77938c3d0e --- /dev/null +++ b/include/linux/blk-crypto.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2019 Google LLC + */ + +#ifndef __LINUX_BLK_CRYPTO_H +#define __LINUX_BLK_CRYPTO_H + +enum blk_crypto_mode_num { + BLK_ENCRYPTION_MODE_INVALID, + BLK_ENCRYPTION_MODE_AES_256_XTS, + BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV, + BLK_ENCRYPTION_MODE_ADIANTUM, + BLK_ENCRYPTION_MODE_MAX, +}; + +#define BLK_CRYPTO_MAX_KEY_SIZE 64 +/** + * struct blk_crypto_config - an inline encryption key's crypto configuration + * @crypto_mode: encryption algorithm this key is for + * @data_unit_size: the data unit size for all encryption/decryptions with this + * key. This is the size in bytes of each individual plaintext and + * ciphertext. This is always a power of 2. It might be e.g. the + * filesystem block size or the disk sector size. + * @dun_bytes: the maximum number of bytes of DUN used when using this key + */ +struct blk_crypto_config { + enum blk_crypto_mode_num crypto_mode; + unsigned int data_unit_size; + unsigned int dun_bytes; +}; + +/** + * struct blk_crypto_key - an inline encryption key + * @crypto_cfg: the crypto configuration (like crypto_mode, key size) for this + * key + * @data_unit_size_bits: log2 of data_unit_size + * @size: size of this key in bytes (determined by @crypto_cfg.crypto_mode) + * @raw: the raw bytes of this key. Only the first @size bytes are used. + * + * A blk_crypto_key is immutable once created, and many bios can reference it at + * the same time. It must not be freed until all bios using it have completed + * and it has been evicted from all devices on which it may have been used. + */ +struct blk_crypto_key { + struct blk_crypto_config crypto_cfg; + unsigned int data_unit_size_bits; + unsigned int size; + u8 raw[BLK_CRYPTO_MAX_KEY_SIZE]; +}; + +#endif /* __LINUX_BLK_CRYPTO_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f9e4b21b051b..354e44eebef9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -43,6 +43,7 @@ struct pr_ops; struct rq_qos; struct blk_queue_stats; struct blk_stat_callback; +struct blk_keyslot_manager; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ @@ -468,6 +469,11 @@ struct request_queue { unsigned int dma_pad_mask; unsigned int dma_alignment; +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + /* Inline crypto capabilities */ + struct blk_keyslot_manager *ksm; +#endif + unsigned int rq_timeout; int poll_nsec; diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h new file mode 100644 index 000000000000..18f3f5346843 --- /dev/null +++ b/include/linux/keyslot-manager.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2019 Google LLC + */ + +#ifndef __LINUX_KEYSLOT_MANAGER_H +#define __LINUX_KEYSLOT_MANAGER_H + +#include +#include + +struct blk_keyslot_manager; + +/** + * struct blk_ksm_ll_ops - functions to manage keyslots in hardware + * @keyslot_program: Program the specified key into the specified slot in the + * inline encryption hardware. + * @keyslot_evict: Evict key from the specified keyslot in the hardware. + * The key is provided so that e.g. dm layers can evict + * keys from the devices that they map over. + * Returns 0 on success, -errno otherwise. + * + * This structure should be provided by storage device drivers when they set up + * a keyslot manager - this structure holds the function ptrs that the keyslot + * manager will use to manipulate keyslots in the hardware. + */ +struct blk_ksm_ll_ops { + int (*keyslot_program)(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + unsigned int slot); + int (*keyslot_evict)(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + unsigned int slot); +}; + +struct blk_keyslot_manager { + /* + * The struct blk_ksm_ll_ops that this keyslot manager will use + * to perform operations like programming and evicting keys on the + * device + */ + struct blk_ksm_ll_ops ksm_ll_ops; + + /* + * The maximum number of bytes supported for specifying the data unit + * number. + */ + unsigned int max_dun_bytes_supported; + + /* + * Array of size BLK_ENCRYPTION_MODE_MAX of bitmasks that represents + * whether a crypto mode and data unit size are supported. The i'th + * bit of crypto_mode_supported[crypto_mode] is set iff a data unit + * size of (1 << i) is supported. We only support data unit sizes + * that are powers of 2. + */ + unsigned int crypto_modes_supported[BLK_ENCRYPTION_MODE_MAX]; + + /* Device for runtime power management (NULL if none) */ + struct device *dev; + + /* Here onwards are *private* fields for internal keyslot manager use */ + + unsigned int num_slots; + + /* Protects programming and evicting keys from the device */ + struct rw_semaphore lock; + + /* List of idle slots, with least recently used slot at front */ + wait_queue_head_t idle_slots_wait_queue; + struct list_head idle_slots; + spinlock_t idle_slots_lock; + + /* + * Hash table which maps struct *blk_crypto_key to keyslots, so that we + * can find a key's keyslot in O(1) time rather than O(num_slots). + * Protected by 'lock'. + */ + struct hlist_head *slot_hashtable; + unsigned int log_slot_ht_size; + + /* Per-keyslot data */ + struct blk_ksm_keyslot *slots; +}; + +int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots); + +blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + struct blk_ksm_keyslot **slot_ptr); + +unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot); + +void blk_ksm_put_slot(struct blk_ksm_keyslot *slot); + +bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm, + const struct blk_crypto_config *cfg); + +int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key); + +void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm); + +void blk_ksm_destroy(struct blk_keyslot_manager *ksm); + +#endif /* __LINUX_KEYSLOT_MANAGER_H */ -- cgit v1.2.3 From a892c8d52c02284076fbbacae6692aa5c5807d11 Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Thu, 14 May 2020 00:37:18 +0000 Subject: block: Inline encryption support for blk-mq We must have some way of letting a storage device driver know what encryption context it should use for en/decrypting a request. However, it's the upper layers (like the filesystem/fscrypt) that know about and manages encryption contexts. As such, when the upper layer submits a bio to the block layer, and this bio eventually reaches a device driver with support for inline encryption, the device driver will need to have been told the encryption context for that bio. We want to communicate the encryption context from the upper layer to the storage device along with the bio, when the bio is submitted to the block layer. To do this, we add a struct bio_crypt_ctx to struct bio, which can represent an encryption context (note that we can't use the bi_private field in struct bio to do this because that field does not function to pass information across layers in the storage stack). We also introduce various functions to manipulate the bio_crypt_ctx and make the bio/request merging logic aware of the bio_crypt_ctx. We also make changes to blk-mq to make it handle bios with encryption contexts. blk-mq can merge many bios into the same request. These bios need to have contiguous data unit numbers (the necessary changes to blk-merge are also made to ensure this) - as such, it suffices to keep the data unit number of just the first bio, since that's all a storage driver needs to infer the data unit number to use for each data block in each bio in a request. blk-mq keeps track of the encryption context to be used for all the bios in a request with the request's rq_crypt_ctx. When the first bio is added to an empty request, blk-mq will program the encryption context of that bio into the request_queue's keyslot manager, and store the returned keyslot in the request's rq_crypt_ctx. All the functions to operate on encryption contexts are in blk-crypto.c. Upper layers only need to call bio_crypt_set_ctx with the encryption key, algorithm and data_unit_num; they don't have to worry about getting a keyslot for each encryption context, as blk-mq/blk-crypto handles that. Blk-crypto also makes it possible for request-based layered devices like dm-rq to make use of inline encryption hardware by cloning the rq_crypt_ctx and programming a keyslot in the new request_queue when necessary. Note that any user of the block layer can submit bios with an encryption context, such as filesystems, device-mapper targets, etc. Signed-off-by: Satya Tangirala Reviewed-by: Eric Biggers Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-crypto.h | 71 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/blk_types.h | 6 ++++ include/linux/blkdev.h | 5 ++++ 3 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h index 4e77938c3d0e..76095b07dd90 100644 --- a/include/linux/blk-crypto.h +++ b/include/linux/blk-crypto.h @@ -6,6 +6,8 @@ #ifndef __LINUX_BLK_CRYPTO_H #define __LINUX_BLK_CRYPTO_H +#include + enum blk_crypto_mode_num { BLK_ENCRYPTION_MODE_INVALID, BLK_ENCRYPTION_MODE_AES_256_XTS, @@ -49,4 +51,73 @@ struct blk_crypto_key { u8 raw[BLK_CRYPTO_MAX_KEY_SIZE]; }; +#define BLK_CRYPTO_MAX_IV_SIZE 32 +#define BLK_CRYPTO_DUN_ARRAY_SIZE (BLK_CRYPTO_MAX_IV_SIZE / sizeof(u64)) + +/** + * struct bio_crypt_ctx - an inline encryption context + * @bc_key: the key, algorithm, and data unit size to use + * @bc_dun: the data unit number (starting IV) to use + * + * A bio_crypt_ctx specifies that the contents of the bio will be encrypted (for + * write requests) or decrypted (for read requests) inline by the storage device + * or controller. + */ +struct bio_crypt_ctx { + const struct blk_crypto_key *bc_key; + u64 bc_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]; +}; + +#include +#include + +struct request; +struct request_queue; + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + +static inline bool bio_has_crypt_ctx(struct bio *bio) +{ + return bio->bi_crypt_context; +} + +void bio_crypt_set_ctx(struct bio *bio, const struct blk_crypto_key *key, + const u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], + gfp_t gfp_mask); + +bool bio_crypt_dun_is_contiguous(const struct bio_crypt_ctx *bc, + unsigned int bytes, + const u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]); + +int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, + enum blk_crypto_mode_num crypto_mode, + unsigned int dun_bytes, + unsigned int data_unit_size); + +int blk_crypto_start_using_key(const struct blk_crypto_key *key, + struct request_queue *q); + +int blk_crypto_evict_key(struct request_queue *q, + const struct blk_crypto_key *key); + +bool blk_crypto_config_supported(struct request_queue *q, + const struct blk_crypto_config *cfg); + +#else /* CONFIG_BLK_INLINE_ENCRYPTION */ + +static inline bool bio_has_crypt_ctx(struct bio *bio) +{ + return false; +} + +#endif /* CONFIG_BLK_INLINE_ENCRYPTION */ + +void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask); +static inline void bio_crypt_clone(struct bio *dst, struct bio *src, + gfp_t gfp_mask) +{ + if (bio_has_crypt_ctx(src)) + __bio_crypt_clone(dst, src, gfp_mask); +} + #endif /* __LINUX_BLK_CRYPTO_H */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index b90dca1fa430..9322261fb316 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -18,6 +18,7 @@ struct block_device; struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); +struct bio_crypt_ctx; /* * Block error status values. See block/blk-core:blk_errors for the details. @@ -185,6 +186,11 @@ struct bio { u64 bi_iocost_cost; #endif #endif + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct bio_crypt_ctx *bi_crypt_context; +#endif + union { #if defined(CONFIG_BLK_DEV_INTEGRITY) struct bio_integrity_payload *bi_integrity; /* data integrity */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 354e44eebef9..52a9f456cadf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -222,6 +222,11 @@ struct request { unsigned short nr_integrity_segments; #endif +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct bio_crypt_ctx *crypt_ctx; + struct blk_ksm_keyslot *crypt_keyslot; +#endif + unsigned short write_hint; unsigned short ioprio; -- cgit v1.2.3 From d145dc23030bbf2de3a8ca5e0c29c2e568f69737 Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Thu, 14 May 2020 00:37:19 +0000 Subject: block: Make blk-integrity preclude hardware inline encryption Whenever a device supports blk-integrity, make the kernel pretend that the device doesn't support inline encryption (essentially by setting the keyslot manager in the request queue to NULL). There's no hardware currently that supports both integrity and inline encryption. However, it seems possible that there will be such hardware in the near future (like the NVMe key per I/O support that might support both inline encryption and PI). But properly integrating both features is not trivial, and without real hardware that implements both, it is difficult to tell if it will be done correctly by the majority of hardware that support both. So it seems best not to support both features together right now, and to decide what to do at probe time. Signed-off-by: Satya Tangirala Reviewed-by: Eric Biggers Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 52a9f456cadf..2b33166b9daf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1583,6 +1583,12 @@ struct blk_integrity *bdev_get_integrity(struct block_device *bdev) return blk_get_integrity(bdev->bd_disk); } +static inline bool +blk_integrity_queue_supports_integrity(struct request_queue *q) +{ + return q->integrity.profile; +} + static inline bool blk_integrity_rq(struct request *rq) { return rq->cmd_flags & REQ_INTEGRITY; @@ -1663,6 +1669,11 @@ static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { return NULL; } +static inline bool +blk_integrity_queue_supports_integrity(struct request_queue *q) +{ + return false; +} static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) { return 0; @@ -1714,6 +1725,25 @@ static inline struct bio_vec *rq_integrity_vec(struct request *rq) #endif /* CONFIG_BLK_DEV_INTEGRITY */ +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + +bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q); + +void blk_ksm_unregister(struct request_queue *q); + +#else /* CONFIG_BLK_INLINE_ENCRYPTION */ + +static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm, + struct request_queue *q) +{ + return true; +} + +static inline void blk_ksm_unregister(struct request_queue *q) { } + +#endif /* CONFIG_BLK_INLINE_ENCRYPTION */ + + struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); -- cgit v1.2.3 From 488f6682c832e9549d28b30075f00c76328eb1be Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Thu, 14 May 2020 00:37:20 +0000 Subject: block: blk-crypto-fallback for Inline Encryption Blk-crypto delegates crypto operations to inline encryption hardware when available. The separately configurable blk-crypto-fallback contains a software fallback to the kernel crypto API - when enabled, blk-crypto will use this fallback for en/decryption when inline encryption hardware is not available. This lets upper layers not have to worry about whether or not the underlying device has support for inline encryption before deciding to specify an encryption context for a bio. It also allows for testing without actual inline encryption hardware - in particular, it makes it possible to test the inline encryption code in ext4 and f2fs simply by running xfstests with the inlinecrypt mount option, which in turn allows for things like the regular upstream regression testing of ext4 to cover the inline encryption code paths. For more details, refer to Documentation/block/inline-encryption.rst. Signed-off-by: Satya Tangirala Reviewed-by: Eric Biggers Signed-off-by: Jens Axboe --- include/linux/blk-crypto.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h index 76095b07dd90..e82342907f2b 100644 --- a/include/linux/blk-crypto.h +++ b/include/linux/blk-crypto.h @@ -61,7 +61,7 @@ struct blk_crypto_key { * * A bio_crypt_ctx specifies that the contents of the bio will be encrypted (for * write requests) or decrypted (for read requests) inline by the storage device - * or controller. + * or controller, or by the crypto API fallback. */ struct bio_crypt_ctx { const struct blk_crypto_key *bc_key; -- cgit v1.2.3 From d639836ab3363f935a9a4336cb4ea3828d0437dd Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Thu, 14 May 2020 12:57:17 +0300 Subject: net: qed: adding hw_err states and handling Here we introduce qed device error tracking flags and error types. qed_hw_err_notify is an entrace point to report errors. It'll notify higher level drivers (qede/qedr/etc) to handle and recover the error. List of posible errors comes from hardware interfaces, but could be extended in future. Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8f29e0d8a7b3..1b7d9548ee43 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -607,6 +607,16 @@ struct qed_sb_info { struct qed_dev *cdev; }; +enum qed_hw_err_type { + QED_HW_ERR_FAN_FAIL, + QED_HW_ERR_MFW_RESP_FAIL, + QED_HW_ERR_HW_ATTN, + QED_HW_ERR_DMAE_FAIL, + QED_HW_ERR_RAMROD_FAIL, + QED_HW_ERR_FW_ASSERT, + QED_HW_ERR_LAST, +}; + enum qed_dev_type { QED_DEV_TYPE_BB, QED_DEV_TYPE_AH, @@ -814,6 +824,8 @@ struct qed_common_cb_ops { void (*link_update)(void *dev, struct qed_link_output *link); void (*schedule_recovery_handler)(void *dev); + void (*schedule_hw_err_handler)(void *dev, + enum qed_hw_err_type err_type); void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); -- cgit v1.2.3 From 936c7ba4dd5e94a3fc784f2296de5d577a9b5e43 Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Thu, 14 May 2020 12:57:22 +0300 Subject: net: qed: attention clearing properties On different hardware events we have to respond differently, on some of hardware indications hw attention (error condition) should be cleared by the driver to continue normal functioning. Here we introduce attention clear flags, and put them on some important events (in aeu_descs). Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 1b7d9548ee43..978e91e9ab65 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1046,6 +1046,15 @@ struct qed_common_ops { */ int (*set_led)(struct qed_dev *cdev, enum qed_led_mode mode); + +/** + * @brief attn_clr_enable - Prevent attentions from being reasserted + * + * @param cdev + * @param clr_enable + */ + void (*attn_clr_enable)(struct qed_dev *cdev, bool clr_enable); + /** * @brief db_recovery_add - add doorbell information to the doorbell * recovery mechanism. -- cgit v1.2.3 From 8f76812e1cc4d561c3efc3b2586c686b5428d31f Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Thu, 14 May 2020 12:57:27 +0300 Subject: net: qed: fix bad formatting On some adjacent code, fix bad code formatting Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 978e91e9ab65..48325d7790f8 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -821,12 +821,11 @@ enum qed_nvm_flash_cmd { struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); - void (*link_update)(void *dev, - struct qed_link_output *link); + void (*link_update)(void *dev, struct qed_link_output *link); void (*schedule_recovery_handler)(void *dev); void (*schedule_hw_err_handler)(void *dev, enum qed_hw_err_type err_type); - void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); + void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); }; -- cgit v1.2.3 From 6ae72bfa656ea04806f98ef85cb44b0789064362 Mon Sep 17 00:00:00 2001 From: Yicong Yang Date: Sat, 9 May 2020 18:19:28 +0800 Subject: PCI: Unify pcie_find_root_port() and pci_find_pcie_root_port() Previously we used pcie_find_root_port() to find a Root Port from a PCIe device and pci_find_pcie_root_port() to find a Root Port from a Conventional PCI device. Unify the two functions and use pcie_find_root_port() to find a Root Port from either a Conventional PCI device or a PCIe device. Then there is no need to distinguish the type of the device. Link: https://lore.kernel.org/r/1589019568-5216-1-git-send-email-yangyicong@hisilicon.com Signed-off-by: Yicong Yang Signed-off-by: Bjorn Helgaas Acked-by: Kalle Valo # wireless Acked-by: Mika Westerberg # thunderbolt --- include/linux/pci.h | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 0453ee458ab1..bbd6510065a7 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1025,7 +1025,6 @@ void pci_bus_add_device(struct pci_dev *dev); void pci_read_bridge_bases(struct pci_bus *child); struct resource *pci_find_parent_resource(const struct pci_dev *dev, struct resource *res); -struct pci_dev *pci_find_pcie_root_port(struct pci_dev *dev); u8 pci_swizzle_interrupt_pin(const struct pci_dev *dev, u8 pin); int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge); u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp); @@ -2143,17 +2142,23 @@ static inline int pci_pcie_type(const struct pci_dev *dev) return (pcie_caps_reg(dev) & PCI_EXP_FLAGS_TYPE) >> 4; } +/** + * pcie_find_root_port - Get the PCIe root port device + * @dev: PCI device + * + * Traverse up the parent chain and return the PCIe Root Port PCI Device + * for a given PCI/PCIe Device. + */ static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) { - while (1) { - if (!pci_is_pcie(dev)) - break; - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) - return dev; - if (!dev->bus->self) - break; - dev = dev->bus->self; + struct pci_dev *bridge = pci_upstream_bridge(dev); + + while (bridge) { + if (pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT) + return bridge; + bridge = pci_upstream_bridge(bridge); } + return NULL; } -- cgit v1.2.3 From 69cf449166987d9a041020be6422ee7bf94a7228 Mon Sep 17 00:00:00 2001 From: Sai Praneeth Prakhya Date: Wed, 13 May 2020 15:47:21 -0700 Subject: iommu: Remove functions that support private domain After moving iommu_group setup to iommu core code [1][2] and removing private domain support in vt-d [3], there are no users for functions such as iommu_request_dm_for_dev(), iommu_request_dma_domain_for_dev() and request_default_domain_for_dev(). So, remove these functions. [1] commit dce8d6964ebd ("iommu/amd: Convert to probe/release_device() call-backs") [2] commit e5d1841f18b2 ("iommu/vt-d: Convert to probe/release_device() call-backs") [3] commit 327d5b2fee91 ("iommu/vt-d: Allow 32bit devices to uses DMA domain") Signed-off-by: Sai Praneeth Prakhya Cc: Joerg Roedel Cc: Lu Baolu Link: https://lore.kernel.org/r/20200513224721.20504-1-sai.praneeth.prakhya@intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7cfd2dddb49d..78a26ae5c2b6 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -482,8 +482,6 @@ extern void iommu_get_resv_regions(struct device *dev, struct list_head *list); extern void iommu_put_resv_regions(struct device *dev, struct list_head *list); extern void generic_iommu_put_resv_regions(struct device *dev, struct list_head *list); -extern int iommu_request_dm_for_dev(struct device *dev); -extern int iommu_request_dma_domain_for_dev(struct device *dev); extern void iommu_set_default_passthrough(bool cmd_line); extern void iommu_set_default_translated(bool cmd_line); extern bool iommu_default_passthrough(void); @@ -804,16 +802,6 @@ static inline int iommu_get_group_resv_regions(struct iommu_group *group, return -ENODEV; } -static inline int iommu_request_dm_for_dev(struct device *dev) -{ - return -ENODEV; -} - -static inline int iommu_request_dma_domain_for_dev(struct device *dev) -{ - return -ENODEV; -} - static inline void iommu_set_default_passthrough(bool cmd_line) { } -- cgit v1.2.3 From c150c0f362c1e51c0e3216c9912b85b71d00e70d Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Tue, 12 May 2020 14:40:02 +0200 Subject: serial: Allow uart_get_rs485_mode() to return errno We're about to amend uart_get_rs485_mode() to support a GPIO pin for rs485 bus termination. Retrieving the GPIO descriptor may fail, so allow uart_get_rs485_mode() to return an errno and change all callers to check for failure. The GPIO descriptor is going to be stored in struct uart_port. Pass that struct to uart_get_rs485_mode() in lieu of a struct device and struct serial_rs485, both of which are directly accessible from struct uart_port. A few drivers call uart_get_rs485_mode() before setting the struct device pointer in struct uart_port. Shuffle those calls around where necessary. [Heiko Stuebner did the ar933x_uart.c portion, hence his Signed-off-by.] Signed-off-by: Heiko Stuebner Signed-off-by: Lukas Wunner Link: https://lore.kernel.org/r/271e814af4b0db3bffbbb74abf2b46b75add4516.1589285873.git.lukas@wunner.de Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 92f5eba86052..b649a2b894e7 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -472,5 +472,5 @@ extern int uart_handle_break(struct uart_port *port); (cflag) & CRTSCTS || \ !((cflag) & CLOCAL)) -void uart_get_rs485_mode(struct device *dev, struct serial_rs485 *rs485conf); +int uart_get_rs485_mode(struct uart_port *port); #endif /* LINUX_SERIAL_CORE_H */ -- cgit v1.2.3 From 0f1c9688a194d22bb81953bd85bd18b0115fd17f Mon Sep 17 00:00:00 2001 From: Emil Velikov Date: Wed, 13 May 2020 22:43:41 +0100 Subject: tty/sysrq: alpha: export and use __sysrq_get_key_op() Export a pointer to the sysrq_get_key_op(). This way we can cleanly unregister it, instead of the current solutions of modifuing it inplace. Since __sysrq_get_key_op() is no longer used externally, let's make it a static function. This patch will allow us to limit access to each and every sysrq op and constify the sysrq handling. Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: linux-kernel@vger.kernel.org Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: linux-alpha@vger.kernel.org Signed-off-by: Emil Velikov Link: https://lore.kernel.org/r/20200513214351.2138580-1-emil.l.velikov@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/sysrq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 8e159e16850f..9b51f98e5f60 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -47,7 +47,7 @@ void handle_sysrq(int key); void __handle_sysrq(int key, bool check_mask); int register_sysrq_key(int key, struct sysrq_key_op *op); int unregister_sysrq_key(int key, struct sysrq_key_op *op); -struct sysrq_key_op *__sysrq_get_key_op(int key); +extern struct sysrq_key_op *__sysrq_reboot_op; int sysrq_toggle_support(int enable_mask); int sysrq_mask(void); -- cgit v1.2.3 From 23cbedf812ff7c7751582928e32d953d84c1c821 Mon Sep 17 00:00:00 2001 From: Emil Velikov Date: Wed, 13 May 2020 22:43:42 +0100 Subject: tty/sysrq: constify the sysrq API The user is not supposed to thinker with the underlying sysrq_key_op. Make that explicit by adding a handful of const notations. Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: linux-kernel@vger.kernel.org Signed-off-by: Emil Velikov Link: https://lore.kernel.org/r/20200513214351.2138580-2-emil.l.velikov@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/sysrq.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 9b51f98e5f60..479028391c08 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -30,10 +30,10 @@ #define SYSRQ_ENABLE_RTNICE 0x0100 struct sysrq_key_op { - void (*handler)(int); - char *help_msg; - char *action_msg; - int enable_mask; + void (* const handler)(int); + const char * const help_msg; + const char * const action_msg; + const int enable_mask; }; #ifdef CONFIG_MAGIC_SYSRQ @@ -45,8 +45,8 @@ struct sysrq_key_op { void handle_sysrq(int key); void __handle_sysrq(int key, bool check_mask); -int register_sysrq_key(int key, struct sysrq_key_op *op); -int unregister_sysrq_key(int key, struct sysrq_key_op *op); +int register_sysrq_key(int key, const struct sysrq_key_op *op); +int unregister_sysrq_key(int key, const struct sysrq_key_op *op); extern struct sysrq_key_op *__sysrq_reboot_op; int sysrq_toggle_support(int enable_mask); @@ -62,12 +62,12 @@ static inline void __handle_sysrq(int key, bool check_mask) { } -static inline int register_sysrq_key(int key, struct sysrq_key_op *op) +static inline int register_sysrq_key(int key, const struct sysrq_key_op *op) { return -EINVAL; } -static inline int unregister_sysrq_key(int key, struct sysrq_key_op *op) +static inline int unregister_sysrq_key(int key, const struct sysrq_key_op *op) { return -EINVAL; } -- cgit v1.2.3 From 7fffe31d3eaa2f08bdfde2403adcaa8029f9bea4 Mon Sep 17 00:00:00 2001 From: Emil Velikov Date: Wed, 13 May 2020 22:43:43 +0100 Subject: tty/sysrq: constify the the sysrq_key_op(s) All the users threat them as immutable - annotate them as such. Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: linux-kernel@vger.kernel.org Signed-off-by: Emil Velikov Link: https://lore.kernel.org/r/20200513214351.2138580-3-emil.l.velikov@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/sysrq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 479028391c08..3a582ec7a2f1 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -47,7 +47,7 @@ void handle_sysrq(int key); void __handle_sysrq(int key, bool check_mask); int register_sysrq_key(int key, const struct sysrq_key_op *op); int unregister_sysrq_key(int key, const struct sysrq_key_op *op); -extern struct sysrq_key_op *__sysrq_reboot_op; +extern const struct sysrq_key_op *__sysrq_reboot_op; int sysrq_toggle_support(int enable_mask); int sysrq_mask(void); -- cgit v1.2.3 From ff4c65ca48f08f4781accfb1d224acd7c897070e Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 14 May 2020 17:50:36 +0530 Subject: usb: hci: add hc_driver as argument for usb_hcd_pci_probe usb_hcd_pci_probe expects users to call this with driver_data set as hc_driver, that limits the possibility of using the driver_data for driver data. Add hc_driver as argument to usb_hcd_pci_probe and modify the callers ehci/ohci/xhci/uhci to pass hc_driver as argument and freeup the driver_data used Tested xhci driver on Dragon-board RB3, compile tested ehci, ohci and uhci. [For all but the xHCI parts] [For the xhci part] Suggested-by: Mathias Nyman Acked-by: Alan Stern Acked-by: Mathias Nyman Signed-off-by: Vinod Koul Link: https://lore.kernel.org/r/20200514122039.300417-2-vkoul@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index e12105ed3834..3dbb42c637c1 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -479,7 +479,8 @@ extern void usb_hcd_platform_shutdown(struct platform_device *dev); struct pci_dev; struct pci_device_id; extern int usb_hcd_pci_probe(struct pci_dev *dev, - const struct pci_device_id *id); + const struct pci_device_id *id, + const struct hc_driver *driver); extern void usb_hcd_pci_remove(struct pci_dev *dev); extern void usb_hcd_pci_shutdown(struct pci_dev *dev); -- cgit v1.2.3 From 6fbeb0048e6b93f7b7f195864f3ddc876ac4d42e Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Fri, 7 Feb 2020 15:59:25 -0500 Subject: dm bufio: implement discard Add functions dm_bufio_issue_discard and dm_bufio_discard_buffers. dm_bufio_issue_discard sends discard request to the underlying device. dm_bufio_discard_buffers frees buffers in the range and then calls dm_bufio_issue_discard. Also, factor out block_to_sector for reuse in dm_bufio_issue_discard. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- include/linux/dm-bufio.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 3c8b7d274bd9..07e1f163e299 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -118,6 +118,18 @@ int dm_bufio_write_dirty_buffers(struct dm_bufio_client *c); */ int dm_bufio_issue_flush(struct dm_bufio_client *c); +/* + * Send a discard request to the underlying device. + */ +int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t count); + +/* + * Free the specified range of buffers. If a buffer is held by other process, it + * is not freed. If a buffer is dirty, it is discarded without writeback. + * Finally, send the discard request to the device. + */ +int dm_bufio_discard_buffers(struct dm_bufio_client *c, sector_t block, sector_t count); + /* * Like dm_bufio_release but also move the buffer to the new * block. dm_bufio_write_dirty_buffers is needed to commit the new block. -- cgit v1.2.3 From 087615bf3acdafd0ba7c7c9ed5286e7b7c80fe1b Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Thu, 30 Apr 2020 16:48:29 -0400 Subject: dm mpath: pass IO start time to path selector The HST path selector needs this information to perform path prediction. For request-based mpath, struct request's io_start_time_ns is used, while for bio-based, use the start_time stored in dm_io. Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index af48d9da3916..934037d938b9 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -332,6 +332,8 @@ void *dm_per_bio_data(struct bio *bio, size_t data_size); struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size); unsigned dm_bio_get_target_bio_nr(const struct bio *bio); +u64 dm_start_time_ns_from_clone(struct bio *bio); + int dm_register_target(struct target_type *t); void dm_unregister_target(struct target_type *t); -- cgit v1.2.3 From 716a7a25969003d82ab738179c3f1068a120ed11 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 14 May 2020 22:34:59 -0700 Subject: driver core: fw_devlink: Add support for batching fwnode parsing The amount of time spent parsing fwnodes of devices can become really high if the devices are added in an non-ideal order. Worst case can be O(N^2) when N devices are added. But this can be optimized to O(N) by adding all the devices and then parsing all their fwnodes in one batch. This commit adds fw_devlink_pause() and fw_devlink_resume() to allow doing this. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20200515053500.215929-4-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fwnode.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index e0abafbb17f8..9506f8ec0974 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -171,5 +171,7 @@ struct fwnode_operations { #define get_dev_from_fwnode(fwnode) get_device((fwnode)->dev) extern u32 fw_devlink_get_flags(void); +void fw_devlink_pause(void); +void fw_devlink_resume(void); #endif -- cgit v1.2.3 From a17b53c4a4b55ec322c132b6670743612229ee9c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 13 May 2020 16:03:53 -0700 Subject: bpf, capability: Introduce CAP_BPF Split BPF operations that are allowed under CAP_SYS_ADMIN into combination of CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN. For backward compatibility include them in CAP_SYS_ADMIN as well. The end result provides simple safety model for applications that use BPF: - to load tracing program types BPF_PROG_TYPE_{KPROBE, TRACEPOINT, PERF_EVENT, RAW_TRACEPOINT, etc} use CAP_BPF and CAP_PERFMON - to load networking program types BPF_PROG_TYPE_{SCHED_CLS, XDP, SK_SKB, etc} use CAP_BPF and CAP_NET_ADMIN There are few exceptions from this rule: - bpf_trace_printk() is allowed in networking programs, but it's using tracing mechanism, hence this helper needs additional CAP_PERFMON if networking program is using this helper. - BPF_F_ZERO_SEED flag for hash/lru map is allowed under CAP_SYS_ADMIN only to discourage production use. - BPF HW offload is allowed under CAP_SYS_ADMIN. - bpf_probe_write_user() is allowed under CAP_SYS_ADMIN only. CAPs are not checked at attach/detach time with two exceptions: - loading BPF_PROG_TYPE_CGROUP_SKB is allowed for unprivileged users, hence CAP_NET_ADMIN is required at attach time. - flow_dissector detach doesn't check prog FD at detach, hence CAP_NET_ADMIN is required at detach time. CAP_SYS_ADMIN is required to iterate BPF objects (progs, maps, links) via get_next_id command and convert them to file descriptor via GET_FD_BY_ID command. This restriction guarantees that mutliple tasks with CAP_BPF are not able to affect each other. That leads to clean isolation of tasks. For example: task A with CAP_BPF and CAP_NET_ADMIN loads and attaches a firewall via bpf_link. task B with the same capabilities cannot detach that firewall unless task A explicitly passed link FD to task B via scm_rights or bpffs. CAP_SYS_ADMIN can still detach/unload everything. Two networking user apps with CAP_SYS_ADMIN and CAP_NET_ADMIN can accidentely mess with each other programs and maps. Two networking user apps with CAP_NET_ADMIN and CAP_BPF cannot affect each other. CAP_NET_ADMIN + CAP_BPF allows networking programs access only packet data. Such networking progs cannot access arbitrary kernel memory or leak pointers. bpftool, bpftrace, bcc tools binaries should NOT be installed with CAP_BPF and CAP_PERFMON, since unpriv users will be able to read kernel secrets. But users with these two permissions will be able to use these tracing tools. CAP_PERFMON is least secure, since it allows kprobes and kernel memory access. CAP_NET_ADMIN can stop network traffic via iproute2. CAP_BPF is the safest from security point of view and harmless on its own. Having CAP_BPF and/or CAP_NET_ADMIN is not enough to write into arbitrary map and if that map is used by firewall-like bpf prog. CAP_BPF allows many bpf prog_load commands in parallel. The verifier may consume large amount of memory and significantly slow down the system. Existing unprivileged BPF operations are not affected. In particular unprivileged users are allowed to load socket_filter and cg_skb program types and to create array, hash, prog_array, map-in-map map types. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200513230355.7858-2-alexei.starovoitov@gmail.com --- include/linux/capability.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index 027d7e4a853b..b4345b38a6be 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -256,6 +256,11 @@ static inline bool perfmon_capable(void) return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN); } +static inline bool bpf_capable(void) +{ + return capable(CAP_BPF) || capable(CAP_SYS_ADMIN); +} + /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); -- cgit v1.2.3 From 2c78ee898d8f10ae6fb2fa23a3fbaec96b1b7366 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 13 May 2020 16:03:54 -0700 Subject: bpf: Implement CAP_BPF Implement permissions as stated in uapi/linux/capability.h In order to do that the verifier allow_ptr_leaks flag is split into four flags and they are set as: env->allow_ptr_leaks = bpf_allow_ptr_leaks(); env->bypass_spec_v1 = bpf_bypass_spec_v1(); env->bypass_spec_v4 = bpf_bypass_spec_v4(); env->bpf_capable = bpf_capable(); The first three currently equivalent to perfmon_capable(), since leaking kernel pointers and reading kernel memory via side channel attacks is roughly equivalent to reading kernel memory with cap_perfmon. 'bpf_capable' enables bounded loops, precision tracking, bpf to bpf calls and other verifier features. 'allow_ptr_leaks' enable ptr leaks, ptr conversions, subtraction of pointers. 'bypass_spec_v1' disables speculative analysis in the verifier, run time mitigations in bpf array, and enables indirect variable access in bpf programs. 'bypass_spec_v4' disables emission of sanitation code by the verifier. That means that the networking BPF program loaded with CAP_BPF + CAP_NET_ADMIN will have speculative checks done by the verifier and other spectre mitigation applied. Such networking BPF program will not be able to leak kernel pointers and will not be able to access arbitrary kernel memory. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200513230355.7858-3-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 18 +++++++++++++++++- include/linux/bpf_verifier.h | 3 +++ 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c45d198ac38c..efe8836b5c48 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -19,6 +19,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -119,7 +120,7 @@ struct bpf_map { struct bpf_map_memory memory; char name[BPF_OBJ_NAME_LEN]; u32 btf_vmlinux_value_type_id; - bool unpriv_array; + bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ /* 22 bytes hole */ @@ -1095,6 +1096,21 @@ struct bpf_map *bpf_map_get_curr_or_next(u32 *id); extern int sysctl_unprivileged_bpf_disabled; +static inline bool bpf_allow_ptr_leaks(void) +{ + return perfmon_capable(); +} + +static inline bool bpf_bypass_spec_v1(void) +{ + return perfmon_capable(); +} + +static inline bool bpf_bypass_spec_v4(void) +{ + return perfmon_capable(); +} + int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 6abd5a778fcd..ea833087e853 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -375,6 +375,9 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; + bool bpf_capable; + bool bypass_spec_v1; + bool bypass_spec_v4; bool seen_direct_write; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ const struct bpf_line_info *prev_linfo; -- cgit v1.2.3 From d08b9f0ca6605e13dcb48f04e55a30545b3c71eb Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Mon, 27 Apr 2020 09:00:07 -0700 Subject: scs: Add support for Clang's Shadow Call Stack (SCS) This change adds generic support for Clang's Shadow Call Stack, which uses a shadow stack to protect return addresses from being overwritten by an attacker. Details are available here: https://clang.llvm.org/docs/ShadowCallStack.html Note that security guarantees in the kernel differ from the ones documented for user space. The kernel must store addresses of shadow stacks in memory, which means an attacker capable reading and writing arbitrary memory may be able to locate them and hijack control flow by modifying the stacks. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Reviewed-by: Miguel Ojeda [will: Numerous cosmetic changes] Signed-off-by: Will Deacon --- include/linux/compiler-clang.h | 4 +++ include/linux/compiler_types.h | 4 +++ include/linux/scs.h | 68 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 76 insertions(+) create mode 100644 include/linux/scs.h (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 333a6695a918..790c0c6b8552 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -42,3 +42,7 @@ * compilers, like ICC. */ #define barrier() __asm__ __volatile__("" : : : "memory") + +#if __has_feature(shadow_call_stack) +# define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) +#endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index e970f97a7fcb..97b62f47a80d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -193,6 +193,10 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif +#ifndef __noscs +# define __noscs +#endif + #ifndef asm_volatile_goto #define asm_volatile_goto(x...) asm goto(x) #endif diff --git a/include/linux/scs.h b/include/linux/scs.h new file mode 100644 index 000000000000..3f3662621a27 --- /dev/null +++ b/include/linux/scs.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shadow Call Stack support. + * + * Copyright (C) 2019 Google LLC + */ + +#ifndef _LINUX_SCS_H +#define _LINUX_SCS_H + +#include +#include +#include +#include + +#ifdef CONFIG_SHADOW_CALL_STACK + +/* + * In testing, 1 KiB shadow stack size (i.e. 128 stack frames on a 64-bit + * architecture) provided ~40% safety margin on stack usage while keeping + * memory allocation overhead reasonable. + */ +#define SCS_SIZE SZ_1K +#define GFP_SCS (GFP_KERNEL | __GFP_ZERO) + +/* An illegal pointer value to mark the end of the shadow stack. */ +#define SCS_END_MAGIC (0x5f6UL + POISON_POINTER_DELTA) + +#define task_scs(tsk) (task_thread_info(tsk)->scs_base) +#define task_scs_offset(tsk) (task_thread_info(tsk)->scs_offset) + +void scs_init(void); +int scs_prepare(struct task_struct *tsk, int node); +void scs_release(struct task_struct *tsk); + +static inline void scs_task_reset(struct task_struct *tsk) +{ + /* + * Reset the shadow stack to the base address in case the task + * is reused. + */ + task_scs_offset(tsk) = 0; +} + +static inline unsigned long *__scs_magic(void *s) +{ + return (unsigned long *)(s + SCS_SIZE) - 1; +} + +static inline bool scs_corrupted(struct task_struct *tsk) +{ + unsigned long *magic = __scs_magic(task_scs(tsk)); + + return (task_scs_offset(tsk) >= SCS_SIZE - 1 || + READ_ONCE_NOCHECK(*magic) != SCS_END_MAGIC); +} + +#else /* CONFIG_SHADOW_CALL_STACK */ + +static inline void scs_init(void) {} +static inline void scs_task_reset(struct task_struct *tsk) {} +static inline int scs_prepare(struct task_struct *tsk, int node) { return 0; } +static inline bool scs_corrupted(struct task_struct *tsk) { return false; } +static inline void scs_release(struct task_struct *tsk) {} + +#endif /* CONFIG_SHADOW_CALL_STACK */ + +#endif /* _LINUX_SCS_H */ -- cgit v1.2.3 From 628d06a48f57c36abdc2a024930212e654a501b7 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Mon, 27 Apr 2020 09:00:08 -0700 Subject: scs: Add page accounting for shadow call stack allocations This change adds accounting for the memory allocated for shadow stacks. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Acked-by: Will Deacon Signed-off-by: Will Deacon --- include/linux/mmzone.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1b9de7d220fb..acffc3bc6178 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -156,6 +156,9 @@ enum zone_stat_item { NR_MLOCK, /* mlock()ed pages found and moved off LRU */ NR_PAGETABLE, /* used for pagetables */ NR_KERNEL_STACK_KB, /* measured in KiB */ +#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) + NR_KERNEL_SCS_KB, /* measured in KiB */ +#endif /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) -- cgit v1.2.3 From b0ed0bbfb3046ed127f6004b5893ccb6cdd9ba90 Mon Sep 17 00:00:00 2001 From: Kevin Lo Date: Sat, 16 May 2020 01:24:47 +0800 Subject: net: phy: broadcom: add support for BCM54811 PHY The BCM54811 PHY shares many similarities with the already supported BCM54810 PHY but additionally requires some semi-unique configuration. Signed-off-by: Kevin Lo Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index d41624db6de2..6ad4c000661a 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -17,6 +17,7 @@ #define PHY_ID_BCM5395 0x0143bcf0 #define PHY_ID_BCM53125 0x03625f20 #define PHY_ID_BCM54810 0x03625d00 +#define PHY_ID_BCM54811 0x03625cc0 #define PHY_ID_BCM5482 0x0143bcb0 #define PHY_ID_BCM5411 0x00206070 #define PHY_ID_BCM5421 0x002060e0 @@ -255,6 +256,7 @@ #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN (1 << 0) #define BCM54810_SHD_CLK_CTL 0x3 #define BCM54810_SHD_CLK_CTL_GTXCLK_EN (1 << 9) +#define BCM54810_SHD_SCR3_TRDDAPD 0x0100 /* BCM54612E Registers */ #define BCM54612E_EXP_SPARE0 (MII_BCM54XX_EXP_SEL_ETC + 0x34) -- cgit v1.2.3 From 90bf45134d55d626ae2713cac50cda10c6c8b0c2 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 15 May 2020 19:22:15 +0200 Subject: mptcp: add new sock flag to deal with join subflows MP_JOIN subflows must not land into the accept queue. Currently tcp_check_req() calls an mptcp specific helper to detect such scenario. Such helper leverages the subflow context to check for MP_JOIN subflows. We need to deal also with MP JOIN failures, even when the subflow context is not available due allocation failure. A possible solution would be changing the syn_recv_sock() signature to allow returning a more descriptive action/ error code and deal with that in tcp_check_req(). Since the above need is MPTCP specific, this patch instead uses a TCP request socket hole to add a MPTCP specific flag. Such flag is used by the MPTCP syn_recv_sock() to tell tcp_check_req() how to deal with the request socket. This change is a no-op for !MPTCP build, and makes the MPTCP code simpler. It allows also the next patch to deal correctly with MP JOIN failure. v1 -> v2: - be more conservative on drop_req initialization (Mat) RFC -> v1: - move the drop_req bit inside tcp_request_sock (Eric) Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Reviewed-by: Christoph Paasch Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e60db06ec28d..bf44e85d709d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -120,6 +120,9 @@ struct tcp_request_sock { u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; bool is_mptcp; +#if IS_ENABLED(CONFIG_MPTCP) + bool drop_req; +#endif u32 txhash; u32 rcv_isn; u32 snt_isn; -- cgit v1.2.3 From 8b85996095049a2216c0a6b582330ec75913243c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 May 2020 16:32:48 -0700 Subject: linux/parser.h: add include guards is missing include guards. Add them. This is needed to allow declaring a function in that takes a substring_t parameter. Link: https://lore.kernel.org/r/20200512233251.118314-2-ebiggers@kernel.org Reviewed-by: Theodore Ts'o Reviewed-by: Jaegeuk Kim Signed-off-by: Eric Biggers --- include/linux/parser.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/parser.h b/include/linux/parser.h index 12fc3482f5fc..89e2b23fb888 100644 --- a/include/linux/parser.h +++ b/include/linux/parser.h @@ -7,7 +7,8 @@ * but could potentially be used anywhere else that simple option=arg * parsing is required. */ - +#ifndef _LINUX_PARSER_H +#define _LINUX_PARSER_H /* associates an integer enumerator with a pattern string. */ struct match_token { @@ -34,3 +35,5 @@ int match_hex(substring_t *, int *result); bool match_wildcard(const char *pattern, const char *str); size_t match_strlcpy(char *, const substring_t *, size_t); char *match_strdup(const substring_t *); + +#endif /* _LINUX_PARSER_H */ -- cgit v1.2.3 From e5006671acc714d9dbfc6f8a618124c36f5cc6f8 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 28 Apr 2020 15:49:45 -0500 Subject: clk: versatile: Drop the legacy IM-PD1 clock code Now that the non-DT IM-PD1 support code has been removed, drop the clock related code from clk-impd1.c. Link: https://lore.kernel.org/r/20200428204945.21067-1-robh@kernel.org Cc: Linus Walleij Cc: Stephen Boyd Cc: linux-arm-kernel@lists.infradead.org Cc: linux-clk@vger.kernel.org Signed-off-by: Rob Herring Reviewed-by: Linus Walleij Reviewed-by: Stephen Boyd Signed-off-by: Arnd Bergmann --- include/linux/platform_data/clk-integrator.h | 2 -- 1 file changed, 2 deletions(-) delete mode 100644 include/linux/platform_data/clk-integrator.h (limited to 'include/linux') diff --git a/include/linux/platform_data/clk-integrator.h b/include/linux/platform_data/clk-integrator.h deleted file mode 100644 index addd48cac625..000000000000 --- a/include/linux/platform_data/clk-integrator.h +++ /dev/null @@ -1,2 +0,0 @@ -void integrator_impd1_clk_init(void __iomem *base, unsigned int id); -void integrator_impd1_clk_exit(unsigned int id); -- cgit v1.2.3 From 2771cefeac499d68ca2fca3861ba9e46d15bd4ae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 May 2020 18:10:05 +0200 Subject: block: remove the REQ_NOWAIT_INLINE flag Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 9322261fb316..ccb895f911b1 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -343,7 +343,6 @@ enum req_flag_bits { __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ - __REQ_NOWAIT_INLINE, /* Return would-block error inline */ /* * When a shared kthread needs to issue a bio for a cgroup, doing * so synchronously can lead to priority inversions as the kthread @@ -378,7 +377,6 @@ enum req_flag_bits { #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (1ULL << __REQ_NOWAIT) -#define REQ_NOWAIT_INLINE (1ULL << __REQ_NOWAIT_INLINE) #define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) -- cgit v1.2.3 From 4930f4831b1547b52c5968e9307fe3d840d7fba0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 16 May 2020 10:46:23 +0200 Subject: net: allow __skb_ext_alloc to sleep mptcp calls this from the transmit side, from process context. Allow a sleeping allocation instead of unconditional GFP_ATOMIC. Acked-by: Paolo Abeni Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3000c526f552..531843952809 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4165,7 +4165,7 @@ struct skb_ext { char data[] __aligned(8); }; -struct skb_ext *__skb_ext_alloc(void); +struct skb_ext *__skb_ext_alloc(gfp_t flags); void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext); void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id); -- cgit v1.2.3 From 9dafdfc2f0a3ae551711098de3d7b621a469f11a Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sun, 17 May 2020 14:18:05 +0300 Subject: splice: export do_tee() export do_tee() for use in io_uring Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/splice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/splice.h b/include/linux/splice.h index ebbbfea48aa0..5c47013f708e 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -82,6 +82,9 @@ extern long do_splice(struct file *in, loff_t __user *off_in, struct file *out, loff_t __user *off_out, size_t len, unsigned int flags); +extern long do_tee(struct file *in, struct file *out, size_t len, + unsigned int flags); + /* * for dynamic pipe sizing */ -- cgit v1.2.3 From 4c033b549912bc301c5e2adfb7b6ca007c11bf31 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 11 May 2020 16:52:54 +0200 Subject: gpiolib: Add support for GPIO lookup by line name Currently a GPIO lookup table can only refer to a specific GPIO by a tuple, consisting of a GPIO controller label and a GPIO offset inside the controller. However, a GPIO may also carry a line name, defined by DT or ACPI. If present, the line name is the most use-centric way to refer to a GPIO. Hence add support for looking up GPIOs by line name. Note that there is no guarantee that GPIO line names are globally unique, so this will use the first match found. Implement this by reusing the existing gpiod_lookup infrastructure. Rename gpiod_lookup.chip_label to gpiod_lookup.key, to make it clear that this field can have two meanings, and update the kerneldoc and GPIO_LOOKUP*() macros. Signed-off-by: Geert Uytterhoeven Tested-by: Eugeniu Rosca Reviewed-by: Ulrich Hecht Reviewed-by: Eugeniu Rosca Link: https://lore.kernel.org/r/20200511145257.22970-4-geert+renesas@glider.be Signed-off-by: Linus Walleij --- include/linux/gpio/machine.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index 1ebe5be05d5f..781a053abbb9 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -20,8 +20,11 @@ enum gpio_lookup_flags { /** * struct gpiod_lookup - lookup table - * @chip_label: name of the chip the GPIO belongs to - * @chip_hwnum: hardware number (i.e. relative to the chip) of the GPIO + * @key: either the name of the chip the GPIO belongs to, or the GPIO line name + * Note that GPIO line names are not guaranteed to be globally unique, + * so this will use the first match found! + * @chip_hwnum: hardware number (i.e. relative to the chip) of the GPIO, or + * U16_MAX to indicate that @key is a GPIO line name * @con_id: name of the GPIO from the device's point of view * @idx: index of the GPIO in case several GPIOs share the same name * @flags: bitmask of gpio_lookup_flags GPIO_* values @@ -30,7 +33,7 @@ enum gpio_lookup_flags { * functions using platform data. */ struct gpiod_lookup { - const char *chip_label; + const char *key; u16 chip_hwnum; const char *con_id; unsigned int idx; @@ -63,17 +66,17 @@ struct gpiod_hog { /* * Simple definition of a single GPIO under a con_id */ -#define GPIO_LOOKUP(_chip_label, _chip_hwnum, _con_id, _flags) \ - GPIO_LOOKUP_IDX(_chip_label, _chip_hwnum, _con_id, 0, _flags) +#define GPIO_LOOKUP(_key, _chip_hwnum, _con_id, _flags) \ + GPIO_LOOKUP_IDX(_key, _chip_hwnum, _con_id, 0, _flags) /* * Use this macro if you need to have several GPIOs under the same con_id. * Each GPIO needs to use a different index and can be accessed using * gpiod_get_index() */ -#define GPIO_LOOKUP_IDX(_chip_label, _chip_hwnum, _con_id, _idx, _flags) \ +#define GPIO_LOOKUP_IDX(_key, _chip_hwnum, _con_id, _idx, _flags) \ { \ - .chip_label = _chip_label, \ + .key = _key, \ .chip_hwnum = _chip_hwnum, \ .con_id = _con_id, \ .idx = _idx, \ -- cgit v1.2.3 From 5c8f77a278737a6af44a892f0700d9aadb2b0de0 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 14 May 2020 10:39:00 +0200 Subject: irqdomain: Make irq_domain_reset_irq_data() available to non-hierarchical users irq_domain_reset_irq_data() doesn't modify the parent data, so it can be made available even if irq domain hierarchy is not being built. We'll subsequently use it in irq_sim code. Signed-off-by: Bartosz Golaszewski Signed-off-by: Marc Zyngier Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20200514083901.23445-2-brgl@bgdev.pl --- include/linux/irqdomain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 8d062e86d954..b37350c4fe37 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -450,6 +450,7 @@ extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, irq_hw_number_t hwirq, struct irq_chip *chip, void *chip_data, irq_flow_handler_t handler, void *handler_data, const char *handler_name); +extern void irq_domain_reset_irq_data(struct irq_data *irq_data); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY extern struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent, unsigned int flags, unsigned int size, @@ -491,7 +492,6 @@ extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, irq_hw_number_t hwirq, struct irq_chip *chip, void *chip_data); -extern void irq_domain_reset_irq_data(struct irq_data *irq_data); extern void irq_domain_free_irqs_common(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs); -- cgit v1.2.3 From 337cbeb2c13eb4cab84f576fd402d7ae4ed31ae1 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 14 May 2020 10:39:01 +0200 Subject: genirq/irq_sim: Simplify the API The interrupt simulator API exposes a lot of custom data structures and functions and doesn't reuse the interfaces already exposed by the irq subsystem. This patch tries to address it. We hide all the simulator-related data structures from users and instead rely on the well-known irq domain. When creating the interrupt simulator the user receives a pointer to a newly created irq_domain and can use it to create mappings for simulated interrupts. It is also possible to pass a handle to fwnode when creating the simulator domain and retrieve it using irq_find_matching_fwnode(). The irq_sim_fire() function is dropped as well. Instead we implement the irq_get/set_irqchip_state interface. We modify the two modules that use the simulator at the same time as adding these changes in order to reduce the intermediate bloat that would result when trying to migrate the drivers in separate patches. Signed-off-by: Bartosz Golaszewski Signed-off-by: Marc Zyngier Reviewed-by: Linus Walleij Acked-by: Jonathan Cameron #for IIO Link: https://lore.kernel.org/r/20200514083901.23445-3-brgl@bgdev.pl --- include/linux/irq_sim.h | 33 +++++++++------------------------ 1 file changed, 9 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq_sim.h b/include/linux/irq_sim.h index 4500d453a63e..ab831e5ae748 100644 --- a/include/linux/irq_sim.h +++ b/include/linux/irq_sim.h @@ -1,41 +1,26 @@ /* SPDX-License-Identifier: GPL-2.0+ */ /* * Copyright (C) 2017-2018 Bartosz Golaszewski + * Copyright (C) 2020 Bartosz Golaszewski */ #ifndef _LINUX_IRQ_SIM_H #define _LINUX_IRQ_SIM_H -#include #include +#include +#include /* * Provides a framework for allocating simulated interrupts which can be * requested like normal irqs and enqueued from process context. */ -struct irq_sim_work_ctx { - struct irq_work work; - unsigned long *pending; -}; - -struct irq_sim_irq_ctx { - int irqnum; - bool enabled; -}; - -struct irq_sim { - struct irq_sim_work_ctx work_ctx; - int irq_base; - unsigned int irq_count; - struct irq_sim_irq_ctx *irqs; -}; - -int irq_sim_init(struct irq_sim *sim, unsigned int num_irqs); -int devm_irq_sim_init(struct device *dev, struct irq_sim *sim, - unsigned int num_irqs); -void irq_sim_fini(struct irq_sim *sim); -void irq_sim_fire(struct irq_sim *sim, unsigned int offset); -int irq_sim_irqnum(struct irq_sim *sim, unsigned int offset); +struct irq_domain *irq_domain_create_sim(struct fwnode_handle *fwnode, + unsigned int num_irqs); +struct irq_domain *devm_irq_domain_create_sim(struct device *dev, + struct fwnode_handle *fwnode, + unsigned int num_irqs); +void irq_domain_remove_sim(struct irq_domain *domain); #endif /* _LINUX_IRQ_SIM_H */ -- cgit v1.2.3 From 3db9983e4327f773c490de2a8c66d6000561d88a Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:44 +0800 Subject: iommu/vt-d: Move domain helper to header Move domain helper to header to be used by SVA code. Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20200516062101.29541-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 980234ae0312..ed7171d2ae1f 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -595,6 +595,12 @@ static inline void __iommu_flush_cache( clflush_cache_range(addr, size); } +/* Convert generic struct iommu_domain to private struct dmar_domain */ +static inline struct dmar_domain *to_dmar_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct dmar_domain, domain); +} + /* * 0: readable * 1: writable -- cgit v1.2.3 From b0d1f8741b812352fe0e5f3b2381427085f23e19 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:46 +0800 Subject: iommu/vt-d: Add nested translation helper function Nested translation mode is supported in VT-d 3.0 Spec.CH 3.8. With PASID granular translation type set to 0x11b, translation result from the first level(FL) also subject to a second level(SL) page table translation. This mode is used for SVA virtualization, where FL performs guest virtual to guest physical translation and SL performs guest physical to host physical translation. This patch adds a helper function for setting up nested translation where second level comes from a domain and first level comes from a guest PGD. Signed-off-by: Jacob Pan Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200516062101.29541-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index ed7171d2ae1f..e0d1fed7cbe4 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -42,6 +42,9 @@ #define DMA_FL_PTE_PRESENT BIT_ULL(0) #define DMA_FL_PTE_XD BIT_ULL(63) +#define ADDR_WIDTH_5LEVEL (57) +#define ADDR_WIDTH_4LEVEL (48) + #define CONTEXT_TT_MULTI_LEVEL 0 #define CONTEXT_TT_DEV_IOTLB 1 #define CONTEXT_TT_PASS_THROUGH 2 @@ -480,6 +483,23 @@ struct context_entry { u64 hi; }; +/* si_domain contains mulitple devices */ +#define DOMAIN_FLAG_STATIC_IDENTITY BIT(0) + +/* + * When VT-d works in the scalable mode, it allows DMA translation to + * happen through either first level or second level page table. This + * bit marks that the DMA translation for the domain goes through the + * first level page table, otherwise, it goes through the second level. + */ +#define DOMAIN_FLAG_USE_FIRST_LEVEL BIT(1) + +/* + * Domain represents a virtual machine which demands iommu nested + * translation mode support. + */ +#define DOMAIN_FLAG_NESTING_MODE BIT(2) + struct dmar_domain { int nid; /* node id */ -- cgit v1.2.3 From 56722a4398a306585ca3ed39ff54fc907af98618 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:47 +0800 Subject: iommu/vt-d: Add bind guest PASID support When supporting guest SVA with emulated IOMMU, the guest PASID table is shadowed in VMM. Updates to guest vIOMMU PASID table will result in PASID cache flush which will be passed down to the host as bind guest PASID calls. For the SL page tables, it will be harvested from device's default domain (request w/o PASID), or aux domain in case of mediated device. .-------------. .---------------------------. | vIOMMU | | Guest process CR3, FL only| | | '---------------------------' .----------------/ | PASID Entry |--- PASID cache flush - '-------------' | | | V | | CR3 in GPA '-------------' Guest ------| Shadow |--------------------------|-------- v v v Host .-------------. .----------------------. | pIOMMU | | Bind FL for GVA-GPA | | | '----------------------' .----------------/ | | PASID Entry | V (Nested xlate) '----------------\.------------------------------. | | |SL for GPA-HPA, default domain| | | '------------------------------' '-------------' Where: - FL = First level/stage one page tables - SL = Second level/stage two page tables Signed-off-by: Jacob Pan Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20200516062101.29541-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 6 +++++- include/linux/intel-svm.h | 12 ++++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index e0d1fed7cbe4..3dfd426dfb03 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -698,7 +698,9 @@ struct dmar_domain *find_domain(struct device *dev); extern void intel_svm_check(struct intel_iommu *iommu); extern int intel_svm_enable_prq(struct intel_iommu *iommu); extern int intel_svm_finish_prq(struct intel_iommu *iommu); - +int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, + struct iommu_gpasid_bind_data *data); +int intel_svm_unbind_gpasid(struct device *dev, int pasid); struct svm_dev_ops; struct intel_svm_dev { @@ -715,9 +717,11 @@ struct intel_svm_dev { struct intel_svm { struct mmu_notifier notifier; struct mm_struct *mm; + struct intel_iommu *iommu; int flags; int pasid; + int gpasid; /* In case that guest PASID is different from host PASID */ struct list_head devs; struct list_head list; }; diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index d7c403d0dd27..1b47ca46373e 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -44,6 +44,18 @@ struct svm_dev_ops { * do such IOTLB flushes automatically. */ #define SVM_FLAG_SUPERVISOR_MODE (1<<1) +/* + * The SVM_FLAG_GUEST_MODE flag is used when a PASID bind is for guest + * processes. Compared to the host bind, the primary differences are: + * 1. mm life cycle management + * 2. fault reporting + */ +#define SVM_FLAG_GUEST_MODE (1<<2) +/* + * The SVM_FLAG_GUEST_PASID flag is used when a guest has its own PASID space, + * which requires guest and host PASID translation at both directions. + */ +#define SVM_FLAG_GUEST_PASID (1<<3) #ifdef CONFIG_INTEL_IOMMU_SVM -- cgit v1.2.3 From 61a06a16e36d830f7811fbf931668d87197d95b7 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:48 +0800 Subject: iommu/vt-d: Support flushing more translation cache types When Shared Virtual Memory is exposed to a guest via vIOMMU, scalable IOTLB invalidation may be passed down from outside IOMMU subsystems. This patch adds invalidation functions that can be used for additional translation cache types. Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200516062101.29541-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 3dfd426dfb03..a9c984b29a72 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -334,7 +334,7 @@ enum { #define QI_IOTLB_GRAN(gran) (((u64)gran) >> (DMA_TLB_FLUSH_GRANU_OFFSET-4)) #define QI_IOTLB_ADDR(addr) (((u64)addr) & VTD_PAGE_MASK) #define QI_IOTLB_IH(ih) (((u64)ih) << 6) -#define QI_IOTLB_AM(am) (((u8)am)) +#define QI_IOTLB_AM(am) (((u8)am) & 0x3f) #define QI_CC_FM(fm) (((u64)fm) << 48) #define QI_CC_SID(sid) (((u64)sid) << 32) @@ -353,16 +353,21 @@ enum { #define QI_PC_DID(did) (((u64)did) << 16) #define QI_PC_GRAN(gran) (((u64)gran) << 4) -#define QI_PC_ALL_PASIDS (QI_PC_TYPE | QI_PC_GRAN(0)) -#define QI_PC_PASID_SEL (QI_PC_TYPE | QI_PC_GRAN(1)) +/* PASID cache invalidation granu */ +#define QI_PC_ALL_PASIDS 0 +#define QI_PC_PASID_SEL 1 #define QI_EIOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) #define QI_EIOTLB_IH(ih) (((u64)ih) << 6) -#define QI_EIOTLB_AM(am) (((u64)am)) +#define QI_EIOTLB_AM(am) (((u64)am) & 0x3f) #define QI_EIOTLB_PASID(pasid) (((u64)pasid) << 32) #define QI_EIOTLB_DID(did) (((u64)did) << 16) #define QI_EIOTLB_GRAN(gran) (((u64)gran) << 4) +/* QI Dev-IOTLB inv granu */ +#define QI_DEV_IOTLB_GRAN_ALL 1 +#define QI_DEV_IOTLB_GRAN_PASID_SEL 0 + #define QI_DEV_EIOTLB_ADDR(a) ((u64)(a) & VTD_PAGE_MASK) #define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) #define QI_DEV_EIOTLB_GLOB(g) ((u64)g) @@ -679,8 +684,16 @@ extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, unsigned int size_order, u64 type); extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, u16 qdep, u64 addr, unsigned mask); + void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, unsigned long npages, bool ih); + +void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, + u32 pasid, u16 qdep, u64 addr, + unsigned int size_order, u64 granu); +void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, + int pasid); + extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu); extern int dmar_ir_support(void); -- cgit v1.2.3 From 24f27d32ab6b71dedcbbeeab8f9bdc143b539ac0 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 16 May 2020 14:20:50 +0800 Subject: iommu/vt-d: Enlightened PASID allocation Enabling IOMMU in a guest requires communication with the host driver for certain aspects. Use of PASID ID to enable Shared Virtual Addressing (SVA) requires managing PASID's in the host. VT-d 3.0 spec provides a Virtual Command Register (VCMD) to facilitate this. Writes to this register in the guest are trapped by vIOMMU which proxies the call to the host driver. This virtual command interface consists of a capability register, a virtual command register, and a virtual response register. Refer to section 10.4.42, 10.4.43, 10.4.44 for more information. This patch adds the enlightened PASID allocation/free interfaces via the virtual command interface. Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Signed-off-by: Jacob Pan Reviewed-by: Eric Auger Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20200516062101.29541-8-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index a9c984b29a72..addb310b4ded 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -169,6 +169,7 @@ #define ecap_smpwc(e) (((e) >> 48) & 0x1) #define ecap_flts(e) (((e) >> 47) & 0x1) #define ecap_slts(e) (((e) >> 46) & 0x1) +#define ecap_vcs(e) (((e) >> 44) & 0x1) #define ecap_smts(e) (((e) >> 43) & 0x1) #define ecap_dit(e) ((e >> 41) & 0x1) #define ecap_pasid(e) ((e >> 40) & 0x1) -- cgit v1.2.3 From 3375303e82877552f3b2b42309e8233fe715fd9f Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:51 +0800 Subject: iommu/vt-d: Add custom allocator for IOASID When VT-d driver runs in the guest, PASID allocation must be performed via virtual command interface. This patch registers a custom IOASID allocator which takes precedence over the default XArray based allocator. The resulting IOASID allocation will always come from the host. This ensures that PASID namespace is system- wide. Virtual command registers are used in the guest only, to prevent vmexit cost, we cache the capability and store it during initialization. Signed-off-by: Liu, Yi L Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200516062101.29541-9-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index addb310b4ded..e14124f74b3a 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -195,6 +196,9 @@ #define ecap_max_handle_mask(e) ((e >> 20) & 0xf) #define ecap_sc_support(e) ((e >> 7) & 0x1) /* Snooping Control */ +/* Virtual command interface capability */ +#define vccap_pasid(v) (((v) & DMA_VCS_PAS)) /* PASID allocation */ + /* IOTLB_REG */ #define DMA_TLB_FLUSH_GRANU_OFFSET 60 #define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60) @@ -288,6 +292,7 @@ /* PRS_REG */ #define DMA_PRS_PPR ((u32)1) +#define DMA_VCS_PAS ((u64)1) #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ do { \ @@ -555,6 +560,7 @@ struct intel_iommu { u64 reg_size; /* size of hw register set */ u64 cap; u64 ecap; + u64 vccap; u32 gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */ raw_spinlock_t register_lock; /* protect register handling */ int seq_id; /* sequence id of the iommu */ @@ -575,6 +581,7 @@ struct intel_iommu { #ifdef CONFIG_INTEL_IOMMU_SVM struct page_req_dsc *prq; unsigned char prq_name[16]; /* Name for PRQ interrupt */ + struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */ #endif struct q_inval *qi; /* Queued invalidation info */ u32 *iommu_state; /* Store iommu states between suspend and resume.*/ -- cgit v1.2.3 From e85bb99b79ca5ad2681612a7bb22f94cc2c71866 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 16 May 2020 14:20:52 +0800 Subject: iommu/vt-d: Add get_domain_info() helper Add a get_domain_info() helper to retrieve the valid per-device iommu private data. Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20200516062101.29541-10-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index e14124f74b3a..caa179e806fc 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -714,6 +714,7 @@ int for_each_device_domain(int (*fn)(struct device_domain_info *info, void iommu_flush_write_buffer(struct intel_iommu *iommu); int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev); struct dmar_domain *find_domain(struct device *dev); +struct device_domain_info *get_domain_info(struct device *dev); #ifdef CONFIG_INTEL_IOMMU_SVM extern void intel_svm_check(struct intel_iommu *iommu); -- cgit v1.2.3 From 064a57d7ddfc46ada02b477b91c478001b03bfa3 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Sat, 16 May 2020 14:20:54 +0800 Subject: iommu/vt-d: Replace intel SVM APIs with generic SVA APIs This patch is an initial step to replace Intel SVM code with the following IOMMU SVA ops: intel_svm_bind_mm() => iommu_sva_bind_device() intel_svm_unbind_mm() => iommu_sva_unbind_device() intel_svm_is_pasid_valid() => iommu_sva_get_pasid() The features below will continue to work but are not included in this patch in that they are handled mostly within the IOMMU subsystem. - IO page fault - mmu notifier Consolidation of the above will come after merging generic IOMMU sva code[1]. There should not be any changes needed for SVA users such as accelerator device drivers during this time. [1] http://jpbrucker.net/sva/ Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20200516062101.29541-12-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 6 ++++ include/linux/intel-svm.h | 86 --------------------------------------------- 2 files changed, 6 insertions(+), 86 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index caa179e806fc..42245e1e1b48 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -723,6 +723,10 @@ extern int intel_svm_finish_prq(struct intel_iommu *iommu); int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, struct iommu_gpasid_bind_data *data); int intel_svm_unbind_gpasid(struct device *dev, int pasid); +struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, + void *drvdata); +void intel_svm_unbind(struct iommu_sva *handle); +int intel_svm_get_pasid(struct iommu_sva *handle); struct svm_dev_ops; struct intel_svm_dev { @@ -730,6 +734,8 @@ struct intel_svm_dev { struct rcu_head rcu; struct device *dev; struct svm_dev_ops *ops; + struct iommu_sva sva; + int pasid; int users; u16 did; u16 dev_iotlb:1; diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 1b47ca46373e..c9e7e601950d 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -21,7 +21,6 @@ struct svm_dev_ops { #define SVM_REQ_EXEC (1<<1) #define SVM_REQ_PRIV (1<<0) - /* * The SVM_FLAG_PRIVATE_PASID flag requests a PASID which is *not* the "main" * PASID for the current process. Even if a PASID already exists, a new one @@ -57,89 +56,4 @@ struct svm_dev_ops { */ #define SVM_FLAG_GUEST_PASID (1<<3) -#ifdef CONFIG_INTEL_IOMMU_SVM - -/** - * intel_svm_bind_mm() - Bind the current process to a PASID - * @dev: Device to be granted access - * @pasid: Address for allocated PASID - * @flags: Flags. Later for requesting supervisor mode, etc. - * @ops: Callbacks to device driver - * - * This function attempts to enable PASID support for the given device. - * If the @pasid argument is non-%NULL, a PASID is allocated for access - * to the MM of the current process. - * - * By using a %NULL value for the @pasid argument, this function can - * be used to simply validate that PASID support is available for the - * given device — i.e. that it is behind an IOMMU which has the - * requisite support, and is enabled. - * - * Page faults are handled transparently by the IOMMU code, and there - * should be no need for the device driver to be involved. If a page - * fault cannot be handled (i.e. is an invalid address rather than - * just needs paging in), then the page request will be completed by - * the core IOMMU code with appropriate status, and the device itself - * can then report the resulting fault to its driver via whatever - * mechanism is appropriate. - * - * Multiple calls from the same process may result in the same PASID - * being re-used. A reference count is kept. - */ -extern int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, - struct svm_dev_ops *ops); - -/** - * intel_svm_unbind_mm() - Unbind a specified PASID - * @dev: Device for which PASID was allocated - * @pasid: PASID value to be unbound - * - * This function allows a PASID to be retired when the device no - * longer requires access to the address space of a given process. - * - * If the use count for the PASID in question reaches zero, the - * PASID is revoked and may no longer be used by hardware. - * - * Device drivers are required to ensure that no access (including - * page requests) is currently outstanding for the PASID in question, - * before calling this function. - */ -extern int intel_svm_unbind_mm(struct device *dev, int pasid); - -/** - * intel_svm_is_pasid_valid() - check if pasid is valid - * @dev: Device for which PASID was allocated - * @pasid: PASID value to be checked - * - * This function checks if the specified pasid is still valid. A - * valid pasid means the backing mm is still having a valid user. - * For kernel callers init_mm is always valid. for other mm, if mm->mm_users - * is non-zero, it is valid. - * - * returns -EINVAL if invalid pasid, 0 if pasid ref count is invalid - * 1 if pasid is valid. - */ -extern int intel_svm_is_pasid_valid(struct device *dev, int pasid); - -#else /* CONFIG_INTEL_IOMMU_SVM */ - -static inline int intel_svm_bind_mm(struct device *dev, int *pasid, - int flags, struct svm_dev_ops *ops) -{ - return -ENOSYS; -} - -static inline int intel_svm_unbind_mm(struct device *dev, int pasid) -{ - BUG(); -} - -static inline int intel_svm_is_pasid_valid(struct device *dev, int pasid) -{ - return -EINVAL; -} -#endif /* CONFIG_INTEL_IOMMU_SVM */ - -#define intel_svm_available(dev) (!intel_svm_bind_mm((dev), NULL, 0, NULL)) - #endif /* __INTEL_SVM_H__ */ -- cgit v1.2.3 From 8a1d824625402b3ef3c3e5965663354ff0394d86 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 16 May 2020 14:20:55 +0800 Subject: iommu/vt-d: Multiple descriptors per qi_submit_sync() Current qi_submit_sync() only supports single invalidation descriptor per submission and appends wait descriptor after each submission to poll the hardware completion. This extends the qi_submit_sync() helper to support multiple descriptors, and add an option so that the caller could specify the Page-request Drain (PD) bit in the wait descriptor. Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20200516062101.29541-13-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 42245e1e1b48..677dee59e3c0 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -333,6 +333,7 @@ enum { #define QI_IWD_STATUS_DATA(d) (((u64)d) << 32) #define QI_IWD_STATUS_WRITE (((u64)1) << 5) +#define QI_IWD_PRQ_DRAIN (((u64)1) << 7) #define QI_IOTLB_DID(did) (((u64)did) << 16) #define QI_IOTLB_DR(dr) (((u64)dr) << 7) @@ -702,7 +703,13 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, int pasid); -extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu); +int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc, + unsigned int count, unsigned long options); +/* + * Options used in qi_submit_sync: + * QI_OPT_WAIT_DRAIN - Wait for PRQ drain completion, spec 6.5.2.8. + */ +#define QI_OPT_WAIT_DRAIN BIT(0) extern int dmar_ir_support(void); -- cgit v1.2.3 From 66ac4db36f4c12a3b02db864ccb0801cd938b6de Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 16 May 2020 14:20:58 +0800 Subject: iommu/vt-d: Add page request draining support When a PASID is stopped or terminated, there can be pending PRQs (requests that haven't received responses) in remapping hardware. This adds the interface to drain page requests and call it when a PASID is terminated. Signed-off-by: Jacob Pan Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20200516062101.29541-16-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 677dee59e3c0..21633cee6331 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -292,6 +292,8 @@ /* PRS_REG */ #define DMA_PRS_PPR ((u32)1) +#define DMA_PRS_PRO ((u32)2) + #define DMA_VCS_PAS ((u64)1) #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ @@ -333,6 +335,7 @@ enum { #define QI_IWD_STATUS_DATA(d) (((u64)d) << 32) #define QI_IWD_STATUS_WRITE (((u64)1) << 5) +#define QI_IWD_FENCE (((u64)1) << 6) #define QI_IWD_PRQ_DRAIN (((u64)1) << 7) #define QI_IOTLB_DID(did) (((u64)did) << 16) @@ -582,6 +585,7 @@ struct intel_iommu { #ifdef CONFIG_INTEL_IOMMU_SVM struct page_req_dsc *prq; unsigned char prq_name[16]; /* Name for PRQ interrupt */ + struct completion prq_complete; struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */ #endif struct q_inval *qi; /* Queued invalidation info */ -- cgit v1.2.3 From 81530a38a36d411e01ea99116503901f75aa758b Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Fri, 15 May 2020 11:05:15 +0300 Subject: phy: omap-usb2: Clean up exported header Move private definitions from header to phy-omap-usb2.c file. Get rid of unused data structures usb_dpll_params and omap_usb_phy_type. Signed-off-by: Roger Quadros Link: https://lore.kernel.org/r/20200515080518.26870-2-rogerq@ti.com Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/omap_usb.h | 69 ++------------------------------------------ 1 file changed, 2 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy/omap_usb.h b/include/linux/phy/omap_usb.h index 5973a6313529..e23b52df93ec 100644 --- a/include/linux/phy/omap_usb.h +++ b/include/linux/phy/omap_usb.h @@ -2,68 +2,14 @@ /* * omap_usb.h -- omap usb2 phy header file * - * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2012-2020 Texas Instruments Incorporated - http://www.ti.com * Author: Kishon Vijay Abraham I */ #ifndef __DRIVERS_OMAP_USB2_H #define __DRIVERS_OMAP_USB2_H -#include -#include - -struct usb_dpll_params { - u16 m; - u8 n; - u8 freq:3; - u8 sd; - u32 mf; -}; - -enum omap_usb_phy_type { - TYPE_USB2, /* USB2_PHY, power down in CONTROL_DEV_CONF */ - TYPE_DRA7USB2, /* USB2 PHY, power and power_aux e.g. DRA7 */ - TYPE_AM437USB2, /* USB2 PHY, power e.g. AM437x */ -}; - -struct omap_usb { - struct usb_phy phy; - struct phy_companion *comparator; - void __iomem *pll_ctrl_base; - void __iomem *phy_base; - struct device *dev; - struct device *control_dev; - struct clk *wkupclk; - struct clk *optclk; - u8 flags; - enum omap_usb_phy_type type; - struct regmap *syscon_phy_power; /* ctrl. reg. acces */ - unsigned int power_reg; /* power reg. index within syscon */ - u32 mask; - u32 power_on; - u32 power_off; -}; - -struct usb_phy_data { - const char *label; - u8 flags; - u32 mask; - u32 power_on; - u32 power_off; -}; - -/* Driver Flags */ -#define OMAP_USB2_HAS_START_SRP (1 << 0) -#define OMAP_USB2_HAS_SET_VBUS (1 << 1) -#define OMAP_USB2_CALIBRATE_FALSE_DISCONNECT (1 << 2) - -#define OMAP_DEV_PHY_PD BIT(0) -#define OMAP_USB2_PHY_PD BIT(28) - -#define AM437X_USB2_PHY_PD BIT(0) -#define AM437X_USB2_OTG_PD BIT(1) -#define AM437X_USB2_OTGVDET_EN BIT(19) -#define AM437X_USB2_OTGSESSEND_EN BIT(20) +#include #define phy_to_omapusb(x) container_of((x), struct omap_usb, phy) @@ -76,15 +22,4 @@ static inline int omap_usb2_set_comparator(struct phy_companion *comparator) } #endif -static inline u32 omap_usb_readl(void __iomem *addr, unsigned offset) -{ - return __raw_readl(addr + offset); -} - -static inline void omap_usb_writel(void __iomem *addr, unsigned offset, - u32 data) -{ - __raw_writel(data, addr + offset); -} - #endif /* __DRIVERS_OMAP_USB_H */ -- cgit v1.2.3 From ca4faf543a33373bed3650812d5f0cd0bd295b1a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 2 May 2020 10:37:44 -0400 Subject: SUNRPC: Move xpt_mutex into socket xpo_sendto methods It appears that the RPC/RDMA transport does not need serialization of calls to its xpo_sendto method. Move the mutex into the socket methods that still need that serialization. Tail latencies are unambiguously better with this patch applied. fio randrw 8KB 70/30 on NFSv3, smaller numbers are better: clat percentiles (usec): With xpt_mutex: r | 99.99th=[ 8848] w | 99.99th=[ 9634] Without xpt_mutex: r | 99.99th=[ 8586] w | 99.99th=[ 8979] Serializing the construction of RPC/RDMA transport headers is not really necessary at this point, because the Linux NFS server implementation never changes its credit grant on a connection. If that should change, then svc_rdma_sendto will need to serialize access to the transport's credit grant fields. Reported-by: kbuild test robot [ cel: fix uninitialized variable warning ] Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_xprt.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 9e1e046de176..aca35ab5cff2 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -117,6 +117,12 @@ static inline int register_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u return 0; } +static inline bool svc_xprt_is_dead(const struct svc_xprt *xprt) +{ + return (test_bit(XPT_DEAD, &xprt->xpt_flags) != 0) || + (test_bit(XPT_CLOSE, &xprt->xpt_flags) != 0); +} + int svc_reg_xprt_class(struct svc_xprt_class *); void svc_unreg_xprt_class(struct svc_xprt_class *); void svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *, -- cgit v1.2.3 From ea740bd5f58e2912e74f401fd01a9d6aa985ca05 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 20 Mar 2020 17:32:41 -0400 Subject: svcrdma: Fix backchannel return code Way back when I was writing the RPC/RDMA server-side backchannel code, I misread the TCP backchannel reply handler logic. When svc_tcp_recvfrom() successfully receives a backchannel reply, it does not return -EAGAIN. It sets XPT_DATA and returns zero. Update svc_rdma_recvfrom() to return zero. Here, XPT_DATA doesn't need to be set again: it is set whenever a new message is received, behind a spin lock in a single threaded context. Also, if handling the cb reply is not successful, the message is simply dropped. There's no special message framing to deal with as there is in the TCP case. Now that the handle_bc_reply() return value is ignored, I've removed the dprintk call sites in the error exit of handle_bc_reply() in favor of trace points in other areas that already report the error cases. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index cbcfbd0521e3..8518c3f37e56 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -160,9 +160,8 @@ struct svc_rdma_send_ctxt { }; /* svc_rdma_backchannel.c */ -extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, - __be32 *rdma_resp, - struct xdr_buf *rcvbuf); +extern void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *rctxt); /* svc_rdma_recvfrom.c */ extern void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma); -- cgit v1.2.3 From 08e3c9f181bfb78d842c4f432888116d66e07c2f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Apr 2020 16:00:12 -0400 Subject: svcrdma: Remove the SVCRDMA_DEBUG macro Clean up: Commit d21b05f101ae ("rdma: SVCRMDA Header File") introduced the SVCRDMA_DEBUG macro, but it doesn't seem to have been used. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 8518c3f37e56..7ed82625dc0b 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -48,7 +48,6 @@ #include #include #include -#define SVCRDMA_DEBUG /* Default and maximum inline threshold sizes */ enum { -- cgit v1.2.3 From 02648908d19a99532b0839959e38ae53d95d2798 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 17 Mar 2020 14:12:15 -0400 Subject: SUNRPC: Rename svc_sock::sk_reclen Clean up. I find the name of the svc_sock::sk_reclen field confusing, so I've changed it to better reflect its function. This field is not read directly to get the record length. Rather, it is a buffer containing a record marker that needs to be decoded. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svcsock.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 771baadaee9d..b7ac7fe68306 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -28,7 +28,7 @@ struct svc_sock { /* private TCP part */ /* On-the-wire fragment header: */ - __be32 sk_reclen; + __be32 sk_marker; /* As we receive a record, this includes the length received so * far (including the fragment header): */ u32 sk_tcplen; @@ -41,12 +41,12 @@ struct svc_sock { static inline u32 svc_sock_reclen(struct svc_sock *svsk) { - return ntohl(svsk->sk_reclen) & RPC_FRAGMENT_SIZE_MASK; + return be32_to_cpu(svsk->sk_marker) & RPC_FRAGMENT_SIZE_MASK; } static inline u32 svc_sock_final_rec(struct svc_sock *svsk) { - return ntohl(svsk->sk_reclen) & RPC_LAST_STREAM_FRAGMENT; + return be32_to_cpu(svsk->sk_marker) & RPC_LAST_STREAM_FRAGMENT; } /* -- cgit v1.2.3 From 356d411c26735bcc62718c4c9181014255dc302d Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Fri, 15 May 2020 15:16:52 -0700 Subject: net/mlx5: Cleanup mlx5_ifc_fte_match_set_misc2_bits Remove the "metadata_reg_b" field and all uses of this field in code to match the device specification. As this field is not in use in SW steering it is safe to remove it. Signed-off-by: Raed Salem Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c9dd6e99ad56..fd8da4875ea0 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -584,9 +584,7 @@ struct mlx5_ifc_fte_match_set_misc2_bits { u8 metadata_reg_a[0x20]; - u8 metadata_reg_b[0x20]; - - u8 reserved_at_1c0[0x40]; + u8 reserved_at_1a0[0x60]; }; struct mlx5_ifc_fte_match_set_misc3_bits { -- cgit v1.2.3 From 555af0c3fa0b632be73c241cc932129af4b70d27 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 15 May 2020 15:16:53 -0700 Subject: net/mlx5: Move iseg access helper routines close to mlx5_core driver Only mlx5_core driver handles fw initialization check and command interface revision check. Hence move them inside the mlx5_core driver where it is used. This avoid exposing these helpers to all mlx5 drivers. Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 24e04901f92e..a988eb405aa6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -823,11 +823,6 @@ static inline u16 fw_rev_sub(struct mlx5_core_dev *dev) return ioread32be(&dev->iseg->cmdif_rev_fw_sub) & 0xffff; } -static inline u16 cmdif_rev(struct mlx5_core_dev *dev) -{ - return ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16; -} - static inline u32 mlx5_base_mkey(const u32 key) { return key & 0xffffff00u; @@ -1012,11 +1007,6 @@ int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index, u8 roce_version, u8 roce_l3_type, const u8 *gid, const u8 *mac, bool vlan, u16 vlan_id, u8 port_num); -static inline int fw_initializing(struct mlx5_core_dev *dev) -{ - return ioread32be(&dev->iseg->initializing) >> 31; -} - static inline u32 mlx5_mkey_to_idx(u32 mkey) { return mkey >> 8; -- cgit v1.2.3 From 51189c7a7ed1b4ed4493e27275d466ff60406d3a Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 15 May 2020 14:11:05 +0100 Subject: arm64: scs: Store absolute SCS stack pointer value in thread_info Storing the SCS information in thread_info as a {base,offset} pair introduces an additional load instruction on the ret-to-user path, since the SCS stack pointer in x18 has to be converted back to an offset by subtracting the base. Replace the offset with the absolute SCS stack pointer value instead and avoid the redundant load. Tested-by: Sami Tolvanen Reviewed-by: Mark Rutland Signed-off-by: Will Deacon --- include/linux/scs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scs.h b/include/linux/scs.h index 3f3662621a27..0eb2485ef832 100644 --- a/include/linux/scs.h +++ b/include/linux/scs.h @@ -27,7 +27,7 @@ #define SCS_END_MAGIC (0x5f6UL + POISON_POINTER_DELTA) #define task_scs(tsk) (task_thread_info(tsk)->scs_base) -#define task_scs_offset(tsk) (task_thread_info(tsk)->scs_offset) +#define task_scs_sp(tsk) (task_thread_info(tsk)->scs_sp) void scs_init(void); int scs_prepare(struct task_struct *tsk, int node); @@ -39,7 +39,7 @@ static inline void scs_task_reset(struct task_struct *tsk) * Reset the shadow stack to the base address in case the task * is reused. */ - task_scs_offset(tsk) = 0; + task_scs_sp(tsk) = task_scs(tsk); } static inline unsigned long *__scs_magic(void *s) @@ -50,9 +50,9 @@ static inline unsigned long *__scs_magic(void *s) static inline bool scs_corrupted(struct task_struct *tsk) { unsigned long *magic = __scs_magic(task_scs(tsk)); + unsigned long sz = task_scs_sp(tsk) - task_scs(tsk); - return (task_scs_offset(tsk) >= SCS_SIZE - 1 || - READ_ONCE_NOCHECK(*magic) != SCS_END_MAGIC); + return sz >= SCS_SIZE - 1 || READ_ONCE_NOCHECK(*magic) != SCS_END_MAGIC; } #else /* CONFIG_SHADOW_CALL_STACK */ -- cgit v1.2.3 From 88485be531f4aee841ddc53b56e2f6e6a338854d Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 15 May 2020 14:56:05 +0100 Subject: scs: Move scs_overflow_check() out of architecture code There is nothing architecture-specific about scs_overflow_check() as it's just a trivial wrapper around scs_corrupted(). For parity with task_stack_end_corrupted(), rename scs_corrupted() to task_scs_end_corrupted() and call it from schedule_debug() when CONFIG_SCHED_STACK_END_CHECK_is enabled, which better reflects its purpose as a debug feature to catch inadvertent overflow of the SCS. Finally, remove the unused scs_overflow_check() function entirely. This has absolutely no impact on architectures that do not support SCS (currently arm64 only). Tested-by: Sami Tolvanen Reviewed-by: Mark Rutland Signed-off-by: Will Deacon --- include/linux/scs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scs.h b/include/linux/scs.h index 0eb2485ef832..2fd3df50e93e 100644 --- a/include/linux/scs.h +++ b/include/linux/scs.h @@ -47,7 +47,7 @@ static inline unsigned long *__scs_magic(void *s) return (unsigned long *)(s + SCS_SIZE) - 1; } -static inline bool scs_corrupted(struct task_struct *tsk) +static inline bool task_scs_end_corrupted(struct task_struct *tsk) { unsigned long *magic = __scs_magic(task_scs(tsk)); unsigned long sz = task_scs_sp(tsk) - task_scs(tsk); @@ -60,8 +60,8 @@ static inline bool scs_corrupted(struct task_struct *tsk) static inline void scs_init(void) {} static inline void scs_task_reset(struct task_struct *tsk) {} static inline int scs_prepare(struct task_struct *tsk, int node) { return 0; } -static inline bool scs_corrupted(struct task_struct *tsk) { return false; } static inline void scs_release(struct task_struct *tsk) {} +static inline bool task_scs_end_corrupted(struct task_struct *tsk) { return false; } #endif /* CONFIG_SHADOW_CALL_STACK */ -- cgit v1.2.3 From 871e100e432c651c9c46fb9c3184b4577e0de3ae Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 15 May 2020 16:17:12 +0100 Subject: scs: Move DEFINE_SCS macro into core code Defining static shadow call stacks is not architecture-specific, so move the DEFINE_SCS() macro into the core header file. Tested-by: Sami Tolvanen Reviewed-by: Mark Rutland Signed-off-by: Will Deacon --- include/linux/scs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scs.h b/include/linux/scs.h index 2fd3df50e93e..6dec390cf154 100644 --- a/include/linux/scs.h +++ b/include/linux/scs.h @@ -26,6 +26,10 @@ /* An illegal pointer value to mark the end of the shadow stack. */ #define SCS_END_MAGIC (0x5f6UL + POISON_POINTER_DELTA) +/* Allocate a static per-CPU shadow stack */ +#define DEFINE_SCS(name) \ + DEFINE_PER_CPU(unsigned long [SCS_SIZE/sizeof(long)], name) \ + #define task_scs(tsk) (task_thread_info(tsk)->scs_base) #define task_scs_sp(tsk) (task_thread_info(tsk)->scs_sp) -- cgit v1.2.3 From 220995622da5317714b5fe659165735f7b44b87e Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Thu, 7 May 2020 13:08:46 -0700 Subject: kgdboc: Add kgdboc_earlycon to support early kgdb using boot consoles We want to enable kgdb to debug the early parts of the kernel. Unfortunately kgdb normally is a client of the tty API in the kernel and serial drivers don't register to the tty layer until fairly late in the boot process. Serial drivers do, however, commonly register a boot console. Let's enable the kgdboc driver to work with boot consoles to provide early debugging. This change co-opts the existing read() function pointer that's part of "struct console". It's assumed that if a boot console (with the flag CON_BOOT) has implemented read() that both the read() and write() function are polling functions. That means they work without interrupts and read() will return immediately (with 0 bytes read) if there's nothing to read. This should be a safe assumption since it appears that no current boot consoles implement read() right now and there seems no reason to do so unless they wanted to support "kgdboc_earlycon". The normal/expected way to make all this work is to use "kgdboc_earlycon" and "kgdboc" together. You should point them both to the same physical serial connection. At boot time, as the system transitions from the boot console to the normal console (and registers a tty), kgdb will switch over. One awkward part of all this, though, is that there can be a window where the boot console goes away and we can't quite transtion over to the main kgdboc that uses the tty layer. There are two main problems: 1. The act of registering the tty doesn't cause any call into kgdboc so there is a window of time when the tty is there but kgdboc's init code hasn't been called so we can't transition to it. 2. On some serial drivers the normal console inits (and replaces the boot console) quite early in the system. Presumably these drivers were coded up before earlycon worked as well as it does today and probably they don't need to do this anymore, but it causes us problems nontheless. Problem #1 is not too big of a deal somewhat due to the luck of probe ordering. kgdboc is last in the tty/serial/Makefile so its probe gets right after all other tty devices. It's not fun to rely on this, but it does work for the most part. Problem #2 is a big deal, but only for some serial drivers. Other serial drivers end up registering the console (which gets rid of the boot console) and tty at nearly the same time. The way we'll deal with the window when the system has stopped using the boot console and the time when we're setup using the tty is to keep using the boot console. This may sound surprising, but it has been found to work well in practice. If it doesn't work, it shouldn't be too hard for a given serial driver to make it keep working. Specifically, it's expected that the read()/write() function provided in the boot console should be the same (or nearly the same) as the normal kgdb polling functions. That means continuing to use them should work just fine. To make things even more likely to work work we'll also trap the recently added exit() function in the boot console we're using and delay any calls to it until we're all done with the boot console. NOTE: there could be ways to use all this in weird / unexpected ways. If you do something like this, it's a bit of a buyer beware situation. Specifically: - If you specify only "kgdboc_earlycon" but not "kgdboc" then (depending on your serial driver) things will probably work OK, but you'll get a warning printed the first time you use kgdb after the boot console is gone. You'd only be able to do this, of course, if the serial driver you're running atop provided an early boot console. - If your "kgdboc_earlycon" and "kgdboc" devices are not the same device things should work OK, but it'll be your job to switch over which device you're monitoring (including figuring out how to switch over gdb in-flight if you're using it). When trying to enable "kgdboc_earlycon" it should be noted that the names that are registered through the boot console layer and the tty layer are not the same for the same port. For example when debugging on one board I'd need to pass "kgdboc_earlycon=qcom_geni kgdboc=ttyMSM0" to enable things properly. Since digging up the boot console name is a pain and there will rarely be more than one boot console enabled, you can provide the "kgdboc_earlycon" parameter without specifying the name of the boot console. In this case we'll just pick the first boot that implements read() that we find. This new "kgdboc_earlycon" parameter should be contrasted to the existing "ekgdboc" parameter. While both provide a way to debug very early, the usage and mechanisms are quite different. Specifically "kgdboc_earlycon" is meant to be used in tandem with "kgdboc" and there is a transition from one to the other. The "ekgdboc" parameter, on the other hand, replaces the "kgdboc" parameter. It runs the same logic as the "kgdboc" parameter but just relies on your TTY driver being present super early. The only known usage of the old "ekgdboc" parameter is documented as "ekgdboc=kbd earlyprintk=vga". It should be noted that "kbd" has special treatment allowing it to init early as a tty device. Signed-off-by: Douglas Anderson Reviewed-by: Greg Kroah-Hartman Tested-by: Sumit Garg Link: https://lore.kernel.org/r/20200507130644.v4.8.I8fba5961bf452ab92350654aa61957f23ecf0100@changeid Signed-off-by: Daniel Thompson --- include/linux/kgdb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index c2caee08e418..c62d76478adc 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -269,6 +269,9 @@ struct kgdb_arch { * @write_char: Pointer to a function that will write one char. * @flush: Pointer to a function that will flush any pending writes. * @init: Pointer to a function that will initialize the device. + * @deinit: Pointer to a function that will deinit the device. Implies that + * this I/O driver is temporary and expects to be replaced. Called when + * an I/O driver is replaced or explicitly unregistered. * @pre_exception: Pointer to a function that will do any prep work for * the I/O driver. * @post_exception: Pointer to a function that will do any cleanup work @@ -282,6 +285,7 @@ struct kgdb_io { void (*write_char) (u8); void (*flush) (void); int (*init) (void); + void (*deinit) (void); void (*pre_exception) (void); void (*post_exception) (void); int is_console; -- cgit v1.2.3 From a307593a644443db12888f45eed0dafb5869e2cc Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Mon, 18 May 2020 15:23:59 -0700 Subject: net: phy: simplify phy_link_change arguments This function was introduced to allow for different handling of link up and link down events particularly with regard to the netif_carrier. The third argument do_carrier allowed the flag to be left unchanged. Since then the phylink has introduced an implementation that completely ignores the third parameter since it never wants to change the flag and the phylib always sets the third parameter to true so the flag is always changed. Therefore the third argument (i.e. do_carrier) is no longer necessary and can be removed. This also means that the phylib phy_link_down() function no longer needs its second argument. Signed-off-by: Doug Berger Signed-off-by: David S. Miller --- include/linux/phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 5d8ff5428010..467aa8bf9f64 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -543,7 +543,7 @@ struct phy_device { u8 mdix; u8 mdix_ctrl; - void (*phy_link_change)(struct phy_device *, bool up, bool do_carrier); + void (*phy_link_change)(struct phy_device *phydev, bool up); void (*adjust_link)(struct net_device *dev); #if IS_ENABLED(CONFIG_MACSEC) -- cgit v1.2.3 From ed318a6cc0b620440e65f48eb527dc3df7269ce4 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 May 2020 16:32:50 -0700 Subject: fscrypt: support test_dummy_encryption=v2 v1 encryption policies are deprecated in favor of v2, and some new features (e.g. encryption+casefolding) are only being added for v2. Therefore, the "test_dummy_encryption" mount option (which is used for encryption I/O testing with xfstests) needs to support v2 policies. To do this, extend its syntax to be "test_dummy_encryption=v1" or "test_dummy_encryption=v2". The existing "test_dummy_encryption" (no argument) also continues to be accepted, to specify the default setting -- currently v1, but the next patch changes it to v2. To cleanly support both v1 and v2 while also making it easy to support specifying other encryption settings in the future (say, accepting "$contents_mode:$filenames_mode:v2"), make ext4 and f2fs maintain a pointer to the dummy fscrypt_context rather than using mount flags. To avoid concurrency issues, don't allow test_dummy_encryption to be set or changed during a remount. (The former restriction is new, but xfstests doesn't run into it, so no one should notice.) Tested with 'gce-xfstests -c {ext4,f2fs}/encrypt -g auto'. On ext4, there are two regressions, both of which are test bugs: ext4/023 and ext4/028 fail because they set an xattr and expect it to be stored inline, but the increase in size of the fscrypt_context from 24 to 40 bytes causes this xattr to be spilled into an external block. Link: https://lore.kernel.org/r/20200512233251.118314-4-ebiggers@kernel.org Acked-by: Jaegeuk Kim Reviewed-by: Theodore Ts'o Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 51 ++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 44 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 0e0c7ad19383..2862ca5fea33 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -15,12 +15,15 @@ #include #include +#include #include #include #define FS_CRYPTO_BLOCK_SIZE 16 +union fscrypt_context; struct fscrypt_info; +struct seq_file; struct fscrypt_str { unsigned char *name; @@ -59,7 +62,8 @@ struct fscrypt_operations { int (*get_context)(struct inode *inode, void *ctx, size_t len); int (*set_context)(struct inode *inode, const void *ctx, size_t len, void *fs_data); - bool (*dummy_context)(struct inode *inode); + const union fscrypt_context *(*get_dummy_context)( + struct super_block *sb); bool (*empty_dir)(struct inode *inode); unsigned int max_namelen; bool (*has_stable_inodes)(struct super_block *sb); @@ -89,10 +93,12 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode); } -static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +static inline const union fscrypt_context * +fscrypt_get_dummy_context(struct super_block *sb) { - return inode->i_sb->s_cop->dummy_context && - inode->i_sb->s_cop->dummy_context(inode); + if (!sb->s_cop->get_dummy_context) + return NULL; + return sb->s_cop->get_dummy_context(sb); } /* @@ -145,6 +151,22 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child); int fscrypt_inherit_context(struct inode *parent, struct inode *child, void *fs_data, bool preload); +struct fscrypt_dummy_context { + const union fscrypt_context *ctx; +}; + +int fscrypt_set_test_dummy_encryption(struct super_block *sb, + const substring_t *arg, + struct fscrypt_dummy_context *dummy_ctx); +void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, + struct super_block *sb); +static inline void +fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx) +{ + kfree(dummy_ctx->ctx); + dummy_ctx->ctx = NULL; +} + /* keyring.c */ void fscrypt_sb_free(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); @@ -219,9 +241,10 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) return false; } -static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +static inline const union fscrypt_context * +fscrypt_get_dummy_context(struct super_block *sb) { - return false; + return NULL; } static inline void fscrypt_handle_d_move(struct dentry *dentry) @@ -316,6 +339,20 @@ static inline int fscrypt_inherit_context(struct inode *parent, return -EOPNOTSUPP; } +struct fscrypt_dummy_context { +}; + +static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq, + char sep, + struct super_block *sb) +{ +} + +static inline void +fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx) +{ +} + /* keyring.c */ static inline void fscrypt_sb_free(struct super_block *sb) { @@ -677,7 +714,7 @@ static inline int fscrypt_prepare_symlink(struct inode *dir, unsigned int max_len, struct fscrypt_str *disk_link) { - if (IS_ENCRYPTED(dir) || fscrypt_dummy_context_enabled(dir)) + if (IS_ENCRYPTED(dir) || fscrypt_get_dummy_context(dir->i_sb) != NULL) return __fscrypt_prepare_symlink(dir, len, max_len, disk_link); disk_link->name = (unsigned char *)target; -- cgit v1.2.3 From 5cab3ff2489ede5abffa6ad730708e087dc45a4d Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 19 May 2020 01:43:18 +0800 Subject: soundwire: bus: rename sdw_bus_master_add/delete, add arguments In preparation for future extensions, rename functions to use sdw_bus_master prefix and add a parent and fwnode argument to sdw_bus_master_add to help with device registration in follow-up patches. No functionality change, just renames and additional arguments. The Intel code is currently unused, the two additional arguments are only needed for compilation. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Acked-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20200518174322.31561-2-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 00f5826092e3..2003e8c55538 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -832,8 +832,9 @@ struct sdw_bus { bool multi_link; }; -int sdw_add_bus_master(struct sdw_bus *bus); -void sdw_delete_bus_master(struct sdw_bus *bus); +int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, + struct fwnode_handle *fwnode); +void sdw_bus_master_delete(struct sdw_bus *bus); /** * sdw_port_config: Master or Slave Port configuration -- cgit v1.2.3 From 90acca1d54ad566b4af5f1030b4a4a2420ce2ef0 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 19 May 2020 01:43:19 +0800 Subject: soundwire: bus_type: introduce sdw_slave_type and sdw_master_type this is a preparatory patch before the introduction of the sdw_master_type. The SoundWire slave support is slightly modified with the use of a sdw_slave_type, and the uevent handling move to slave.c (since it's not necessary for the master). No functionality change other than moving code around. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Acked-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20200518174322.31561-3-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_type.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_type.h b/include/linux/soundwire/sdw_type.h index aaa7f4267c14..52eb66cd11bc 100644 --- a/include/linux/soundwire/sdw_type.h +++ b/include/linux/soundwire/sdw_type.h @@ -5,6 +5,13 @@ #define __SOUNDWIRE_TYPES_H extern struct bus_type sdw_bus_type; +extern struct device_type sdw_slave_type; +extern struct device_type sdw_master_type; + +static inline int is_sdw_slave(const struct device *dev) +{ + return dev->type == &sdw_slave_type; +} #define drv_to_sdw_driver(_drv) container_of(_drv, struct sdw_driver, driver) @@ -14,7 +21,7 @@ extern struct bus_type sdw_bus_type; int __sdw_register_driver(struct sdw_driver *drv, struct module *owner); void sdw_unregister_driver(struct sdw_driver *drv); -int sdw_slave_modalias(const struct sdw_slave *slave, char *buf, size_t size); +int sdw_slave_uevent(struct device *dev, struct kobj_uevent_env *env); /** * module_sdw_driver() - Helper macro for registering a Soundwire driver -- cgit v1.2.3 From dbb50c7a9949506f750d59d9ba4d58f0ce8ccd42 Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Tue, 19 May 2020 01:43:20 +0800 Subject: soundwire: bus: add unique bus id Adding an unique id for each bus. Suggested-by: Vinod Koul Signed-off-by: Bard Liao Acked-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20200518174322.31561-4-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 2003e8c55538..a32cb26f1815 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -789,6 +789,7 @@ struct sdw_master_ops { * struct sdw_bus - SoundWire bus * @dev: Master linux device * @link_id: Link id number, can be 0 to N, unique for each Master + * @id: bus system-wide unique id * @slaves: list of Slaves on this bus * @assigned: Bitmap for Slave device numbers. * Bit set implies used number, bit clear implies unused number. @@ -813,6 +814,7 @@ struct sdw_master_ops { struct sdw_bus { struct device *dev; unsigned int link_id; + int id; struct list_head slaves; DECLARE_BITMAP(assigned, SDW_MAX_DEVICES); struct mutex bus_lock; -- cgit v1.2.3 From 7ceaa40b930e462ba0477ca6af34ec04d08181dc Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 19 May 2020 01:43:21 +0800 Subject: soundwire: bus_type: add sdw_master_device support In the existing SoundWire code, Master Devices are not explicitly represented - only SoundWire Slave Devices are exposed (the use of capital letters follows the SoundWire specification conventions). With the existing code, the bus is handled without using a proper device, and bus->dev typically points to a platform device. The right thing to do as discussed in multiple reviews is use a device for each bus. The sdw_master_device addition is done with minimal internal plumbing and not exposed externally. The existing API based on sdw_bus_master_add() and sdw_bus_master_delete() will deal with the sdw_master_device life cycle, which minimizes changes to existing drivers. Note that the Intel code will be modified in follow-up patches (no impact on any platform since the connection with ASoC is not supported upstream so far). Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Acked-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20200518174322.31561-5-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index a32cb26f1815..7658d9698dd5 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -632,6 +632,19 @@ struct sdw_slave { #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev) +/** + * struct sdw_master_device - SoundWire 'Master Device' representation + * @dev: Linux device for this Master + * @bus: Bus handle shortcut + */ +struct sdw_master_device { + struct device dev; + struct sdw_bus *bus; +}; + +#define dev_to_sdw_master_device(d) \ + container_of(d, struct sdw_master_device, dev) + struct sdw_driver { const char *name; @@ -787,7 +800,8 @@ struct sdw_master_ops { /** * struct sdw_bus - SoundWire bus - * @dev: Master linux device + * @dev: Shortcut to &bus->md->dev to avoid changing the entire code. + * @md: Master device * @link_id: Link id number, can be 0 to N, unique for each Master * @id: bus system-wide unique id * @slaves: list of Slaves on this bus @@ -813,6 +827,7 @@ struct sdw_master_ops { */ struct sdw_bus { struct device *dev; + struct sdw_master_device *md; unsigned int link_id; int id; struct list_head slaves; -- cgit v1.2.3 From 2318976619daf0e868de5b8aff19c1fd8d585867 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Thu, 14 May 2020 11:36:41 +0100 Subject: ARM: 8976/1: module: allow arch overrides for .init section names ARM stores unwind information for .init.text in sections named .ARM.extab.init.text and .ARM.exidx.init.text. Since those aren't currently recognized as init sections, they're allocated along with the core section, and relocation fails if the core and the init section are allocated from different regions and can't reach other. final section addresses: ... 0x7f800000 .init.text .. 0xcbb54078 .ARM.exidx.init.text .. section 16 reloc 0 sym '': relocation 42 out of range (0xcbb54078 -> 0x7f800000) Allow architectures to override the section name so that ARM can fix this. Acked-by: Jessica Yu Signed-off-by: Vincent Whitchurch Signed-off-by: Russell King --- include/linux/moduleloader.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index ca92aea8a6bd..4fa67a8b2265 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -29,6 +29,11 @@ void *module_alloc(unsigned long size); /* Free memory returned from module_alloc. */ void module_memfree(void *module_region); +/* Determines if the section name is an init section (that is only used during + * module loading). + */ +bool module_init_section(const char *name); + /* Determines if the section name is an exit section (that is only used during * module unloading) */ -- cgit v1.2.3 From 333cff6c963fbc8b9820ca2b6a8b2e22a572cd43 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 29 Apr 2020 12:36:39 +0200 Subject: powercap/drivers/idle_inject: Specify idle state max latency Currently the idle injection framework uses the play_idle() function which puts the current CPU in an idle state. The idle state is the deepest one, as specified by the latency constraint when calling the subsequent play_idle_precise() function with the INT_MAX. The idle_injection is used by the cpuidle_cooling device which computes the idle / run duration to mitigate the temperature by injecting idle cycles. The cooling device has no control on the depth of the idle state. Allow finer control of the idle injection mechanism by allowing to specify the latency for the idle state. Thus the cooling device has the ability to have a guarantee on the exit latency of the idle states it is injecting. Acked-by: Rafael J. Wysocki Signed-off-by: Daniel Lezcano Reviewed-by: Amit Kucheria Link: https://lore.kernel.org/r/20200429103644.5492-1-daniel.lezcano@linaro.org --- include/linux/idle_inject.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/idle_inject.h b/include/linux/idle_inject.h index a445cd1a36c5..91a8612b8bf9 100644 --- a/include/linux/idle_inject.h +++ b/include/linux/idle_inject.h @@ -26,4 +26,8 @@ void idle_inject_set_duration(struct idle_inject_device *ii_dev, void idle_inject_get_duration(struct idle_inject_device *ii_dev, unsigned int *run_duration_us, unsigned int *idle_duration_us); + +void idle_inject_set_latency(struct idle_inject_device *ii_dev, + unsigned int latency_ns); + #endif /* __IDLE_INJECT_H__ */ -- cgit v1.2.3 From dfd0bda3703cdaf1fccd5da72cb7101a4fedfe68 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 29 Apr 2020 12:36:41 +0200 Subject: thermal/drivers/cpuidle_cooling: Change the registration function Today, there is no user for the cpuidle cooling device. The targetted platform is ARM and ARM64. The cpuidle and the cpufreq cooling device are based on the device tree. As the cpuidle cooling device can have its own configuration depending on the platform and the available idle states. The DT node description will give the optional properties to set the cooling device up. Do no longer rely on the CPU node which is prone to error and will lead to a confusion in the DT because the cpufreq cooling device is also using it. Let initialize the cpuidle cooling device with the DT binding. This was tested on: - hikey960 - hikey6220 - rock960 - db845c Acked-by: Viresh Kumar Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Reviewed-by: Amit Kucheria Tested-by: Amit Kucheria Link: https://lore.kernel.org/r/20200429103644.5492-3-daniel.lezcano@linaro.org --- include/linux/cpu_cooling.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index 65501d8f9778..a3bdc8a98f2c 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -63,18 +63,10 @@ of_cpufreq_cooling_register(struct cpufreq_policy *policy) struct cpuidle_driver; #ifdef CONFIG_CPU_IDLE_THERMAL -int cpuidle_cooling_register(struct cpuidle_driver *drv); -int cpuidle_of_cooling_register(struct device_node *np, - struct cpuidle_driver *drv); +void cpuidle_cooling_register(struct cpuidle_driver *drv); #else /* CONFIG_CPU_IDLE_THERMAL */ -static inline int cpuidle_cooling_register(struct cpuidle_driver *drv) +static inline void cpuidle_cooling_register(struct cpuidle_driver *drv) { - return 0; -} -static inline int cpuidle_of_cooling_register(struct device_node *np, - struct cpuidle_driver *drv) -{ - return 0; } #endif /* CONFIG_CPU_IDLE_THERMAL */ -- cgit v1.2.3 From 9d78edeaec759f997c303f286ecd39daee166f2a Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Mon, 18 May 2020 20:07:38 +0200 Subject: proc: proc_pid_ns takes super_block as an argument syzbot found that touch /proc/testfile causes NULL pointer dereference at tomoyo_get_local_path() because inode of the dentry is NULL. Before c59f415a7cb6, Tomoyo received pid_ns from proc's s_fs_info directly. Since proc_pid_ns() can only work with inode, using it in the tomoyo_get_local_path() was wrong. To avoid creating more functions for getting proc_ns, change the argument type of the proc_pid_ns() function. Then, Tomoyo can use the existing super_block to get pid_ns. Link: https://lkml.kernel.org/r/0000000000002f0c7505a5b0e04c@google.com Link: https://lkml.kernel.org/r/20200518180738.2939611-1-gladkov.alexey@gmail.com Reported-by: syzbot+c1af344512918c61362c@syzkaller.appspotmail.com Fixes: c59f415a7cb6 ("Use proc_pid_ns() to get pid_namespace from the proc superblock") Signed-off-by: Alexey Gladkov Signed-off-by: Eric W. Biederman --- include/linux/proc_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 2cb424e6f36a..6ec524d8842c 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -202,9 +202,9 @@ int open_related_ns(struct ns_common *ns, struct ns_common *(*get_ns)(struct ns_common *ns)); /* get the associated pid namespace for a file in procfs */ -static inline struct pid_namespace *proc_pid_ns(const struct inode *inode) +static inline struct pid_namespace *proc_pid_ns(struct super_block *sb) { - return proc_sb_info(inode->i_sb)->pid_ns; + return proc_sb_info(sb)->pid_ns; } #endif /* _LINUX_PROC_FS_H */ -- cgit v1.2.3 From 6553896666433e7efec589838b400a2a652b3ffa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 9 Mar 2020 22:47:17 +0100 Subject: vmlinux.lds.h: Create section for protection against instrumentation Some code pathes, especially the low level entry code, must be protected against instrumentation for various reasons: - Low level entry code can be a fragile beast, especially on x86. - With NO_HZ_FULL RCU state needs to be established before using it. Having a dedicated section for such code allows to validate with tooling that no unsafe functions are invoked. Add the .noinstr.text section and the noinstr attribute to mark functions. noinstr implies notrace. Kprobes will gain a section check later. Provide also a set of markers: instrumentation_begin()/end() These are used to mark code inside a noinstr function which calls into regular instrumentable text section as safe. The instrumentation markers are only active when CONFIG_DEBUG_ENTRY is enabled as the end marker emits a NOP to prevent the compiler from merging the annotation points. This means the objtool verification requires a kernel compiled with this option. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134100.075416272@linutronix.de --- include/linux/compiler.h | 53 ++++++++++++++++++++++++++++++++++++++++++ include/linux/compiler_types.h | 4 ++++ 2 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 034b0a644efc..e9ead0505671 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -120,12 +120,65 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(.rodata..c_jump_table) +#ifdef CONFIG_DEBUG_ENTRY +/* Begin/end of an instrumentation safe region */ +#define instrumentation_begin() ({ \ + asm volatile("%c0:\n\t" \ + ".pushsection .discard.instr_begin\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__COUNTER__)); \ +}) + +/* + * Because instrumentation_{begin,end}() can nest, objtool validation considers + * _begin() a +1 and _end() a -1 and computes a sum over the instructions. + * When the value is greater than 0, we consider instrumentation allowed. + * + * There is a problem with code like: + * + * noinstr void foo() + * { + * instrumentation_begin(); + * ... + * if (cond) { + * instrumentation_begin(); + * ... + * instrumentation_end(); + * } + * bar(); + * instrumentation_end(); + * } + * + * If instrumentation_end() would be an empty label, like all the other + * annotations, the inner _end(), which is at the end of a conditional block, + * would land on the instruction after the block. + * + * If we then consider the sum of the !cond path, we'll see that the call to + * bar() is with a 0-value, even though, we meant it to happen with a positive + * value. + * + * To avoid this, have _end() be a NOP instruction, this ensures it will be + * part of the condition block and does not escape. + */ +#define instrumentation_end() ({ \ + asm volatile("%c0: nop\n\t" \ + ".pushsection .discard.instr_end\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__COUNTER__)); \ +}) +#endif /* CONFIG_DEBUG_ENTRY */ + #else #define annotate_reachable() #define annotate_unreachable() #define __annotate_jump_table #endif +#ifndef instrumentation_begin +#define instrumentation_begin() do { } while(0) +#define instrumentation_end() do { } while(0) +#endif + #ifndef ASM_UNREACHABLE # define ASM_UNREACHABLE #endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index e970f97a7fcb..5da257cbebf1 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -118,6 +118,10 @@ struct ftrace_likely_data { #define notrace __attribute__((__no_instrument_function__)) #endif +/* Section for code which can't be instrumented at all */ +#define noinstr \ + noinline notrace __attribute((__section__(".noinstr.text"))) + /* * it doesn't make sense on ARM (currently the only user of __naked) * to trace naked functions because then mcount is called without -- cgit v1.2.3 From 0995a5dfbe49badff78e78761fb66f46579f2f9a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 4 Mar 2020 13:09:50 +0100 Subject: tracing: Provide lockdep less trace_hardirqs_on/off() variants trace_hardirqs_on/off() is only partially safe vs. RCU idle. The tracer core itself is safe, but the resulting tracepoints can be utilized by e.g. BPF which is unsafe. Provide variants which do not contain the lockdep invocation so the lockdep and tracer invocations can be split at the call site and placed properly. This is required because lockdep needs to be aware of the state before switching away from RCU idle and after switching to RCU idle because these transitions can take locks. As these code pathes are going to be non-instrumentable the tracer can be invoked after RCU is turned on and before the switch to RCU idle. So for these new variants there is no need to invoke the rcuidle aware tracer functions. Name them so they match the lockdep counterparts. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134100.270771162@linutronix.de --- include/linux/irqflags.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 61a9ced3aa50..f150e69ab81d 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -29,6 +29,8 @@ #endif #ifdef CONFIG_TRACE_IRQFLAGS + extern void trace_hardirqs_on_prepare(void); + extern void trace_hardirqs_off_prepare(void); extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); # define lockdep_hardirq_context(p) ((p)->hardirq_context) @@ -96,6 +98,8 @@ do { \ } while (0) #else +# define trace_hardirqs_on_prepare() do { } while (0) +# define trace_hardirqs_off_prepare() do { } while (0) # define trace_hardirqs_on() do { } while (0) # define trace_hardirqs_off() do { } while (0) # define lockdep_hardirq_context(p) 0 -- cgit v1.2.3 From c86e9b987cea3dd0209203e714553a47f5d7c6dd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 18 Mar 2020 14:22:03 +0100 Subject: lockdep: Prepare for noinstr sections Force inlining and prevent instrumentation of all sorts by marking the functions which are invoked from low level entry code with 'noinstr'. Split the irqflags tracking into two parts. One which does the heavy lifting while RCU is watching and the final one which can be invoked after RCU is turned off. Signed-off-by: Peter Zijlstra Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Link: https://lkml.kernel.org/r/20200505134100.484532537@linutronix.de --- include/linux/irqflags.h | 2 ++ include/linux/sched.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index f150e69ab81d..d7f7e436c3af 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -19,11 +19,13 @@ #ifdef CONFIG_PROVE_LOCKING extern void lockdep_softirqs_on(unsigned long ip); extern void lockdep_softirqs_off(unsigned long ip); + extern void lockdep_hardirqs_on_prepare(unsigned long ip); extern void lockdep_hardirqs_on(unsigned long ip); extern void lockdep_hardirqs_off(unsigned long ip); #else static inline void lockdep_softirqs_on(unsigned long ip) { } static inline void lockdep_softirqs_off(unsigned long ip) { } + static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { } static inline void lockdep_hardirqs_on(unsigned long ip) { } static inline void lockdep_hardirqs_off(unsigned long ip) { } #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 4418f5cb8324..658de6164853 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -983,6 +983,7 @@ struct task_struct { unsigned int hardirq_disable_event; int hardirqs_enabled; int hardirq_context; + u64 hardirq_chain_key; unsigned long softirq_disable_ip; unsigned long softirq_enable_ip; unsigned int softirq_disable_event; -- cgit v1.2.3 From af1e56b78534c38bb0e0c712ca70e59f816b74e9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 19 Mar 2020 14:53:56 +0100 Subject: context_tracking: Make guest_enter/exit() .noinstr ready Force inlining of the helpers and mark the instrumentable parts accordingly. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134341.672545766@linutronix.de --- include/linux/context_tracking.h | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 8150f5ac176c..8cac62ee6add 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -101,12 +101,14 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN /* must be called with irqs disabled */ -static inline void guest_enter_irqoff(void) +static __always_inline void guest_enter_irqoff(void) { + instrumentation_begin(); if (vtime_accounting_enabled_this_cpu()) vtime_guest_enter(current); else current->flags |= PF_VCPU; + instrumentation_end(); if (context_tracking_enabled()) __context_tracking_enter(CONTEXT_GUEST); @@ -118,39 +120,48 @@ static inline void guest_enter_irqoff(void) * one time slice). Lets treat guest mode as quiescent state, just like * we do with user-mode execution. */ - if (!context_tracking_enabled_this_cpu()) + if (!context_tracking_enabled_this_cpu()) { + instrumentation_begin(); rcu_virt_note_context_switch(smp_processor_id()); + instrumentation_end(); + } } -static inline void guest_exit_irqoff(void) +static __always_inline void guest_exit_irqoff(void) { if (context_tracking_enabled()) __context_tracking_exit(CONTEXT_GUEST); + instrumentation_begin(); if (vtime_accounting_enabled_this_cpu()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; + instrumentation_end(); } #else -static inline void guest_enter_irqoff(void) +static __always_inline void guest_enter_irqoff(void) { /* * This is running in ioctl context so its safe * to assume that it's the stime pending cputime * to flush. */ + instrumentation_begin(); vtime_account_kernel(current); current->flags |= PF_VCPU; rcu_virt_note_context_switch(smp_processor_id()); + instrumentation_end(); } -static inline void guest_exit_irqoff(void) +static __always_inline void guest_exit_irqoff(void) { + instrumentation_begin(); /* Flush the guest cputime we spent on the guest */ vtime_account_kernel(current); current->flags &= ~PF_VCPU; + instrumentation_end(); } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -- cgit v1.2.3 From 69ea03b56ed2c7189ccd0b5910ad39f3cad1df21 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 Feb 2020 09:46:47 +0100 Subject: hardirq/nmi: Allow nested nmi_enter() Since there are already a number of sites (ARM64, PowerPC) that effectively nest nmi_enter(), make the primitive support this before adding even more. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Acked-by: Marc Zyngier Acked-by: Will Deacon Cc: Michael Ellerman Link: https://lkml.kernel.org/r/20200505134100.864179229@linutronix.de --- include/linux/hardirq.h | 5 ++++- include/linux/preempt.h | 4 ++-- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 7c8b82f69288..a043ad826c67 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -65,13 +65,16 @@ extern void irq_exit(void); #define arch_nmi_exit() do { } while (0) #endif +/* + * nmi_enter() can nest up to 15 times; see NMI_BITS. + */ #define nmi_enter() \ do { \ arch_nmi_enter(); \ printk_nmi_enter(); \ lockdep_off(); \ ftrace_nmi_enter(); \ - BUG_ON(in_nmi()); \ + BUG_ON(in_nmi() == NMI_MASK); \ preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ rcu_nmi_enter(); \ lockdep_hardirq_enter(); \ diff --git a/include/linux/preempt.h b/include/linux/preempt.h index bc3f1aecaa19..7d9c1c0e149c 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -26,13 +26,13 @@ * PREEMPT_MASK: 0x000000ff * SOFTIRQ_MASK: 0x0000ff00 * HARDIRQ_MASK: 0x000f0000 - * NMI_MASK: 0x00100000 + * NMI_MASK: 0x00f00000 * PREEMPT_NEED_RESCHED: 0x80000000 */ #define PREEMPT_BITS 8 #define SOFTIRQ_BITS 8 #define HARDIRQ_BITS 4 -#define NMI_BITS 1 +#define NMI_BITS 4 #define PREEMPT_SHIFT 0 #define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) -- cgit v1.2.3 From e616cb8daadf637175af4fe53138a94c190c4816 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 24 Feb 2020 22:14:51 +0100 Subject: lockdep: Always inline lockdep_{off,on}() These functions are called {early,late} in nmi_{enter,exit} and should not be traced or probed. They are also puny, so 'inline' them. Reported-by: Steven Rostedt Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Link: https://lkml.kernel.org/r/20200505134101.048523500@linutronix.de --- include/linux/lockdep.h | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 206774ac6946..8fce5c98a4b0 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -308,8 +308,27 @@ extern void lockdep_set_selftest_task(struct task_struct *task); extern void lockdep_init_task(struct task_struct *task); -extern void lockdep_off(void); -extern void lockdep_on(void); +/* + * Split the recrursion counter in two to readily detect 'off' vs recursion. + */ +#define LOCKDEP_RECURSION_BITS 16 +#define LOCKDEP_OFF (1U << LOCKDEP_RECURSION_BITS) +#define LOCKDEP_RECURSION_MASK (LOCKDEP_OFF - 1) + +/* + * lockdep_{off,on}() are macros to avoid tracing and kprobes; not inlines due + * to header dependencies. + */ + +#define lockdep_off() \ +do { \ + current->lockdep_recursion += LOCKDEP_OFF; \ +} while (0) + +#define lockdep_on() \ +do { \ + current->lockdep_recursion -= LOCKDEP_OFF; \ +} while (0) extern void lockdep_register_key(struct lock_class_key *key); extern void lockdep_unregister_key(struct lock_class_key *key); -- cgit v1.2.3 From 178ba00c354eb15cec6806a812771e60a5ae3ea1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 24 Feb 2020 22:26:21 +0100 Subject: sh/ftrace: Move arch_ftrace_nmi_{enter,exit} into nmi exception SuperH is the last remaining user of arch_ftrace_nmi_{enter,exit}(), remove it from the generic code and into the SuperH code. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Steven Rostedt (VMware) Cc: Rich Felker Cc: Yoshinori Sato Link: https://lkml.kernel.org/r/20200505134101.248881738@linutronix.de --- include/linux/ftrace_irq.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_irq.h b/include/linux/ftrace_irq.h index ccda97dc7f8b..0abd9a1d2852 100644 --- a/include/linux/ftrace_irq.h +++ b/include/linux/ftrace_irq.h @@ -2,15 +2,6 @@ #ifndef _LINUX_FTRACE_IRQ_H #define _LINUX_FTRACE_IRQ_H - -#ifdef CONFIG_FTRACE_NMI_ENTER -extern void arch_ftrace_nmi_enter(void); -extern void arch_ftrace_nmi_exit(void); -#else -static inline void arch_ftrace_nmi_enter(void) { } -static inline void arch_ftrace_nmi_exit(void) { } -#endif - #ifdef CONFIG_HWLAT_TRACER extern bool trace_hwlat_callback_enabled; extern void trace_hwlat_callback(bool enter); @@ -22,12 +13,10 @@ static inline void ftrace_nmi_enter(void) if (trace_hwlat_callback_enabled) trace_hwlat_callback(true); #endif - arch_ftrace_nmi_enter(); } static inline void ftrace_nmi_exit(void) { - arch_ftrace_nmi_exit(); #ifdef CONFIG_HWLAT_TRACER if (trace_hwlat_callback_enabled) trace_hwlat_callback(false); -- cgit v1.2.3 From f93524eb9c54f49be150167918f6546b0a2e09b1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 12 Feb 2020 21:01:16 +0100 Subject: sched,rcu,tracing: Avoid tracing before in_nmi() is correct If a tracer is invoked before in_nmi() becomes true, the tracer can no longer detect it is called from NMI context and behave correctly. Therefore change nmi_{enter,exit}() to use __preempt_count_{add,sub}() as the normal preempt_count_{add,sub}() have a (desired) function trace entry. This fixes a potential issue with the current code; when the function-tracer has stack-tracing enabled __trace_stack() will malfunction when it hits the preempt_count_add() function entry from NMI context. Suggested-by: Steven Rostedt (VMware) Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Alexandre Chartre Link: https://lkml.kernel.org/r/20200505134101.434193525@linutronix.de --- include/linux/hardirq.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index a043ad826c67..621556efe45f 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -65,6 +65,15 @@ extern void irq_exit(void); #define arch_nmi_exit() do { } while (0) #endif +/* + * NMI vs Tracing + * -------------- + * + * We must not land in a tracer until (or after) we've changed preempt_count + * such that in_nmi() becomes true. To that effect all NMI C entry points must + * be marked 'notrace' and call nmi_enter() as soon as possible. + */ + /* * nmi_enter() can nest up to 15 times; see NMI_BITS. */ @@ -75,7 +84,7 @@ extern void irq_exit(void); lockdep_off(); \ ftrace_nmi_enter(); \ BUG_ON(in_nmi() == NMI_MASK); \ - preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ + __preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ rcu_nmi_enter(); \ lockdep_hardirq_enter(); \ } while (0) @@ -85,7 +94,7 @@ extern void irq_exit(void); lockdep_hardirq_exit(); \ rcu_nmi_exit(); \ BUG_ON(!in_nmi()); \ - preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ + __preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ ftrace_nmi_exit(); \ lockdep_on(); \ printk_nmi_exit(); \ -- cgit v1.2.3 From 5567d11c21a1d508a91a8cb64a819783a0835d9f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 Feb 2020 10:22:06 +0100 Subject: x86/mce: Send #MC singal from task work Convert #MC over to using task_work_add(); it will run the same code slightly later, on the return to user path of the same exception. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Reviewed-by: Alexandre Chartre Link: https://lkml.kernel.org/r/20200505134100.957390899@linutronix.de --- include/linux/sched.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9437b53cc603..57d0ed061ae4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1297,6 +1297,12 @@ struct task_struct { unsigned long prev_lowest_stack; #endif +#ifdef CONFIG_X86_MCE + u64 mce_addr; + u64 mce_status; + struct callback_head mce_kill_me; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. -- cgit v1.2.3 From 8ae0ae6737ad449c8ae21e2bb01d9736f360a933 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 3 May 2020 15:08:52 +0200 Subject: rcu: Provide rcu_irq_exit_preempt() Interrupts and exceptions invoke rcu_irq_enter() on entry and need to invoke rcu_irq_exit() before they either return to the interrupted code or invoke the scheduler due to preemption. The general assumption is that RCU idle code has to have preemption disabled so that a return from interrupt cannot schedule. So the return from interrupt code invokes rcu_irq_exit() and preempt_schedule_irq(). If there is any imbalance in the rcu_irq/nmi* invocations or RCU idle code had preemption enabled then this goes unnoticed until the CPU goes idle or some other RCU check is executed. Provide rcu_irq_exit_preempt() which can be invoked from the interrupt/exception return code in case that preemption is enabled. It invokes rcu_irq_exit() and contains a few sanity checks in case that CONFIG_PROVE_RCU is enabled to catch such issues directly. Signed-off-by: Thomas Gleixner Reviewed-by: Paul E. McKenney Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134904.364456424@linutronix.de --- include/linux/rcutiny.h | 1 + include/linux/rcutree.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 3465ba704a11..980eb78751d9 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -71,6 +71,7 @@ static inline void rcu_irq_enter(void) { } static inline void rcu_irq_exit_irqson(void) { } static inline void rcu_irq_enter_irqson(void) { } static inline void rcu_irq_exit(void) { } +static inline void rcu_irq_exit_preempt(void) { } static inline void exit_rcu(void) { } static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t) { diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index fbc26274af4d..02016e0aa8eb 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -47,6 +47,7 @@ void rcu_idle_enter(void); void rcu_idle_exit(void); void rcu_irq_enter(void); void rcu_irq_exit(void); +void rcu_irq_exit_preempt(void); void rcu_irq_enter_irqson(void); void rcu_irq_exit_irqson(void); -- cgit v1.2.3 From b1fcf9b83c4149c63d1e0c699e85f93cbe28e211 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 May 2020 09:44:43 +0200 Subject: rcu: Provide __rcu_is_watching() Same as rcu_is_watching() but without the preempt_disable/enable() pair inside the function. It is merked noinstr so it ends up in the non-instrumentable text section. This is useful for non-preemptible code especially in the low level entry section. Using rcu_is_watching() there results in a call to the preempt_schedule_notrace() thunk which triggers noinstr section warnings in objtool. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200512213810.518709291@linutronix.de --- include/linux/rcutiny.h | 1 + include/linux/rcutree.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 980eb78751d9..c869fb20cc51 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -86,6 +86,7 @@ static inline void rcu_scheduler_starting(void) { } static inline void rcu_end_inkernel_boot(void) { } static inline bool rcu_inkernel_boot_has_ended(void) { return true; } static inline bool rcu_is_watching(void) { return true; } +static inline bool __rcu_is_watching(void) { return true; } static inline void rcu_momentary_dyntick_idle(void) { } static inline void kfree_rcu_scheduler_running(void) { } static inline bool rcu_gp_might_be_stalled(void) { return false; } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 02016e0aa8eb..9366fa4d0717 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -58,6 +58,7 @@ extern int rcu_scheduler_active __read_mostly; void rcu_end_inkernel_boot(void); bool rcu_inkernel_boot_has_ended(void); bool rcu_is_watching(void); +bool __rcu_is_watching(void); #ifndef CONFIG_PREEMPTION void rcu_all_qs(void); #endif -- cgit v1.2.3 From 66e9b0717102507e64f638790eaece88765cc9e5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Mar 2020 14:04:34 +0100 Subject: kprobes: Prevent probes in .noinstr.text section Instrumentation is forbidden in the .noinstr.text section. Make kprobes respect this. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Acked-by: Masami Hiramatsu Link: https://lkml.kernel.org/r/20200505134100.179862032@linutronix.de --- include/linux/module.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 1192097c9a69..d849d06e4d44 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -458,6 +458,8 @@ struct module { void __percpu *percpu; unsigned int percpu_size; #endif + void *noinstr_text_start; + unsigned int noinstr_text_size; #ifdef CONFIG_TRACEPOINTS unsigned int num_tracepoints; -- cgit v1.2.3 From 344fa64ef8f6740e99b32ab788b6e3742d7284b3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 12 Feb 2020 13:58:35 +0000 Subject: security: Add a hook for the point of notification insertion Add a security hook that allows an LSM to rule on whether a notification message is allowed to be inserted into a particular watch queue. The hook is given the following information: (1) The credentials of the triggerer (which may be init_cred for a system notification, eg. a hardware error). (2) The credentials of the whoever set the watch. (3) The notification message. Signed-off-by: David Howells Acked-by: James Morris cc: Casey Schaufler cc: Stephen Smalley cc: linux-security-module@vger.kernel.org --- include/linux/lsm_hook_defs.h | 5 +++++ include/linux/lsm_hooks.h | 9 +++++++++ include/linux/security.h | 15 +++++++++++++++ 3 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 5616b2567aa7..e0def45b5cc5 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -253,6 +253,11 @@ LSM_HOOK(int, 0, inode_setsecctx, struct dentry *dentry, void *ctx, u32 ctxlen) LSM_HOOK(int, 0, inode_getsecctx, struct inode *inode, void **ctx, u32 *ctxlen) +#if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) +LSM_HOOK(int, 0, post_notification, const struct cred *w_cred, + const struct cred *cred, struct watch_notification *n) +#endif /* CONFIG_SECURITY && CONFIG_KEY_NOTIFICATIONS */ + #ifdef CONFIG_SECURITY_NETWORK LSM_HOOK(int, 0, unix_stream_connect, struct sock *sock, struct sock *other, struct sock *newsk) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 988ca0df7824..0b5e5769b836 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1437,6 +1437,15 @@ * @ctx is a pointer in which to place the allocated security context. * @ctxlen points to the place to put the length of @ctx. * + * Security hooks for the general notification queue: + * + * @post_notification: + * Check to see if a watch notification can be posted to a particular + * queue. + * @w_cred: The credentials of the whoever set the watch. + * @cred: The event-triggerer's credentials + * @n: The notification being posted + * * Security hooks for using the eBPF maps and programs functionalities through * eBPF syscalls. * diff --git a/include/linux/security.h b/include/linux/security.h index a8d9310472df..9a5d12ab491b 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -56,6 +56,8 @@ struct mm_struct; struct fs_context; struct fs_parameter; enum fs_value_type; +struct watch; +struct watch_notification; /* Default (no) options for the capable function */ #define CAP_OPT_NONE 0x0 @@ -1275,6 +1277,19 @@ static inline int security_locked_down(enum lockdown_reason what) } #endif /* CONFIG_SECURITY */ +#if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) +int security_post_notification(const struct cred *w_cred, + const struct cred *cred, + struct watch_notification *n); +#else +static inline int security_post_notification(const struct cred *w_cred, + const struct cred *cred, + struct watch_notification *n) +{ + return 0; +} +#endif + #ifdef CONFIG_SECURITY_NETWORK int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk); -- cgit v1.2.3 From c73be61cede5882f9605a852414db559c0ebedfd Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Jan 2020 17:07:11 +0000 Subject: pipe: Add general notification queue support Make it possible to have a general notification queue built on top of a standard pipe. Notifications are 'spliced' into the pipe and then read out. splice(), vmsplice() and sendfile() are forbidden on pipes used for notifications as post_one_notification() cannot take pipe->mutex. This means that notifications could be posted in between individual pipe buffers, making iov_iter_revert() difficult to effect. The way the notification queue is used is: (1) An application opens a pipe with a special flag and indicates the number of messages it wishes to be able to queue at once (this can only be set once): pipe2(fds, O_NOTIFICATION_PIPE); ioctl(fds[0], IOC_WATCH_QUEUE_SET_SIZE, queue_depth); (2) The application then uses poll() and read() as normal to extract data from the pipe. read() will return multiple notifications if the buffer is big enough, but it will not split a notification across buffers - rather it will return a short read or EMSGSIZE. Notification messages include a length in the header so that the caller can split them up. Each message has a header that describes it: struct watch_notification { __u32 type:24; __u32 subtype:8; __u32 info; }; The type indicates the source (eg. mount tree changes, superblock events, keyring changes, block layer events) and the subtype indicates the event type (eg. mount, unmount; EIO, EDQUOT; link, unlink). The info field indicates a number of things, including the entry length, an ID assigned to a watchpoint contributing to this buffer and type-specific flags. Supplementary data, such as the key ID that generated an event, can be attached in additional slots. The maximum message size is 127 bytes. Messages may not be padded or aligned, so there is no guarantee, for example, that the notification type will be on a 4-byte bounary. Signed-off-by: David Howells --- include/linux/pipe_fs_i.h | 19 ++++++- include/linux/watch_queue.h | 127 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 145 insertions(+), 1 deletion(-) create mode 100644 include/linux/watch_queue.h (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index ae58fad7f1e0..1d3eaa233f4a 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -35,6 +35,7 @@ struct pipe_buffer { * @tail: The point of buffer consumption * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) + * @nr_accounted: The amount this pipe accounts for in user->pipe_bufs * @tmp_page: cached released page * @readers: number of current readers of this pipe * @writers: number of current writers of this pipe @@ -45,6 +46,7 @@ struct pipe_buffer { * @fasync_writers: writer side fasync * @bufs: the circular array of pipe buffers * @user: the user who created this pipe + * @watch_queue: If this pipe is a watch_queue, this is the stuff for that **/ struct pipe_inode_info { struct mutex mutex; @@ -53,6 +55,7 @@ struct pipe_inode_info { unsigned int tail; unsigned int max_usage; unsigned int ring_size; + unsigned int nr_accounted; unsigned int readers; unsigned int writers; unsigned int files; @@ -63,6 +66,9 @@ struct pipe_inode_info { struct fasync_struct *fasync_writers; struct pipe_buffer *bufs; struct user_struct *user; +#ifdef CONFIG_WATCH_QUEUE + struct watch_queue *watch_queue; +#endif }; /* @@ -237,9 +243,20 @@ void pipe_buf_mark_unmergeable(struct pipe_buffer *buf); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; +#ifdef CONFIG_WATCH_QUEUE +unsigned long account_pipe_buffers(struct user_struct *user, + unsigned long old, unsigned long new); +bool too_many_pipe_buffers_soft(unsigned long user_bufs); +bool too_many_pipe_buffers_hard(unsigned long user_bufs); +bool pipe_is_unprivileged_user(void); +#endif + /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ +#ifdef CONFIG_WATCH_QUEUE +int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots); +#endif long pipe_fcntl(struct file *, unsigned int, unsigned long arg); -struct pipe_inode_info *get_pipe_info(struct file *file); +struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice); int create_pipe_files(struct file **, int); unsigned int round_pipe_size(unsigned long size); diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h new file mode 100644 index 000000000000..5e08db2adc31 --- /dev/null +++ b/include/linux/watch_queue.h @@ -0,0 +1,127 @@ +// SPDX-License-Identifier: GPL-2.0 +/* User-mappable watch queue + * + * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * See Documentation/watch_queue.rst + */ + +#ifndef _LINUX_WATCH_QUEUE_H +#define _LINUX_WATCH_QUEUE_H + +#include +#include +#include + +#ifdef CONFIG_WATCH_QUEUE + +struct cred; + +struct watch_type_filter { + enum watch_notification_type type; + __u32 subtype_filter[1]; /* Bitmask of subtypes to filter on */ + __u32 info_filter; /* Filter on watch_notification::info */ + __u32 info_mask; /* Mask of relevant bits in info_filter */ +}; + +struct watch_filter { + union { + struct rcu_head rcu; + unsigned long type_filter[2]; /* Bitmask of accepted types */ + }; + u32 nr_filters; /* Number of filters */ + struct watch_type_filter filters[]; +}; + +struct watch_queue { + struct rcu_head rcu; + struct watch_filter __rcu *filter; + struct pipe_inode_info *pipe; /* The pipe we're using as a buffer */ + struct hlist_head watches; /* Contributory watches */ + struct page **notes; /* Preallocated notifications */ + unsigned long *notes_bitmap; /* Allocation bitmap for notes */ + struct kref usage; /* Object usage count */ + spinlock_t lock; + unsigned int nr_notes; /* Number of notes */ + unsigned int nr_pages; /* Number of pages in notes[] */ + bool defunct; /* T when queues closed */ +}; + +/* + * Representation of a watch on an object. + */ +struct watch { + union { + struct rcu_head rcu; + u32 info_id; /* ID to be OR'd in to info field */ + }; + struct watch_queue __rcu *queue; /* Queue to post events to */ + struct hlist_node queue_node; /* Link in queue->watches */ + struct watch_list __rcu *watch_list; + struct hlist_node list_node; /* Link in watch_list->watchers */ + const struct cred *cred; /* Creds of the owner of the watch */ + void *private; /* Private data for the watched object */ + u64 id; /* Internal identifier */ + struct kref usage; /* Object usage count */ +}; + +/* + * List of watches on an object. + */ +struct watch_list { + struct rcu_head rcu; + struct hlist_head watchers; + void (*release_watch)(struct watch *); + spinlock_t lock; +}; + +extern void __post_watch_notification(struct watch_list *, + struct watch_notification *, + const struct cred *, + u64); +extern struct watch_queue *get_watch_queue(int); +extern void put_watch_queue(struct watch_queue *); +extern void init_watch(struct watch *, struct watch_queue *); +extern int add_watch_to_object(struct watch *, struct watch_list *); +extern int remove_watch_from_object(struct watch_list *, struct watch_queue *, u64, bool); +extern long watch_queue_set_size(struct pipe_inode_info *, unsigned int); +extern long watch_queue_set_filter(struct pipe_inode_info *, + struct watch_notification_filter __user *); +extern int watch_queue_init(struct pipe_inode_info *); +extern void watch_queue_clear(struct watch_queue *); + +static inline void init_watch_list(struct watch_list *wlist, + void (*release_watch)(struct watch *)) +{ + INIT_HLIST_HEAD(&wlist->watchers); + spin_lock_init(&wlist->lock); + wlist->release_watch = release_watch; +} + +static inline void post_watch_notification(struct watch_list *wlist, + struct watch_notification *n, + const struct cred *cred, + u64 id) +{ + if (unlikely(wlist)) + __post_watch_notification(wlist, n, cred, id); +} + +static inline void remove_watch_list(struct watch_list *wlist, u64 id) +{ + if (wlist) { + remove_watch_from_object(wlist, NULL, id, true); + kfree_rcu(wlist, rcu); + } +} + +/** + * watch_sizeof - Calculate the information part of the size of a watch record, + * given the structure size. + */ +#define watch_sizeof(STRUCT) (sizeof(STRUCT) << WATCH_INFO_LENGTH__SHIFT) + +#endif + +#endif /* _LINUX_WATCH_QUEUE_H */ -- cgit v1.2.3 From 998f50407ffc9370565c7ed3fcd1366adccdfbbf Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 12 Feb 2020 13:58:35 +0000 Subject: security: Add hooks to rule on setting a watch Add security hooks that will allow an LSM to rule on whether or not a watch may be set. More than one hook is required as the watches watch different types of object. Signed-off-by: David Howells Acked-by: James Morris cc: Casey Schaufler cc: Stephen Smalley cc: linux-security-module@vger.kernel.org --- include/linux/lsm_hook_defs.h | 4 ++++ include/linux/lsm_hooks.h | 5 +++++ include/linux/security.h | 9 +++++++++ 3 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index e0def45b5cc5..a54f49e95708 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -256,6 +256,10 @@ LSM_HOOK(int, 0, inode_getsecctx, struct inode *inode, void **ctx, #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) LSM_HOOK(int, 0, post_notification, const struct cred *w_cred, const struct cred *cred, struct watch_notification *n) +#endif /* CONFIG_SECURITY && CONFIG_WATCH_QUEUE */ + +#if defined(CONFIG_SECURITY) && defined(CONFIG_KEY_NOTIFICATIONS) +LSM_HOOK(int, 0, watch_key, struct key *key) #endif /* CONFIG_SECURITY && CONFIG_KEY_NOTIFICATIONS */ #ifdef CONFIG_SECURITY_NETWORK diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 0b5e5769b836..3f1374cffb76 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1446,6 +1446,11 @@ * @cred: The event-triggerer's credentials * @n: The notification being posted * + * @watch_key: + * Check to see if a process is allowed to watch for event notifications + * from a key or keyring. + * @key: The key to watch. + * * Security hooks for using the eBPF maps and programs functionalities through * eBPF syscalls. * diff --git a/include/linux/security.h b/include/linux/security.h index 9a5d12ab491b..e7914e4e0b02 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1290,6 +1290,15 @@ static inline int security_post_notification(const struct cred *w_cred, } #endif +#if defined(CONFIG_SECURITY) && defined(CONFIG_KEY_NOTIFICATIONS) +int security_watch_key(struct key *key); +#else +static inline int security_watch_key(struct key *key) +{ + return 0; +} +#endif + #ifdef CONFIG_SECURITY_NETWORK int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk); -- cgit v1.2.3 From f7e47677e39a03057dcced2016c92a9c868693ec Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Jan 2020 17:07:11 +0000 Subject: watch_queue: Add a key/keyring notification facility Add a key/keyring change notification facility whereby notifications about changes in key and keyring content and attributes can be received. Firstly, an event queue needs to be created: pipe2(fds, O_NOTIFICATION_PIPE); ioctl(fds[1], IOC_WATCH_QUEUE_SET_SIZE, 256); then a notification can be set up to report notifications via that queue: struct watch_notification_filter filter = { .nr_filters = 1, .filters = { [0] = { .type = WATCH_TYPE_KEY_NOTIFY, .subtype_filter[0] = UINT_MAX, }, }, }; ioctl(fds[1], IOC_WATCH_QUEUE_SET_FILTER, &filter); keyctl_watch_key(KEY_SPEC_SESSION_KEYRING, fds[1], 0x01); After that, records will be placed into the queue when events occur in which keys are changed in some way. Records are of the following format: struct key_notification { struct watch_notification watch; __u32 key_id; __u32 aux; } *n; Where: n->watch.type will be WATCH_TYPE_KEY_NOTIFY. n->watch.subtype will indicate the type of event, such as NOTIFY_KEY_REVOKED. n->watch.info & WATCH_INFO_LENGTH will indicate the length of the record. n->watch.info & WATCH_INFO_ID will be the second argument to keyctl_watch_key(), shifted. n->key will be the ID of the affected key. n->aux will hold subtype-dependent information, such as the key being linked into the keyring specified by n->key in the case of NOTIFY_KEY_LINKED. Note that it is permissible for event records to be of variable length - or, at least, the length may be dependent on the subtype. Note also that the queue can be shared between multiple notifications of various types. Signed-off-by: David Howells Reviewed-by: James Morris --- include/linux/key.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index 6cf8e71cf8b7..b99b40db08fc 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -176,6 +176,9 @@ struct key { struct list_head graveyard_link; struct rb_node serial_node; }; +#ifdef CONFIG_KEY_NOTIFICATIONS + struct watch_list *watchers; /* Entities watching this key for changes */ +#endif struct rw_semaphore sem; /* change vs change sem */ struct key_user *user; /* owner of this key */ void *security; /* security data for this key */ -- cgit v1.2.3 From 80961525880e58e0efcf536fd357d642c68f4176 Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Mon, 18 May 2020 12:02:22 -0600 Subject: coresight: Add generic sysfs link creation functions To allow the connections between coresight components to be represented in sysfs, generic methods for creating sysfs links between two coresight devices are added. Signed-off-by: Mike Leach Reviewed-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200518180242.7916-4-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 193cc9dbf448..a2ec25e02ca9 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -148,6 +148,20 @@ struct coresight_connection { struct coresight_device *child_dev; }; +/** + * struct coresight_sysfs_link - representation of a connection in sysfs. + * @orig: Originating (master) coresight device for the link. + * @orig_name: Name to use for the link orig->target. + * @target: Target (slave) coresight device for the link. + * @target_name: Name to use for the link target->orig. + */ +struct coresight_sysfs_link { + struct coresight_device *orig; + const char *orig_name; + struct coresight_device *target; + const char *target_name; +}; + /** * struct coresight_device - representation of a device as used by the framework * @pdata: Platform data with device connections associated to this device. @@ -165,6 +179,9 @@ struct coresight_connection { * @ea: Device attribute for sink representation under PMU directory. * @ect_dev: Associated cross trigger device. Not part of the trace data * path or connections. + * @nr_links: number of sysfs links created to other components from this + * device. These will appear in the "connections" group. + * @has_conns_grp: Have added a "connections" group for sysfs links. */ struct coresight_device { struct coresight_platform_data *pdata; @@ -180,6 +197,9 @@ struct coresight_device { struct dev_ext_attribute *ea; /* cross trigger handling */ struct coresight_device *ect_dev; + /* sysfs links between components */ + int nr_links; + bool has_conns_grp; }; /* -- cgit v1.2.3 From 8a7365c2d41898f2376efa929aadf2723dc281b0 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 18 May 2020 12:02:23 -0600 Subject: coresight: Expose device connections via sysfs Coresight device connections are a bit complicated and is not exposed currently to the user. One has to look at the platform descriptions (DT bindings or ACPI bindings) to make an understanding. Given the new naming scheme, it will be helpful to have this information to choose the appropriate devices for tracing. This patch exposes the device connections via links in the sysfs directories. e.g, for a connection devA[OutputPort_X] -> devB[InputPort_Y] is represented as two symlinks: /sys/bus/coresight/.../devA/out:X -> /sys/bus/coresight/.../devB /sys/bus/coresight/.../devB/in:Y -> /sys/bus/coresight/.../devA Signed-off-by: Suzuki K Poulose [Revised to use the generic sysfs links functions & link structures. Provides a connections sysfs group in each device to hold the links.] Co-developed-by: Mike Leach Signed-off-by: Mike Leach Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200518180242.7916-5-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index a2ec25e02ca9..ccd17304d7bd 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -140,12 +140,14 @@ struct coresight_desc { * @chid_fwnode: remote component's fwnode handle. * @child_dev: a @coresight_device representation of the component connected to @outport. + * @link: Representation of the connection as a sysfs link. */ struct coresight_connection { int outport; int child_port; struct fwnode_handle *child_fwnode; struct coresight_device *child_dev; + struct coresight_sysfs_link *link; }; /** -- cgit v1.2.3 From d375b356e687f2eefb51ddc3f1f2414cfa498f86 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 18 May 2020 12:02:31 -0600 Subject: coresight: Fix support for sparsely populated ports On some systems the firmware may not describe all the ports connected to a component (e.g, for security reasons). This could be especially problematic for "funnels" where we could end up in modifying memory beyond the allocated space for refcounts. e.g, for a funnel with input ports listed 0, 3, 5, nr_inport = 3. However the we could access refcnts[5] while checking for references, like : [ 526.110401] ================================================================== [ 526.117988] BUG: KASAN: slab-out-of-bounds in funnel_enable+0x54/0x1b0 [ 526.124706] Read of size 4 at addr ffffff8135f9549c by task bash/1114 [ 526.131324] [ 526.132886] CPU: 3 PID: 1114 Comm: bash Tainted: G S 5.4.25 #232 [ 526.140397] Hardware name: Qualcomm Technologies, Inc. SC7180 IDP (DT) [ 526.147113] Call trace: [ 526.149653] dump_backtrace+0x0/0x188 [ 526.153431] show_stack+0x20/0x2c [ 526.156852] dump_stack+0xdc/0x144 [ 526.160370] print_address_description+0x3c/0x494 [ 526.165211] __kasan_report+0x144/0x168 [ 526.169170] kasan_report+0x10/0x18 [ 526.172769] check_memory_region+0x1a4/0x1b4 [ 526.177164] __kasan_check_read+0x18/0x24 [ 526.181292] funnel_enable+0x54/0x1b0 [ 526.185072] coresight_enable_path+0x104/0x198 [ 526.189649] coresight_enable+0x118/0x26c ... [ 526.237782] Allocated by task 280: [ 526.241298] __kasan_kmalloc+0xf0/0x1ac [ 526.245249] kasan_kmalloc+0xc/0x14 [ 526.248849] __kmalloc+0x28c/0x3b4 [ 526.252361] coresight_register+0x88/0x250 [ 526.256587] funnel_probe+0x15c/0x228 [ 526.260365] dynamic_funnel_probe+0x20/0x2c [ 526.264679] amba_probe+0xbc/0x158 [ 526.268193] really_probe+0x144/0x408 [ 526.271970] driver_probe_device+0x70/0x140 ... [ 526.316810] [ 526.318364] Freed by task 0: [ 526.321344] (stack is not available) [ 526.325024] [ 526.326580] The buggy address belongs to the object at ffffff8135f95480 [ 526.326580] which belongs to the cache kmalloc-128 of size 128 [ 526.339439] The buggy address is located 28 bytes inside of [ 526.339439] 128-byte region [ffffff8135f95480, ffffff8135f95500) [ 526.351399] The buggy address belongs to the page: [ 526.356342] page:ffffffff04b7e500 refcount:1 mapcount:0 mapping:ffffff814b00c380 index:0x0 compound_mapcount: 0 [ 526.366711] flags: 0x4000000000010200(slab|head) [ 526.371475] raw: 4000000000010200 ffffffff05034008 ffffffff0501eb08 ffffff814b00c380 [ 526.379435] raw: 0000000000000000 0000000000190019 00000001ffffffff 0000000000000000 [ 526.387393] page dumped because: kasan: bad access detected [ 526.393128] [ 526.394681] Memory state around the buggy address: [ 526.399619] ffffff8135f95380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 526.407046] ffffff8135f95400: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 526.414473] >ffffff8135f95480: 04 fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 526.421900] ^ [ 526.426029] ffffff8135f95500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 526.433456] ffffff8135f95580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 526.440883] ================================================================== To keep the code simple, we now track the maximum number of possible input/output connections to/from this component @ nr_inport and nr_outport in platform_data, respectively. Thus the output connections could be sparse and code is adjusted to skip the unspecified connections. Cc: Mathieu Poirier Cc: Mike Leach Reported-by: Sai Prakash Ranjan Tested-by: Sai Prakash Ranjan Tested-by: Stephen Boyd Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200518180242.7916-13-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index ccd17304d7bd..e3e9f0e3a878 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -100,10 +100,12 @@ union coresight_dev_subtype { }; /** - * struct coresight_platform_data - data harvested from the DT specification - * @nr_inport: number of input ports for this component. - * @nr_outport: number of output ports for this component. - * @conns: Array of nr_outport connections from this component + * struct coresight_platform_data - data harvested from the firmware + * specification. + * + * @nr_inport: Number of elements for the input connections. + * @nr_outport: Number of elements for the output connections. + * @conns: Sparse array of nr_outport connections from this component. */ struct coresight_platform_data { int nr_inport; -- cgit v1.2.3 From e9b880581d555c8f7b58c7d19cc3f8f9016a1b5f Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Mon, 18 May 2020 12:02:41 -0600 Subject: coresight: cti: Add CPU Hotplug handling to CTI driver Adds registration of CPU start and stop functions to CPU hotplug mechanisms - for any CPU bound CTI. Sets CTI powered flag according to state. Will enable CTI on CPU start if there are existing enable requests. Signed-off-by: Mike Leach Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200518180242.7916-23-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 77d70b633531..6dc7332307ca 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -142,6 +142,7 @@ enum cpuhp_state { CPUHP_AP_ARM_XEN_STARTING, CPUHP_AP_ARM_KVMPV_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, + CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, CPUHP_AP_X86_TBOOT_DYING, -- cgit v1.2.3 From 8cfba76383e902acbed95092163052b1572f17a8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Jan 2020 17:07:11 +0000 Subject: pipe: Allow buffers to be marked read-whole-or-error for notifications Allow a buffer to be marked such that read() must return the entire buffer in one go or return ENOBUFS. Multiple buffers can be amalgamated into a single read, but a short read will occur if the next "whole" buffer won't fit. This is useful for watch queue notifications to make sure we don't split a notification across multiple reads, especially given that we need to fabricate an overrun record under some circumstances - and that isn't in the buffers. Signed-off-by: David Howells --- include/linux/pipe_fs_i.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 1d3eaa233f4a..eaff59a2f074 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -8,6 +8,7 @@ #define PIPE_BUF_FLAG_ATOMIC 0x02 /* was atomically mapped */ #define PIPE_BUF_FLAG_GIFT 0x04 /* page is a gift */ #define PIPE_BUF_FLAG_PACKET 0x08 /* read() as a packet */ +#define PIPE_BUF_FLAG_WHOLE 0x10 /* read() must return entire buffer or error */ /** * struct pipe_buffer - a linux kernel pipe buffer -- cgit v1.2.3 From e7d553d69cf63aec7de0f38fed49ccbb30922e1e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Jan 2020 17:07:12 +0000 Subject: pipe: Add notification lossage handling Add handling for loss of notifications by having read() insert a loss-notification message after it has read the pipe buffer that was last in the ring when the loss occurred. Lossage can come about either by running out of notification descriptors or by running out of space in the pipe ring. Signed-off-by: David Howells --- include/linux/pipe_fs_i.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index eaff59a2f074..6626f511de6f 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -9,6 +9,9 @@ #define PIPE_BUF_FLAG_GIFT 0x04 /* page is a gift */ #define PIPE_BUF_FLAG_PACKET 0x08 /* read() as a packet */ #define PIPE_BUF_FLAG_WHOLE 0x10 /* read() must return entire buffer or error */ +#ifdef CONFIG_WATCH_QUEUE +#define PIPE_BUF_FLAG_LOSS 0x20 /* Message loss happened after this buffer */ +#endif /** * struct pipe_buffer - a linux kernel pipe buffer @@ -34,6 +37,7 @@ struct pipe_buffer { * @wr_wait: writer wait point in case of full pipe * @head: The point of buffer production * @tail: The point of buffer consumption + * @note_loss: The next read() should insert a data-lost message * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) * @nr_accounted: The amount this pipe accounts for in user->pipe_bufs @@ -56,6 +60,9 @@ struct pipe_inode_info { unsigned int tail; unsigned int max_usage; unsigned int ring_size; +#ifdef CONFIG_WATCH_QUEUE + bool note_loss; +#endif unsigned int nr_accounted; unsigned int readers; unsigned int writers; -- cgit v1.2.3 From 8c0637e950d68933a67f7438f779d79b049b5e5c Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2020 15:16:29 +0100 Subject: keys: Make the KEY_NEED_* perms an enum rather than a mask Since the meaning of combining the KEY_NEED_* constants is undefined, make it so that you can't do that by turning them into an enum. The enum is also given some extra values to represent special circumstances, such as: (1) The '0' value is reserved and causes a warning to trap the parameter being unset. (2) The key is to be unlinked and we require no permissions on it, only the keyring, (this replaces the KEY_LOOKUP_FOR_UNLINK flag). (3) An override due to CAP_SYS_ADMIN. (4) An override due to an instantiation token being present. (5) The permissions check is being deferred to later key_permission() calls. The extra values give the opportunity for LSMs to audit these situations. [Note: This really needs overhauling so that lookup_user_key() tells key_task_permission() and the LSM what operation is being done and leaves it to those functions to decide how to map that onto the available permits. However, I don't really want to make these change in the middle of the notifications patchset.] Signed-off-by: David Howells cc: Jarkko Sakkinen cc: Paul Moore cc: Stephen Smalley cc: Casey Schaufler cc: keyrings@vger.kernel.org cc: selinux@vger.kernel.org --- include/linux/key.h | 30 ++++++++++++++++++------------ include/linux/security.h | 6 +++--- 2 files changed, 21 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index b99b40db08fc..0f2e24f13c2b 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -71,6 +71,23 @@ struct net; #define KEY_PERM_UNDEF 0xffffffff +/* + * The permissions required on a key that we're looking up. + */ +enum key_need_perm { + KEY_NEED_UNSPECIFIED, /* Needed permission unspecified */ + KEY_NEED_VIEW, /* Require permission to view attributes */ + KEY_NEED_READ, /* Require permission to read content */ + KEY_NEED_WRITE, /* Require permission to update / modify */ + KEY_NEED_SEARCH, /* Require permission to search (keyring) or find (key) */ + KEY_NEED_LINK, /* Require permission to link */ + KEY_NEED_SETATTR, /* Require permission to change attributes */ + KEY_NEED_UNLINK, /* Require permission to unlink key */ + KEY_SYSADMIN_OVERRIDE, /* Special: override by CAP_SYS_ADMIN */ + KEY_AUTHTOKEN_OVERRIDE, /* Special: override by possession of auth token */ + KEY_DEFER_PERM_CHECK, /* Special: permission check is deferred */ +}; + struct seq_file; struct user_struct; struct signal_struct; @@ -420,20 +437,9 @@ static inline key_serial_t key_serial(const struct key *key) extern void key_set_timeout(struct key *, unsigned); extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags, - key_perm_t perm); + enum key_need_perm need_perm); extern void key_free_user_ns(struct user_namespace *); -/* - * The permissions required on a key that we're looking up. - */ -#define KEY_NEED_VIEW 0x01 /* Require permission to view attributes */ -#define KEY_NEED_READ 0x02 /* Require permission to read content */ -#define KEY_NEED_WRITE 0x04 /* Require permission to update / modify */ -#define KEY_NEED_SEARCH 0x08 /* Require permission to search (keyring) or find (key) */ -#define KEY_NEED_LINK 0x10 /* Require permission to link */ -#define KEY_NEED_SETATTR 0x20 /* Require permission to change attributes */ -#define KEY_NEED_ALL 0x3f /* All the above permissions */ - static inline short key_read_state(const struct key *key) { /* Barrier versus mark_key_instantiated(). */ diff --git a/include/linux/security.h b/include/linux/security.h index e7914e4e0b02..57aac14e3418 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1767,8 +1767,8 @@ static inline int security_path_chroot(const struct path *path) int security_key_alloc(struct key *key, const struct cred *cred, unsigned long flags); void security_key_free(struct key *key); -int security_key_permission(key_ref_t key_ref, - const struct cred *cred, unsigned perm); +int security_key_permission(key_ref_t key_ref, const struct cred *cred, + enum key_need_perm need_perm); int security_key_getsecurity(struct key *key, char **_buffer); #else @@ -1786,7 +1786,7 @@ static inline void security_key_free(struct key *key) static inline int security_key_permission(key_ref_t key_ref, const struct cred *cred, - unsigned perm) + enum key_need_perm need_perm) { return 0; } -- cgit v1.2.3 From a8478a602913dc89a7cd2060e613edecd07e1dbd Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Jan 2020 17:07:13 +0000 Subject: smack: Implement the watch_key and post_notification hooks Implement the watch_key security hook in Smack to make sure that a key grants the caller Read permission in order to set a watch on a key. Also implement the post_notification security hook to make sure that the notification source is granted Write permission by the watch queue. For the moment, the watch_devices security hook is left unimplemented as it's not obvious what the object should be since the queue is global and didn't previously exist. Signed-off-by: David Howells Acked-by: Casey Schaufler --- include/linux/lsm_audit.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index 99d629fd9944..28f23b341c1c 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -75,6 +75,7 @@ struct common_audit_data { #define LSM_AUDIT_DATA_IBPKEY 13 #define LSM_AUDIT_DATA_IBENDPORT 14 #define LSM_AUDIT_DATA_LOCKDOWN 15 +#define LSM_AUDIT_DATA_NOTIFICATION 16 union { struct path path; struct dentry *dentry; -- cgit v1.2.3 From c1527c0e12d461ff4c603996f77983f37b85c286 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 18 May 2020 21:07:35 -0700 Subject: bio.h: Declare the arguments of the bio iteration functions const This change makes it possible to pass 'const struct bio *' arguments to these functions. Signed-off-by: Bart Van Assche Reviewed-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Cc: Ming Lei Cc: Damien Le Moal Cc: Chaitanya Kulkarni Cc: Alexander Potapenko Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index a0ee494a6329..950c9dc44c4f 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -70,7 +70,7 @@ static inline bool bio_has_data(struct bio *bio) return false; } -static inline bool bio_no_advance_iter(struct bio *bio) +static inline bool bio_no_advance_iter(const struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || @@ -138,8 +138,8 @@ static inline bool bio_next_segment(const struct bio *bio, #define bio_for_each_segment_all(bvl, bio, iter) \ for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); ) -static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, - unsigned bytes) +static inline void bio_advance_iter(const struct bio *bio, + struct bvec_iter *iter, unsigned int bytes) { iter->bi_sector += bytes >> 9; -- cgit v1.2.3 From 854b5f01dc6a7b59f0dddd646a80b1fcd767a8db Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 18 May 2020 21:07:36 -0700 Subject: block: Document the bio_vec properties Since it is nontrivial that nth_page() does not have to be used for a bio_vec, document this. Signed-off-by: Bart Van Assche Reviewed-by: Christoph Hellwig CC: Christoph Hellwig Cc: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bvec.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index a81c13ac1972..ac0c7299d5b8 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -12,8 +12,17 @@ #include #include -/* - * was unsigned short, but we might as well be ready for > 64kB I/O pages +/** + * struct bio_vec - a contiguous range of physical memory addresses + * @bv_page: First page associated with the address range. + * @bv_len: Number of bytes in the address range. + * @bv_offset: Start of the address range relative to the start of @bv_page. + * + * The following holds for a bvec if n * PAGE_SIZE < bv_offset + bv_len: + * + * nth_page(@bv_page, n) == @bv_page + n + * + * This holds because page_is_mergeable() checks the above property. */ struct bio_vec { struct page *bv_page; -- cgit v1.2.3 From 062022315e8ad9e0628515dfc756ab54b5fdb26b Mon Sep 17 00:00:00 2001 From: James Morse Date: Fri, 1 May 2020 17:45:41 +0100 Subject: mm/memory-failure: Add memory_failure_queue_kick() The GHES code calls memory_failure_queue() from IRQ context to schedule work on the current CPU so that memory_failure() can sleep. For synchronous memory errors the arch code needs to know any signals that memory_failure() will trigger are pending before it returns to user-space, possibly when exiting from the IRQ. Add a helper to kick the memory failure queue, to ensure the scheduled work has happened. This has to be called from process context, so may have been migrated from the original cpu. Pass the cpu the work was queued on. Change memory_failure_work_func() to permit being called on the 'wrong' cpu. Signed-off-by: James Morse Tested-by: Tyler Baicar Acked-by: Naoya Horiguchi Signed-off-by: Rafael J. Wysocki --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a323422d783..c606dbbfa5e1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3012,6 +3012,7 @@ enum mf_flags { }; extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); +extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern int get_hwpoison_page(struct page *page); #define put_hwpoison_page(page) put_page(page) -- cgit v1.2.3 From 1b66d253610c7f8f257103808a9460223a087469 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 19 May 2020 00:45:45 +0200 Subject: bpf: Add get{peer, sock}name attach types for sock_addr As stated in 983695fa6765 ("bpf: fix unconnected udp hooks"), the objective for the existing cgroup connect/sendmsg/recvmsg/bind BPF hooks is to be transparent to applications. In Cilium we make use of these hooks [0] in order to enable E-W load balancing for existing Kubernetes service types for all Cilium managed nodes in the cluster. Those backends can be local or remote. The main advantage of this approach is that it operates as close as possible to the socket, and therefore allows to avoid packet-based NAT given in connect/sendmsg/recvmsg hooks we only need to xlate sock addresses. This also allows to expose NodePort services on loopback addresses in the host namespace, for example. As another advantage, this also efficiently blocks bind requests for applications in the host namespace for exposed ports. However, one missing item is that we also need to perform reverse xlation for inet{,6}_getname() hooks such that we can return the service IP/port tuple back to the application instead of the remote peer address. The vast majority of applications does not bother about getpeername(), but in a few occasions we've seen breakage when validating the peer's address since it returns unexpectedly the backend tuple instead of the service one. Therefore, this trivial patch allows to customise and adds a getpeername() as well as getsockname() BPF cgroup hook for both IPv4 and IPv6 in order to address this situation. Simple example: # ./cilium/cilium service list ID Frontend Service Type Backend 1 1.2.3.4:80 ClusterIP 1 => 10.0.0.10:80 Before; curl's verbose output example, no getpeername() reverse xlation: # curl --verbose 1.2.3.4 * Rebuilt URL to: 1.2.3.4/ * Trying 1.2.3.4... * TCP_NODELAY set * Connected to 1.2.3.4 (10.0.0.10) port 80 (#0) > GET / HTTP/1.1 > Host: 1.2.3.4 > User-Agent: curl/7.58.0 > Accept: */* [...] After; with getpeername() reverse xlation: # curl --verbose 1.2.3.4 * Rebuilt URL to: 1.2.3.4/ * Trying 1.2.3.4... * TCP_NODELAY set * Connected to 1.2.3.4 (1.2.3.4) port 80 (#0) > GET / HTTP/1.1 > Host: 1.2.3.4 > User-Agent: curl/7.58.0 > Accept: */* [...] Originally, I had both under a BPF_CGROUP_INET{4,6}_GETNAME type and exposed peer to the context similar as in inet{,6}_getname() fashion, but API-wise this is suboptimal as it always enforces programs having to test for ctx->peer which can easily be missed, hence BPF_CGROUP_INET{4,6}_GET{PEER,SOCK}NAME split. Similarly, the checked return code is on tnum_range(1, 1), but if a use case comes up in future, it can easily be changed to return an error code instead. Helper and ctx member access is the same as with connect/sendmsg/etc hooks. [0] https://github.com/cilium/cilium/blob/master/bpf/bpf_sock.c Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Andrey Ignatov Link: https://lore.kernel.org/bpf/61a479d759b2482ae3efb45546490bacd796a220.1589841594.git.daniel@iogearbox.net --- include/linux/bpf-cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 272626cc3fc9..c66c545e161a 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -396,6 +396,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, } #define cgroup_bpf_enabled (0) +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) -- cgit v1.2.3 From c50c75e9b87946499a62bffc021e95c87a1d57cd Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 11 May 2020 15:12:27 -0500 Subject: perf/core: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200511201227.GA14041@embeddedor --- include/linux/perf_event.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 87e21681759c..d7b610c4eebd 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -61,7 +61,7 @@ struct perf_guest_info_callbacks { struct perf_callchain_entry { __u64 nr; - __u64 ip[0]; /* /proc/sys/kernel/perf_event_max_stack */ + __u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { @@ -113,7 +113,7 @@ struct perf_raw_record { struct perf_branch_stack { __u64 nr; __u64 hw_idx; - struct perf_branch_entry entries[0]; + struct perf_branch_entry entries[]; }; struct task_struct; -- cgit v1.2.3 From 607259a695312cdfac2b52fb9d5b5890c834d573 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 May 2020 15:03:13 +0200 Subject: net: add a new ndo_tunnel_ioctl method This method is used to properly allow kernel callers of the IPv4 route management ioctls. The exsting ip_tunnel_ioctl helper is renamed to ip_tunnel_ctl to better reflect that it doesn't directly implement ioctls touching user memory, and is used for the guts of ndo_tunnel_ctl implementations. A new ip_tunnel_ioctl helper is added that can be wired up directly to the ndo_do_ioctl method and takes care of the copy to and from userspace. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6a8f8daef09d..a18f8fdf4260 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -53,6 +53,7 @@ struct netpoll_info; struct device; struct phy_device; struct dsa_port; +struct ip_tunnel_parm; struct macsec_context; struct macsec_ops; @@ -1274,6 +1275,9 @@ struct netdev_net_notifier { * Get devlink port instance associated with a given netdev. * Called with a reference on the netdevice and devlink locks only, * rtnl_lock is not held. + * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, + * int cmd); + * Add, change, delete or get information on an IPv4 tunnel. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1479,6 +1483,8 @@ struct net_device_ops { int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev); + int (*ndo_tunnel_ctl)(struct net_device *dev, + struct ip_tunnel_parm *p, int cmd); }; /** -- cgit v1.2.3 From febd668d375caf13a7fcd93b3498366854de854a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 18 May 2020 06:30:09 -0400 Subject: rcuwait: avoid lockdep splats from rcuwait_active() rcuwait_active only returns whether w->task is not NULL. This is exactly one of the usecases that are mentioned in the documentation for rcu_access_pointer() where it is correct to bypass lockdep checks. This avoids a splat from kvm_vcpu_on_spin(). Reported-by: Wanpeng Li Tested-by: Wanpeng Li Acked-by: Davidlohr Bueso Cc: Peter Zijlstra Signed-off-by: Paolo Bonzini --- include/linux/rcuwait.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index c1414ce44abc..61c56cca95c4 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -31,7 +31,7 @@ static inline void rcuwait_init(struct rcuwait *w) */ static inline int rcuwait_active(struct rcuwait *w) { - return !!rcu_dereference(w->task); + return !!rcu_access_pointer(w->task); } extern int rcuwait_wake_up(struct rcuwait *w); -- cgit v1.2.3 From a1ceea67f2e5b73cebd456e7fb463b3052bc6344 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Mon, 27 Apr 2020 16:25:27 +0200 Subject: PCI/IOV: Introduce pci_iov_sysfs_link() function Currently pci_iov_add_virtfn() scans the SR-IOV BARs, adds the VF to the bus and also creates the sysfs links between the newly added VF and its parent PF. With pdev->no_vf_scan fencing off the entire pci_iov_add_virtfn() call s390 as the sole pdev->no_vf_scan user thus ends up missing these sysfs links which are required for example by QEMU/libvirt. Instead of duplicating the code refactor pci_iov_add_virtfn() to make sysfs link creation callable separately. Signed-off-by: Niklas Schnelle Acked-by: Bjorn Helgaas Reviewed-by: Pierre Morel Link: https://lore.kernel.org/r/20200506154139.90609-1-schnelle@linux.ibm.com Signed-off-by: Vasily Gorbik --- include/linux/pci.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 83ce1cdf5676..93a063a7d7f9 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2048,6 +2048,8 @@ int pci_iov_virtfn_devfn(struct pci_dev *dev, int id); int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); void pci_disable_sriov(struct pci_dev *dev); + +int pci_iov_sysfs_link(struct pci_dev *dev, struct pci_dev *virtfn, int id); int pci_iov_add_virtfn(struct pci_dev *dev, int id); void pci_iov_remove_virtfn(struct pci_dev *dev, int id); int pci_num_vf(struct pci_dev *dev); @@ -2073,6 +2075,12 @@ static inline int pci_iov_virtfn_devfn(struct pci_dev *dev, int id) } static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { return -ENODEV; } + +static inline int pci_iov_sysfs_link(struct pci_dev *dev, + struct pci_dev *virtfn, int id) +{ + return -ENODEV; +} static inline int pci_iov_add_virtfn(struct pci_dev *dev, int id) { return -ENOSYS; -- cgit v1.2.3 From 7769e18c201aa88eade5556faf9da7f2bc15bb8a Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 6 Apr 2020 02:15:14 +0200 Subject: scsi: storvsc: Re-init stor_chns when a channel interrupt is re-assigned For each storvsc_device, storvsc keeps track of the channel target CPUs associated to the device (alloced_cpus) and it uses this information to fill a "cache" (stor_chns) mapping CPU->channel according to a certain heuristic. Update the alloced_cpus mask and the stor_chns array when a channel of the storvsc device is re-assigned to a different CPU. Signed-off-by: Andrea Parri (Microsoft) Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Link: https://lore.kernel.org/r/20200406001514.19876-12-parri.andrea@gmail.com Reviewed-by; Long Li Reviewed-by: Michael Kelley [ wei: fix a small issue reported by kbuild test robot ] Signed-off-by: Wei Liu --- include/linux/hyperv.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b85d7580f2c1..cd64ab7bb3b7 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -773,6 +773,9 @@ struct vmbus_channel { void (*onchannel_callback)(void *context); void *channel_callback_context; + void (*change_target_cpu_callback)(struct vmbus_channel *channel, + u32 old, u32 new); + /* * Synchronize channel scheduling and channel removal; see the inline * comments in vmbus_chan_sched() and vmbus_reset_channel_cb(). -- cgit v1.2.3 From b7d18c57c94a38a81c1dbcfee0d63153ffaf1856 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 23 Apr 2020 16:45:05 +0300 Subject: hyper-v: Switch to use UUID types directly uuid_le is an alias for guid_t and is going to be removed in the future. Replace it with original type. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200423134505.78221-4-andriy.shevchenko@linux.intel.com Signed-off-by: Wei Liu --- include/linux/mod_devicetable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 4c2ddd0941a7..f36b1cf5ffe3 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -434,7 +434,7 @@ struct virtio_device_id { * For Hyper-V devices we use the device guid as the id. */ struct hv_vmbus_device_id { - uuid_le guid; + guid_t guid; kernel_ulong_t driver_data; /* Data private to the driver */ }; -- cgit v1.2.3 From db5871e85533f06ffe1795c1cb9b9153860d1e4f Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:53:23 -0500 Subject: vmbus: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200507185323.GA14416@embeddedor Signed-off-by: Wei Liu --- include/linux/hyperv.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index cd64ab7bb3b7..d783847d8cb4 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -117,7 +117,7 @@ struct hv_ring_buffer { * Ring data starts here + RingDataStartOffset * !!! DO NOT place any fields below this !!! */ - u8 buffer[0]; + u8 buffer[]; } __packed; struct hv_ring_buffer_info { @@ -313,7 +313,7 @@ struct vmadd_remove_transfer_page_set { struct gpa_range { u32 byte_count; u32 byte_offset; - u64 pfn_array[0]; + u64 pfn_array[]; }; /* @@ -563,7 +563,7 @@ struct vmbus_channel_gpadl_header { u32 gpadl; u16 range_buflen; u16 rangecount; - struct gpa_range range[0]; + struct gpa_range range[]; } __packed; /* This is the followup packet that contains more PFNs. */ @@ -571,7 +571,7 @@ struct vmbus_channel_gpadl_body { struct vmbus_channel_message_header header; u32 msgnumber; u32 gpadl; - u64 pfn[0]; + u64 pfn[]; } __packed; struct vmbus_channel_gpadl_created { @@ -679,7 +679,7 @@ struct vmbus_channel_msginfo { * The channel message that goes out on the "wire". * It will contain at minimum the VMBUS_CHANNEL_MESSAGE_HEADER header */ - unsigned char msg[0]; + unsigned char msg[]; }; struct vmbus_close_msg { -- cgit v1.2.3 From d85234994b2fb2d88fadd3d9e60385b02b244dac Mon Sep 17 00:00:00 2001 From: Tim Harvey Date: Fri, 15 May 2020 10:57:07 -0700 Subject: mfd: Add Gateworks System Controller core driver The Gateworks System Controller (GSC) is an I2C slave controller implemented with an MSP430 micro-controller whose firmware embeds the following features: - I/O expander (16 GPIO's) using PCA955x protocol - Real Time Clock using DS1672 protocol - User EEPROM using AT24 protocol - HWMON using custom protocol - Interrupt controller with tamper detect, user pushbotton - Watchdog controller capable of full board power-cycle - Power Control capable of full board power-cycle see http://trac.gateworks.com/wiki/gsc for more details Signed-off-by: Tim Harvey Signed-off-by: Lee Jones --- include/linux/mfd/gsc.h | 76 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+) create mode 100644 include/linux/mfd/gsc.h (limited to 'include/linux') diff --git a/include/linux/mfd/gsc.h b/include/linux/mfd/gsc.h new file mode 100644 index 000000000000..6bd639c285b4 --- /dev/null +++ b/include/linux/mfd/gsc.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (C) 2020 Gateworks Corporation + */ +#ifndef __LINUX_MFD_GSC_H_ +#define __LINUX_MFD_GSC_H_ + +#include + +/* Device Addresses */ +#define GSC_MISC 0x20 +#define GSC_UPDATE 0x21 +#define GSC_GPIO 0x23 +#define GSC_HWMON 0x29 +#define GSC_EEPROM0 0x50 +#define GSC_EEPROM1 0x51 +#define GSC_EEPROM2 0x52 +#define GSC_EEPROM3 0x53 +#define GSC_RTC 0x68 + +/* Register offsets */ +enum { + GSC_CTRL_0 = 0x00, + GSC_CTRL_1 = 0x01, + GSC_TIME = 0x02, + GSC_TIME_ADD = 0x06, + GSC_IRQ_STATUS = 0x0A, + GSC_IRQ_ENABLE = 0x0B, + GSC_FW_CRC = 0x0C, + GSC_FW_VER = 0x0E, + GSC_WP = 0x0F, +}; + +/* Bit definitions */ +#define GSC_CTRL_0_PB_HARD_RESET 0 +#define GSC_CTRL_0_PB_CLEAR_SECURE_KEY 1 +#define GSC_CTRL_0_PB_SOFT_POWER_DOWN 2 +#define GSC_CTRL_0_PB_BOOT_ALTERNATE 3 +#define GSC_CTRL_0_PERFORM_CRC 4 +#define GSC_CTRL_0_TAMPER_DETECT 5 +#define GSC_CTRL_0_SWITCH_HOLD 6 + +#define GSC_CTRL_1_SLEEP_ENABLE 0 +#define GSC_CTRL_1_SLEEP_ACTIVATE 1 +#define GSC_CTRL_1_SLEEP_ADD 2 +#define GSC_CTRL_1_SLEEP_NOWAKEPB 3 +#define GSC_CTRL_1_WDT_TIME 4 +#define GSC_CTRL_1_WDT_ENABLE 5 +#define GSC_CTRL_1_SWITCH_BOOT_ENABLE 6 +#define GSC_CTRL_1_SWITCH_BOOT_CLEAR 7 + +#define GSC_IRQ_PB 0 +#define GSC_IRQ_KEY_ERASED 1 +#define GSC_IRQ_EEPROM_WP 2 +#define GSC_IRQ_RESV 3 +#define GSC_IRQ_GPIO 4 +#define GSC_IRQ_TAMPER 5 +#define GSC_IRQ_WDT_TIMEOUT 6 +#define GSC_IRQ_SWITCH_HOLD 7 + +int gsc_read(void *context, unsigned int reg, unsigned int *val); +int gsc_write(void *context, unsigned int reg, unsigned int val); + +struct gsc_dev { + struct device *dev; + + struct i2c_client *i2c; /* 0x20: interrupt controller, WDT */ + struct i2c_client *i2c_hwmon; /* 0x29: hwmon, fan controller */ + + struct regmap *regmap; + + unsigned int fwver; + unsigned short fwcrc; +}; + +#endif /* __LINUX_MFD_GSC_H_ */ -- cgit v1.2.3 From 3bce5377ef66a8700dcf7a9cb89b7aeb99326cb7 Mon Sep 17 00:00:00 2001 From: Tim Harvey Date: Fri, 15 May 2020 10:57:08 -0700 Subject: hwmon: Add Gateworks System Controller support The Gateworks System Controller has a hwmon sub-component that exposes up to 16 ADC's, some of which are temperature sensors, others which are voltage inputs. The ADC configuration (register mapping and name) is configured via device-tree and varies board to board. Signed-off-by: Tim Harvey Reviewed-by: Guenter Roeck Signed-off-by: Lee Jones --- include/linux/platform_data/gsc_hwmon.h | 44 +++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 include/linux/platform_data/gsc_hwmon.h (limited to 'include/linux') diff --git a/include/linux/platform_data/gsc_hwmon.h b/include/linux/platform_data/gsc_hwmon.h new file mode 100644 index 000000000000..ec1611aff863 --- /dev/null +++ b/include/linux/platform_data/gsc_hwmon.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _GSC_HWMON_H +#define _GSC_HWMON_H + +enum gsc_hwmon_mode { + mode_temperature, + mode_voltage, + mode_voltage_raw, + mode_max, +}; + +/** + * struct gsc_hwmon_channel - configuration parameters + * @reg: I2C register offset + * @mode: channel mode + * @name: channel name + * @mvoffset: voltage offset + * @vdiv: voltage divider array (2 resistor values in milli-ohms) + */ +struct gsc_hwmon_channel { + unsigned int reg; + unsigned int mode; + const char *name; + unsigned int mvoffset; + unsigned int vdiv[2]; +}; + +/** + * struct gsc_hwmon_platform_data - platform data for gsc_hwmon driver + * @channels: pointer to array of gsc_hwmon_channel structures + * describing channels + * @nchannels: number of elements in @channels array + * @vreference: voltage reference (mV) + * @resolution: ADC bit resolution + * @fan_base: register base for FAN controller + */ +struct gsc_hwmon_platform_data { + const struct gsc_hwmon_channel *channels; + int nchannels; + unsigned int resolution; + unsigned int vreference; + unsigned int fan_base; +}; +#endif -- cgit v1.2.3 From 6bf393c577c4a6e324ab103425fbf71126e5385b Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 19 May 2020 04:35:49 +0800 Subject: soundwire: disco: s/ch/channels/ Use more meaningful member names in preparation for sysfs support. No functionality change. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20200518203551.2053-2-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 7658d9698dd5..9c27a32df9bb 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -291,8 +291,8 @@ struct sdw_dpn_audio_mode { * implementation-defined interrupts * @max_ch: Maximum channels supported * @min_ch: Minimum channels supported - * @num_ch: Number of discrete channels supported - * @ch: Discrete channels supported + * @num_channels: Number of discrete channels supported + * @channels: Discrete channels supported * @num_ch_combinations: Number of channel combinations supported * @ch_combinations: Channel combinations supported * @modes: SDW mode supported @@ -316,8 +316,8 @@ struct sdw_dpn_prop { u32 imp_def_interrupts; u32 max_ch; u32 min_ch; - u32 num_ch; - u32 *ch; + u32 num_channels; + u32 *channels; u32 num_ch_combinations; u32 *ch_combinations; u32 modes; -- cgit v1.2.3 From 6fe12cdbcfe35ad4726a619a9546822d34fc934c Mon Sep 17 00:00:00 2001 From: Bibby Hsieh Date: Tue, 19 May 2020 15:27:29 +0800 Subject: i2c: core: support bus regulator controlling in adapter Although in the most platforms, the bus power of i2c are alway on, some platforms disable the i2c bus power in order to meet low power request. We get and enable bulk regulator in i2c adapter device. Signed-off-by: Bibby Hsieh Reviewed-by: Tomasz Figa Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 456fc17ecb1c..bc83af0d38d1 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -15,6 +15,7 @@ #include /* for struct device */ #include /* for completion */ #include +#include #include #include /* for Host Notify IRQ */ #include /* for struct device_node */ @@ -721,6 +722,7 @@ struct i2c_adapter { const struct i2c_adapter_quirks *quirks; struct irq_domain *host_notify_domain; + struct regulator *bus_regulator; }; #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev) -- cgit v1.2.3 From f6dd975583bd8ce088400648fd9819e4691c8958 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 May 2020 17:58:12 +0200 Subject: pipe: merge anon_pipe_buf*_ops All the op vectors are exactly the same, they are just used to encode packet or nomerge behavior. There already is a flag for the packet behavior, so just add a new one to allow for merging. Inverting it vs the previous nomerge special casing actually allows for much nicer code. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/pipe_fs_i.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index ae58fad7f1e0..3f7b07b38824 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -8,6 +8,7 @@ #define PIPE_BUF_FLAG_ATOMIC 0x02 /* was atomically mapped */ #define PIPE_BUF_FLAG_GIFT 0x04 /* page is a gift */ #define PIPE_BUF_FLAG_PACKET 0x08 /* read() as a packet */ +#define PIPE_BUF_FLAG_CAN_MERGE 0x10 /* can merge buffers */ /** * struct pipe_buffer - a linux kernel pipe buffer @@ -233,7 +234,6 @@ int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); -void pipe_buf_mark_unmergeable(struct pipe_buffer *buf); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; -- cgit v1.2.3 From 76887c256744740d6121af9bc4aa787712a1f694 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 May 2020 17:58:14 +0200 Subject: fs: make the pipe_buf_operations ->steal operation optional Just return 1 for failure if it is not present. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/pipe_fs_i.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 3f7b07b38824..e022b2459301 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -206,6 +206,8 @@ static inline int pipe_buf_confirm(struct pipe_inode_info *pipe, static inline int pipe_buf_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { + if (!buf->ops->steal) + return 1; return buf->ops->steal(pipe, buf); } @@ -232,7 +234,6 @@ void free_pipe_info(struct pipe_inode_info *); bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); -int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; -- cgit v1.2.3 From b8d9e7f2411b0744df2ec33e80d7698180fef21a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 May 2020 17:58:15 +0200 Subject: fs: make the pipe_buf_operations ->confirm operation optional Just return 0 for success if it is not present. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/pipe_fs_i.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index e022b2459301..7c057daa0931 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -82,7 +82,7 @@ struct pipe_buf_operations { * and that the contents are good. If the pages in the pipe belong * to a file system, we may need to wait for IO completion in this * hook. Returns 0 for good, or a negative error value in case of - * error. + * error. If not present all pages are considered good. */ int (*confirm)(struct pipe_inode_info *, struct pipe_buffer *); @@ -195,6 +195,8 @@ static inline void pipe_buf_release(struct pipe_inode_info *pipe, static inline int pipe_buf_confirm(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { + if (!buf->ops->confirm) + return 0; return buf->ops->confirm(pipe, buf); } @@ -232,7 +234,6 @@ void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); -int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); -- cgit v1.2.3 From c928f642c29a5ffb02e16f2430b42b876dde69de Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 May 2020 17:58:16 +0200 Subject: fs: rename pipe_buf ->steal to ->try_steal And replace the arcane return value convention with a simple bool where true means success and false means failure. [AV: braino fix folded in] Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/pipe_fs_i.h | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 7c057daa0931..0c31b9461262 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -70,11 +70,11 @@ struct pipe_inode_info { * Note on the nesting of these functions: * * ->confirm() - * ->steal() + * ->try_steal() * - * That is, ->steal() must be called on a confirmed buffer. - * See below for the meaning of each operation. Also see kerneldoc - * in fs/pipe.c for the pipe and generic variants of these hooks. + * That is, ->try_steal() must be called on a confirmed buffer. See below for + * the meaning of each operation. Also see the kerneldoc in fs/pipe.c for the + * pipe and generic variants of these hooks. */ struct pipe_buf_operations { /* @@ -94,13 +94,13 @@ struct pipe_buf_operations { /* * Attempt to take ownership of the pipe buffer and its contents. - * ->steal() returns 0 for success, in which case the contents - * of the pipe (the buf->page) is locked and now completely owned - * by the caller. The page may then be transferred to a different - * mapping, the most often used case is insertion into different - * file address space cache. + * ->try_steal() returns %true for success, in which case the contents + * of the pipe (the buf->page) is locked and now completely owned by the + * caller. The page may then be transferred to a different mapping, the + * most often used case is insertion into different file address space + * cache. */ - int (*steal)(struct pipe_inode_info *, struct pipe_buffer *); + bool (*try_steal)(struct pipe_inode_info *, struct pipe_buffer *); /* * Get a reference to the pipe buffer. @@ -201,16 +201,16 @@ static inline int pipe_buf_confirm(struct pipe_inode_info *pipe, } /** - * pipe_buf_steal - attempt to take ownership of a pipe_buffer + * pipe_buf_try_steal - attempt to take ownership of a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal */ -static inline int pipe_buf_steal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) +static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) { - if (!buf->ops->steal) - return 1; - return buf->ops->steal(pipe, buf); + if (!buf->ops->try_steal) + return false; + return buf->ops->try_steal(pipe, buf); } /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual @@ -234,7 +234,7 @@ void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); -int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); +bool generic_pipe_buf_try_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; -- cgit v1.2.3 From 9b47c5275614a16fd64359fab73fe6c736bf57a0 Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Mon, 18 May 2020 15:07:10 -0400 Subject: efi/libstub: Add definitions for console input and events Add the required typedefs etc for using con_in's simple text input protocol, and for using the boottime event services. Also add the prototype for the "stall" boot service. Signed-off-by: Arvind Sankar Link: https://lore.kernel.org/r/20200518190716.751506-19-nivedita@alum.mit.edu Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 9b7c7ec319ac..974648db0c68 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -426,6 +426,7 @@ typedef struct { u32 tables; } efi_system_table_32_t; +typedef union efi_simple_text_input_protocol efi_simple_text_input_protocol_t; typedef union efi_simple_text_output_protocol efi_simple_text_output_protocol_t; typedef union { @@ -434,7 +435,7 @@ typedef union { unsigned long fw_vendor; /* physical addr of CHAR16 vendor string */ u32 fw_revision; unsigned long con_in_handle; - unsigned long con_in; + efi_simple_text_input_protocol_t *con_in; unsigned long con_out_handle; efi_simple_text_output_protocol_t *con_out; unsigned long stderr_handle; -- cgit v1.2.3 From 14c574f35cfbc9272fc67b41f074c847db139652 Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Mon, 18 May 2020 15:07:11 -0400 Subject: efi/gop: Add an option to list out the available GOP modes Add video=efifb:list option to list the modes that are available. Signed-off-by: Arvind Sankar Link: https://lore.kernel.org/r/20200518190716.751506-20-nivedita@alum.mit.edu Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 974648db0c68..609201bd4682 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -39,6 +39,7 @@ #define EFI_WRITE_PROTECTED ( 8 | (1UL << (BITS_PER_LONG-1))) #define EFI_OUT_OF_RESOURCES ( 9 | (1UL << (BITS_PER_LONG-1))) #define EFI_NOT_FOUND (14 | (1UL << (BITS_PER_LONG-1))) +#define EFI_TIMEOUT (18 | (1UL << (BITS_PER_LONG-1))) #define EFI_ABORTED (21 | (1UL << (BITS_PER_LONG-1))) #define EFI_SECURITY_VIOLATION (26 | (1UL << (BITS_PER_LONG-1))) -- cgit v1.2.3 From 15c704ab6244ac95be54b2c05411b70501d50e8f Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 18 May 2020 10:12:17 +0100 Subject: firmware: smccc: Update link to latest SMCCC specification The current link gets redirected to the revision B published in November 2016 though it actually points to the original revision A published in June 2013. Let us update the link to point to the latest version, so that it doesn't get stale anytime soon. Currently it points to v1.2 published in March 2020(i.e. DEN0028C). Signed-off-by: Sudeep Holla Tested-by: Etienne Carriere Reviewed-by: Steven Price Reviewed-by: Etienne Carriere Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20200518091222.27467-3-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 59494df0f55b..31b15db9685d 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -10,7 +10,9 @@ /* * This file provides common defines for ARM SMC Calling Convention as * specified in - * http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html + * https://developer.arm.com/docs/den0028/latest + * + * This code is up-to-date with version DEN 0028 B */ #define ARM_SMCCC_STD_CALL _AC(0,U) -- cgit v1.2.3 From 0441bfe7f00acaae7c4937ba0ca48ee1de9b709f Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 18 May 2020 10:12:18 +0100 Subject: firmware: smccc: Add the definition for SMCCCv1.2 version/error codes Add the definition for SMCCC v1.2 version and new error code added. While at it, also add a note that ARM DEN 0070A is deprecated and is now merged into the main SMCCC specification(ARM DEN 0028C). Signed-off-by: Sudeep Holla Tested-by: Etienne Carriere Reviewed-by: Steven Price Reviewed-by: Etienne Carriere Link: https://lore.kernel.org/r/20200518091222.27467-4-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 31b15db9685d..c3784ba8e2a4 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -12,7 +12,7 @@ * specified in * https://developer.arm.com/docs/den0028/latest * - * This code is up-to-date with version DEN 0028 B + * This code is up-to-date with version DEN 0028 C */ #define ARM_SMCCC_STD_CALL _AC(0,U) @@ -58,6 +58,7 @@ #define ARM_SMCCC_VERSION_1_0 0x10000 #define ARM_SMCCC_VERSION_1_1 0x10001 +#define ARM_SMCCC_VERSION_1_2 0x10002 #define ARM_SMCCC_VERSION_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ @@ -316,10 +317,14 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, */ #define arm_smccc_1_1_hvc(...) __arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__) -/* Return codes defined in ARM DEN 0070A */ +/* + * Return codes defined in ARM DEN 0070A + * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C + */ #define SMCCC_RET_SUCCESS 0 #define SMCCC_RET_NOT_SUPPORTED -1 #define SMCCC_RET_NOT_REQUIRED -2 +#define SMCCC_RET_INVALID_PARAMETER -3 /* * Like arm_smccc_1_1* but always returns SMCCC_RET_NOT_SUPPORTED. -- cgit v1.2.3 From ad5a57dfe434b02ab28852703d7ad5510998ccef Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 18 May 2020 10:12:19 +0100 Subject: firmware: smccc: Drop smccc_version enum and use ARM_SMCCC_VERSION_1_x instead Instead of maintaining 2 sets of enums/macros for tracking SMCCC version, let us drop smccc_version enum and use ARM_SMCCC_VERSION_1_x directly instead. This is in preparation to drop smccc_version here and move it separately under drivers/firmware/smccc. Signed-off-by: Sudeep Holla Tested-by: Etienne Carriere Reviewed-by: Steven Price Reviewed-by: Etienne Carriere Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20200518091222.27467-5-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/psci.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/psci.h b/include/linux/psci.h index a67712b73b6c..29bd0671e5bb 100644 --- a/include/linux/psci.h +++ b/include/linux/psci.h @@ -21,11 +21,6 @@ bool psci_power_state_is_valid(u32 state); int psci_set_osi_mode(void); bool psci_has_osi_support(void); -enum smccc_version { - SMCCC_VERSION_1_0, - SMCCC_VERSION_1_1, -}; - struct psci_operations { u32 (*get_version)(void); int (*cpu_suspend)(u32 state, unsigned long entry_point); @@ -36,7 +31,7 @@ struct psci_operations { unsigned long lowest_affinity_level); int (*migrate_info_type)(void); enum arm_smccc_conduit conduit; - enum smccc_version smccc_version; + u32 smccc_version; }; extern struct psci_operations psci_ops; -- cgit v1.2.3 From f2ae97062a48b114bcf8fb2e99574d9ed2c2cd1b Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 18 May 2020 10:12:20 +0100 Subject: firmware: smccc: Refactor SMCCC specific bits into separate file In order to add newer SMCCC v1.1+ functionality and to avoid cluttering PSCI firmware driver with SMCCC bits, let us move the SMCCC specific details under drivers/firmware/smccc/smccc.c We can also drop conduit and smccc_version from psci_operations structure as SMCCC was the sole user and now it maintains those. No functionality change in this patch though. Signed-off-by: Sudeep Holla Tested-by: Etienne Carriere Reviewed-by: Etienne Carriere Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20200518091222.27467-6-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/psci.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/psci.h b/include/linux/psci.h index 29bd0671e5bb..14ad9b9ebcd6 100644 --- a/include/linux/psci.h +++ b/include/linux/psci.h @@ -30,8 +30,6 @@ struct psci_operations { int (*affinity_info)(unsigned long target_affinity, unsigned long lowest_affinity_level); int (*migrate_info_type)(void); - enum arm_smccc_conduit conduit; - u32 smccc_version; }; extern struct psci_operations psci_ops; -- cgit v1.2.3 From a4fb17465182c9fc13104e4df04d050892055205 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 18 May 2020 10:12:21 +0100 Subject: firmware: smccc: Add function to fetch SMCCC version For backward compatibility reasons, PSCI maintains SMCCC version as SMCCC didn't provide ARM_SMCCC_VERSION_FUNC_ID until v1.1. PSCI initialises both the SMCCC version and conduit. Similar to the conduit, let us provide accessors to fetch the SMCCC version also so that other SMCCC v1.1+ features can use it. Signed-off-by: Sudeep Holla Tested-by: Etienne Carriere Reviewed-by: Steven Price Reviewed-by: Etienne Carriere Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20200518091222.27467-7-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index c3784ba8e2a4..c491d210e3c3 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -100,6 +100,17 @@ enum arm_smccc_conduit { */ enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void); +/** + * arm_smccc_get_version() + * + * Returns the version to be used for SMCCCv1.1 or later. + * + * When SMCCCv1.1 or above is not present, returns SMCCCv1.0, but this + * does not imply the presence of firmware or a valid conduit. Caller + * handling SMCCCv1.0 must determine the conduit by other means. + */ +u32 arm_smccc_get_version(void); + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 -- cgit v1.2.3 From b8bff599261c930630385ee21d3f98e7ce7d4843 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 22 Mar 2020 15:46:24 -0500 Subject: exec: Factor security_bprm_creds_for_exec out of security_bprm_set_creds Today security_bprm_set_creds has several implementations: apparmor_bprm_set_creds, cap_bprm_set_creds, selinux_bprm_set_creds, smack_bprm_set_creds, and tomoyo_bprm_set_creds. Except for cap_bprm_set_creds they all test bprm->called_set_creds and return immediately if it is true. The function cap_bprm_set_creds ignores bprm->calld_sed_creds entirely. Create a new LSM hook security_bprm_creds_for_exec that is called just before prepare_binprm in __do_execve_file, resulting in a LSM hook that is called exactly once for the entire of exec. Modify the bits of security_bprm_set_creds that only want to be called once per exec into security_bprm_creds_for_exec, leaving only cap_bprm_set_creds behind. Remove bprm->called_set_creds all of it's former users have been moved to security_bprm_creds_for_exec. Add or upate comments a appropriate to bring them up to date and to reflect this change. Link: https://lkml.kernel.org/r/87v9kszrzh.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds Acked-by: Casey Schaufler # For the LSM and Smack bits Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 18 +++++----------- include/linux/lsm_hook_defs.h | 1 + include/linux/lsm_hooks.h | 50 ++++++++++++++++++++++++------------------- include/linux/security.h | 6 ++++++ 4 files changed, 40 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 1b48e2154766..d1217fcdedea 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -27,22 +27,14 @@ struct linux_binprm { unsigned long argmin; /* rlimit marker for copy_strings() */ unsigned int /* - * True after the bprm_set_creds hook has been called once - * (multiple calls can be made via prepare_binprm() for - * binfmt_script/misc). - */ - called_set_creds:1, - /* - * True if most recent call to the commoncaps bprm_set_creds - * hook (due to multiple prepare_binprm() calls from the - * binfmt_script/misc handlers) resulted in elevated - * privileges. + * True if most recent call to cap_bprm_set_creds + * resulted in elevated privileges. */ cap_elevated:1, /* - * Set by bprm_set_creds hook to indicate a privilege-gaining - * exec has happened. Used to sanitize execution environment - * and to set AT_SECURE auxv for glibc. + * Set by bprm_creds_for_exec hook to indicate a + * privilege-gaining exec has happened. Used to set + * AT_SECURE auxv for glibc. */ secureexec:1, /* diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 9cd4455528e5..aab0695f41df 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -49,6 +49,7 @@ LSM_HOOK(int, 0, syslog, int type) LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) +LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) LSM_HOOK(int, 0, bprm_set_creds, struct linux_binprm *bprm) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 988ca0df7824..c719af37df20 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -34,40 +34,46 @@ * * Security hooks for program execution operations. * + * @bprm_creds_for_exec: + * If the setup in prepare_exec_creds did not setup @bprm->cred->security + * properly for executing @bprm->file, update the LSM's portion of + * @bprm->cred->security to be what commit_creds needs to install for the + * new program. This hook may also optionally check permissions + * (e.g. for transitions between security domains). + * The hook must set @bprm->secureexec to 1 if AT_SECURE should be set to + * request libc enable secure mode. + * @bprm contains the linux_binprm structure. + * Return 0 if the hook is successful and permission is granted. * @bprm_set_creds: - * Save security information in the bprm->security field, typically based - * on information about the bprm->file, for later use by the apply_creds - * hook. This hook may also optionally check permissions (e.g. for + * Assuming that the relevant bits of @bprm->cred->security have been + * previously set, examine @bprm->file and regenerate them. This is + * so that the credentials derived from the interpreter the code is + * actually going to run are used rather than credentials derived + * from a script. This done because the interpreter binary needs to + * reopen script, and may end up opening something completely different. + * This hook may also optionally check permissions (e.g. for * transitions between security domains). - * This hook may be called multiple times during a single execve, e.g. for - * interpreters. The hook can tell whether it has already been called by - * checking to see if @bprm->security is non-NULL. If so, then the hook - * may decide either to retain the security information saved earlier or - * to replace it. The hook must set @bprm->secureexec to 1 if a "secure - * exec" has happened as a result of this hook call. The flag is used to - * indicate the need for a sanitized execution environment, and is also - * passed in the ELF auxiliary table on the initial stack to indicate - * whether libc should enable secure mode. + * The hook must set @bprm->cap_elevated to 1 if AT_SECURE should be set to + * request libc enable secure mode. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. * @bprm_check_security: * This hook mediates the point when a search for a binary handler will - * begin. It allows a check the @bprm->security value which is set in the - * preceding set_creds call. The primary difference from set_creds is - * that the argv list and envp list are reliably available in @bprm. This - * hook may be called multiple times during a single execve; and in each - * pass set_creds is called first. + * begin. It allows a check against the @bprm->cred->security value + * which was set in the preceding creds_for_exec call. The argv list and + * envp list are reliably available in @bprm. This hook may be called + * multiple times during a single execve. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. * @bprm_committing_creds: * Prepare to install the new security attributes of a process being * transformed by an execve operation, based on the old credentials * pointed to by @current->cred and the information set in @bprm->cred by - * the bprm_set_creds hook. @bprm points to the linux_binprm structure. - * This hook is a good place to perform state changes on the process such - * as closing open file descriptors to which access will no longer be - * granted when the attributes are changed. This is called immediately - * before commit_creds(). + * the bprm_creds_for_exec hook. @bprm points to the linux_binprm + * structure. This hook is a good place to perform state changes on the + * process such as closing open file descriptors to which access will no + * longer be granted when the attributes are changed. This is called + * immediately before commit_creds(). * @bprm_committed_creds: * Tidy up after the installation of the new security attributes of a * process being transformed by an execve operation. The new credentials diff --git a/include/linux/security.h b/include/linux/security.h index a8d9310472df..1bd7a6582775 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -276,6 +276,7 @@ int security_quota_on(struct dentry *dentry); int security_syslog(int type); int security_settime64(const struct timespec64 *ts, const struct timezone *tz); int security_vm_enough_memory_mm(struct mm_struct *mm, long pages); +int security_bprm_creds_for_exec(struct linux_binprm *bprm); int security_bprm_set_creds(struct linux_binprm *bprm); int security_bprm_check(struct linux_binprm *bprm); void security_bprm_committing_creds(struct linux_binprm *bprm); @@ -569,6 +570,11 @@ static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) return __vm_enough_memory(mm, pages, cap_vm_enough_memory(mm, pages)); } +static inline int security_bprm_creds_for_exec(struct linux_binprm *bprm) +{ + return 0; +} + static inline int security_bprm_set_creds(struct linux_binprm *bprm) { return cap_bprm_set_creds(bprm); -- cgit v1.2.3 From 74244b59a82358b9f51c80981a99c5951ea3028f Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Thu, 14 May 2020 08:09:28 +0200 Subject: dm: use dynamic debug instead of compile-time config option Switch to use dynamic debug to avoid having recompile the kernel just to enable debugging messages. Signed-off-by: Hannes Reinecke Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 934037d938b9..8750f2dc5613 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -559,13 +559,8 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); #define DMINFO(fmt, ...) pr_info(DM_FMT(fmt), ##__VA_ARGS__) #define DMINFO_LIMIT(fmt, ...) pr_info_ratelimited(DM_FMT(fmt), ##__VA_ARGS__) -#ifdef CONFIG_DM_DEBUG -#define DMDEBUG(fmt, ...) printk(KERN_DEBUG DM_FMT(fmt), ##__VA_ARGS__) +#define DMDEBUG(fmt, ...) pr_debug(DM_FMT(fmt), ##__VA_ARGS__) #define DMDEBUG_LIMIT(fmt, ...) pr_debug_ratelimited(DM_FMT(fmt), ##__VA_ARGS__) -#else -#define DMDEBUG(fmt, ...) no_printk(fmt, ##__VA_ARGS__) -#define DMDEBUG_LIMIT(fmt, ...) no_printk(fmt, ##__VA_ARGS__) -#endif #define DMEMIT(x...) sz += ((sz >= maxlen) ? \ 0 : scnprintf(result + sz, maxlen - sz, x)) -- cgit v1.2.3 From ca07eda33e01eafa7a26ec06974f7eacee6a89c8 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 20 May 2020 17:30:12 -0400 Subject: SUNRPC: Refactor svc_recvfrom() This function is not currently "generic" so remove the documenting comment and rename it appropriately. Its internals are converted to use bio_vecs for reading from the transport socket. In existing typical sunrpc uses of bio_vecs, the bio_vec array is allocated dynamically. Here, instead, an array of bio_vecs is added to svc_rqst. The lifetime of this array can be greater than one call to xpo_recvfrom(): - Multiple calls to xpo_recvfrom() might be needed to read an RPC message completely. - At some later point, rq_arg.bvecs will point to this array and it will carry the received message into svc_process(). I also expect that a future optimization will remove either the rq_vec or rq_pages array in favor of rq_bvec, thus conserving the size of struct svc_rqst. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index fd390894a584..05da19a0516d 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -254,6 +254,7 @@ struct svc_rqst { struct page * *rq_page_end; /* one past the last page */ struct kvec rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */ + struct bio_vec rq_bvec[RPCSVC_MAXPAGES]; __be32 rq_xid; /* transmission id */ u32 rq_prog; /* program number */ -- cgit v1.2.3 From 931ca7ab7fe804d77bc6952f1512950c0d870f26 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 29 Mar 2020 17:18:30 -0400 Subject: ip*_mc_gsfget(): lift copyout of struct group_filter into callers pass the userland pointer to the array in its tail, so that part gets copied out by our functions; copyout of everything else is done in the callers. Rationale: reuse for compat; the array is the same in native and compat, the layout of parts before it is different for compat. Signed-off-by: Al Viro --- include/linux/igmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index faa6586a5783..64ce8cd1cfaf 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -123,7 +123,7 @@ extern int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf,int ifindex); extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, struct ip_msfilter __user *optval, int __user *optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, - struct group_filter __user *optval, int __user *optlen); + struct sockaddr_storage __user *p); extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); -- cgit v1.2.3 From 4e2e7cfec13afa41fcbed1d9b93d83432aa0154f Mon Sep 17 00:00:00 2001 From: Hsin-Hsiung Wang Date: Tue, 21 Apr 2020 11:00:07 +0800 Subject: mfd: mt6397: Modify suspend/resume behavior Some pmics don't need backup interrupt settings, so we change to use pm notifier for the pmics which are necessary to store settings. Signed-off-by: Hsin-Hsiung Wang Signed-off-by: Lee Jones --- include/linux/mfd/mt6397/core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6397/core.h b/include/linux/mfd/mt6397/core.h index fc88d315bdde..b81d33325ade 100644 --- a/include/linux/mfd/mt6397/core.h +++ b/include/linux/mfd/mt6397/core.h @@ -8,6 +8,7 @@ #define __MFD_MT6397_CORE_H__ #include +#include enum chip_id { MT6323_CHIP_ID = 0x23, @@ -54,6 +55,7 @@ enum mt6397_irq_numbers { struct mt6397_chip { struct device *dev; struct regmap *regmap; + struct notifier_block pm_nb; int irq; struct irq_domain *irq_domain; struct mutex irqlock; -- cgit v1.2.3 From 2b91c28f2abd9471aac4aa6cd8de7896ef469153 Mon Sep 17 00:00:00 2001 From: Hsin-Hsiung Wang Date: Tue, 21 Apr 2020 11:00:10 +0800 Subject: mfd: Add support for the MediaTek MT6358 PMIC This adds support for the MediaTek MT6358 PMIC. This is a multifunction device with the following sub modules: - Regulator - RTC - Codec - Interrupt It is interfaced to the host controller using SPI interface by a proprietary hardware called PMIC wrapper or pwrap. MT6358 MFD is a child device of the pwrap. Signed-off-by: Hsin-Hsiung Wang Signed-off-by: Lee Jones --- include/linux/mfd/mt6358/core.h | 158 ++++++++++++++++++++ include/linux/mfd/mt6358/registers.h | 282 +++++++++++++++++++++++++++++++++++ include/linux/mfd/mt6397/core.h | 3 + 3 files changed, 443 insertions(+) create mode 100644 include/linux/mfd/mt6358/core.h create mode 100644 include/linux/mfd/mt6358/registers.h (limited to 'include/linux') diff --git a/include/linux/mfd/mt6358/core.h b/include/linux/mfd/mt6358/core.h new file mode 100644 index 000000000000..c5a11b7458d4 --- /dev/null +++ b/include/linux/mfd/mt6358/core.h @@ -0,0 +1,158 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 MediaTek Inc. + */ + +#ifndef __MFD_MT6358_CORE_H__ +#define __MFD_MT6358_CORE_H__ + +#define MT6358_REG_WIDTH 16 + +struct irq_top_t { + int hwirq_base; + unsigned int num_int_regs; + unsigned int num_int_bits; + unsigned int en_reg; + unsigned int en_reg_shift; + unsigned int sta_reg; + unsigned int sta_reg_shift; + unsigned int top_offset; +}; + +struct pmic_irq_data { + unsigned int num_top; + unsigned int num_pmic_irqs; + unsigned short top_int_status_reg; + bool *enable_hwirq; + bool *cache_hwirq; +}; + +enum mt6358_irq_top_status_shift { + MT6358_BUCK_TOP = 0, + MT6358_LDO_TOP, + MT6358_PSC_TOP, + MT6358_SCK_TOP, + MT6358_BM_TOP, + MT6358_HK_TOP, + MT6358_AUD_TOP, + MT6358_MISC_TOP, +}; + +enum mt6358_irq_numbers { + MT6358_IRQ_VPROC11_OC = 0, + MT6358_IRQ_VPROC12_OC, + MT6358_IRQ_VCORE_OC, + MT6358_IRQ_VGPU_OC, + MT6358_IRQ_VMODEM_OC, + MT6358_IRQ_VDRAM1_OC, + MT6358_IRQ_VS1_OC, + MT6358_IRQ_VS2_OC, + MT6358_IRQ_VPA_OC, + MT6358_IRQ_VCORE_PREOC, + MT6358_IRQ_VFE28_OC = 16, + MT6358_IRQ_VXO22_OC, + MT6358_IRQ_VRF18_OC, + MT6358_IRQ_VRF12_OC, + MT6358_IRQ_VEFUSE_OC, + MT6358_IRQ_VCN33_OC, + MT6358_IRQ_VCN28_OC, + MT6358_IRQ_VCN18_OC, + MT6358_IRQ_VCAMA1_OC, + MT6358_IRQ_VCAMA2_OC, + MT6358_IRQ_VCAMD_OC, + MT6358_IRQ_VCAMIO_OC, + MT6358_IRQ_VLDO28_OC, + MT6358_IRQ_VA12_OC, + MT6358_IRQ_VAUX18_OC, + MT6358_IRQ_VAUD28_OC, + MT6358_IRQ_VIO28_OC, + MT6358_IRQ_VIO18_OC, + MT6358_IRQ_VSRAM_PROC11_OC, + MT6358_IRQ_VSRAM_PROC12_OC, + MT6358_IRQ_VSRAM_OTHERS_OC, + MT6358_IRQ_VSRAM_GPU_OC, + MT6358_IRQ_VDRAM2_OC, + MT6358_IRQ_VMC_OC, + MT6358_IRQ_VMCH_OC, + MT6358_IRQ_VEMC_OC, + MT6358_IRQ_VSIM1_OC, + MT6358_IRQ_VSIM2_OC, + MT6358_IRQ_VIBR_OC, + MT6358_IRQ_VUSB_OC, + MT6358_IRQ_VBIF28_OC, + MT6358_IRQ_PWRKEY = 48, + MT6358_IRQ_HOMEKEY, + MT6358_IRQ_PWRKEY_R, + MT6358_IRQ_HOMEKEY_R, + MT6358_IRQ_NI_LBAT_INT, + MT6358_IRQ_CHRDET, + MT6358_IRQ_CHRDET_EDGE, + MT6358_IRQ_VCDT_HV_DET, + MT6358_IRQ_RTC = 64, + MT6358_IRQ_FG_BAT0_H = 80, + MT6358_IRQ_FG_BAT0_L, + MT6358_IRQ_FG_CUR_H, + MT6358_IRQ_FG_CUR_L, + MT6358_IRQ_FG_ZCV, + MT6358_IRQ_FG_BAT1_H, + MT6358_IRQ_FG_BAT1_L, + MT6358_IRQ_FG_N_CHARGE_L, + MT6358_IRQ_FG_IAVG_H, + MT6358_IRQ_FG_IAVG_L, + MT6358_IRQ_FG_TIME_H, + MT6358_IRQ_FG_DISCHARGE, + MT6358_IRQ_FG_CHARGE, + MT6358_IRQ_BATON_LV = 96, + MT6358_IRQ_BATON_HT, + MT6358_IRQ_BATON_BAT_IN, + MT6358_IRQ_BATON_BAT_OUT, + MT6358_IRQ_BIF, + MT6358_IRQ_BAT_H = 112, + MT6358_IRQ_BAT_L, + MT6358_IRQ_BAT2_H, + MT6358_IRQ_BAT2_L, + MT6358_IRQ_BAT_TEMP_H, + MT6358_IRQ_BAT_TEMP_L, + MT6358_IRQ_AUXADC_IMP, + MT6358_IRQ_NAG_C_DLTV, + MT6358_IRQ_AUDIO = 128, + MT6358_IRQ_ACCDET = 133, + MT6358_IRQ_ACCDET_EINT0, + MT6358_IRQ_ACCDET_EINT1, + MT6358_IRQ_SPI_CMD_ALERT = 144, + MT6358_IRQ_NR, +}; + +#define MT6358_IRQ_BUCK_BASE MT6358_IRQ_VPROC11_OC +#define MT6358_IRQ_LDO_BASE MT6358_IRQ_VFE28_OC +#define MT6358_IRQ_PSC_BASE MT6358_IRQ_PWRKEY +#define MT6358_IRQ_SCK_BASE MT6358_IRQ_RTC +#define MT6358_IRQ_BM_BASE MT6358_IRQ_FG_BAT0_H +#define MT6358_IRQ_HK_BASE MT6358_IRQ_BAT_H +#define MT6358_IRQ_AUD_BASE MT6358_IRQ_AUDIO +#define MT6358_IRQ_MISC_BASE MT6358_IRQ_SPI_CMD_ALERT + +#define MT6358_IRQ_BUCK_BITS (MT6358_IRQ_VCORE_PREOC - MT6358_IRQ_BUCK_BASE + 1) +#define MT6358_IRQ_LDO_BITS (MT6358_IRQ_VBIF28_OC - MT6358_IRQ_LDO_BASE + 1) +#define MT6358_IRQ_PSC_BITS (MT6358_IRQ_VCDT_HV_DET - MT6358_IRQ_PSC_BASE + 1) +#define MT6358_IRQ_SCK_BITS (MT6358_IRQ_RTC - MT6358_IRQ_SCK_BASE + 1) +#define MT6358_IRQ_BM_BITS (MT6358_IRQ_BIF - MT6358_IRQ_BM_BASE + 1) +#define MT6358_IRQ_HK_BITS (MT6358_IRQ_NAG_C_DLTV - MT6358_IRQ_HK_BASE + 1) +#define MT6358_IRQ_AUD_BITS (MT6358_IRQ_ACCDET_EINT1 - MT6358_IRQ_AUD_BASE + 1) +#define MT6358_IRQ_MISC_BITS \ + (MT6358_IRQ_SPI_CMD_ALERT - MT6358_IRQ_MISC_BASE + 1) + +#define MT6358_TOP_GEN(sp) \ +{ \ + .hwirq_base = MT6358_IRQ_##sp##_BASE, \ + .num_int_regs = \ + ((MT6358_IRQ_##sp##_BITS - 1) / MT6358_REG_WIDTH) + 1, \ + .num_int_bits = MT6358_IRQ_##sp##_BITS, \ + .en_reg = MT6358_##sp##_TOP_INT_CON0, \ + .en_reg_shift = 0x6, \ + .sta_reg = MT6358_##sp##_TOP_INT_STATUS0, \ + .sta_reg_shift = 0x2, \ + .top_offset = MT6358_##sp##_TOP, \ +} + +#endif /* __MFD_MT6358_CORE_H__ */ diff --git a/include/linux/mfd/mt6358/registers.h b/include/linux/mfd/mt6358/registers.h new file mode 100644 index 000000000000..2ad0b312aa28 --- /dev/null +++ b/include/linux/mfd/mt6358/registers.h @@ -0,0 +1,282 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 MediaTek Inc. + */ + +#ifndef __MFD_MT6358_REGISTERS_H__ +#define __MFD_MT6358_REGISTERS_H__ + +/* PMIC Registers */ +#define MT6358_SWCID 0xa +#define MT6358_MISC_TOP_INT_CON0 0x188 +#define MT6358_MISC_TOP_INT_STATUS0 0x194 +#define MT6358_TOP_INT_STATUS0 0x19e +#define MT6358_SCK_TOP_INT_CON0 0x52e +#define MT6358_SCK_TOP_INT_STATUS0 0x53a +#define MT6358_EOSC_CALI_CON0 0x540 +#define MT6358_EOSC_CALI_CON1 0x542 +#define MT6358_RTC_MIX_CON0 0x544 +#define MT6358_RTC_MIX_CON1 0x546 +#define MT6358_RTC_MIX_CON2 0x548 +#define MT6358_RTC_DSN_ID 0x580 +#define MT6358_RTC_DSN_REV0 0x582 +#define MT6358_RTC_DBI 0x584 +#define MT6358_RTC_DXI 0x586 +#define MT6358_RTC_BBPU 0x588 +#define MT6358_RTC_IRQ_STA 0x58a +#define MT6358_RTC_IRQ_EN 0x58c +#define MT6358_RTC_CII_EN 0x58e +#define MT6358_RTC_AL_MASK 0x590 +#define MT6358_RTC_TC_SEC 0x592 +#define MT6358_RTC_TC_MIN 0x594 +#define MT6358_RTC_TC_HOU 0x596 +#define MT6358_RTC_TC_DOM 0x598 +#define MT6358_RTC_TC_DOW 0x59a +#define MT6358_RTC_TC_MTH 0x59c +#define MT6358_RTC_TC_YEA 0x59e +#define MT6358_RTC_AL_SEC 0x5a0 +#define MT6358_RTC_AL_MIN 0x5a2 +#define MT6358_RTC_AL_HOU 0x5a4 +#define MT6358_RTC_AL_DOM 0x5a6 +#define MT6358_RTC_AL_DOW 0x5a8 +#define MT6358_RTC_AL_MTH 0x5aa +#define MT6358_RTC_AL_YEA 0x5ac +#define MT6358_RTC_OSC32CON 0x5ae +#define MT6358_RTC_POWERKEY1 0x5b0 +#define MT6358_RTC_POWERKEY2 0x5b2 +#define MT6358_RTC_PDN1 0x5b4 +#define MT6358_RTC_PDN2 0x5b6 +#define MT6358_RTC_SPAR0 0x5b8 +#define MT6358_RTC_SPAR1 0x5ba +#define MT6358_RTC_PROT 0x5bc +#define MT6358_RTC_DIFF 0x5be +#define MT6358_RTC_CALI 0x5c0 +#define MT6358_RTC_WRTGR 0x5c2 +#define MT6358_RTC_CON 0x5c4 +#define MT6358_RTC_SEC_CTRL 0x5c6 +#define MT6358_RTC_INT_CNT 0x5c8 +#define MT6358_RTC_SEC_DAT0 0x5ca +#define MT6358_RTC_SEC_DAT1 0x5cc +#define MT6358_RTC_SEC_DAT2 0x5ce +#define MT6358_RTC_SEC_DSN_ID 0x600 +#define MT6358_RTC_SEC_DSN_REV0 0x602 +#define MT6358_RTC_SEC_DBI 0x604 +#define MT6358_RTC_SEC_DXI 0x606 +#define MT6358_RTC_TC_SEC_SEC 0x608 +#define MT6358_RTC_TC_MIN_SEC 0x60a +#define MT6358_RTC_TC_HOU_SEC 0x60c +#define MT6358_RTC_TC_DOM_SEC 0x60e +#define MT6358_RTC_TC_DOW_SEC 0x610 +#define MT6358_RTC_TC_MTH_SEC 0x612 +#define MT6358_RTC_TC_YEA_SEC 0x614 +#define MT6358_RTC_SEC_CK_PDN 0x616 +#define MT6358_RTC_SEC_WRTGR 0x618 +#define MT6358_PSC_TOP_INT_CON0 0x910 +#define MT6358_PSC_TOP_INT_STATUS0 0x91c +#define MT6358_BM_TOP_INT_CON0 0xc32 +#define MT6358_BM_TOP_INT_CON1 0xc38 +#define MT6358_BM_TOP_INT_STATUS0 0xc4a +#define MT6358_BM_TOP_INT_STATUS1 0xc4c +#define MT6358_HK_TOP_INT_CON0 0xf92 +#define MT6358_HK_TOP_INT_STATUS0 0xf9e +#define MT6358_BUCK_TOP_INT_CON0 0x1318 +#define MT6358_BUCK_TOP_INT_STATUS0 0x1324 +#define MT6358_BUCK_VPROC11_CON0 0x1388 +#define MT6358_BUCK_VPROC11_DBG0 0x139e +#define MT6358_BUCK_VPROC11_DBG1 0x13a0 +#define MT6358_BUCK_VPROC11_ELR0 0x13a6 +#define MT6358_BUCK_VPROC12_CON0 0x1408 +#define MT6358_BUCK_VPROC12_DBG0 0x141e +#define MT6358_BUCK_VPROC12_DBG1 0x1420 +#define MT6358_BUCK_VPROC12_ELR0 0x1426 +#define MT6358_BUCK_VCORE_CON0 0x1488 +#define MT6358_BUCK_VCORE_DBG0 0x149e +#define MT6358_BUCK_VCORE_DBG1 0x14a0 +#define MT6358_BUCK_VCORE_ELR0 0x14aa +#define MT6358_BUCK_VGPU_CON0 0x1508 +#define MT6358_BUCK_VGPU_DBG0 0x151e +#define MT6358_BUCK_VGPU_DBG1 0x1520 +#define MT6358_BUCK_VGPU_ELR0 0x1526 +#define MT6358_BUCK_VMODEM_CON0 0x1588 +#define MT6358_BUCK_VMODEM_DBG0 0x159e +#define MT6358_BUCK_VMODEM_DBG1 0x15a0 +#define MT6358_BUCK_VMODEM_ELR0 0x15a6 +#define MT6358_BUCK_VDRAM1_CON0 0x1608 +#define MT6358_BUCK_VDRAM1_DBG0 0x161e +#define MT6358_BUCK_VDRAM1_DBG1 0x1620 +#define MT6358_BUCK_VDRAM1_ELR0 0x1626 +#define MT6358_BUCK_VS1_CON0 0x1688 +#define MT6358_BUCK_VS1_DBG0 0x169e +#define MT6358_BUCK_VS1_DBG1 0x16a0 +#define MT6358_BUCK_VS1_ELR0 0x16ae +#define MT6358_BUCK_VS2_CON0 0x1708 +#define MT6358_BUCK_VS2_DBG0 0x171e +#define MT6358_BUCK_VS2_DBG1 0x1720 +#define MT6358_BUCK_VS2_ELR0 0x172e +#define MT6358_BUCK_VPA_CON0 0x1788 +#define MT6358_BUCK_VPA_CON1 0x178a +#define MT6358_BUCK_VPA_ELR0 MT6358_BUCK_VPA_CON1 +#define MT6358_BUCK_VPA_DBG0 0x1792 +#define MT6358_BUCK_VPA_DBG1 0x1794 +#define MT6358_VPROC_ANA_CON0 0x180c +#define MT6358_VCORE_VGPU_ANA_CON0 0x1828 +#define MT6358_VMODEM_ANA_CON0 0x1888 +#define MT6358_VDRAM1_ANA_CON0 0x1896 +#define MT6358_VS1_ANA_CON0 0x18a2 +#define MT6358_VS2_ANA_CON0 0x18ae +#define MT6358_VPA_ANA_CON0 0x18ba +#define MT6358_LDO_TOP_INT_CON0 0x1a50 +#define MT6358_LDO_TOP_INT_CON1 0x1a56 +#define MT6358_LDO_TOP_INT_STATUS0 0x1a68 +#define MT6358_LDO_TOP_INT_STATUS1 0x1a6a +#define MT6358_LDO_VXO22_CON0 0x1a88 +#define MT6358_LDO_VXO22_CON1 0x1a96 +#define MT6358_LDO_VA12_CON0 0x1a9c +#define MT6358_LDO_VA12_CON1 0x1aaa +#define MT6358_LDO_VAUX18_CON0 0x1ab0 +#define MT6358_LDO_VAUX18_CON1 0x1abe +#define MT6358_LDO_VAUD28_CON0 0x1ac4 +#define MT6358_LDO_VAUD28_CON1 0x1ad2 +#define MT6358_LDO_VIO28_CON0 0x1ad8 +#define MT6358_LDO_VIO28_CON1 0x1ae6 +#define MT6358_LDO_VIO18_CON0 0x1aec +#define MT6358_LDO_VIO18_CON1 0x1afa +#define MT6358_LDO_VDRAM2_CON0 0x1b08 +#define MT6358_LDO_VDRAM2_CON1 0x1b16 +#define MT6358_LDO_VEMC_CON0 0x1b1c +#define MT6358_LDO_VEMC_CON1 0x1b2a +#define MT6358_LDO_VUSB_CON0_0 0x1b30 +#define MT6358_LDO_VUSB_CON1 0x1b40 +#define MT6358_LDO_VSRAM_PROC11_CON0 0x1b46 +#define MT6358_LDO_VSRAM_PROC11_DBG0 0x1b60 +#define MT6358_LDO_VSRAM_PROC11_DBG1 0x1b62 +#define MT6358_LDO_VSRAM_PROC11_TRACKING_CON0 0x1b64 +#define MT6358_LDO_VSRAM_PROC11_TRACKING_CON1 0x1b66 +#define MT6358_LDO_VSRAM_PROC11_TRACKING_CON2 0x1b68 +#define MT6358_LDO_VSRAM_PROC11_TRACKING_CON3 0x1b6a +#define MT6358_LDO_VSRAM_PROC12_TRACKING_CON0 0x1b6c +#define MT6358_LDO_VSRAM_PROC12_TRACKING_CON1 0x1b6e +#define MT6358_LDO_VSRAM_PROC12_TRACKING_CON2 0x1b70 +#define MT6358_LDO_VSRAM_PROC12_TRACKING_CON3 0x1b72 +#define MT6358_LDO_VSRAM_WAKEUP_CON0 0x1b74 +#define MT6358_LDO_GON1_ELR_NUM 0x1b76 +#define MT6358_LDO_VDRAM2_ELR0 0x1b78 +#define MT6358_LDO_VSRAM_PROC12_CON0 0x1b88 +#define MT6358_LDO_VSRAM_PROC12_DBG0 0x1ba2 +#define MT6358_LDO_VSRAM_PROC12_DBG1 0x1ba4 +#define MT6358_LDO_VSRAM_OTHERS_CON0 0x1ba6 +#define MT6358_LDO_VSRAM_OTHERS_DBG0 0x1bc0 +#define MT6358_LDO_VSRAM_OTHERS_DBG1 0x1bc2 +#define MT6358_LDO_VSRAM_GPU_CON0 0x1bc8 +#define MT6358_LDO_VSRAM_GPU_DBG0 0x1be2 +#define MT6358_LDO_VSRAM_GPU_DBG1 0x1be4 +#define MT6358_LDO_VSRAM_CON0 0x1bee +#define MT6358_LDO_VSRAM_CON1 0x1bf0 +#define MT6358_LDO_VSRAM_CON2 0x1bf2 +#define MT6358_LDO_VSRAM_CON3 0x1bf4 +#define MT6358_LDO_VFE28_CON0 0x1c08 +#define MT6358_LDO_VFE28_CON1 0x1c16 +#define MT6358_LDO_VFE28_CON2 0x1c18 +#define MT6358_LDO_VFE28_CON3 0x1c1a +#define MT6358_LDO_VRF18_CON0 0x1c1c +#define MT6358_LDO_VRF18_CON1 0x1c2a +#define MT6358_LDO_VRF18_CON2 0x1c2c +#define MT6358_LDO_VRF18_CON3 0x1c2e +#define MT6358_LDO_VRF12_CON0 0x1c30 +#define MT6358_LDO_VRF12_CON1 0x1c3e +#define MT6358_LDO_VRF12_CON2 0x1c40 +#define MT6358_LDO_VRF12_CON3 0x1c42 +#define MT6358_LDO_VEFUSE_CON0 0x1c44 +#define MT6358_LDO_VEFUSE_CON1 0x1c52 +#define MT6358_LDO_VEFUSE_CON2 0x1c54 +#define MT6358_LDO_VEFUSE_CON3 0x1c56 +#define MT6358_LDO_VCN18_CON0 0x1c58 +#define MT6358_LDO_VCN18_CON1 0x1c66 +#define MT6358_LDO_VCN18_CON2 0x1c68 +#define MT6358_LDO_VCN18_CON3 0x1c6a +#define MT6358_LDO_VCAMA1_CON0 0x1c6c +#define MT6358_LDO_VCAMA1_CON1 0x1c7a +#define MT6358_LDO_VCAMA1_CON2 0x1c7c +#define MT6358_LDO_VCAMA1_CON3 0x1c7e +#define MT6358_LDO_VCAMA2_CON0 0x1c88 +#define MT6358_LDO_VCAMA2_CON1 0x1c96 +#define MT6358_LDO_VCAMA2_CON2 0x1c98 +#define MT6358_LDO_VCAMA2_CON3 0x1c9a +#define MT6358_LDO_VCAMD_CON0 0x1c9c +#define MT6358_LDO_VCAMD_CON1 0x1caa +#define MT6358_LDO_VCAMD_CON2 0x1cac +#define MT6358_LDO_VCAMD_CON3 0x1cae +#define MT6358_LDO_VCAMIO_CON0 0x1cb0 +#define MT6358_LDO_VCAMIO_CON1 0x1cbe +#define MT6358_LDO_VCAMIO_CON2 0x1cc0 +#define MT6358_LDO_VCAMIO_CON3 0x1cc2 +#define MT6358_LDO_VMC_CON0 0x1cc4 +#define MT6358_LDO_VMC_CON1 0x1cd2 +#define MT6358_LDO_VMC_CON2 0x1cd4 +#define MT6358_LDO_VMC_CON3 0x1cd6 +#define MT6358_LDO_VMCH_CON0 0x1cd8 +#define MT6358_LDO_VMCH_CON1 0x1ce6 +#define MT6358_LDO_VMCH_CON2 0x1ce8 +#define MT6358_LDO_VMCH_CON3 0x1cea +#define MT6358_LDO_VIBR_CON0 0x1d08 +#define MT6358_LDO_VIBR_CON1 0x1d16 +#define MT6358_LDO_VIBR_CON2 0x1d18 +#define MT6358_LDO_VIBR_CON3 0x1d1a +#define MT6358_LDO_VCN33_CON0_0 0x1d1c +#define MT6358_LDO_VCN33_CON0_1 0x1d2a +#define MT6358_LDO_VCN33_CON1 0x1d2c +#define MT6358_LDO_VCN33_BT_CON1 MT6358_LDO_VCN33_CON1 +#define MT6358_LDO_VCN33_WIFI_CON1 MT6358_LDO_VCN33_CON1 +#define MT6358_LDO_VCN33_CON2 0x1d2e +#define MT6358_LDO_VCN33_CON3 0x1d30 +#define MT6358_LDO_VLDO28_CON0_0 0x1d32 +#define MT6358_LDO_VLDO28_CON0_1 0x1d40 +#define MT6358_LDO_VLDO28_CON1 0x1d42 +#define MT6358_LDO_VLDO28_CON2 0x1d44 +#define MT6358_LDO_VLDO28_CON3 0x1d46 +#define MT6358_LDO_VSIM1_CON0 0x1d48 +#define MT6358_LDO_VSIM1_CON1 0x1d56 +#define MT6358_LDO_VSIM1_CON2 0x1d58 +#define MT6358_LDO_VSIM1_CON3 0x1d5a +#define MT6358_LDO_VSIM2_CON0 0x1d5c +#define MT6358_LDO_VSIM2_CON1 0x1d6a +#define MT6358_LDO_VSIM2_CON2 0x1d6c +#define MT6358_LDO_VSIM2_CON3 0x1d6e +#define MT6358_LDO_VCN28_CON0 0x1d88 +#define MT6358_LDO_VCN28_CON1 0x1d96 +#define MT6358_LDO_VCN28_CON2 0x1d98 +#define MT6358_LDO_VCN28_CON3 0x1d9a +#define MT6358_VRTC28_CON0 0x1d9c +#define MT6358_LDO_VBIF28_CON0 0x1d9e +#define MT6358_LDO_VBIF28_CON1 0x1dac +#define MT6358_LDO_VBIF28_CON2 0x1dae +#define MT6358_LDO_VBIF28_CON3 0x1db0 +#define MT6358_VCAMA1_ANA_CON0 0x1e08 +#define MT6358_VCAMA2_ANA_CON0 0x1e0c +#define MT6358_VCN33_ANA_CON0 0x1e28 +#define MT6358_VSIM1_ANA_CON0 0x1e2c +#define MT6358_VSIM2_ANA_CON0 0x1e30 +#define MT6358_VUSB_ANA_CON0 0x1e34 +#define MT6358_VEMC_ANA_CON0 0x1e38 +#define MT6358_VLDO28_ANA_CON0 0x1e3c +#define MT6358_VIO28_ANA_CON0 0x1e40 +#define MT6358_VIBR_ANA_CON0 0x1e44 +#define MT6358_VMCH_ANA_CON0 0x1e48 +#define MT6358_VMC_ANA_CON0 0x1e4c +#define MT6358_VRF18_ANA_CON0 0x1e88 +#define MT6358_VCN18_ANA_CON0 0x1e8c +#define MT6358_VCAMIO_ANA_CON0 0x1e90 +#define MT6358_VIO18_ANA_CON0 0x1e94 +#define MT6358_VEFUSE_ANA_CON0 0x1e98 +#define MT6358_VRF12_ANA_CON0 0x1e9c +#define MT6358_VSRAM_PROC11_ANA_CON0 0x1ea0 +#define MT6358_VSRAM_PROC12_ANA_CON0 0x1ea4 +#define MT6358_VSRAM_OTHERS_ANA_CON0 0x1ea6 +#define MT6358_VSRAM_GPU_ANA_CON0 0x1ea8 +#define MT6358_VDRAM2_ANA_CON0 0x1eaa +#define MT6358_VCAMD_ANA_CON0 0x1eae +#define MT6358_VA12_ANA_CON0 0x1eb2 +#define MT6358_AUD_TOP_INT_CON0 0x2228 +#define MT6358_AUD_TOP_INT_STATUS0 0x2234 + +#endif /* __MFD_MT6358_REGISTERS_H__ */ diff --git a/include/linux/mfd/mt6397/core.h b/include/linux/mfd/mt6397/core.h index b81d33325ade..949268581b36 100644 --- a/include/linux/mfd/mt6397/core.h +++ b/include/linux/mfd/mt6397/core.h @@ -12,6 +12,7 @@ enum chip_id { MT6323_CHIP_ID = 0x23, + MT6358_CHIP_ID = 0x58, MT6391_CHIP_ID = 0x91, MT6397_CHIP_ID = 0x97, }; @@ -65,8 +66,10 @@ struct mt6397_chip { u16 int_con[2]; u16 int_status[2]; u16 chip_id; + void *irq_data; }; +int mt6358_irq_init(struct mt6397_chip *chip); int mt6397_irq_init(struct mt6397_chip *chip); #endif /* __MFD_MT6397_CORE_H__ */ -- cgit v1.2.3 From 29ee40091e27615530c0ba7773a2879d8266381e Mon Sep 17 00:00:00 2001 From: Ran Bi Date: Tue, 21 Apr 2020 11:00:11 +0800 Subject: rtc: mt6397: Add support for the MediaTek MT6358 RTC This add support for the MediaTek MT6358 RTC. Driver using compatible data to store different RTC_WRTGR address offset. This replace RTC_WRTGR to RTC_WRTGR_MT6323 in mt6323-poweroff driver which only needed by armv7 CPU without ATF. Signed-off-by: Ran Bi Signed-off-by: Hsin-Hsiung Wang Reviewed-by: Nicolas Boichat Acked-by: Alexandre Belloni Acked-by: Sebastian Reichel Reviewed-by: Yingjoe Chen Signed-off-by: Lee Jones --- include/linux/mfd/mt6397/rtc.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h index 7dfb63b81373..66989a16221a 100644 --- a/include/linux/mfd/mt6397/rtc.h +++ b/include/linux/mfd/mt6397/rtc.h @@ -18,7 +18,9 @@ #define RTC_BBPU_CBUSY BIT(6) #define RTC_BBPU_KEY (0x43 << 8) -#define RTC_WRTGR 0x003c +#define RTC_WRTGR_MT6358 0x003a +#define RTC_WRTGR_MT6397 0x003c +#define RTC_WRTGR_MT6323 RTC_WRTGR_MT6397 #define RTC_IRQ_STA 0x0002 #define RTC_IRQ_STA_AL BIT(0) @@ -65,6 +67,10 @@ #define MTK_RTC_POLL_DELAY_US 10 #define MTK_RTC_POLL_TIMEOUT (jiffies_to_usecs(HZ)) +struct mtk_rtc_data { + u32 wrtgr; +}; + struct mt6397_rtc { struct device *dev; struct rtc_device *rtc_dev; @@ -74,6 +80,7 @@ struct mt6397_rtc { struct regmap *regmap; int irq; u32 addr_base; + const struct mtk_rtc_data *data; }; #endif /* _LINUX_MFD_MT6397_RTC_H_ */ -- cgit v1.2.3 From 269fd61e15d785b9e20786672765400732dde8a0 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 21 May 2020 12:08:36 +0100 Subject: firmware: smccc: Fix missing prototype warning for arm_smccc_version_init Commit f2ae97062a48 ("firmware: smccc: Refactor SMCCC specific bits into separate file") introduced the following build warning: drivers/firmware/smccc/smccc.c:14:13: warning: no previous prototype for function 'arm_smccc_version_init' [-Wmissing-prototypes] void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit) ^~~~~~~~~~~~~~~~~~~~~~ Fix the same by adding the missing prototype in arm-smccc.h Reported-by: kbuild test robot Signed-off-by: Sudeep Holla Link: https://lore.kernel.org/r/20200521110836.57252-1-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index c491d210e3c3..56d6a5c6e353 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -5,6 +5,7 @@ #ifndef __LINUX_ARM_SMCCC_H #define __LINUX_ARM_SMCCC_H +#include #include /* @@ -111,6 +112,8 @@ enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void); */ u32 arm_smccc_get_version(void); +void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit); + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 -- cgit v1.2.3 From 26d7e28e38206b1b3207af1409eee2269ab36f82 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Tue, 19 May 2020 16:22:59 +0200 Subject: s390/dasd: remove ioctl_by_bdev calls The IBM partition parser requires device type specific information only available to the DASD driver to correctly register partitions. The current approach of using ioctl_by_bdev with a fake user space pointer is discouraged. Fix this by replacing IOCTL calls with direct in-kernel function calls. Suggested-by: Christoph Hellwig Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Reviewed-by: Peter Oberparleiter Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/dasd_mod.h | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 include/linux/dasd_mod.h (limited to 'include/linux') diff --git a/include/linux/dasd_mod.h b/include/linux/dasd_mod.h new file mode 100644 index 000000000000..d39abad2ff6e --- /dev/null +++ b/include/linux/dasd_mod.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef DASD_MOD_H +#define DASD_MOD_H + +#include + +extern int dasd_biodasdinfo(struct gendisk *disk, dasd_information2_t *info); + +#endif -- cgit v1.2.3 From 3783daeb1d24696ff00125050353cfce4f5b6239 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 May 2020 16:33:21 +0200 Subject: block: remove ioctl_by_bdev No callers left. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1a95e5158811..861ca61d728b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2636,7 +2636,6 @@ extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; #ifdef CONFIG_BLOCK -extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); -- cgit v1.2.3 From 112b7147592e8f46bd1da4f961773e6d974f38a8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 14 May 2020 12:53:44 -0500 Subject: exec: Convert security_bprm_set_creds into security_bprm_repopulate_creds Rename bprm->cap_elevated to bprm->active_secureexec and initialize it in prepare_binprm instead of in cap_bprm_set_creds. Initializing bprm->active_secureexec in prepare_binprm allows multiple implementations of security_bprm_repopulate_creds to play nicely with each other. Rename security_bprm_set_creds to security_bprm_reopulate_creds to emphasize that this path recomputes part of bprm->cred. This recomputation avoids the time of check vs time of use problems that are inherent in unix #! interpreters. In short two renames and a move in the location of initializing bprm->active_secureexec. Link: https://lkml.kernel.org/r/87o8qkzrxp.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 4 ++-- include/linux/lsm_hook_defs.h | 2 +- include/linux/lsm_hooks.h | 4 ++-- include/linux/security.h | 8 ++++---- 4 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index d1217fcdedea..8605ab4a0f89 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -27,10 +27,10 @@ struct linux_binprm { unsigned long argmin; /* rlimit marker for copy_strings() */ unsigned int /* - * True if most recent call to cap_bprm_set_creds + * True if most recent call to security_bprm_set_creds * resulted in elevated privileges. */ - cap_elevated:1, + active_secureexec:1, /* * Set by bprm_creds_for_exec hook to indicate a * privilege-gaining exec has happened. Used to set diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index aab0695f41df..1e295ba12c0d 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -50,7 +50,7 @@ LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) -LSM_HOOK(int, 0, bprm_set_creds, struct linux_binprm *bprm) +LSM_HOOK(int, 0, bprm_repopulate_creds, struct linux_binprm *bprm) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index c719af37df20..d618ecc4d660 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -44,7 +44,7 @@ * request libc enable secure mode. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. - * @bprm_set_creds: + * @bprm_repopulate_creds: * Assuming that the relevant bits of @bprm->cred->security have been * previously set, examine @bprm->file and regenerate them. This is * so that the credentials derived from the interpreter the code is @@ -53,7 +53,7 @@ * reopen script, and may end up opening something completely different. * This hook may also optionally check permissions (e.g. for * transitions between security domains). - * The hook must set @bprm->cap_elevated to 1 if AT_SECURE should be set to + * The hook must set @bprm->active_secureexec to 1 if AT_SECURE should be set to * request libc enable secure mode. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. diff --git a/include/linux/security.h b/include/linux/security.h index 1bd7a6582775..6dcec9375e8f 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -140,7 +140,7 @@ extern int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); -extern int cap_bprm_set_creds(struct linux_binprm *bprm); +extern int cap_bprm_repopulate_creds(struct linux_binprm *bprm); extern int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); extern int cap_inode_removexattr(struct dentry *dentry, const char *name); @@ -277,7 +277,7 @@ int security_syslog(int type); int security_settime64(const struct timespec64 *ts, const struct timezone *tz); int security_vm_enough_memory_mm(struct mm_struct *mm, long pages); int security_bprm_creds_for_exec(struct linux_binprm *bprm); -int security_bprm_set_creds(struct linux_binprm *bprm); +int security_bprm_repopulate_creds(struct linux_binprm *bprm); int security_bprm_check(struct linux_binprm *bprm); void security_bprm_committing_creds(struct linux_binprm *bprm); void security_bprm_committed_creds(struct linux_binprm *bprm); @@ -575,9 +575,9 @@ static inline int security_bprm_creds_for_exec(struct linux_binprm *bprm) return 0; } -static inline int security_bprm_set_creds(struct linux_binprm *bprm) +static inline int security_bprm_repopulate_creds(struct linux_binprm *bprm) { - return cap_bprm_set_creds(bprm); + return cap_bprm_repopulate_creds(bprm); } static inline int security_bprm_check(struct linux_binprm *bprm) -- cgit v1.2.3 From a16b3357b2b8e910bb614254d8a7e84d2bd59b4c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 16 May 2020 06:02:54 -0500 Subject: exec: Allow load_misc_binary to call prepare_binprm unconditionally Add a flag preserve_creds that binfmt_misc can set to prevent credentials from being updated. This allows binfmt_misc to always call prepare_binprm. Allowing the credential computation logic to be consolidated. Not replacing the credentials with the interpreters credentials is safe because because an open file descriptor to the executable is passed to the interpreter. As the interpreter does not need to reopen the executable it is guaranteed to see the same file that exec sees. Ref: c407c033de84 ("[PATCH] binfmt_misc: improve calculation of interpreter's credentials") Link: https://lkml.kernel.org/r/87imgszrwo.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 8605ab4a0f89..dbb5614d62a2 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -26,6 +26,8 @@ struct linux_binprm { unsigned long p; /* current top of mem */ unsigned long argmin; /* rlimit marker for copy_strings() */ unsigned int + /* It is safe to use the creds of a script (see binfmt_misc) */ + preserve_creds:1, /* * True if most recent call to security_bprm_set_creds * resulted in elevated privileges. -- cgit v1.2.3 From 8b72ca9004ed35104deb80b07990da5503bc5252 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 13 May 2020 22:25:20 -0500 Subject: exec: Move the call of prepare_binprm into search_binary_handler The code in prepare_binary_handler needs to be run every time search_binary_handler is called so move the call into search_binary_handler itself to make the code simpler and easier to understand. Link: https://lkml.kernel.org/r/87d070zrvx.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds Reviewed-by: Kees Cook Reviewed-by: James Morris Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index dbb5614d62a2..8c7779d6bf19 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -116,7 +116,6 @@ static inline void insert_binfmt(struct linux_binfmt *fmt) extern void unregister_binfmt(struct linux_binfmt *); -extern int prepare_binprm(struct linux_binprm *); extern int __must_check remove_arg_zero(struct linux_binprm *); extern int search_binary_handler(struct linux_binprm *); extern int begin_new_exec(struct linux_binprm * bprm); -- cgit v1.2.3 From b8a61c9e7b4a0fec493d191429e9653d66a79ccc Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 14 May 2020 15:17:40 -0500 Subject: exec: Generic execfd support Most of the support for passing the file descriptor of an executable to an interpreter already lives in the generic code and in binfmt_elf. Rework the fields in binfmt_elf that deal with executable file descriptor passing to make executable file descriptor passing a first class concept. Move the fd_install from binfmt_misc into begin_new_exec after the new creds have been installed. This means that accessing the file through /proc//fd/N is able to see the creds for the new executable before allowing access to the new executables files. Performing the install of the executables file descriptor after the point of no return also means that nothing special needs to be done on error. The exiting of the process will close all of it's open files. Move the would_dump from binfmt_misc into begin_new_exec right after would_dump is called on the bprm->file. This makes it obvious this case exists and that no nesting of bprm->file is currently supported. In binfmt_misc the movement of fd_install into generic code means that it's special error exit path is no longer needed. Link: https://lkml.kernel.org/r/87y2poyd91.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 8c7779d6bf19..653508b25815 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -26,6 +26,9 @@ struct linux_binprm { unsigned long p; /* current top of mem */ unsigned long argmin; /* rlimit marker for copy_strings() */ unsigned int + /* Should an execfd be passed to userspace? */ + have_execfd:1, + /* It is safe to use the creds of a script (see binfmt_misc) */ preserve_creds:1, /* @@ -48,6 +51,7 @@ struct linux_binprm { unsigned int taso:1; #endif unsigned int recursion_depth; /* only for search_binary_handler() */ + struct file * executable; /* Executable to pass to the interpreter */ struct file * file; struct cred *cred; /* new credentials */ int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ @@ -58,7 +62,7 @@ struct linux_binprm { of the time same as filename, but could be different for binfmt_{misc,script} */ unsigned interp_flags; - unsigned interp_data; + int execfd; /* File descriptor of the executable */ unsigned long loader, exec; struct rlimit rlim_stack; /* Saved RLIMIT_STACK used during exec. */ @@ -69,10 +73,6 @@ struct linux_binprm { #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 #define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT) -/* fd of the binary should be passed to the interpreter */ -#define BINPRM_FLAGS_EXECFD_BIT 1 -#define BINPRM_FLAGS_EXECFD (1 << BINPRM_FLAGS_EXECFD_BIT) - /* filename of the binary will be inaccessible after exec */ #define BINPRM_FLAGS_PATH_INACCESSIBLE_BIT 2 #define BINPRM_FLAGS_PATH_INACCESSIBLE (1 << BINPRM_FLAGS_PATH_INACCESSIBLE_BIT) -- cgit v1.2.3 From bc2bf338d54b7aadaed49bb45b9e10d4592b2a46 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 18 May 2020 18:43:20 -0500 Subject: exec: Remove recursion from search_binary_handler Recursion in kernel code is generally a bad idea as it can overflow the kernel stack. Recursion in exec also hides that the code is looping and that the loop changes bprm->file. Instead of recursing in search_binary_handler have the methods that would recurse set bprm->interpreter and return 0. Modify exec_binprm to loop when bprm->interpreter is set. Consolidate all of the reassignments of bprm->file in that loop to make it clear what is going on. The structure of the new loop in exec_binprm is that all errors return immediately, while successful completion (ret == 0 && !bprm->interpreter) just breaks out of the loop and runs what exec_bprm has always run upon successful completion. Fail if the an interpreter is being call after execfd has been set. The code has never properly handled an interpreter being called with execfd being set and with reassignments of bprm->file and the assignment of bprm->executable in generic code it has finally become possible to test and fail when if this problematic condition happens. With the reassignments of bprm->file and the assignment of bprm->executable moved into the generic code add a test to see if bprm->executable is being reassigned. In search_binary_handler remove the test for !bprm->file. With all reassignments of bprm->file moved to exec_binprm bprm->file can never be NULL in search_binary_handler. Link: https://lkml.kernel.org/r/87sgfwyd84.fsf_-_@x220.int.ebiederm.org Acked-by: Linus Torvalds Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 653508b25815..7fc05929c967 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -50,8 +50,8 @@ struct linux_binprm { #ifdef __alpha__ unsigned int taso:1; #endif - unsigned int recursion_depth; /* only for search_binary_handler() */ struct file * executable; /* Executable to pass to the interpreter */ + struct file * interpreter; struct file * file; struct cred *cred; /* new credentials */ int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ @@ -117,7 +117,6 @@ static inline void insert_binfmt(struct linux_binfmt *fmt) extern void unregister_binfmt(struct linux_binfmt *); extern int __must_check remove_arg_zero(struct linux_binprm *); -extern int search_binary_handler(struct linux_binprm *); extern int begin_new_exec(struct linux_binprm * bprm); extern void setup_new_exec(struct linux_binprm * bprm); extern void finalize_exec(struct linux_binprm *bprm); -- cgit v1.2.3 From 6e0688dbff625f1e49e3ddb028720ae9fd606f0b Mon Sep 17 00:00:00 2001 From: Krzysztof Wilczynski Date: Wed, 20 May 2020 18:34:10 +0000 Subject: PCI: Use bridge window names (PCI_BRIDGE_IO_WINDOW etc) Use bridge resource definitions instead of using the PCI_BRIDGE_RESOURCES constant with an integer offeset. Link: https://lore.kernel.org/r/20200520183411.1534621-2-kw@linux.com Signed-off-by: Krzysztof Wilczynski Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 83ce1cdf5676..cdfb07bfdf7d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -100,9 +100,21 @@ enum { PCI_IOV_RESOURCE_END = PCI_IOV_RESOURCES + PCI_SRIOV_NUM_BARS - 1, #endif - /* Resources assigned to buses behind the bridge */ +/* PCI-to-PCI (P2P) bridge windows */ +#define PCI_BRIDGE_IO_WINDOW (PCI_BRIDGE_RESOURCES + 0) +#define PCI_BRIDGE_MEM_WINDOW (PCI_BRIDGE_RESOURCES + 1) +#define PCI_BRIDGE_PREF_MEM_WINDOW (PCI_BRIDGE_RESOURCES + 2) + +/* CardBus bridge windows */ +#define PCI_CB_BRIDGE_IO_0_WINDOW (PCI_BRIDGE_RESOURCES + 0) +#define PCI_CB_BRIDGE_IO_1_WINDOW (PCI_BRIDGE_RESOURCES + 1) +#define PCI_CB_BRIDGE_MEM_0_WINDOW (PCI_BRIDGE_RESOURCES + 2) +#define PCI_CB_BRIDGE_MEM_1_WINDOW (PCI_BRIDGE_RESOURCES + 3) + +/* Total number of bridge resources for P2P and CardBus */ #define PCI_BRIDGE_RESOURCE_NUM 4 + /* Resources assigned to buses behind the bridge */ PCI_BRIDGE_RESOURCES, PCI_BRIDGE_RESOURCE_END = PCI_BRIDGE_RESOURCES + PCI_BRIDGE_RESOURCE_NUM - 1, -- cgit v1.2.3 From 7bfb399eca460500f048098bf427c45b40e17cae Mon Sep 17 00:00:00 2001 From: Yuval Basson Date: Tue, 19 May 2020 23:51:26 +0300 Subject: qed: Add XRC to RoCE Add support for XRC-SRQ's and XRC-QP's for upper layer driver. We maintain separate bitmaps for resource management for srq and xrc-srq, However, the range in FW is one, The xrc-srq's are first and then the srq's follow. Therefore we maintain a srq-id offset. v2: perform cleanups if XRC bitmpas allocation fail. Signed-off-by: Michal Kalderon Signed-off-by: Yuval Bason Signed-off-by: David S. Miller --- include/linux/qed/qed_rdma_if.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index 74efca15fde7..f93edd5750a5 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -53,6 +53,13 @@ enum qed_roce_qp_state { QED_ROCE_QP_STATE_SQE }; +enum qed_rdma_qp_type { + QED_RDMA_QP_TYPE_RC, + QED_RDMA_QP_TYPE_XRC_INI, + QED_RDMA_QP_TYPE_XRC_TGT, + QED_RDMA_QP_TYPE_INVAL = 0xffff, +}; + enum qed_rdma_tid_type { QED_RDMA_TID_REGISTERED_MR, QED_RDMA_TID_FMR, @@ -291,6 +298,12 @@ struct qed_rdma_create_srq_in_params { u16 num_pages; u16 pd_id; u16 page_size; + + /* XRC related only */ + bool reserved_key_en; + bool is_xrc; + u32 cq_cid; + u16 xrcd_id; }; struct qed_rdma_destroy_cq_in_params { @@ -319,7 +332,9 @@ struct qed_rdma_create_qp_in_params { u16 rq_num_pages; u64 rq_pbl_ptr; u16 srq_id; + u16 xrcd_id; u8 stats_queue; + enum qed_rdma_qp_type qp_type; }; struct qed_rdma_create_qp_out_params { @@ -429,11 +444,13 @@ struct qed_rdma_create_srq_out_params { struct qed_rdma_destroy_srq_in_params { u16 srq_id; + bool is_xrc; }; struct qed_rdma_modify_srq_in_params { u32 wqe_limit; u16 srq_id; + bool is_xrc; }; struct qed_rdma_stats_out_params { @@ -611,6 +628,8 @@ struct qed_rdma_ops { int (*rdma_set_rdma_int)(struct qed_dev *cdev, u16 cnt); int (*rdma_alloc_pd)(void *rdma_cxt, u16 *pd); void (*rdma_dealloc_pd)(void *rdma_cxt, u16 pd); + int (*rdma_alloc_xrcd)(void *rdma_cxt, u16 *xrcd); + void (*rdma_dealloc_xrcd)(void *rdma_cxt, u16 xrcd); int (*rdma_create_cq)(void *rdma_cxt, struct qed_rdma_create_cq_in_params *params, u16 *icid); -- cgit v1.2.3 From 8066021915924f58ed338bf38208215f5a7355f6 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 20 May 2020 08:29:14 +0200 Subject: ethtool: provide UAPI for PHY Signal Quality Index (SQI) Signal Quality Index is a mandatory value required by "OPEN Alliance SIG" for the 100Base-T1 PHYs [1]. This indicator can be used for cable integrity diagnostic and investigating other noise sources and implement by at least two vendors: NXP[2] and TI[3]. [1] http://www.opensig.org/download/document/218/Advanced_PHY_features_for_automotive_Ethernet_V1.0.pdf [2] https://www.nxp.com/docs/en/data-sheet/TJA1100.pdf [3] https://www.ti.com/product/DP83TC811R-Q1 Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Reviewed-by: Michal Kubecek Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 467aa8bf9f64..2bcdf19ed3b4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -723,6 +723,8 @@ struct phy_driver { struct ethtool_tunable *tuna, const void *data); int (*set_loopback)(struct phy_device *dev, bool enable); + int (*get_sqi)(struct phy_device *dev); + int (*get_sqi_max)(struct phy_device *dev); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) -- cgit v1.2.3 From 560e3a045961ed0c7184ef9f6a93b95bd38c1c48 Mon Sep 17 00:00:00 2001 From: Bhaumik Bhatt Date: Thu, 21 May 2020 22:32:40 +0530 Subject: bus: mhi: core: Handle firmware load using state worker Upon power up, driver queues firmware worker thread if the execution environment is PBL. Firmware worker is blocked with a timeout until state worker gets a chance to run and unblock firmware worker. An endpoint power up failure can be seen if state worker gets a chance to run after firmware worker has timed out. Remove this dependency and handle firmware load directly using state worker thread. Signed-off-by: Bhaumik Bhatt Reviewed-by: Jeffrey Hugo Reviewed-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200521170249.21795-6-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index b0739ad1bae4..8289202b8cbe 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -331,7 +331,6 @@ struct mhi_controller_config { * @wlock: Lock for protecting device wakeup * @mhi_link_info: Device bandwidth info * @st_worker: State transition worker - * @fw_worker: Firmware download worker * @syserr_worker: System error worker * @state_event: State change event * @status_cb: CB function to notify power states of the device (required) @@ -412,7 +411,6 @@ struct mhi_controller { spinlock_t wlock; struct mhi_link_info mhi_link_info; struct work_struct st_worker; - struct work_struct fw_worker; struct work_struct syserr_worker; wait_queue_head_t state_event; -- cgit v1.2.3 From bc7ccce5a5192cf277da0aef05e45cd92c81c79a Mon Sep 17 00:00:00 2001 From: Hemant Kumar Date: Thu, 21 May 2020 22:32:44 +0530 Subject: bus: mhi: core: Remove the system error worker thread Remove the system error worker thread and instead have the execution environment worker handle that transition to serialize processing and avoid any possible race conditions during shutdown. Signed-off-by: Hemant Kumar Reviewed-by: Jeffrey Hugo Reviewed-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20200521170249.21795-10-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 8289202b8cbe..c4a940d98912 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -331,7 +331,6 @@ struct mhi_controller_config { * @wlock: Lock for protecting device wakeup * @mhi_link_info: Device bandwidth info * @st_worker: State transition worker - * @syserr_worker: System error worker * @state_event: State change event * @status_cb: CB function to notify power states of the device (required) * @wake_get: CB function to assert device wake (optional) @@ -411,7 +410,6 @@ struct mhi_controller { spinlock_t wlock; struct mhi_link_info mhi_link_info; struct work_struct st_worker; - struct work_struct syserr_worker; wait_queue_head_t state_event; void (*status_cb)(struct mhi_controller *mhi_cntrl, -- cgit v1.2.3 From 8786eda9a97763c768e2e81cfd7b4f420281b6e1 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 21 May 2020 13:05:40 -0500 Subject: misc: rtsx: Remove unused pcr_ops Remove the following unused function pointers from struct pcr_ops: int (*set_ltr_latency)(struct rtsx_pcr *pcr, u32 latency); int (*set_l1off_sub)(struct rtsx_pcr *pcr, u8 val); void (*full_on)(struct rtsx_pcr *pcr); void (*power_saving)(struct rtsx_pcr *pcr); Signed-off-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20200521180545.1159896-2-helgaas@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 65b8142a7fed..df86afb2b4fe 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1080,11 +1080,7 @@ struct pcr_ops { void (*stop_cmd)(struct rtsx_pcr *pcr); void (*set_aspm)(struct rtsx_pcr *pcr, bool enable); - int (*set_ltr_latency)(struct rtsx_pcr *pcr, u32 latency); - int (*set_l1off_sub)(struct rtsx_pcr *pcr, u8 val); void (*set_l1off_cfg_sub_d0)(struct rtsx_pcr *pcr, int active); - void (*full_on)(struct rtsx_pcr *pcr); - void (*power_saving)(struct rtsx_pcr *pcr); void (*enable_ocp)(struct rtsx_pcr *pcr); void (*disable_ocp)(struct rtsx_pcr *pcr); void (*init_ocp)(struct rtsx_pcr *pcr); -- cgit v1.2.3 From 51876e22bf7f8f5d2b9ca7d2b3dcbfaaac2991a9 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 21 May 2020 13:05:41 -0500 Subject: misc: rtsx: Removed unused dev_aspm_mode The struct rtsx_cr_option.dev_aspm_mode member is never set to anything other than DEV_ASPM_DYNAMIC (0). Remove it and code that tests it. No functional change intended. Signed-off-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20200521180545.1159896-3-helgaas@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index df86afb2b4fe..a75132a0cf8f 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1104,13 +1104,6 @@ enum PDEV_STAT {PDEV_STAT_IDLE, PDEV_STAT_RUN}; #define L1_SNOOZE_TEST_EN BIT(5) #define LTR_L1SS_PWR_GATE_CHECK_CARD_EN BIT(6) -enum dev_aspm_mode { - DEV_ASPM_DYNAMIC, - DEV_ASPM_BACKDOOR, - DEV_ASPM_STATIC, - DEV_ASPM_DISABLE, -}; - /* * struct rtsx_cr_option - card reader option * @dev_flags: device flags @@ -1121,7 +1114,6 @@ enum dev_aspm_mode { * @ltr_active_latency: ltr mode active latency * @ltr_idle_latency: ltr mode idle latency * @ltr_l1off_latency: ltr mode l1off latency - * @dev_aspm_mode: device aspm mode * @l1_snooze_delay: l1 snooze delay * @ltr_l1off_sspwrgate: ltr l1off sspwrgate * @ltr_l1off_snooze_sspwrgate: ltr l1off snooze sspwrgate @@ -1138,7 +1130,6 @@ struct rtsx_cr_option { u32 ltr_active_latency; u32 ltr_idle_latency; u32 ltr_l1off_latency; - enum dev_aspm_mode dev_aspm_mode; u32 l1_snooze_delay; u8 ltr_l1off_sspwrgate; u8 ltr_l1off_snooze_sspwrgate; -- cgit v1.2.3 From 3d1e7aa80d1c0e7ce8313f21c1e9c14a12d3ba48 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 21 May 2020 13:05:43 -0500 Subject: misc: rtsx: Use pcie_capability_clear_and_set_word() for PCI_EXP_LNKCTL Instead of using the driver-specific rtsx_pci_update_cfg_byte() to update the PCIe Link Control Register, use pcie_capability_clear_and_set_word() like the rest of the kernel does. This makes it easier to maintain ASPM across the PCI core and drivers. Remove the now-unused rtsx_pci_update_cfg_byte() and ASPM_MASK_NEG definitions. No functional change intended. Signed-off-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20200521180545.1159896-5-helgaas@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index a75132a0cf8f..e8780d4e4636 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1307,18 +1307,6 @@ static inline u8 *rtsx_pci_get_cmd_data(struct rtsx_pcr *pcr) return (u8 *)(pcr->host_cmds_ptr); } -static inline int rtsx_pci_update_cfg_byte(struct rtsx_pcr *pcr, int addr, - u8 mask, u8 append) -{ - int err; - u8 val; - - err = pci_read_config_byte(pcr->pci, addr, &val); - if (err < 0) - return err; - return pci_write_config_byte(pcr->pci, addr, (val & mask) | append); -} - static inline void rtsx_pci_write_be32(struct rtsx_pcr *pcr, u16 reg, u32 val) { rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, reg, 0xFF, val >> 24); -- cgit v1.2.3 From d45e3c1a5979efd40dbbac9a5c3586f4fa41f734 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Thu, 7 May 2020 13:33:16 +0100 Subject: PCI: endpoint: Add support to handle multiple base for mapping outbound memory R-Car PCIe controller has support to map multiple memory regions for mapping the outbound memory in local system also the controller limits single allocation for each region (that is, once a chunk is used from the region it cannot be used to allocate a new one). This features inspires to add support for handling multiple memory bases in endpoint framework. With this patch pci_epc_mem_init() initializes address space for endpoint controller which support single window and pci_epc_multi_mem_init() initializes multiple windows supported by endpoint controller. Link: https://lore.kernel.org/r/1588854799-13710-6-git-send-email-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Lad Prabhakar Signed-off-by: Lorenzo Pieralisi Reviewed-by: Yoshihiro Shimoda Acked-by: Kishon Vijay Abraham I --- include/linux/pci-epc.h | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 5bc1de65849e..cc66bec8be90 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -65,20 +65,28 @@ struct pci_epc_ops { struct module *owner; }; +/** + * struct pci_epc_mem_window - address window of the endpoint controller + * @phys_base: physical base address of the PCI address window + * @size: the size of the PCI address window + * @page_size: size of each page + */ +struct pci_epc_mem_window { + phys_addr_t phys_base; + size_t size; + size_t page_size; +}; + /** * struct pci_epc_mem - address space of the endpoint controller - * @phys_base: physical base address of the PCI address space - * @size: the size of the PCI address space + * @window: address window of the endpoint controller * @bitmap: bitmap to manage the PCI address space * @pages: number of bits representing the address region - * @page_size: size of each page * @lock: mutex to protect bitmap */ struct pci_epc_mem { - phys_addr_t phys_base; - size_t size; + struct pci_epc_mem_window window; unsigned long *bitmap; - size_t page_size; int pages; /* mutex to protect against concurrent access for memory allocation*/ struct mutex lock; @@ -89,7 +97,11 @@ struct pci_epc_mem { * @dev: PCI EPC device * @pci_epf: list of endpoint functions present in this EPC device * @ops: function pointers for performing endpoint operations - * @mem: address space of the endpoint controller + * @windows: array of address space of the endpoint controller + * @mem: first window of the endpoint controller, which corresponds to + * default address space of the endpoint controller supporting + * single window. + * @num_windows: number of windows supported by device * @max_functions: max number of functions that can be configured in this EPC * @group: configfs group representing the PCI EPC device * @lock: mutex to protect pci_epc ops @@ -100,7 +112,9 @@ struct pci_epc { struct device dev; struct list_head pci_epf; const struct pci_epc_ops *ops; + struct pci_epc_mem **windows; struct pci_epc_mem *mem; + unsigned int num_windows; u8 max_functions; struct config_group *group; /* mutex to protect against concurrent access of EP controller */ @@ -194,8 +208,9 @@ void pci_epc_put(struct pci_epc *epc); int pci_epc_mem_init(struct pci_epc *epc, phys_addr_t base, size_t size, size_t page_size); -int __pci_epc_mem_init(struct pci_epc *epc, phys_addr_t phys_addr, size_t size, - size_t page_size); +int pci_epc_multi_mem_init(struct pci_epc *epc, + struct pci_epc_mem_window *window, + unsigned int num_windows); void pci_epc_mem_exit(struct pci_epc *epc); void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc, phys_addr_t *phys_addr, size_t size); -- cgit v1.2.3 From 4ffea5e083f8125fe273cf331ecb10d901eb64a2 Mon Sep 17 00:00:00 2001 From: Jonathan Bakker Date: Sat, 16 May 2020 12:47:59 -0700 Subject: regulator: max8998: Add charger regulator The max8998 has a current regulator for charging control. The charger driver in drivers/power/supply/max8998_charger.c has a comment in it stating that 'charger control is done by a current regulator "CHARGER"', but this regulator was never added until now. The current values have been extracted from a downstream driver for the SGH-T959V. Signed-off-by: Jonathan Bakker Link: https://lore.kernel.org/r/BN6PR04MB0660E1F4A3D5A348BE88311CA3BA0@BN6PR04MB0660.namprd04.prod.outlook.com Signed-off-by: Mark Brown --- include/linux/mfd/max8998.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h index 061af220dcd3..79c020bd0c70 100644 --- a/include/linux/mfd/max8998.h +++ b/include/linux/mfd/max8998.h @@ -39,6 +39,7 @@ enum { MAX8998_ENVICHG, MAX8998_ESAFEOUT1, MAX8998_ESAFEOUT2, + MAX8998_CHARGER, }; /** -- cgit v1.2.3 From 9398554fb3979852512ff4f1405e759889b45c16 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 13 May 2020 14:36:00 +0200 Subject: block: remove the error_sector argument to blkdev_issue_flush The argument isn't used by any caller, and drivers don't fill out bi_sector for flush requests either. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2b33166b9daf..7d10f4e63232 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1233,7 +1233,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) extern void blk_io_schedule(void); -extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); +int blkdev_issue_flush(struct block_device *, gfp_t); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); @@ -1872,8 +1872,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) return false; } -static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, - sector_t *error_sector) +static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask) { return 0; } -- cgit v1.2.3 From 7a4e63cb0905672fd52e7316a885f19d4aeed976 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 22 May 2020 16:56:58 +0200 Subject: Revert "i2c: core: support bus regulator controlling in adapter" This reverts commit 6fe12cdbcfe35ad4726a619a9546822d34fc934c. Testing in linux-next showed it needs some more time. Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 7433aba207bd..49d29054e657 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -15,7 +15,6 @@ #include /* for struct device */ #include /* for completion */ #include -#include #include #include /* for Host Notify IRQ */ #include /* for struct device_node */ @@ -716,7 +715,6 @@ struct i2c_adapter { const struct i2c_adapter_quirks *quirks; struct irq_domain *host_notify_domain; - struct regulator *bus_regulator; }; #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev) -- cgit v1.2.3 From ab91c2a89f86be2898cee208d492816ec238b2cf Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 8 May 2020 11:38:26 -0500 Subject: tpm: eventlog: Replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. Also, the following issue shows up due to the flexible-array member having incomplete type[4]: drivers/char/tpm/eventlog/tpm2.c: In function ‘tpm2_bios_measurements_start’: drivers/char/tpm/eventlog/tpm2.c:54:46: error: invalid application of ‘sizeof’ to incomplete type ‘u8[]’ {aka ‘unsigned char[]’} 54 | size = sizeof(struct tcg_pcr_event) - sizeof(event_header->event) | ^ drivers/char/tpm/eventlog/tpm2.c: In function ‘tpm2_bios_measurements_next’: drivers/char/tpm/eventlog/tpm2.c:102:10: error: invalid application of ‘sizeof’ to incomplete type ‘u8[]’ {aka ‘unsigned char[]’} 102 | sizeof(event_header->event) + event_header->event_size; | ^ drivers/char/tpm/eventlog/tpm2.c: In function ‘tpm2_binary_bios_measurements_show’: drivers/char/tpm/eventlog/tpm2.c:140:10: error: invalid application of ‘sizeof’ to incomplete type ‘u8[]’ {aka ‘unsigned char[]’} 140 | sizeof(event_header->event) + event_header->event_size; | ^ scripts/Makefile.build:266: recipe for target 'drivers/char/tpm/eventlog/tpm2.o' failed make[3]: *** [drivers/char/tpm/eventlog/tpm2.o] Error 1 As mentioned above: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] As in "sizeof(event_header->event) always evaluated to 0, so removing it has no effect". Lastly, make use of the struct_size() helper to deal with the flexible array member and its host structure. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") [4] https://github.com/KSPP/linux/issues/43 Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/linux/tpm_eventlog.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index c253461b1c4e..4f8c90c93c29 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -97,7 +97,7 @@ struct tcg_pcr_event { u32 event_type; u8 digest[20]; u32 event_size; - u8 event[0]; + u8 event[]; } __packed; struct tcg_event_field { -- cgit v1.2.3 From a4e91825d7e1252f7cba005f1451e5464b23c15d Mon Sep 17 00:00:00 2001 From: Alexander Monakov Date: Sun, 10 May 2020 20:48:40 +0000 Subject: x86/amd_nb: Add AMD family 17h model 60h PCI IDs Add PCI IDs for AMD Renoir (4000-series Ryzen CPUs). This is necessary to enable support for temperature sensors via the k10temp module. Signed-off-by: Alexander Monakov Signed-off-by: Borislav Petkov Acked-by: Yazen Ghannam Acked-by: Guenter Roeck Link: https://lkml.kernel.org/r/20200510204842.2603-2-amonakov@ispras.ru --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 1dfc4e1dcb94..3155f5ada02e 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -550,6 +550,7 @@ #define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F3 0x1493 +#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F3 0x144b #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443 #define PCI_DEVICE_ID_AMD_19H_DF_F3 0x1653 #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 -- cgit v1.2.3 From 8eb613c0b8f19627ba1846dcf78bb2c85edbe8dd Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Sun, 3 May 2020 01:00:02 -0400 Subject: ima: verify mprotect change is consistent with mmap policy Files can be mmap'ed read/write and later changed to execute to circumvent IMA's mmap appraise policy rules. Due to locking issues (mmap semaphore would be taken prior to i_mutex), files can not be measured or appraised at this point. Eliminate this integrity gap, by denying the mprotect PROT_EXECUTE change, if an mmap appraise policy rule exists. On mprotect change success, return 0. On failure, return -EACESS. Reviewed-by: Lakshmi Ramasubramanian Signed-off-by: Mimi Zohar --- include/linux/ima.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index aefe758f4466..9164e1534ec9 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -18,6 +18,7 @@ extern int ima_file_check(struct file *file, int mask); extern void ima_post_create_tmpfile(struct inode *inode); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); +extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot); extern int ima_load_data(enum kernel_load_data_id id); extern int ima_read_file(struct file *file, enum kernel_read_file_id id); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, @@ -70,6 +71,12 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot) return 0; } +static inline int ima_file_mprotect(struct vm_area_struct *vma, + unsigned long prot) +{ + return 0; +} + static inline int ima_load_data(enum kernel_load_data_id id) { return 0; -- cgit v1.2.3 From d3e81989c0f028aa80cb97fcba83df40585b640d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:53:01 -0500 Subject: treewide: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Li Yang --- include/linux/fsl/bestcomm/bestcomm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsl/bestcomm/bestcomm.h b/include/linux/fsl/bestcomm/bestcomm.h index a0e2e6b19b57..154e541ce57e 100644 --- a/include/linux/fsl/bestcomm/bestcomm.h +++ b/include/linux/fsl/bestcomm/bestcomm.h @@ -27,7 +27,7 @@ */ struct bcom_bd { u32 status; - u32 data[0]; /* variable payload size */ + u32 data[]; /* variable payload size */ }; /* ======================================================================== */ -- cgit v1.2.3 From 65ece6de0114fc84fbc0487bf68cae91d535dd78 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 16 Apr 2020 11:50:49 +0200 Subject: virtchnl: Add missing explicit padding to structures MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On e.g. m68k, the alignment of 32-bit values is only 2 bytes, leading to the following: ./include/linux/avf/virtchnl.h:147:36: warning: division by zero [-Wdiv-by-zero] { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:577:1: note: in expansion of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); ^~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:577:32: error: enumerator value for ‘virtchnl_static_assert_virtchnl_filter’ is not an integer constant VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); ^~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:147:53: note: in definition of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:147:36: warning: division by zero [-Wdiv-by-zero] { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:619:1: note: in expansion of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_pf_event); ^~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:619:31: error: enumerator value for ‘virtchnl_static_assert_virtchnl_pf_event’ is not an integer constant VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_pf_event); ^~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:147:53: note: in definition of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:147:36: warning: division by zero [-Wdiv-by-zero] { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:640:1: note: in expansion of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_iwarp_qv_info); ^~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:640:31: error: enumerator value for ‘virtchnl_static_assert_virtchnl_iwarp_qv_info’ is not an integer constant VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_iwarp_qv_info); ^~~~~~~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:147:53: note: in definition of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:147:36: warning: division by zero [-Wdiv-by-zero] { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ ./include/linux/avf/virtchnl.h:647:1: note: in expansion of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_iwarp_qvlist_info); ^~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:647:31: error: enumerator value for ‘virtchnl_static_assert_virtchnl_iwarp_qvlist_info’ is not an integer constant VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_iwarp_qvlist_info); ^~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/avf/virtchnl.h:147:53: note: in definition of macro ‘VIRTCHNL_CHECK_STRUCT_LEN’ { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } ^ Fix this by adding explicit padding to structures with holes. Reported-by: Signed-off-by: Geert Uytterhoeven Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index ca956b672ac0..40bad71865ea 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -476,6 +476,7 @@ struct virtchnl_rss_key { u16 vsi_id; u16 key_len; u8 key[1]; /* RSS hash key, packed bytes */ + u8 pad[1]; }; VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key); @@ -484,6 +485,7 @@ struct virtchnl_rss_lut { u16 vsi_id; u16 lut_entries; u8 lut[1]; /* RSS lookup table */ + u8 pad[1]; }; VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut); @@ -572,6 +574,7 @@ struct virtchnl_filter { enum virtchnl_action action; u32 action_meta; u8 field_flags; + u8 pad[3]; }; VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); @@ -610,6 +613,7 @@ struct virtchnl_pf_event { /* link_speed provided in Mbps */ u32 link_speed; u8 link_status; + u8 pad[3]; } link_event_adv; } event_data; @@ -635,6 +639,7 @@ struct virtchnl_iwarp_qv_info { u16 ceq_idx; u16 aeq_idx; u8 itr_idx; + u8 pad[3]; }; VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_iwarp_qv_info); -- cgit v1.2.3 From afaa33da08abd10be8978781d7c99a9e67d2bbff Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Fri, 22 May 2020 19:19:01 +0200 Subject: Drivers: hv: vmbus: Resolve more races involving init_vp_index() init_vp_index() uses the (per-node) hv_numa_map[] masks to record the CPUs allocated for channel interrupts at a given time, and distribute the performance-critical channels across the available CPUs: in part., the mask of "candidate" target CPUs in a given NUMA node, for a newly offered channel, is determined by XOR-ing the node's CPU mask and the node's hv_numa_map. This operation/mechanism assumes that no offline CPUs is set in the hv_numa_map mask, an assumption that does not hold since such mask is currently not updated when a channel is removed or assigned to a different CPU. To address the issues described above, this adds hooks in the channel removal path (hv_process_channel_removal()) and in target_cpu_store() in order to clear, resp. to update, the hv_numa_map[] masks as needed. This also adds a (missed) update of the masks in init_vp_index() (cf., e.g., the memory-allocation failure path in this function). Like in the case of init_vp_index(), such hooks require to determine if the given channel is performance critical. init_vp_index() does this by parsing the channel's offer, it can not rely on the device data structure (device_obj) to retrieve such information because the device data structure has not been allocated/linked with the channel by the time that init_vp_index() executes. A similar situation may hold in hv_is_alloced_cpu() (defined below); the adopted approach is to "cache" the device type of the channel, as computed by parsing the channel's offer, in the channel structure itself. Fixes: 7527810573436f ("Drivers: hv: vmbus: Introduce the CHANNELMSG_MODIFYCHANNEL message type") Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20200522171901.204127-3-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index d783847d8cb4..40df3103e890 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -901,6 +901,13 @@ struct vmbus_channel { bool probe_done; + /* + * Cache the device ID here for easy access; this is useful, in + * particular, in situations where the channel's device_obj has + * not been allocated/initialized yet. + */ + u16 device_id; + /* * We must offload the handling of the primary/sub channels * from the single-threaded vmbus_connection.work_queue to -- cgit v1.2.3 From cd16627fc0468564fdd60f20ad52420b87195127 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Sat, 23 May 2020 15:27:10 +0200 Subject: net: devres: provide devm_register_netdev() Provide devm_register_netdev() - a device resource managed variant of register_netdev(). This new helper will only work for net_device structs that are also already managed by devres. Signed-off-by: Bartosz Golaszewski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a18f8fdf4260..1a96e9c4ec36 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4280,6 +4280,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, int register_netdev(struct net_device *dev); void unregister_netdev(struct net_device *dev); +int devm_register_netdev(struct device *dev, struct net_device *ndev); + /* General hardware address lists handling functions */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); -- cgit v1.2.3 From 1f1ec622623fe8e49a1036d4127b895a0f0e2c43 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 5 May 2020 12:13:35 +0200 Subject: mtd: rawnand: Propage CS selection to sub operations Some controller using the instruction parse infrastructure might need to know which CS a specific sub-operation is targeting. Let's propagate this information. Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20200505101353.1776394-2-boris.brezillon@collabora.com --- include/linux/mtd/rawnand.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 0f45b6984ad1..a3bac8824937 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -709,6 +709,7 @@ struct nand_op_instr { /** * struct nand_subop - a sub operation + * @cs: the CS line to select for this NAND sub-operation * @instrs: array of instructions * @ninstrs: length of the @instrs array * @first_instr_start_off: offset to start from for the first instruction @@ -724,6 +725,7 @@ struct nand_op_instr { * controller driver. */ struct nand_subop { + unsigned int cs; const struct nand_op_instr *instrs; unsigned int ninstrs; unsigned int first_instr_start_off; -- cgit v1.2.3 From c8ae3f744ddca0da164bcacee42d1d4b6fe7027d Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 09:45:42 +0200 Subject: lib/bch: Rework a little bit the exported function names There are four exported functions, all suffixed by _bch, which is clearly not the norm. Let's rename them by prefixing them with bch_ instead. This is a mechanical change: init_bch -> bch_init free_bch -> bch_free encode_bch -> bch_encode decode_bch -> bch_decode Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200519074549.23673-2-miquel.raynal@bootlin.com --- include/linux/bch.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bch.h b/include/linux/bch.h index aa765af85c38..9c35e7cd5890 100644 --- a/include/linux/bch.h +++ b/include/linux/bch.h @@ -53,14 +53,14 @@ struct bch_control { struct gf_poly *poly_2t[4]; }; -struct bch_control *init_bch(int m, int t, unsigned int prim_poly); +struct bch_control *bch_init(int m, int t, unsigned int prim_poly); -void free_bch(struct bch_control *bch); +void bch_free(struct bch_control *bch); -void encode_bch(struct bch_control *bch, const uint8_t *data, +void bch_encode(struct bch_control *bch, const uint8_t *data, unsigned int len, uint8_t *ecc); -int decode_bch(struct bch_control *bch, const uint8_t *data, unsigned int len, +int bch_decode(struct bch_control *bch, const uint8_t *data, unsigned int len, const uint8_t *recv_ecc, const uint8_t *calc_ecc, const unsigned int *syn, unsigned int *errloc); -- cgit v1.2.3 From 1759279ad138cb0a903224a89f4bf40f69c417e8 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 09:45:43 +0200 Subject: lib/bch: Allow easy bit swapping It seems that several hardware ECC engine use a swapped representation of bytes compared to software. This might having to do with how the ECC engine is wired to the NAND controller or the order the bits are passed to the hardware BCH logic. This means that when the software BCH engine is working in conjunction with data generated with hardware, sometimes we might need to swap the bits inside bytes, eg: 0x0A = b0000_1010 -> b0101_0000 = 0x50 Make it possible by adding a boolean to the BCH initialization routine. Regarding the implementation itself, this is a rather simple approach that can probably be enhanced in the future by preparing the ->a_{mod,pow}_tab tables with the swapping in mind. Suggested-by: Boris Brezillon Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200519074549.23673-3-miquel.raynal@bootlin.com --- include/linux/bch.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bch.h b/include/linux/bch.h index 9c35e7cd5890..85fdce83d4e2 100644 --- a/include/linux/bch.h +++ b/include/linux/bch.h @@ -33,6 +33,7 @@ * @cache: log-based polynomial representation buffer * @elp: error locator polynomial * @poly_2t: temporary polynomials of degree 2t + * @swap_bits: swap bits within data and syndrome bytes */ struct bch_control { unsigned int m; @@ -51,9 +52,11 @@ struct bch_control { int *cache; struct gf_poly *elp; struct gf_poly *poly_2t[4]; + bool swap_bits; }; -struct bch_control *bch_init(int m, int t, unsigned int prim_poly); +struct bch_control *bch_init(int m, int t, unsigned int prim_poly, + bool swap_bits); void bch_free(struct bch_control *bch); -- cgit v1.2.3 From d7904619ea0636411f40fb1f34057288c0783ecf Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 09:45:45 +0200 Subject: mtd: rawnand: Add nand_extract_bits() There are cases where ECC bytes are not byte-aligned. Indeed, BCH implies using a number of ECC bits, which are not always a multiple of 8. We then need a helper like nand_extract_bits() to extract these syndromes from a buffer. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200519074549.23673-5-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index a3bac8824937..2804c13e5662 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1414,6 +1414,10 @@ int nand_gpio_waitrdy(struct nand_chip *chip, struct gpio_desc *gpiod, void nand_select_target(struct nand_chip *chip, unsigned int cs); void nand_deselect_target(struct nand_chip *chip); +/* Bitops */ +void nand_extract_bits(u8 *dst, unsigned int dst_off, const u8 *src, + unsigned int src_off, unsigned int nbits); + /** * nand_get_data_buf() - Get the internal page buffer * @chip: NAND chip object -- cgit v1.2.3 From 5469fd64efcfbc2b9b2edb92c4f906912736d5b0 Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Tue, 5 May 2020 19:46:13 -0700 Subject: usb: gadget: Introduce usb_request->is_last To take advantage of DWC3 internal TRB prefetch and cache for performance, inform the controller the last request with stream_id before switching to a different stream transfer. This allows the controller to maintain its transfer burst within the stream ID. Introduce the usb-request is_last field to help inform the DWC3 controller of this. Signed-off-by: Thinh Nguyen Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index e959c09a97c9..281eabae7f33 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -42,6 +42,8 @@ struct usb_ep; * @num_mapped_sgs: number of SG entries mapped to DMA (internal) * @length: Length of that data * @stream_id: The stream id, when USB3.0 bulk streams are being used + * @is_last: Indicates if this is the last request of a stream_id before + * switching to a different stream (required for DWC3 controllers). * @no_interrupt: If true, hints that no completion irq is needed. * Helpful sometimes with deep request queues that are handled * directly by DMA controllers. @@ -104,6 +106,7 @@ struct usb_request { unsigned num_mapped_sgs; unsigned stream_id:16; + unsigned is_last:1; unsigned no_interrupt:1; unsigned zero:1; unsigned short_not_ok:1; -- cgit v1.2.3 From 3c73bc52195def14165c3a7d91bdbb33b51725f5 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Sun, 10 May 2020 13:30:41 +0800 Subject: usb: gadget: core: sync interrupt before unbind the udc The threaded interrupt handler may still be called after the usb_gadget_disconnect is called, it causes the structures used at interrupt handler was freed before it uses, eg the usb_request. This issue usually occurs we remove the udc function during the transfer. Below is the example when doing stress test for android switch function, the EP0's request is freed by .unbind (configfs_composite_unbind -> composite_dev_cleanup), but the threaded handler accesses this request during handling setup packet request. In fact, there is no protection between unbind the udc and udc interrupt handling, so we have to avoid the interrupt handler is occurred or scheduled during the .unbind flow. init: Sending signal 9 to service 'adbd' (pid 18077) process group... android_work: did not send uevent (0 0 000000007bec2039) libprocessgroup: Successfully killed process cgroup uid 0 pid 18077 in 6ms init: Service 'adbd' (pid 18077) received signal 9 init: Sending signal 9 to service 'adbd' (pid 18077) process group... libprocessgroup: Successfully killed process cgroup uid 0 pid 18077 in 0ms init: processing action (init.svc.adbd=stopped) from (/init.usb.configfs.rc:14) init: Received control message 'start' for 'adbd' from pid: 399 (/vendor/bin/hw/android.hardware.usb@1. init: starting service 'adbd'... read descriptors read strings Unable to handle kernel read from unreadable memory at virtual address 000000000000002a android_work: sent uevent USB_STATE=CONNECTED Mem abort info: ESR = 0x96000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=00000000e97f1000 using random self ethernet address [000000000000002a] pgd=0000000000000000 Internal error: Oops: 96000004 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 232 Comm: irq/68-5b110000 Not tainted 5.4.24-06075-g94a6b52b5815 #92 Hardware name: Freescale i.MX8QXP MEK (DT) pstate: 00400085 (nzcv daIf +PAN -UAO) using random host ethernet address pc : composite_setup+0x5c/0x1730 lr : android_setup+0xc0/0x148 sp : ffff80001349bba0 x29: ffff80001349bba0 x28: ffff00083a50da00 x27: ffff8000124e6000 x26: ffff800010177950 x25: 0000000000000040 x24: ffff000834e18010 x23: 0000000000000000 x22: 0000000000000000 x21: ffff00083a50da00 x20: ffff00082e75ec40 x19: 0000000000000000 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000001 x11: ffff80001180fb58 x10: 0000000000000040 x9 : ffff8000120fc980 x8 : 0000000000000000 x7 : ffff00083f98df50 x6 : 0000000000000100 x5 : 00000307e8978431 x4 : ffff800011386788 x3 : 0000000000000000 x2 : ffff800012342000 x1 : 0000000000000000 x0 : ffff800010c6d3a0 Call trace: composite_setup+0x5c/0x1730 android_setup+0xc0/0x148 cdns3_ep0_delegate_req+0x64/0x90 cdns3_check_ep0_interrupt_proceed+0x384/0x738 cdns3_device_thread_irq_handler+0x124/0x6e0 cdns3_thread_irq+0x94/0xa0 irq_thread_fn+0x30/0xa0 irq_thread+0x150/0x248 kthread+0xfc/0x128 ret_from_fork+0x10/0x18 Code: 910e8000 f9400693 12001ed7 79400f79 (3940aa61) ---[ end trace c685db37f8773fba ]--- Kernel panic - not syncing: Fatal exception SMP: stopping secondary CPUs Kernel Offset: disabled CPU features: 0x0002,20002008 Memory Limit: none Rebooting in 5 seconds.. Reviewed-by: Jun Li Signed-off-by: Peter Chen Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 281eabae7f33..6a178177e4c9 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -376,6 +376,7 @@ struct usb_gadget_ops { * @connected: True if gadget is connected. * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag * indicates that it supports LPM as per the LPM ECN & errata. + * @irq: the interrupt number for device controller. * * Gadgets have a mostly-portable "gadget driver" implementing device * functions, handling all usb configurations and interfaces. Gadget @@ -430,6 +431,7 @@ struct usb_gadget { unsigned deactivated:1; unsigned connected:1; unsigned lpm_capable:1; + int irq; }; #define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) -- cgit v1.2.3 From 5d363120aa548ba52d58907a295eee25f8207ed2 Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Mon, 18 May 2020 12:08:45 +0200 Subject: usb: gadget: Fix issue with config_ep_by_speed function This patch adds new config_ep_by_speed_and_alt function which extends the config_ep_by_speed about alt parameter. This additional parameter allows to find proper usb_ss_ep_comp_descriptor. Problem has appeared during testing f_tcm (BOT/UAS) driver function. f_tcm function for SS use array of headers for both BOT/UAS alternate setting: static struct usb_descriptor_header *uasp_ss_function_desc[] = { (struct usb_descriptor_header *) &bot_intf_desc, (struct usb_descriptor_header *) &uasp_ss_bi_desc, (struct usb_descriptor_header *) &bot_bi_ep_comp_desc, (struct usb_descriptor_header *) &uasp_ss_bo_desc, (struct usb_descriptor_header *) &bot_bo_ep_comp_desc, (struct usb_descriptor_header *) &uasp_intf_desc, (struct usb_descriptor_header *) &uasp_ss_bi_desc, (struct usb_descriptor_header *) &uasp_bi_ep_comp_desc, (struct usb_descriptor_header *) &uasp_bi_pipe_desc, (struct usb_descriptor_header *) &uasp_ss_bo_desc, (struct usb_descriptor_header *) &uasp_bo_ep_comp_desc, (struct usb_descriptor_header *) &uasp_bo_pipe_desc, (struct usb_descriptor_header *) &uasp_ss_status_desc, (struct usb_descriptor_header *) &uasp_status_in_ep_comp_desc, (struct usb_descriptor_header *) &uasp_status_pipe_desc, (struct usb_descriptor_header *) &uasp_ss_cmd_desc, (struct usb_descriptor_header *) &uasp_cmd_comp_desc, (struct usb_descriptor_header *) &uasp_cmd_pipe_desc, NULL, }; The first 5 descriptors are associated with BOT alternate setting, and others are associated with UAS. During handling UAS alternate setting f_tcm driver invokes config_ep_by_speed and this function sets incorrect companion endpoint descriptor in usb_ep object. Instead setting ep->comp_desc to uasp_bi_ep_comp_desc function in this case set ep->comp_desc to uasp_ss_bi_desc. This is due to the fact that it searches endpoint based on endpoint address: for_each_ep_desc(speed_desc, d_spd) { chosen_desc = (struct usb_endpoint_descriptor *)*d_spd; if (chosen_desc->bEndpoitAddress == _ep->address) goto ep_found; } And in result it uses the descriptor from BOT alternate setting instead UAS. Finally, it causes that controller driver during enabling endpoints detect that just enabled endpoint for bot. Signed-off-by: Jayshri Pawar Signed-off-by: Pawel Laszczak Signed-off-by: Felipe Balbi --- include/linux/usb/composite.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 8675e145ea8b..2040696d75b6 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -249,6 +249,9 @@ int usb_function_activate(struct usb_function *); int usb_interface_id(struct usb_configuration *, struct usb_function *); +int config_ep_by_speed_and_alt(struct usb_gadget *g, struct usb_function *f, + struct usb_ep *_ep, u8 alt); + int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, struct usb_ep *_ep); -- cgit v1.2.3 From eb012d125a2419786f5bcaaf8a901babc7b6e3d7 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 25 May 2020 00:32:43 +0900 Subject: printk: Remove pr_cont_once() pr_cont_once() does not make sense; at least emitting module name using pr_fmt() into middle of a line (after e.g. pr_info_once()) does not make sense. Let's remove unused pr_cont_once(). Link: https://lore.kernel.org/r/20200524153243.11690-1-penguin-kernel@I-love.SAKURA.ne.jp Cc: Joe Perches Signed-off-by: Tetsuo Handa Acked-by: Sergey Senozhatsky Signed-off-by: Petr Mladek --- include/linux/printk.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index e061635e0409..07f2d08f79ff 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -384,8 +384,7 @@ extern int kptr_restrict; printk_once(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info_once(fmt, ...) \ printk_once(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) -#define pr_cont_once(fmt, ...) \ - printk_once(KERN_CONT pr_fmt(fmt), ##__VA_ARGS__) +/* no pr_cont_once, don't do that... */ #if defined(DEBUG) #define pr_devel_once(fmt, ...) \ -- cgit v1.2.3 From 551cb86cbb7d85a3d16d10f6fb4fb954f13a7556 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 19 May 2020 16:12:33 +0300 Subject: gpio: dwapb: Remove unneeded has_irq member in struct dwapb_port_property has_irq member of struct dwapb_port_property is used only in one place, so, make it local test instead and remove from the structure. This local test is using memchr_inv() which is quite efficient in comparison to the original loop and possible little overhead can be neglected. Signed-off-by: Andy Shevchenko Tested-by: Serge Semin Acked-by: Lee Jones Acked-by: Serge Semin Link: https://lore.kernel.org/r/20200519131233.59032-4-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-dwapb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-dwapb.h b/include/linux/platform_data/gpio-dwapb.h index 3c606c450d05..ff1be737bad6 100644 --- a/include/linux/platform_data/gpio-dwapb.h +++ b/include/linux/platform_data/gpio-dwapb.h @@ -12,7 +12,6 @@ struct dwapb_port_property { unsigned int ngpio; unsigned int gpio_base; int irq[32]; - bool has_irq; bool irq_shared; }; -- cgit v1.2.3 From 1072c12d7d58b5512b6c05c2268f57d32f1ab76c Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 16 Apr 2020 14:46:11 -0700 Subject: block: add bio_for_each_bvec_all() An upcoming Btrfs fix needs to know the original size of a non-cloned bios. Rather than accessing the bvec table directly, let's add a bio_for_each_bvec_all() accessor. Reviewed-by: Johannes Thumshirn Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- include/linux/bio.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index a0ee494a6329..8e23f51ccfa4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -169,6 +169,14 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, #define bio_for_each_bvec(bvl, bio, iter) \ __bio_for_each_bvec(bvl, bio, iter, (bio)->bi_iter) +/* + * Iterate over all multi-page bvecs. Drivers shouldn't use this version for the + * same reasons as bio_for_each_segment_all(). + */ +#define bio_for_each_bvec_all(bvl, bio, i) \ + for (i = 0, bvl = bio_first_bvec_all(bio); \ + i < (bio)->bi_vcnt; i++, bvl++) \ + #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) static inline unsigned bio_segments(struct bio *bio) -- cgit v1.2.3 From d85dc2e116fdce776280224ed2bee4c78e5e5af2 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Fri, 30 Aug 2019 12:09:24 -0500 Subject: fs: export generic_file_buffered_read() Export generic_file_buffered_read() to be used to supplement incomplete direct reads. Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Goldwyn Rodrigues Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 45cc10cdf6dd..366c533d30cd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3124,6 +3124,8 @@ extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t *count, unsigned int flags); +extern ssize_t generic_file_buffered_read(struct kiocb *iocb, + struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); -- cgit v1.2.3 From 8cecd0ba854799cda72d03a470e7de9eed3ed6c4 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Tue, 14 May 2019 18:54:27 -0500 Subject: iomap: add a filesystem hook for direct I/O bio submission This helps filesystems to perform tasks on the bio while submitting for I/O. This could be post-write operations such as data CRC or data replication for fs-handled RAID. Reviewed-by: Johannes Thumshirn Reviewed-by: Nikolay Borisov Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Goldwyn Rodrigues Signed-off-by: David Sterba --- include/linux/iomap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 8b09463dae0d..5b4875344874 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -252,6 +252,8 @@ int iomap_writepages(struct address_space *mapping, struct iomap_dio_ops { int (*end_io)(struct kiocb *iocb, ssize_t size, int error, unsigned flags); + blk_qc_t (*submit_io)(struct inode *inode, struct iomap *iomap, + struct bio *bio, loff_t file_offset); }; ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, -- cgit v1.2.3 From cea0fad0f8b41481c0052a1f30d296d6d6dd0b2e Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Thu, 30 Apr 2020 15:52:24 +0200 Subject: mailmap: change email for Ricardo Ribalda Modify emails to ribalda@kernel.org and unify my surname in all the files. Signed-off-by: Ricardo Ribalda Link: https://lore.kernel.org/r/20200430135224.362700-1-ricardo@ribalda.com Signed-off-by: Jonathan Corbet --- include/linux/platform_data/ad5761.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/ad5761.h b/include/linux/platform_data/ad5761.h index 02bef5177ff5..69e261e2ca14 100644 --- a/include/linux/platform_data/ad5761.h +++ b/include/linux/platform_data/ad5761.h @@ -3,7 +3,7 @@ * AD5721, AD5721R, AD5761, AD5761R, Voltage Output Digital to Analog Converter * * Copyright 2016 Qtechnology A/S - * 2016 Ricardo Ribalda + * 2016 Ricardo Ribalda */ #ifndef __LINUX_PLATFORM_DATA_AD5761_H__ #define __LINUX_PLATFORM_DATA_AD5761_H__ -- cgit v1.2.3 From 11399346ac39a26ade2a90303d38ad318163c665 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:00:33 -0500 Subject: mtd: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Acked-by: Miquel Raynal Signed-off-by: Vignesh Raghavendra Link: https://lore.kernel.org/r/20200507190033.GA15215@embeddedor --- include/linux/mtd/cfi.h | 6 +++--- include/linux/mtd/qinfo.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index c98a21108688..fd1ecb821106 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -138,7 +138,7 @@ struct cfi_ident { uint16_t InterfaceDesc; uint16_t MaxBufWriteSize; uint8_t NumEraseRegions; - uint32_t EraseRegionInfo[0]; /* Not host ordered */ + uint32_t EraseRegionInfo[]; /* Not host ordered */ } __packed; /* Extended Query Structure for both PRI and ALT */ @@ -165,7 +165,7 @@ struct cfi_pri_intelext { uint16_t ProtRegAddr; uint8_t FactProtRegSize; uint8_t UserProtRegSize; - uint8_t extra[0]; + uint8_t extra[]; } __packed; struct cfi_intelext_otpinfo { @@ -286,7 +286,7 @@ struct cfi_private { map_word sector_erase_cmd; unsigned long chipshift; /* Because they're of the same type */ const char *im_name; /* inter_module name for cmdset_setup */ - struct flchip chips[0]; /* per-chip data structure for each chip */ + struct flchip chips[]; /* per-chip data structure for each chip */ }; uint32_t cfi_build_cmd_addr(uint32_t cmd_ofs, diff --git a/include/linux/mtd/qinfo.h b/include/linux/mtd/qinfo.h index df5b9fddea16..2e3f43788d48 100644 --- a/include/linux/mtd/qinfo.h +++ b/include/linux/mtd/qinfo.h @@ -24,7 +24,7 @@ struct lpddr_private { struct qinfo_chip *qinfo; int numchips; unsigned long chipshift; - struct flchip chips[0]; + struct flchip chips[]; }; /* qinfo_query_info structure contains request information for -- cgit v1.2.3 From 06081646450e46efcc1ca58c3b227bd60083cd3e Mon Sep 17 00:00:00 2001 From: Saravanan Sekar Date: Tue, 26 May 2020 11:06:42 +0200 Subject: mfd: mp2629: Add support for mps battery charger mp2629 is a highly-integrated switching-mode battery charge management device for single-cell Li-ion or Li-polymer battery. Add MFD core enables chip access for ADC driver for battery readings, and a power supply battery-charger driver Signed-off-by: Saravanan Sekar Reviewed-by: Andy Shevchenko Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones --- include/linux/mfd/mp2629.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/linux/mfd/mp2629.h (limited to 'include/linux') diff --git a/include/linux/mfd/mp2629.h b/include/linux/mfd/mp2629.h new file mode 100644 index 000000000000..baaeeaf82949 --- /dev/null +++ b/include/linux/mfd/mp2629.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2020 Monolithic Power Systems, Inc + */ + +#ifndef __MP2629_H__ +#define __MP2629_H__ + +#include +#include + +struct mp2629_data { + struct device *dev; + struct regmap *regmap; +}; + +#endif -- cgit v1.2.3 From 7abd9fb6468225f5c7f83149ce279cc1a912a68a Mon Sep 17 00:00:00 2001 From: Saravanan Sekar Date: Tue, 26 May 2020 11:06:43 +0200 Subject: iio: adc: mp2629: Add support for mp2629 ADC driver Add support for 8-bit resolution ADC readings for input power supply and battery charging measurement. Provides voltage, current readings to mp2629 power supply driver. Signed-off-by: Saravanan Sekar Reviewed-by: Andy Shevchenko Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones --- include/linux/mfd/mp2629.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mp2629.h b/include/linux/mfd/mp2629.h index baaeeaf82949..89b706900b57 100644 --- a/include/linux/mfd/mp2629.h +++ b/include/linux/mfd/mp2629.h @@ -14,4 +14,13 @@ struct mp2629_data { struct regmap *regmap; }; +enum mp2629_adc_chan { + MP2629_BATT_VOLT, + MP2629_SYSTEM_VOLT, + MP2629_INPUT_VOLT, + MP2629_BATT_CURRENT, + MP2629_INPUT_CURRENT, + MP2629_ADC_CHAN_END +}; + #endif -- cgit v1.2.3 From 9aa8759960e36291e7663288d58b47ee4927b6f5 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Sat, 16 May 2020 14:06:08 +0300 Subject: mfd: Constify properties in mfd_cell Constify 'struct property_entry *properties' in mfd_cell. It is always passed around as a pointer const struct. Signed-off-by: Tomas Winkler Signed-off-by: Lee Jones --- include/linux/mfd/core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index d01d1299e49d..7e5ac3c00891 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -70,7 +70,7 @@ struct mfd_cell { size_t pdata_size; /* device properties passed to the sub devices drivers */ - struct property_entry *properties; + const struct property_entry *properties; /* * Device Tree compatible string -- cgit v1.2.3 From 97eda5dcc2cde5dcc778bef7a9344db3b6bf8ef5 Mon Sep 17 00:00:00 2001 From: Amelie Delaunay Date: Wed, 22 Apr 2020 11:08:33 +0200 Subject: mfd: stmfx: Disable IRQ in suspend to avoid spurious interrupt When STMFX supply is stopped, spurious interrupt can occur. To avoid that, disable the interrupt in suspend before disabling the regulator and re-enable it at the end of resume. Fixes: 06252ade9156 ("mfd: Add ST Multi-Function eXpander (STMFX) core driver") Signed-off-by: Amelie Delaunay Signed-off-by: Lee Jones --- include/linux/mfd/stmfx.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/stmfx.h b/include/linux/mfd/stmfx.h index 3c67983678ec..744dce63946e 100644 --- a/include/linux/mfd/stmfx.h +++ b/include/linux/mfd/stmfx.h @@ -109,6 +109,7 @@ struct stmfx { struct device *dev; struct regmap *map; struct regulator *vdd; + int irq; struct irq_domain *irq_domain; struct mutex lock; /* IRQ bus lock */ u8 irq_src; -- cgit v1.2.3 From aaf2bc50df1f4bfc6857fc601fc7b21d5a18c6a1 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 21 May 2020 22:05:15 +0200 Subject: rcu: Abstract out rcu_irq_enter_check_tick() from rcu_nmi_enter() There will likely be exception handlers that can sleep, which rules out the usual approach of invoking rcu_nmi_enter() on entry and also rcu_nmi_exit() on all exit paths. However, the alternative approach of just not calling anything can prevent RCU from coaxing quiescent states from nohz_full CPUs that are looping in the kernel: RCU must instead IPI them explicitly. It would be better to enable the scheduler tick on such CPUs to interact with RCU in a lighter-weight manner, and this enabling is one of the things that rcu_nmi_enter() currently does. What is needed is something that helps RCU coax quiescent states while not preventing subsequent sleeps. This commit therefore splits out the nohz_full scheduler-tick enabling from the rest of the rcu_nmi_enter() logic into a new function named rcu_irq_enter_check_tick(). [ tglx: Renamed the function and made it a nop when context tracking is off ] [ mingo: Fixed a CONFIG_NO_HZ_FULL assumption, harmonized and fixed all the comment blocks and cleaned up rcu_nmi_enter()/exit() definitions. ] Suggested-by: Andy Lutomirski Signed-off-by: Paul E. McKenney Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200521202116.996113173@linutronix.de --- include/linux/hardirq.h | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 621556efe45f..e07cf853aa16 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -2,31 +2,28 @@ #ifndef LINUX_HARDIRQ_H #define LINUX_HARDIRQ_H +#include #include #include #include #include #include - extern void synchronize_irq(unsigned int irq); extern bool synchronize_hardirq(unsigned int irq); -#if defined(CONFIG_TINY_RCU) - -static inline void rcu_nmi_enter(void) -{ -} +#ifdef CONFIG_NO_HZ_FULL +void __rcu_irq_enter_check_tick(void); +#else +static inline void __rcu_irq_enter_check_tick(void) { } +#endif -static inline void rcu_nmi_exit(void) +static __always_inline void rcu_irq_enter_check_tick(void) { + if (context_tracking_enabled()) + __rcu_irq_enter_check_tick(); } -#else -extern void rcu_nmi_enter(void); -extern void rcu_nmi_exit(void); -#endif - /* * It is safe to do non-atomic ops on ->hardirq_context, * because NMI handlers may not preempt and the ops are @@ -65,6 +62,14 @@ extern void irq_exit(void); #define arch_nmi_exit() do { } while (0) #endif +#ifdef CONFIG_TINY_RCU +static inline void rcu_nmi_enter(void) { } +static inline void rcu_nmi_exit(void) { } +#else +extern void rcu_nmi_enter(void); +extern void rcu_nmi_exit(void); +#endif + /* * NMI vs Tracing * -------------- -- cgit v1.2.3 From 07325d4a90d2d84de45cc07b134fd0f023dbb971 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 May 2020 22:05:16 +0200 Subject: rcu: Provide rcu_irq_exit_check_preempt() Provide a debug check which can be invoked from exception return to kernel mode before an attempt is made to schedule. Warn if RCU is not ready for this. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Cc: Paul E. McKenney Link: https://lore.kernel.org/r/20200521202117.089709607@linutronix.de --- include/linux/rcutiny.h | 1 + include/linux/rcutree.h | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index c869fb20cc51..8512caeb7682 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -72,6 +72,7 @@ static inline void rcu_irq_exit_irqson(void) { } static inline void rcu_irq_enter_irqson(void) { } static inline void rcu_irq_exit(void) { } static inline void rcu_irq_exit_preempt(void) { } +static inline void rcu_irq_exit_check_preempt(void) { } static inline void exit_rcu(void) { } static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t) { diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 9366fa4d0717..d5cc9d675987 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -51,6 +51,12 @@ void rcu_irq_exit_preempt(void); void rcu_irq_enter_irqson(void); void rcu_irq_exit_irqson(void); +#ifdef CONFIG_PROVE_RCU +void rcu_irq_exit_check_preempt(void); +#else +static inline void rcu_irq_exit_check_preempt(void) { } +#endif + void exit_rcu(void); void rcu_scheduler_starting(void); -- cgit v1.2.3 From 46d26819a5056f4831649c5887ad5c71a16d86f7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 24 May 2020 17:30:40 +0200 Subject: software node: implement software_node_unregister() Sometimes it is better to unregister individual nodes instead of trying to do them all at once with software_node_unregister_nodes(), so create software_node_unregister() so that you can unregister them one at a time. This is especially important when creating nodes in a hierarchy, with parent -> children representations. Children always need to be removed before a parent is, as the swnode logic assumes this is going to be the case. Fix up the lib/test_printf.c fwnode_pointer() test which to use this new function as it had the problem of tearing things down in the backwards order. Fixes: f1ce39df508d ("lib/test_printf: Add tests for %pfw printk modifier") Cc: stable Cc: Andy Shevchenko Cc: Brendan Higgins Cc: Dmitry Torokhov Cc: Petr Mladek Cc: Rafael J. Wysocki Cc: Rasmus Villemoes Cc: Sakari Ailus Cc: Sergey Senozhatsky Cc: Steven Rostedt Reported-by: Naresh Kamboju Reported-by: kernel test robot Reported-by: Randy Dunlap Tested-by: Petr Mladek Tested-by: Randy Dunlap Tested-by: Guenter Roeck Reviewed-by: Heikki Krogerus Acked-by: Randy Dunlap Link: https://lore.kernel.org/r/20200524153041.2361-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/property.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index d86de017c689..0d4099b4ce1f 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -441,6 +441,7 @@ int software_node_register_nodes(const struct software_node *nodes); void software_node_unregister_nodes(const struct software_node *nodes); int software_node_register(const struct software_node *node); +void software_node_unregister(const struct software_node *node); int software_node_notify(struct device *dev, unsigned long action); -- cgit v1.2.3 From ff937b916eb6316fe4644564a572ed3b5867bc1f Mon Sep 17 00:00:00 2001 From: Yuval Basson Date: Tue, 26 May 2020 09:41:20 +0300 Subject: qed: Add EDPM mode type for user-fw compatibility In older FW versions the completion flag was treated as the ack flag in edpm messages. Expose the FW option of setting which mode the QP is in by adding a flag to the qedr <-> qed API. Flag is added for backward compatibility with libqedr. This flag will be set by qedr after determining whether the libqedr is using the updated version. Fixes: f10939403352 ("qed: Add support for QP verbs") Signed-off-by: Yuval Basson Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_rdma_if.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index f93edd5750a5..584077565f12 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -335,6 +335,9 @@ struct qed_rdma_create_qp_in_params { u16 xrcd_id; u8 stats_queue; enum qed_rdma_qp_type qp_type; + u8 flags; +#define QED_ROCE_EDPM_MODE_MASK 0x1 +#define QED_ROCE_EDPM_MODE_SHIFT 0 }; struct qed_rdma_create_qp_out_params { -- cgit v1.2.3 From 90ce665c6a40dc1be771bf5f86e624c0acf3a76f Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 26 May 2020 16:29:36 +0100 Subject: net: mdiobus: add clause 45 mdiobus accessors There is a recurring pattern throughout some of the PHY code converting a devad and regnum to our packed clause 45 representation. Rather than having this scattered around the code, let's put a common translation function in mdio.h, and provide some register accessors. Convert the phylib core, phylink, bcm87xx and cortina to use these. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio.h | 31 +++++++++++++++++++++++++++++++ include/linux/phy.h | 6 ------ 2 files changed, 31 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 917e4bb2ed71..36d2e0673d03 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -9,6 +9,13 @@ #include #include +/* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit + * IEEE 802.3ae clause 45 addressing mode used by 10GIGE phy chips. + */ +#define MII_ADDR_C45 (1<<30) +#define MII_DEVADDR_C45_SHIFT 16 +#define MII_REGADDR_C45_MASK GENMASK(15, 0) + struct gpio_desc; struct mii_bus; @@ -326,6 +333,30 @@ int mdiobus_write_nested(struct mii_bus *bus, int addr, u32 regnum, u16 val); int mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set); +static inline u32 mdiobus_c45_addr(int devad, u16 regnum) +{ + return MII_ADDR_C45 | devad << MII_DEVADDR_C45_SHIFT | regnum; +} + +static inline int __mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, + u16 regnum) +{ + return __mdiobus_read(bus, prtad, mdiobus_c45_addr(devad, regnum)); +} + +static inline int __mdiobus_c45_write(struct mii_bus *bus, int prtad, int devad, + u16 regnum, u16 val) +{ + return __mdiobus_write(bus, prtad, mdiobus_c45_addr(devad, regnum), + val); +} + +static inline int mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, + u16 regnum) +{ + return mdiobus_read(bus, prtad, mdiobus_c45_addr(devad, regnum)); +} + int mdiobus_register_device(struct mdio_device *mdiodev); int mdiobus_unregister_device(struct mdio_device *mdiodev); bool mdiobus_is_registered_device(struct mii_bus *bus, int addr); diff --git a/include/linux/phy.h b/include/linux/phy.h index 2bcdf19ed3b4..6d256e720a66 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -209,12 +209,6 @@ static inline const char *phy_modes(phy_interface_t interface) #define MII_BUS_ID_SIZE 61 -/* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit - IEEE 802.3ae clause 45 addressing mode used by 10GIGE phy chips. */ -#define MII_ADDR_C45 (1<<30) -#define MII_DEVADDR_C45_SHIFT 16 -#define MII_REGADDR_C45_MASK GENMASK(15, 0) - struct device; struct phylink; struct sfp_bus; -- cgit v1.2.3 From f1e71d75f04792721d411170168e68019ccb7de3 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:04:52 -0500 Subject: nvme: replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index b235a48eac8c..e2993e6a9d7c 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1185,7 +1185,7 @@ struct nvmf_disc_rsp_page_hdr { __le64 numrec; __le16 recfmt; __u8 resv14[1006]; - struct nvmf_disc_rsp_page_entry entries[0]; + struct nvmf_disc_rsp_page_entry entries[]; }; enum { -- cgit v1.2.3 From c295ee4742fda49de598a304ef9a95cf8da6b1f5 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Tue, 19 May 2020 17:05:48 +0300 Subject: block: always define struct blk_integrity in genhd.h This will reduce the amount of ifdefs inside the source code for various drivers and also will reduce the amount of stub functions that were created for the !CONFIG_BLK_DEV_INTEGRITY case. Suggested-by: Christoph Hellwig Signed-off-by: Max Gurtovoy Reviewed-by: Israel Rukshin Reviewed-by: Martin K. Petersen Signed-off-by: Christoph Hellwig --- include/linux/genhd.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index f9c226f9546a..2590bed6e6b3 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -169,8 +169,6 @@ struct disk_part_tbl { struct disk_events; struct badblocks; -#if defined(CONFIG_BLK_DEV_INTEGRITY) - struct blk_integrity { const struct blk_integrity_profile *profile; unsigned char flags; @@ -179,8 +177,6 @@ struct blk_integrity { unsigned char tag_size; }; -#endif /* CONFIG_BLK_DEV_INTEGRITY */ - struct gendisk { /* major, first_minor and minors are input parameters only, * don't use directly. Use disk_devt() and disk_max_parts(). -- cgit v1.2.3 From 39481fbd14ee272edd419d73a98bc637e2a3fd35 Mon Sep 17 00:00:00 2001 From: Israel Rukshin Date: Tue, 19 May 2020 17:06:00 +0300 Subject: nvme: add Metadata Capabilities enumerations The enumerations will be used to expose the namespace metadata format by the target. Suggested-by: Christoph Hellwig Signed-off-by: Israel Rukshin Signed-off-by: Max Gurtovoy Reviewed-by: James Smart Reviewed-by: Martin K. Petersen Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index e2993e6a9d7c..5ce51ab4c50e 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -420,6 +420,12 @@ enum { NVME_NS_DPS_PI_TYPE3 = 3, }; +/* Identify Namespace Metadata Capabilities (MC): */ +enum { + NVME_MC_EXTENDED_LBA = (1 << 0), + NVME_MC_METADATA_PTR = (1 << 1), +}; + struct nvme_ns_id_desc { __u8 nidt; __u8 nidl; -- cgit v1.2.3 From 1a644de29f712771c2ec00e52caa391544eb6141 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 27 May 2020 00:21:38 +0200 Subject: net: ethtool: Add generic parts of cable test TDR Add the generic parts of the code used to trigger a cable test and return raw TDR data. Any PHY driver which support this must implement the new driver op. Signed-off-by: Andrew Lunn v2 Update nxp-tja11xx for API change. Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 4 ++-- include/linux/phy.h | 13 +++++++++++++ 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index e317fc99565e..24817ba252a0 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -17,13 +17,13 @@ enum ethtool_multicast_groups { struct phy_device; #if IS_ENABLED(CONFIG_ETHTOOL_NETLINK) -int ethnl_cable_test_alloc(struct phy_device *phydev); +int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd); void ethnl_cable_test_free(struct phy_device *phydev); void ethnl_cable_test_finished(struct phy_device *phydev); int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result); int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm); #else -static inline int ethnl_cable_test_alloc(struct phy_device *phydev) +static inline int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd) { return -EOPNOTSUPP; } diff --git a/include/linux/phy.h b/include/linux/phy.h index 6d256e720a66..d3c384f353ca 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -699,6 +699,10 @@ struct phy_driver { /* Start a cable test */ int (*cable_test_start)(struct phy_device *dev); + + /* Start a raw TDR cable test */ + int (*cable_test_tdr_start)(struct phy_device *dev); + /* Once per second, or on interrupt, request the status of the * test. */ @@ -1251,6 +1255,8 @@ int phy_reset_after_clk_enable(struct phy_device *phydev); #if IS_ENABLED(CONFIG_PHYLIB) int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack); +int phy_start_cable_test_tdr(struct phy_device *phydev, + struct netlink_ext_ack *extack); #else static inline int phy_start_cable_test(struct phy_device *phydev, @@ -1259,6 +1265,13 @@ int phy_start_cable_test(struct phy_device *phydev, NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; } +static inline +int phy_start_cable_test_tdr(struct phy_device *phydev, + struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); + return -EOPNOTSUPP; +} #endif int phy_cable_test_result(struct phy_device *phydev, u8 pair, u16 result); -- cgit v1.2.3 From 6b4a0fc106521e480c00b55a7ef38c89f02dc4e8 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 27 May 2020 00:21:39 +0200 Subject: net: ethtool: Add helpers for cable test TDR data Add helpers for returning raw TDR helpers in netlink messages. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 24817ba252a0..8fbe4f97ffad 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -22,6 +22,10 @@ void ethnl_cable_test_free(struct phy_device *phydev); void ethnl_cable_test_finished(struct phy_device *phydev); int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result); int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm); +int ethnl_cable_test_amplitude(struct phy_device *phydev, u8 pair, s16 mV); +int ethnl_cable_test_pulse(struct phy_device *phydev, u16 mV); +int ethnl_cable_test_step(struct phy_device *phydev, u32 first, u32 last, + u32 step); #else static inline int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd) { @@ -46,5 +50,22 @@ static inline int ethnl_cable_test_fault_length(struct phy_device *phydev, { return -EOPNOTSUPP; } + +static inline int ethnl_cable_test_amplitude(struct phy_device *phydev, + u8 pair, s16 mV) +{ + return -EOPNOTSUPP; +} + +static inline int ethnl_cable_test_pulse(struct phy_device *phydev, u16 mV) +{ + return -EOPNOTSUPP; +} + +static inline int ethnl_cable_test_step(struct phy_device *phydev, u32 first, + u32 last, u32 step) +{ + return -EOPNOTSUPP; +} #endif /* IS_ENABLED(ETHTOOL_NETLINK) */ #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ -- cgit v1.2.3 From f2bc8ad31a7f814237bc6301d59296d76505a688 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 27 May 2020 00:21:41 +0200 Subject: net: ethtool: Allow PHY cable test TDR data to configured Allow the user to configure where on the cable the TDR data should be retrieved, in terms of first and last sample, and the step between samples. Also add the ability to ask for TDR data for just one pair. If this configuration is not provided, it defaults to 1-150m at 1m intervals for all pairs. Signed-off-by: Andrew Lunn v3: Move the TDR configuration into a structure Add a range check on step Use NL_SET_ERR_MSG_ATTR() when appropriate Move TDR configuration into a nest Document attributes in the request Signed-off-by: David S. Miller --- include/linux/phy.h | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index d3c384f353ca..8c05d0fb5c00 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -548,6 +548,18 @@ struct phy_device { #define to_phy_device(d) container_of(to_mdio_device(d), \ struct phy_device, mdio) +/* A structure containing possible configuration parameters + * for a TDR cable test. The driver does not need to implement + * all the parameters, but should report what is actually used. + */ +struct phy_tdr_config { + u32 first; + u32 last; + u32 step; + s8 pair; +}; +#define PHY_PAIR_ALL -1 + /* struct phy_driver: Driver structure for a particular PHY type * * driver_data: static driver data @@ -701,7 +713,8 @@ struct phy_driver { int (*cable_test_start)(struct phy_device *dev); /* Start a raw TDR cable test */ - int (*cable_test_tdr_start)(struct phy_device *dev); + int (*cable_test_tdr_start)(struct phy_device *dev, + const struct phy_tdr_config *config); /* Once per second, or on interrupt, request the status of the * test. @@ -1256,7 +1269,8 @@ int phy_reset_after_clk_enable(struct phy_device *phydev); int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack); int phy_start_cable_test_tdr(struct phy_device *phydev, - struct netlink_ext_ack *extack); + struct netlink_ext_ack *extack, + const struct phy_tdr_config *config); #else static inline int phy_start_cable_test(struct phy_device *phydev, @@ -1267,7 +1281,8 @@ int phy_start_cable_test(struct phy_device *phydev, } static inline int phy_start_cable_test_tdr(struct phy_device *phydev, - struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack, + const struct phy_tdr_config *config) { NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; -- cgit v1.2.3 From 7edd363421dab1d4806802ac65613d1c0ec85824 Mon Sep 17 00:00:00 2001 From: Gene Chen Date: Thu, 23 Apr 2020 19:24:52 +0800 Subject: mfd: Add support for PMIC MT6360 Add MFD driver for mt6360 pmic chip include Battery Charger/ USB_PD/Flash, LED/RGB and LED/LDO/Buck Signed-off-by: Gene Chen Signed-off-by: Lee Jones --- include/linux/mfd/mt6360.h | 240 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 240 insertions(+) create mode 100644 include/linux/mfd/mt6360.h (limited to 'include/linux') diff --git a/include/linux/mfd/mt6360.h b/include/linux/mfd/mt6360.h new file mode 100644 index 000000000000..ea1304035d4d --- /dev/null +++ b/include/linux/mfd/mt6360.h @@ -0,0 +1,240 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 MediaTek Inc. + */ + +#ifndef __MT6360_H__ +#define __MT6360_H__ + +#include + +enum { + MT6360_SLAVE_PMU = 0, + MT6360_SLAVE_PMIC, + MT6360_SLAVE_LDO, + MT6360_SLAVE_TCPC, + MT6360_SLAVE_MAX, +}; + +#define MT6360_PMU_SLAVEID (0x34) +#define MT6360_PMIC_SLAVEID (0x1A) +#define MT6360_LDO_SLAVEID (0x64) +#define MT6360_TCPC_SLAVEID (0x4E) + +struct mt6360_pmu_data { + struct i2c_client *i2c[MT6360_SLAVE_MAX]; + struct device *dev; + struct regmap *regmap; + struct regmap_irq_chip_data *irq_data; + unsigned int chip_rev; +}; + +/* PMU register defininition */ +#define MT6360_PMU_DEV_INFO (0x00) +#define MT6360_PMU_CORE_CTRL1 (0x01) +#define MT6360_PMU_RST1 (0x02) +#define MT6360_PMU_CRCEN (0x03) +#define MT6360_PMU_RST_PAS_CODE1 (0x04) +#define MT6360_PMU_RST_PAS_CODE2 (0x05) +#define MT6360_PMU_CORE_CTRL2 (0x06) +#define MT6360_PMU_TM_PAS_CODE1 (0x07) +#define MT6360_PMU_TM_PAS_CODE2 (0x08) +#define MT6360_PMU_TM_PAS_CODE3 (0x09) +#define MT6360_PMU_TM_PAS_CODE4 (0x0A) +#define MT6360_PMU_IRQ_IND (0x0B) +#define MT6360_PMU_IRQ_MASK (0x0C) +#define MT6360_PMU_IRQ_SET (0x0D) +#define MT6360_PMU_SHDN_CTRL (0x0E) +#define MT6360_PMU_TM_INF (0x0F) +#define MT6360_PMU_I2C_CTRL (0x10) +#define MT6360_PMU_CHG_CTRL1 (0x11) +#define MT6360_PMU_CHG_CTRL2 (0x12) +#define MT6360_PMU_CHG_CTRL3 (0x13) +#define MT6360_PMU_CHG_CTRL4 (0x14) +#define MT6360_PMU_CHG_CTRL5 (0x15) +#define MT6360_PMU_CHG_CTRL6 (0x16) +#define MT6360_PMU_CHG_CTRL7 (0x17) +#define MT6360_PMU_CHG_CTRL8 (0x18) +#define MT6360_PMU_CHG_CTRL9 (0x19) +#define MT6360_PMU_CHG_CTRL10 (0x1A) +#define MT6360_PMU_CHG_CTRL11 (0x1B) +#define MT6360_PMU_CHG_CTRL12 (0x1C) +#define MT6360_PMU_CHG_CTRL13 (0x1D) +#define MT6360_PMU_CHG_CTRL14 (0x1E) +#define MT6360_PMU_CHG_CTRL15 (0x1F) +#define MT6360_PMU_CHG_CTRL16 (0x20) +#define MT6360_PMU_CHG_AICC_RESULT (0x21) +#define MT6360_PMU_DEVICE_TYPE (0x22) +#define MT6360_PMU_QC_CONTROL1 (0x23) +#define MT6360_PMU_QC_CONTROL2 (0x24) +#define MT6360_PMU_QC30_CONTROL1 (0x25) +#define MT6360_PMU_QC30_CONTROL2 (0x26) +#define MT6360_PMU_USB_STATUS1 (0x27) +#define MT6360_PMU_QC_STATUS1 (0x28) +#define MT6360_PMU_QC_STATUS2 (0x29) +#define MT6360_PMU_CHG_PUMP (0x2A) +#define MT6360_PMU_CHG_CTRL17 (0x2B) +#define MT6360_PMU_CHG_CTRL18 (0x2C) +#define MT6360_PMU_CHRDET_CTRL1 (0x2D) +#define MT6360_PMU_CHRDET_CTRL2 (0x2E) +#define MT6360_PMU_DPDN_CTRL (0x2F) +#define MT6360_PMU_CHG_HIDDEN_CTRL1 (0x30) +#define MT6360_PMU_CHG_HIDDEN_CTRL2 (0x31) +#define MT6360_PMU_CHG_HIDDEN_CTRL3 (0x32) +#define MT6360_PMU_CHG_HIDDEN_CTRL4 (0x33) +#define MT6360_PMU_CHG_HIDDEN_CTRL5 (0x34) +#define MT6360_PMU_CHG_HIDDEN_CTRL6 (0x35) +#define MT6360_PMU_CHG_HIDDEN_CTRL7 (0x36) +#define MT6360_PMU_CHG_HIDDEN_CTRL8 (0x37) +#define MT6360_PMU_CHG_HIDDEN_CTRL9 (0x38) +#define MT6360_PMU_CHG_HIDDEN_CTRL10 (0x39) +#define MT6360_PMU_CHG_HIDDEN_CTRL11 (0x3A) +#define MT6360_PMU_CHG_HIDDEN_CTRL12 (0x3B) +#define MT6360_PMU_CHG_HIDDEN_CTRL13 (0x3C) +#define MT6360_PMU_CHG_HIDDEN_CTRL14 (0x3D) +#define MT6360_PMU_CHG_HIDDEN_CTRL15 (0x3E) +#define MT6360_PMU_CHG_HIDDEN_CTRL16 (0x3F) +#define MT6360_PMU_CHG_HIDDEN_CTRL17 (0x40) +#define MT6360_PMU_CHG_HIDDEN_CTRL18 (0x41) +#define MT6360_PMU_CHG_HIDDEN_CTRL19 (0x42) +#define MT6360_PMU_CHG_HIDDEN_CTRL20 (0x43) +#define MT6360_PMU_CHG_HIDDEN_CTRL21 (0x44) +#define MT6360_PMU_CHG_HIDDEN_CTRL22 (0x45) +#define MT6360_PMU_CHG_HIDDEN_CTRL23 (0x46) +#define MT6360_PMU_CHG_HIDDEN_CTRL24 (0x47) +#define MT6360_PMU_CHG_HIDDEN_CTRL25 (0x48) +#define MT6360_PMU_BC12_CTRL (0x49) +#define MT6360_PMU_CHG_STAT (0x4A) +#define MT6360_PMU_RESV1 (0x4B) +#define MT6360_PMU_TYPEC_OTP_TH_SEL_CODEH (0x4E) +#define MT6360_PMU_TYPEC_OTP_TH_SEL_CODEL (0x4F) +#define MT6360_PMU_TYPEC_OTP_HYST_TH (0x50) +#define MT6360_PMU_TYPEC_OTP_CTRL (0x51) +#define MT6360_PMU_ADC_BAT_DATA_H (0x52) +#define MT6360_PMU_ADC_BAT_DATA_L (0x53) +#define MT6360_PMU_IMID_BACKBST_ON (0x54) +#define MT6360_PMU_IMID_BACKBST_OFF (0x55) +#define MT6360_PMU_ADC_CONFIG (0x56) +#define MT6360_PMU_ADC_EN2 (0x57) +#define MT6360_PMU_ADC_IDLE_T (0x58) +#define MT6360_PMU_ADC_RPT_1 (0x5A) +#define MT6360_PMU_ADC_RPT_2 (0x5B) +#define MT6360_PMU_ADC_RPT_3 (0x5C) +#define MT6360_PMU_ADC_RPT_ORG1 (0x5D) +#define MT6360_PMU_ADC_RPT_ORG2 (0x5E) +#define MT6360_PMU_BAT_OVP_TH_SEL_CODEH (0x5F) +#define MT6360_PMU_BAT_OVP_TH_SEL_CODEL (0x60) +#define MT6360_PMU_CHG_CTRL19 (0x61) +#define MT6360_PMU_VDDASUPPLY (0x62) +#define MT6360_PMU_BC12_MANUAL (0x63) +#define MT6360_PMU_CHGDET_FUNC (0x64) +#define MT6360_PMU_FOD_CTRL (0x65) +#define MT6360_PMU_CHG_CTRL20 (0x66) +#define MT6360_PMU_CHG_HIDDEN_CTRL26 (0x67) +#define MT6360_PMU_CHG_HIDDEN_CTRL27 (0x68) +#define MT6360_PMU_RESV2 (0x69) +#define MT6360_PMU_USBID_CTRL1 (0x6D) +#define MT6360_PMU_USBID_CTRL2 (0x6E) +#define MT6360_PMU_USBID_CTRL3 (0x6F) +#define MT6360_PMU_FLED_CFG (0x70) +#define MT6360_PMU_RESV3 (0x71) +#define MT6360_PMU_FLED1_CTRL (0x72) +#define MT6360_PMU_FLED_STRB_CTRL (0x73) +#define MT6360_PMU_FLED1_STRB_CTRL2 (0x74) +#define MT6360_PMU_FLED1_TOR_CTRL (0x75) +#define MT6360_PMU_FLED2_CTRL (0x76) +#define MT6360_PMU_RESV4 (0x77) +#define MT6360_PMU_FLED2_STRB_CTRL2 (0x78) +#define MT6360_PMU_FLED2_TOR_CTRL (0x79) +#define MT6360_PMU_FLED_VMIDTRK_CTRL1 (0x7A) +#define MT6360_PMU_FLED_VMID_RTM (0x7B) +#define MT6360_PMU_FLED_VMIDTRK_CTRL2 (0x7C) +#define MT6360_PMU_FLED_PWSEL (0x7D) +#define MT6360_PMU_FLED_EN (0x7E) +#define MT6360_PMU_FLED_Hidden1 (0x7F) +#define MT6360_PMU_RGB_EN (0x80) +#define MT6360_PMU_RGB1_ISNK (0x81) +#define MT6360_PMU_RGB2_ISNK (0x82) +#define MT6360_PMU_RGB3_ISNK (0x83) +#define MT6360_PMU_RGB_ML_ISNK (0x84) +#define MT6360_PMU_RGB1_DIM (0x85) +#define MT6360_PMU_RGB2_DIM (0x86) +#define MT6360_PMU_RGB3_DIM (0x87) +#define MT6360_PMU_RESV5 (0x88) +#define MT6360_PMU_RGB12_Freq (0x89) +#define MT6360_PMU_RGB34_Freq (0x8A) +#define MT6360_PMU_RGB1_Tr (0x8B) +#define MT6360_PMU_RGB1_Tf (0x8C) +#define MT6360_PMU_RGB1_TON_TOFF (0x8D) +#define MT6360_PMU_RGB2_Tr (0x8E) +#define MT6360_PMU_RGB2_Tf (0x8F) +#define MT6360_PMU_RGB2_TON_TOFF (0x90) +#define MT6360_PMU_RGB3_Tr (0x91) +#define MT6360_PMU_RGB3_Tf (0x92) +#define MT6360_PMU_RGB3_TON_TOFF (0x93) +#define MT6360_PMU_RGB_Hidden_CTRL1 (0x94) +#define MT6360_PMU_RGB_Hidden_CTRL2 (0x95) +#define MT6360_PMU_RESV6 (0x97) +#define MT6360_PMU_SPARE1 (0x9A) +#define MT6360_PMU_SPARE2 (0xA0) +#define MT6360_PMU_SPARE3 (0xB0) +#define MT6360_PMU_SPARE4 (0xC0) +#define MT6360_PMU_CHG_IRQ1 (0xD0) +#define MT6360_PMU_CHG_IRQ2 (0xD1) +#define MT6360_PMU_CHG_IRQ3 (0xD2) +#define MT6360_PMU_CHG_IRQ4 (0xD3) +#define MT6360_PMU_CHG_IRQ5 (0xD4) +#define MT6360_PMU_CHG_IRQ6 (0xD5) +#define MT6360_PMU_QC_IRQ (0xD6) +#define MT6360_PMU_FOD_IRQ (0xD7) +#define MT6360_PMU_BASE_IRQ (0xD8) +#define MT6360_PMU_FLED_IRQ1 (0xD9) +#define MT6360_PMU_FLED_IRQ2 (0xDA) +#define MT6360_PMU_RGB_IRQ (0xDB) +#define MT6360_PMU_BUCK1_IRQ (0xDC) +#define MT6360_PMU_BUCK2_IRQ (0xDD) +#define MT6360_PMU_LDO_IRQ1 (0xDE) +#define MT6360_PMU_LDO_IRQ2 (0xDF) +#define MT6360_PMU_CHG_STAT1 (0xE0) +#define MT6360_PMU_CHG_STAT2 (0xE1) +#define MT6360_PMU_CHG_STAT3 (0xE2) +#define MT6360_PMU_CHG_STAT4 (0xE3) +#define MT6360_PMU_CHG_STAT5 (0xE4) +#define MT6360_PMU_CHG_STAT6 (0xE5) +#define MT6360_PMU_QC_STAT (0xE6) +#define MT6360_PMU_FOD_STAT (0xE7) +#define MT6360_PMU_BASE_STAT (0xE8) +#define MT6360_PMU_FLED_STAT1 (0xE9) +#define MT6360_PMU_FLED_STAT2 (0xEA) +#define MT6360_PMU_RGB_STAT (0xEB) +#define MT6360_PMU_BUCK1_STAT (0xEC) +#define MT6360_PMU_BUCK2_STAT (0xED) +#define MT6360_PMU_LDO_STAT1 (0xEE) +#define MT6360_PMU_LDO_STAT2 (0xEF) +#define MT6360_PMU_CHG_MASK1 (0xF0) +#define MT6360_PMU_CHG_MASK2 (0xF1) +#define MT6360_PMU_CHG_MASK3 (0xF2) +#define MT6360_PMU_CHG_MASK4 (0xF3) +#define MT6360_PMU_CHG_MASK5 (0xF4) +#define MT6360_PMU_CHG_MASK6 (0xF5) +#define MT6360_PMU_QC_MASK (0xF6) +#define MT6360_PMU_FOD_MASK (0xF7) +#define MT6360_PMU_BASE_MASK (0xF8) +#define MT6360_PMU_FLED_MASK1 (0xF9) +#define MT6360_PMU_FLED_MASK2 (0xFA) +#define MT6360_PMU_FAULTB_MASK (0xFB) +#define MT6360_PMU_BUCK1_MASK (0xFC) +#define MT6360_PMU_BUCK2_MASK (0xFD) +#define MT6360_PMU_LDO_MASK1 (0xFE) +#define MT6360_PMU_LDO_MASK2 (0xFF) +#define MT6360_PMU_MAXREG (MT6360_PMU_LDO_MASK2) + +/* MT6360_PMU_IRQ_SET */ +#define MT6360_PMU_IRQ_REGNUM (MT6360_PMU_LDO_IRQ2 - MT6360_PMU_CHG_IRQ1 + 1) +#define MT6360_IRQ_RETRIG BIT(2) + +#define CHIP_VEN_MASK (0xF0) +#define CHIP_VEN_MT6360 (0x50) +#define CHIP_REV_MASK (0x0F) + +#endif /* __MT6360_H__ */ -- cgit v1.2.3 From e76fede8bf7c90d92c799d9ceb092dec48346e2c Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Thu, 30 Apr 2020 10:25:50 -0700 Subject: cfg80211: add KHz variants of frame RX API Drivers may wish to report the RX frequency in units of KHz. Provide cfg80211_rx_mgmt_khz() and wrap it with cfg80211_rx_mgmt() so exisiting drivers which can't report KHz anyway don't need to change. Add a similar wrapper for cfg80211_report_obss_beacon() so the frequency units stay somewhat consistent. This doesn't actually change the nl80211 API yet. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200430172554.18383-2-thomas@adapt-ip.com [fix mac80211 calling the non-khz version of obss beacon report, drop trace point name changes] Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a561db435a4b..41d5f000c0d9 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -3333,6 +3333,8 @@ static inline int ieee80211_get_tdls_action(struct sk_buff *skb, u32 hdr_size) /* convert frequencies */ #define MHZ_TO_KHZ(freq) ((freq) * 1000) #define KHZ_TO_MHZ(freq) ((freq) / 1000) +#define PR_KHZ(f) KHZ_TO_MHZ(f), f % 1000 +#define KHZ_F "%d.%03d" /* convert powers */ #define DBI_TO_MBI(gain) ((gain) * 100) -- cgit v1.2.3 From d6fb67ff86bb991d5ac18471e5f739bc32e5090e Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Thu, 30 Apr 2020 10:25:53 -0700 Subject: ieee80211: S1G defines These are found in IEEE-802.11ah-2016. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200430172554.18383-5-thomas@adapt-ip.com Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 221 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 221 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 41d5f000c0d9..f630b8978a43 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -105,6 +105,51 @@ /* extension, added by 802.11ad */ #define IEEE80211_STYPE_DMG_BEACON 0x0000 +#define IEEE80211_STYPE_S1G_BEACON 0x0010 + +/* bits unique to S1G beacon */ +#define IEEE80211_S1G_BCN_NEXT_TBTT 0x100 + +/* see 802.11ah-2016 9.9 NDP CMAC frames */ +#define IEEE80211_S1G_1MHZ_NDP_BITS 25 +#define IEEE80211_S1G_1MHZ_NDP_BYTES 4 +#define IEEE80211_S1G_2MHZ_NDP_BITS 37 +#define IEEE80211_S1G_2MHZ_NDP_BYTES 5 + +#define IEEE80211_NDP_FTYPE_CTS 0 +#define IEEE80211_NDP_FTYPE_CF_END 0 +#define IEEE80211_NDP_FTYPE_PS_POLL 1 +#define IEEE80211_NDP_FTYPE_ACK 2 +#define IEEE80211_NDP_FTYPE_PS_POLL_ACK 3 +#define IEEE80211_NDP_FTYPE_BA 4 +#define IEEE80211_NDP_FTYPE_BF_REPORT_POLL 5 +#define IEEE80211_NDP_FTYPE_PAGING 6 +#define IEEE80211_NDP_FTYPE_PREQ 7 + +#define SM64(f, v) ((((u64)v) << f##_S) & f) + +/* NDP CMAC frame fields */ +#define IEEE80211_NDP_FTYPE 0x0000000000000007 +#define IEEE80211_NDP_FTYPE_S 0x0000000000000000 + +/* 1M Probe Request 11ah 9.9.3.1.1 */ +#define IEEE80211_NDP_1M_PREQ_ANO 0x0000000000000008 +#define IEEE80211_NDP_1M_PREQ_ANO_S 3 +#define IEEE80211_NDP_1M_PREQ_CSSID 0x00000000000FFFF0 +#define IEEE80211_NDP_1M_PREQ_CSSID_S 4 +#define IEEE80211_NDP_1M_PREQ_RTYPE 0x0000000000100000 +#define IEEE80211_NDP_1M_PREQ_RTYPE_S 20 +#define IEEE80211_NDP_1M_PREQ_RSV 0x0000000001E00000 +#define IEEE80211_NDP_1M_PREQ_RSV 0x0000000001E00000 +/* 2M Probe Request 11ah 9.9.3.1.2 */ +#define IEEE80211_NDP_2M_PREQ_ANO 0x0000000000000008 +#define IEEE80211_NDP_2M_PREQ_ANO_S 3 +#define IEEE80211_NDP_2M_PREQ_CSSID 0x0000000FFFFFFFF0 +#define IEEE80211_NDP_2M_PREQ_CSSID_S 4 +#define IEEE80211_NDP_2M_PREQ_RTYPE 0x0000001000000000 +#define IEEE80211_NDP_2M_PREQ_RTYPE_S 36 + +#define IEEE80211_ANO_NETTYPE_WILD 15 /* control extension - for IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTL_EXT */ #define IEEE80211_CTL_EXT_POLL 0x2000 @@ -121,6 +166,21 @@ #define IEEE80211_MAX_SN IEEE80211_SN_MASK #define IEEE80211_SN_MODULO (IEEE80211_MAX_SN + 1) + +/* PV1 Layout 11ah 9.8.3.1 */ +#define IEEE80211_PV1_FCTL_VERS 0x0003 +#define IEEE80211_PV1_FCTL_FTYPE 0x001c +#define IEEE80211_PV1_FCTL_STYPE 0x00e0 +#define IEEE80211_PV1_FCTL_TODS 0x0100 +#define IEEE80211_PV1_FCTL_MOREFRAGS 0x0200 +#define IEEE80211_PV1_FCTL_PM 0x0400 +#define IEEE80211_PV1_FCTL_MOREDATA 0x0800 +#define IEEE80211_PV1_FCTL_PROTECTED 0x1000 +#define IEEE80211_PV1_FCTL_END_SP 0x2000 +#define IEEE80211_PV1_FCTL_RELAYED 0x4000 +#define IEEE80211_PV1_FCTL_ACK_POLICY 0x8000 +#define IEEE80211_PV1_FCTL_CTL_EXT 0x0f00 + static inline bool ieee80211_sn_less(u16 sn1, u16 sn2) { return ((sn1 - sn2) & IEEE80211_SN_MASK) > (IEEE80211_SN_MODULO >> 1); @@ -148,6 +208,7 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_MAX_FRAG_THRESHOLD 2352 #define IEEE80211_MAX_RTS_THRESHOLD 2353 #define IEEE80211_MAX_AID 2007 +#define IEEE80211_MAX_AID_S1G 8191 #define IEEE80211_MAX_TIM_LEN 251 #define IEEE80211_MAX_MESH_PEERINGS 63 /* Maximum size for the MA-UNITDATA primitive, 802.11 standard section @@ -371,6 +432,17 @@ static inline bool ieee80211_is_data(__le16 fc) cpu_to_le16(IEEE80211_FTYPE_DATA); } +/** + * ieee80211_is_ext - check if type is IEEE80211_FTYPE_EXT + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee80211_is_ext(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == + cpu_to_le16(IEEE80211_FTYPE_EXT); +} + + /** * ieee80211_is_data_qos - check if type is IEEE80211_FTYPE_DATA and IEEE80211_STYPE_QOS_DATA is set * @fc: frame control bytes in little-endian byteorder @@ -469,6 +541,18 @@ static inline bool ieee80211_is_beacon(__le16 fc) cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON); } +/** + * ieee80211_is_s1g_beacon - check if IEEE80211_FTYPE_EXT && + * IEEE80211_STYPE_S1G_BEACON + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee80211_is_s1g_beacon(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | + IEEE80211_FCTL_STYPE)) == + cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON); +} + /** * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder @@ -900,6 +984,59 @@ struct ieee80211_addba_ext_ie { u8 data; } __packed; +/** + * struct ieee80211_s1g_bcn_compat_ie + * + * S1G Beacon Compatibility element + */ +struct ieee80211_s1g_bcn_compat_ie { + __le16 compat_info; + __le16 beacon_int; + __le32 tsf_completion; +} __packed; + +/** + * struct ieee80211_s1g_oper_ie + * + * S1G Operation element + */ +struct ieee80211_s1g_oper_ie { + u8 ch_width; + u8 oper_class; + u8 primary_ch; + u8 oper_ch; + __le16 basic_mcs_nss; +} __packed; + +/** + * struct ieee80211_aid_response_ie + * + * AID Response element + */ +struct ieee80211_aid_response_ie { + __le16 aid; + u8 switch_count; + __le16 response_int; +} __packed; + +struct ieee80211_s1g_cap { + u8 capab_info[10]; + u8 supp_mcs_nss[5]; +} __packed; + +struct ieee80211_ext { + __le16 frame_control; + __le16 duration; + union { + struct { + u8 sa[ETH_ALEN]; + __le32 timestamp; + u8 change_seq; + u8 variable[0]; + } __packed s1g_beacon; + } u; +} __packed __aligned(2); + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; @@ -2137,6 +2274,86 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) return spr_len; } +/* S1G Capabilities Information field */ +#define S1G_CAPAB_B0_S1G_LONG BIT(0) +#define S1G_CAPAB_B0_SGI_1MHZ BIT(1) +#define S1G_CAPAB_B0_SGI_2MHZ BIT(2) +#define S1G_CAPAB_B0_SGI_4MHZ BIT(3) +#define S1G_CAPAB_B0_SGI_8MHZ BIT(4) +#define S1G_CAPAB_B0_SGI_16MHZ BIT(5) +#define S1G_CAPAB_B0_SUPP_CH_WIDTH_MASK (BIT(6) | BIT(7)) +#define S1G_CAPAB_B0_SUPP_CH_WIDTH_SHIFT 6 + +#define S1G_CAPAB_B1_RX_LDPC BIT(0) +#define S1G_CAPAB_B1_TX_STBC BIT(1) +#define S1G_CAPAB_B1_RX_STBC BIT(2) +#define S1G_CAPAB_B1_SU_BFER BIT(3) +#define S1G_CAPAB_B1_SU_BFEE BIT(4) +#define S1G_CAPAB_B1_BFEE_STS_MASK (BIT(5) | BIT(6) | BIT(7)) +#define S1G_CAPAB_B1_BFEE_STS_SHIFT 5 + +#define S1G_CAPAB_B2_SOUNDING_DIMENSIONS_MASK (BIT(0) | BIT(1) | BIT(2)) +#define S1G_CAPAB_B2_SOUNDING_DIMENSIONS_SHIFT 0 +#define S1G_CAPAB_B2_MU_BFER BIT(3) +#define S1G_CAPAB_B2_MU_BFEE BIT(4) +#define S1G_CAPAB_B2_PLUS_HTC_VHT BIT(5) +#define S1G_CAPAB_B2_TRAVELING_PILOT_MASK (BIT(6) | BIT(7)) +#define S1G_CAPAB_B2_TRAVELING_PILOT_SHIFT 6 + +#define S1G_CAPAB_B3_RD_RESPONDER BIT(0) +#define S1G_CAPAB_B3_HT_DELAYED_BA BIT(1) +#define S1G_CAPAB_B3_MAX_MPDU_LEN BIT(2) +#define S1G_CAPAB_B3_MAX_AMPDU_LEN_EXP_MASK (BIT(3) | BIT(4)) +#define S1G_CAPAB_B3_MAX_AMPDU_LEN_EXP_SHIFT 3 +#define S1G_CAPAB_B3_MIN_MPDU_START_MASK (BIT(5) | BIT(6) | BIT(7)) +#define S1G_CAPAB_B3_MIN_MPDU_START_SHIFT 5 + +#define S1G_CAPAB_B4_UPLINK_SYNC BIT(0) +#define S1G_CAPAB_B4_DYNAMIC_AID BIT(1) +#define S1G_CAPAB_B4_BAT BIT(2) +#define S1G_CAPAB_B4_TIME_ADE BIT(3) +#define S1G_CAPAB_B4_NON_TIM BIT(4) +#define S1G_CAPAB_B4_GROUP_AID BIT(5) +#define S1G_CAPAB_B4_STA_TYPE_MASK (BIT(6) | BIT(7)) +#define S1G_CAPAB_B4_STA_TYPE_SHIFT 6 + +#define S1G_CAPAB_B5_CENT_AUTH_CONTROL BIT(0) +#define S1G_CAPAB_B5_DIST_AUTH_CONTROL BIT(1) +#define S1G_CAPAB_B5_AMSDU BIT(2) +#define S1G_CAPAB_B5_AMPDU BIT(3) +#define S1G_CAPAB_B5_ASYMMETRIC_BA BIT(4) +#define S1G_CAPAB_B5_FLOW_CONTROL BIT(5) +#define S1G_CAPAB_B5_SECTORIZED_BEAM_MASK (BIT(6) | BIT(7)) +#define S1G_CAPAB_B5_SECTORIZED_BEAM_SHIFT 6 + +#define S1G_CAPAB_B6_OBSS_MITIGATION BIT(0) +#define S1G_CAPAB_B6_FRAGMENT_BA BIT(1) +#define S1G_CAPAB_B6_NDP_PS_POLL BIT(2) +#define S1G_CAPAB_B6_RAW_OPERATION BIT(3) +#define S1G_CAPAB_B6_PAGE_SLICING BIT(4) +#define S1G_CAPAB_B6_TXOP_SHARING_IMP_ACK BIT(5) +#define S1G_CAPAB_B6_VHT_LINK_ADAPT_MASK (BIT(6) | BIT(7)) +#define S1G_CAPAB_B6_VHT_LINK_ADAPT_SHIFT 6 + +#define S1G_CAPAB_B7_TACK_AS_PS_POLL BIT(0) +#define S1G_CAPAB_B7_DUP_1MHZ BIT(1) +#define S1G_CAPAB_B7_MCS_NEGOTIATION BIT(2) +#define S1G_CAPAB_B7_1MHZ_CTL_RESPONSE_PREAMBLE BIT(3) +#define S1G_CAPAB_B7_NDP_BFING_REPORT_POLL BIT(4) +#define S1G_CAPAB_B7_UNSOLICITED_DYN_AID BIT(5) +#define S1G_CAPAB_B7_SECTOR_TRAINING_OPERATION BIT(6) +#define S1G_CAPAB_B7_TEMP_PS_MODE_SWITCH BIT(7) + +#define S1G_CAPAB_B8_TWT_GROUPING BIT(0) +#define S1G_CAPAB_B8_BDT BIT(1) +#define S1G_CAPAB_B8_COLOR_MASK (BIT(2) | BIT(3) | BIT(4)) +#define S1G_CAPAB_B8_COLOR_SHIFT 2 +#define S1G_CAPAB_B8_TWT_REQUEST BIT(5) +#define S1G_CAPAB_B8_TWT_RESPOND BIT(6) +#define S1G_CAPAB_B8_PV1_FRAME BIT(7) + +#define S1G_CAPAB_B9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0) + /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 @@ -2532,8 +2749,12 @@ enum ieee80211_eid { WLAN_EID_QUIET_CHANNEL = 198, WLAN_EID_OPMODE_NOTIF = 199, + WLAN_EID_S1G_BCN_COMPAT = 213, + WLAN_EID_S1G_SHORT_BCN_INTERVAL = 214, + WLAN_EID_S1G_CAPABILITIES = 217, WLAN_EID_VENDOR_SPECIFIC = 221, WLAN_EID_QOS_PARAMETER = 222, + WLAN_EID_S1G_OPERATION = 232, WLAN_EID_CAG_NUMBER = 237, WLAN_EID_AP_CSN = 239, WLAN_EID_FILS_INDICATION = 240, -- cgit v1.2.3 From fedd0fe4e89b009f31eb53ec36dbdf1e457616c0 Mon Sep 17 00:00:00 2001 From: Tamizh Chelvam Date: Mon, 4 May 2020 22:34:59 +0530 Subject: mac80211: Add new AMPDU factor macro for HE peer caps Add IEEE80211_HE_VHT_MAX_AMPDU_FACTOR and IEEE80211_HE_HT_MAX_AMPDU_FACTOR as per spec to use for peer max ampdu factor. Signed-off-by: Tamizh Chelvam Link: https://lore.kernel.org/r/1588611900-21185-1-git-send-email-tamizhr@codeaurora.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f630b8978a43..2153d465d752 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1958,6 +1958,8 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 #define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_SHIFT 3 + #define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 #define IEEE80211_HE_MAC_CAP4_QTP 0x02 #define IEEE80211_HE_MAC_CAP4_BQR 0x04 @@ -1979,6 +1981,9 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_MAC_CAP5_PUNCTURED_SOUNDING 0x40 #define IEEE80211_HE_MAC_CAP5_HT_VHT_TRIG_FRAME_RX 0x80 +#define IEEE80211_HE_VHT_MAX_AMPDU_FACTOR 20 +#define IEEE80211_HE_HT_MAX_AMPDU_FACTOR 16 + /* 802.11ax HE PHY capabilities */ #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 -- cgit v1.2.3 From 396fba0a59f3c94d6fd6443fbeabd8bd9e3956eb Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:39:09 -0500 Subject: cfg80211: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200507183909.GA12993@embeddedor Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2153d465d752..0320ca4c7d28 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -800,7 +800,7 @@ struct ieee80211_msrment_ie { u8 token; u8 mode; u8 type; - u8 request[0]; + u8 request[]; } __packed; /** @@ -1781,7 +1781,7 @@ struct ieee80211_he_operation { __le32 he_oper_params; __le16 he_mcs_nss_set; /* Optional 0,1,3,4,5,7 or 8 bytes: depends on @he_oper_params */ - u8 optional[0]; + u8 optional[]; } __packed; /** @@ -1793,7 +1793,7 @@ struct ieee80211_he_operation { struct ieee80211_he_spr { u8 he_sr_control; /* Optional 0 to 19 bytes: depends on @he_sr_control */ - u8 optional[0]; + u8 optional[]; } __packed; /** -- cgit v1.2.3 From 3234ac664a870e6ea69ae3a57d824cd7edbeacc5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 21 May 2020 14:06:17 -0700 Subject: /dev/mem: Revoke mappings when a driver claims the region Close the hole of holding a mapping over kernel driver takeover event of a given address range. Commit 90a545e98126 ("restrict /dev/mem to idle io memory ranges") introduced CONFIG_IO_STRICT_DEVMEM with the goal of protecting the kernel against scenarios where a /dev/mem user tramples memory that a kernel driver owns. However, this protection only prevents *new* read(), write() and mmap() requests. Established mappings prior to the driver calling request_mem_region() are left alone. Especially with persistent memory, and the core kernel metadata that is stored there, there are plentiful scenarios for a /dev/mem user to violate the expectations of the driver and cause amplified damage. Teach request_mem_region() to find and shoot down active /dev/mem mappings that it believes it has successfully claimed for the exclusive use of the driver. Effectively a driver call to request_mem_region() becomes a hole-punch on the /dev/mem device. The typical usage of unmap_mapping_range() is part of truncate_pagecache() to punch a hole in a file, but in this case the implementation is only doing the "first half" of a hole punch. Namely it is just evacuating current established mappings of the "hole", and it relies on the fact that /dev/mem establishes mappings in terms of absolute physical address offsets. Once existing mmap users are invalidated they can attempt to re-establish the mapping, or attempt to continue issuing read(2) / write(2) to the invalidated extent, but they will then be subject to the CONFIG_IO_STRICT_DEVMEM checking that can block those subsequent accesses. Cc: Arnd Bergmann Cc: Ingo Molnar Cc: Kees Cook Cc: Matthew Wilcox Cc: Russell King Cc: Andrew Morton Cc: Greg Kroah-Hartman Fixes: 90a545e98126 ("restrict /dev/mem to idle io memory ranges") Signed-off-by: Dan Williams Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/159009507306.847224.8502634072429766747.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/ioport.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index a9b9170b5dd2..6c3eca90cbc4 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -301,5 +301,11 @@ struct resource *devm_request_free_mem_region(struct device *dev, struct resource *request_free_mem_region(struct resource *base, unsigned long size, const char *name); +#ifdef CONFIG_IO_STRICT_DEVMEM +void revoke_devmem(struct resource *res); +#else +static inline void revoke_devmem(struct resource *res) { }; +#endif + #endif /* __ASSEMBLY__ */ #endif /* _LINUX_IOPORT_H */ -- cgit v1.2.3 From 6b646a7e4af69814dd1a3340fca0f02d4977420d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 9 Mar 2020 16:44:25 +0200 Subject: net/mlx5: Add ability to read and write ECE options The end result of RDMA-CM ECE handshake is ECE options, which is needed to be used while configuring data QPs. Such options can come in any QP state, so add in/out fields to set and query ECE options. OUT fields: * create_qp() - default ECE options for that type of QP. * modify_qp() - enabled ECE options after QP state transition. IN fields: * create_qp() - create QP with this ECE option. * modify_qp() - requested options. For unconnected QPs, the FW will return an error if ECE is already configured with any options that not equal to previously set. Reviewed-by: Mark Zhang Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fd8da4875ea0..1a56dc079c32 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1208,7 +1208,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_99[0x2]; u8 log_max_qp[0x5]; - u8 reserved_at_a0[0xb]; + u8 reserved_at_a0[0x3]; + u8 ece_support[0x1]; + u8 reserved_at_a4[0x7]; u8 log_max_srq[0x5]; u8 reserved_at_b0[0x10]; @@ -4216,7 +4218,8 @@ struct mlx5_ifc_rts2rts_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_rts2rts_qp_in_bits { @@ -4233,7 +4236,7 @@ struct mlx5_ifc_rts2rts_qp_in_bits { u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; @@ -4246,7 +4249,8 @@ struct mlx5_ifc_rtr2rts_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_rtr2rts_qp_in_bits { @@ -4263,7 +4267,7 @@ struct mlx5_ifc_rtr2rts_qp_in_bits { u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; @@ -4815,7 +4819,8 @@ struct mlx5_ifc_query_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + u8 ece[0x20]; u8 opt_param_mask[0x20]; @@ -6580,7 +6585,8 @@ struct mlx5_ifc_init2rtr_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_init2rtr_qp_in_bits { @@ -6597,7 +6603,7 @@ struct mlx5_ifc_init2rtr_qp_in_bits { u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; @@ -7693,7 +7699,7 @@ struct mlx5_ifc_create_qp_out_bits { u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_at_60[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_create_qp_in_bits { @@ -7707,7 +7713,7 @@ struct mlx5_ifc_create_qp_in_bits { u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; -- cgit v1.2.3 From 956d510ee78caebc83c0eaeb892db5b239a36a06 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 27 May 2020 07:24:04 +0200 Subject: block: add disk/bio-based accounting helpers Add two new helpers to simplify I/O accounting for bio based drivers. Currently these drivers use the generic_start_io_acct and generic_end_io_acct helpers which have very cumbersome calling conventions, don't actually return the time they started accounting, and try to deal with accounting for partitions, which can't happen for bio based drivers. The new helpers will be used to subsequently replace uses of the old helpers. The main API is the bio based wrappes in blkdev.h, but for zram which wants to account rw_page based I/O lower level routines are provided as well. Signed-off-by: Christoph Hellwig Reviewed-by: Konstantin Khlebnikov Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7d10f4e63232..6f7ff0fa8fcf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1892,4 +1892,32 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } +unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, + unsigned int op); +void disk_end_io_acct(struct gendisk *disk, unsigned int op, + unsigned long start_time); + +#ifdef CONFIG_BLOCK +/** + * bio_start_io_acct - start I/O accounting for bio based drivers + * @bio: bio to start account for + * + * Returns the start time that should be passed back to bio_end_io_acct(). + */ +static inline unsigned long bio_start_io_acct(struct bio *bio) +{ + return disk_start_io_acct(bio->bi_disk, bio_sectors(bio), bio_op(bio)); +} + +/** + * bio_end_io_acct - end I/O accounting for bio based drivers + * @bio: bio to end account for + * @start: start time returned by bio_start_io_acct() + */ +static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) +{ + return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time); +} +#endif /* CONFIG_BLOCK */ + #endif -- cgit v1.2.3 From e722fff238bbfe6308d7778a8c2163c181bf998a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 27 May 2020 07:24:12 +0200 Subject: block: remove generic_{start,end}_io_acct Remove these now unused functions. Signed-off-by: Christoph Hellwig Reviewed-by: Konstantin Khlebnikov Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 950c9dc44c4f..941378ec5b39 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -444,12 +444,6 @@ void bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); -void generic_start_io_acct(struct request_queue *q, int op, - unsigned long sectors, struct hd_struct *part); -void generic_end_io_acct(struct request_queue *q, int op, - struct hd_struct *part, - unsigned long start_time); - extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, struct bio *src, struct bvec_iter *src_iter); extern void bio_copy_data(struct bio *dst, struct bio *src); -- cgit v1.2.3 From 58d4f14fc30ac26288cfed74d7e566921c22cf59 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 27 May 2020 07:24:14 +0200 Subject: block: always use a percpu variable for disk stats percpu variables have a perfectly fine working stub implementation for UP kernels, so use that. Signed-off-by: Christoph Hellwig Reviewed-by: Konstantin Khlebnikov Signed-off-by: Jens Axboe --- include/linux/genhd.h | 13 ----------- include/linux/part_stat.h | 55 ++++++++++------------------------------------- 2 files changed, 11 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index a9384449465a..f0d6d77309a5 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -39,15 +39,6 @@ extern struct class block_class; #include #include -struct disk_stats { - u64 nsecs[NR_STAT_GROUPS]; - unsigned long sectors[NR_STAT_GROUPS]; - unsigned long ios[NR_STAT_GROUPS]; - unsigned long merges[NR_STAT_GROUPS]; - unsigned long io_ticks; - local_t in_flight[2]; -}; - #define PARTITION_META_INFO_VOLNAMELTH 64 /* * Enough for the string representation of any kind of UUID plus NULL. @@ -72,11 +63,7 @@ struct hd_struct { seqcount_t nr_sects_seq; #endif unsigned long stamp; -#ifdef CONFIG_SMP struct disk_stats __percpu *dkstats; -#else - struct disk_stats dkstats; -#endif struct percpu_ref ref; sector_t alignment_offset; diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index ece607607a86..6644197980b9 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -4,19 +4,23 @@ #include +struct disk_stats { + u64 nsecs[NR_STAT_GROUPS]; + unsigned long sectors[NR_STAT_GROUPS]; + unsigned long ios[NR_STAT_GROUPS]; + unsigned long merges[NR_STAT_GROUPS]; + unsigned long io_ticks; + local_t in_flight[2]; +}; + /* * Macros to operate on percpu disk statistics: * - * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters - * and should be called between disk_stat_lock() and - * disk_stat_unlock(). + * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters and should + * be called between disk_stat_lock() and disk_stat_unlock(). * * part_stat_read() can be called at any time. - * - * part_stat_{add|set_all}() and {init|free}_part_stats are for - * internal use only. */ -#ifdef CONFIG_SMP #define part_stat_lock() ({ rcu_read_lock(); get_cpu(); }) #define part_stat_unlock() do { put_cpu(); rcu_read_unlock(); } while (0) @@ -44,43 +48,6 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) sizeof(struct disk_stats)); } -static inline int init_part_stats(struct hd_struct *part) -{ - part->dkstats = alloc_percpu(struct disk_stats); - if (!part->dkstats) - return 0; - return 1; -} - -static inline void free_part_stats(struct hd_struct *part) -{ - free_percpu(part->dkstats); -} - -#else /* !CONFIG_SMP */ -#define part_stat_lock() ({ rcu_read_lock(); 0; }) -#define part_stat_unlock() rcu_read_unlock() - -#define part_stat_get(part, field) ((part)->dkstats.field) -#define part_stat_get_cpu(part, field, cpu) part_stat_get(part, field) -#define part_stat_read(part, field) part_stat_get(part, field) - -static inline void part_stat_set_all(struct hd_struct *part, int value) -{ - memset(&part->dkstats, value, sizeof(struct disk_stats)); -} - -static inline int init_part_stats(struct hd_struct *part) -{ - return 1; -} - -static inline void free_part_stats(struct hd_struct *part) -{ -} - -#endif /* CONFIG_SMP */ - #define part_stat_read_accum(part, field) \ (part_stat_read(part, field[STAT_READ]) + \ part_stat_read(part, field[STAT_WRITE]) + \ -- cgit v1.2.3 From 8ab1d40a646e753adb6814642432a093d93dbf47 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 27 May 2020 07:24:17 +0200 Subject: block: remove rcu_read_lock() from part_stat_lock() The RCU lock is required only in disk_map_sector_rcu() to lookup the partition. After that request holds reference to related hd_struct. Replace get_cpu() with preempt_disable() - returned cpu index is unused. [hch: rebased] Signed-off-by: Konstantin Khlebnikov Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/part_stat.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index 6644197980b9..a6b0938ce82e 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -21,8 +21,8 @@ struct disk_stats { * * part_stat_read() can be called at any time. */ -#define part_stat_lock() ({ rcu_read_lock(); get_cpu(); }) -#define part_stat_unlock() do { put_cpu(); rcu_read_unlock(); } while (0) +#define part_stat_lock() preempt_disable() +#define part_stat_unlock() preempt_enable() #define part_stat_get_cpu(part, field, cpu) \ (per_cpu_ptr((part)->dkstats, (cpu))->field) -- cgit v1.2.3 From b2d76adbc0828e0f108567973bcc500ed1abc139 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 27 May 2020 07:24:18 +0200 Subject: block: use __this_cpu_add() instead of access by smp_processor_id() Most architectures have fast path to access percpu for current cpu. The required preempt_disable() is provided by part_stat_lock(). [hch: rebased] Signed-off-by: Konstantin Khlebnikov Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/part_stat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index a6b0938ce82e..24125778ef3e 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -54,7 +54,7 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) part_stat_read(part, field[STAT_DISCARD])) #define __part_stat_add(part, field, addnd) \ - (part_stat_get(part, field) += (addnd)) + __this_cpu_add((part)->dkstats->field, addnd) #define part_stat_add(part, field, addnd) do { \ __part_stat_add((part), field, addnd); \ -- cgit v1.2.3 From 521376741b2c26fe53a1ec24d02da24d477eb739 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 20 May 2020 17:22:00 +0200 Subject: PCI/ATS: Only enable ATS for trusted devices Add pci_ats_supported(), which checks whether a device has an ATS capability, and whether it is trusted. A device is untrusted if it is plugged into an external-facing port such as Thunderbolt and could be spoofing an existing device to exploit weaknesses in the IOMMU configuration. PCIe ATS is one such weaknesses since it allows endpoints to cache IOMMU translations and emit transactions with 'Translated' Address Type (10b) that partially bypass the IOMMU translation. The SMMUv3 and VT-d IOMMU drivers already disallow ATS and transactions with 'Translated' Address Type for untrusted devices. Add the check to pci_enable_ats() to let other drivers (AMD IOMMU for now) benefit from it. By checking ats_cap, the pci_ats_supported() helper also returns whether ATS was globally disabled with pci=noats, and could later include more things, for example whether the whole PCIe hierarchy down to the endpoint supports ATS. Signed-off-by: Jean-Philippe Brucker Reviewed-by: Joerg Roedel Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20200520152201.3309416-2-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- include/linux/pci-ats.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index d08f0869f121..f75c307f346d 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -6,11 +6,14 @@ #ifdef CONFIG_PCI_ATS /* Address Translation Service */ +bool pci_ats_supported(struct pci_dev *dev); int pci_enable_ats(struct pci_dev *dev, int ps); void pci_disable_ats(struct pci_dev *dev); int pci_ats_queue_depth(struct pci_dev *dev); int pci_ats_page_aligned(struct pci_dev *dev); #else /* CONFIG_PCI_ATS */ +static inline bool pci_ats_supported(struct pci_dev *d) +{ return false; } static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } static inline void pci_disable_ats(struct pci_dev *d) { } -- cgit v1.2.3 From d04659db7b8089531ccbee364c52909fe4670408 Mon Sep 17 00:00:00 2001 From: Zheng Bin Date: Fri, 24 Apr 2020 16:17:23 +0800 Subject: nfs4: Remove unneeded semicolon Fixes coccicheck warning: include/linux/nfs4.h:298:2-3: Unneeded semicolon Reported-by: Hulk Robot Signed-off-by: Zheng Bin Signed-off-by: Anna Schumaker --- include/linux/nfs4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 82d8fb422092..4a51db7363a5 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -295,7 +295,7 @@ static inline bool seqid_mutating_err(u32 err) case NFS4ERR_NOFILEHANDLE: case NFS4ERR_MOVED: return false; - }; + } return true; } -- cgit v1.2.3 From 1ad8dd939a9826ff6f8c69ac13e4e1dbba076703 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:02:23 -0500 Subject: NFS: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Anna Schumaker --- include/linux/nfs4.h | 2 +- include/linux/nfs_xdr.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 4a51db7363a5..4dba3c948932 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -38,7 +38,7 @@ struct nfs4_ace { struct nfs4_acl { uint32_t naces; - struct nfs4_ace aces[0]; + struct nfs4_ace aces[]; }; #define NFS4_MAXLABELLEN 2048 diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e5f3e7d8d3d5..5fd0a9ef425f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1227,7 +1227,7 @@ struct nfs4_secinfo4 { struct nfs4_secinfo_flavors { unsigned int num_flavors; - struct nfs4_secinfo4 flavors[0]; + struct nfs4_secinfo4 flavors[]; }; struct nfs4_secinfo_arg { -- cgit v1.2.3 From ad1e4f74c072eaa2c6d77dd710db31aafecd614f Mon Sep 17 00:00:00 2001 From: Domenico Andreoli Date: Tue, 19 May 2020 20:14:10 +0200 Subject: PM: hibernate: Restrict writes to the resume device Hibernation via snapshot device requires write permission to the swap block device, the one that more often (but not necessarily) is used to store the hibernation image. With this patch, such permissions are granted iff: 1) snapshot device config option is enabled 2) swap partition is used as resume device In other circumstances the swap device is not writable from userspace. In order to achieve this, every write attempt to a swap device is checked against the device configured as part of the uswsusp API [0] using a pointer to the inode struct in memory. If the swap device being written was not configured for resuming, the write request is denied. NOTE: this implementation works only for swap block devices, where the inode configured by swapon (which sets S_SWAPFILE) is the same used by SNAPSHOT_SET_SWAP_AREA. In case of swap file, SNAPSHOT_SET_SWAP_AREA indeed receives the inode of the block device containing the filesystem where the swap file is located (+ offset in it) which is never passed to swapon and then has not set S_SWAPFILE. As result, the swap file itself (as a file) has never an option to be written from userspace. Instead it remains writable if accessed directly from the containing block device, which is always writeable from root. [0] Documentation/power/userland-swsusp.rst v2: - rename is_hibernate_snapshot_dev() to is_hibernate_resume_dev() - fix description so to correctly refer to the resume device Signed-off-by: Domenico Andreoli Acked-by: Darrick J. Wong Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 4fcc6fd0cbd6..b960098acfb0 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -466,6 +466,12 @@ static inline bool system_entering_hibernation(void) { return false; } static inline bool hibernation_available(void) { return false; } #endif /* CONFIG_HIBERNATION */ +#ifdef CONFIG_HIBERNATION_SNAPSHOT_DEV +int is_hibernate_resume_dev(const struct inode *); +#else +static inline int is_hibernate_resume_dev(const struct inode *i) { return 0; } +#endif + /* Hibernation and suspend events */ #define PM_HIBERNATION_PREPARE 0x0001 /* Going to hibernate */ #define PM_POST_HIBERNATION 0x0002 /* Hibernation finished */ -- cgit v1.2.3 From f18e26af6aba778b888044859d9c69bb9bbc7bc1 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 26 May 2020 14:54:38 +0300 Subject: RDMA/mlx5: Convert modify QP to use MLX5_SET macros Instead of hand crafted mlx5_qp_context and mlx5_qp_path use common MLX5_SET() macros. Link: https://lore.kernel.org/r/20200526115440.205922-7-leon@kernel.org Reviewed-by: Maor Gottlieb Reviewed-by: Mark Zhang Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/qp.h | 66 ------------------------------------------------- 1 file changed, 66 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index def601199a1a..b8992b861ae6 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -495,72 +495,6 @@ struct mlx5_core_dct { struct completion drained; }; -struct mlx5_qp_path { - u8 fl_free_ar; - u8 rsvd3; - __be16 pkey_index; - u8 rsvd0; - u8 grh_mlid; - __be16 rlid; - u8 ackto_lt; - u8 mgid_index; - u8 static_rate; - u8 hop_limit; - __be32 tclass_flowlabel; - union { - u8 rgid[16]; - u8 rip[16]; - }; - u8 f_dscp_ecn_prio; - u8 ecn_dscp; - __be16 udp_sport; - u8 dci_cfi_prio_sl; - u8 port; - u8 rmac[6]; -}; - -/* FIXME: use mlx5_ifc.h qpc */ -struct mlx5_qp_context { - __be32 flags; - __be32 flags_pd; - u8 mtu_msgmax; - u8 rq_size_stride; - __be16 sq_crq_size; - __be32 qp_counter_set_usr_page; - __be32 wire_qpn; - __be32 log_pg_sz_remote_qpn; - struct mlx5_qp_path pri_path; - struct mlx5_qp_path alt_path; - __be32 params1; - u8 reserved2[4]; - __be32 next_send_psn; - __be32 cqn_send; - __be32 deth_sqpn; - u8 reserved3[4]; - __be32 last_acked_psn; - __be32 ssn; - __be32 params2; - __be32 rnr_nextrecvpsn; - __be32 xrcd; - __be32 cqn_recv; - __be64 db_rec_addr; - __be32 qkey; - __be32 rq_type_srqn; - __be32 rmsn; - __be16 hw_sq_wqe_counter; - __be16 sw_sq_wqe_counter; - __be16 hw_rcyclic_byte_counter; - __be16 hw_rq_counter; - __be16 sw_rcyclic_byte_counter; - __be16 sw_rq_counter; - u8 rsvd0[5]; - u8 cgs; - u8 cs_req; - u8 cs_res; - __be64 dc_access_key; - u8 rsvd1[24]; -}; - int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp); void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp); -- cgit v1.2.3 From 3910ebaca8eae0cb9d41a20efe1bcb375ec64dfb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Tue, 26 May 2020 21:39:05 +0000 Subject: PCI: Rename _DSM constants to align with spec MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename PCI-related _DSM constants to align them with the PCI Firmware Spec, r3.2, sec 4.6. No functional change intended. Link: https://lore.kernel.org/r/20200526213905.2479381-1-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- include/linux/pci-acpi.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 2d155bfb8fbf..a3bb8e768778 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -107,10 +107,12 @@ static inline void acpiphp_check_host_bridge(struct acpi_device *adev) { } #endif extern const guid_t pci_acpi_dsm_guid; -#define IGNORE_PCI_BOOT_CONFIG_DSM 0x05 -#define DEVICE_LABEL_DSM 0x07 -#define RESET_DELAY_DSM 0x08 -#define FUNCTION_DELAY_DSM 0x09 + +/* _DSM Definitions for PCI */ +#define DSM_PCI_PRESERVE_BOOT_CONFIG 0x05 +#define DSM_PCI_DEVICE_NAME 0x07 +#define DSM_PCI_POWER_ON_RESET_DELAY 0x08 +#define DSM_PCI_DEVICE_READINESS_DURATIONS 0x09 #ifdef CONFIG_PCIE_EDR void pci_acpi_add_edr_notifier(struct pci_dev *pdev); -- cgit v1.2.3 From 7a15b2e013f535a125ad7351ffc808c79bc6de35 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 27 May 2020 20:22:29 +0200 Subject: net: remove kernel_getsockopt No users left. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/net.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 6451425e828f..74ef5d7315f7 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -303,8 +303,6 @@ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags); int kernel_getsockname(struct socket *sock, struct sockaddr *addr); int kernel_getpeername(struct socket *sock, struct sockaddr *addr); -int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval, - int *optlen); int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, unsigned int optlen); int kernel_sendpage(struct socket *sock, struct page *page, int offset, -- cgit v1.2.3 From 1ac71ec0130cce5bed3ec11ffc88651097a24173 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Tue, 28 Apr 2020 08:47:43 +0000 Subject: mtd: spi-nor: Fix SPI NOR acronym The correct terminology is serial NOR flash or SPI NOR. s/SPI-NOR/SPI NOR and s/spi-nor/SPI NOR across the subsystem. Signed-off-by: Tudor Ambarus Reviewed-by: Sergei Shtylyov --- include/linux/mtd/spi-nor.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index bebff2729c18..60bac2c0ec45 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -302,7 +302,7 @@ struct spi_nor; * @read: read data from the SPI NOR. * @write: write data to the SPI NOR. * @erase: erase a sector of the SPI NOR at the offset @offs; if - * not provided by the driver, spi-nor will send the erase + * not provided by the driver, SPI NOR will send the erase * opcode via write_reg(). */ struct spi_nor_controller_ops { @@ -336,7 +336,7 @@ struct spi_nor_flash_parameter; * layer is not DMA-able * @bouncebuf_size: size of the bounce buffer * @info: SPI NOR part JEDEC MFR ID and other info - * @manufacturer: spi-nor manufacturer + * @manufacturer: SPI NOR manufacturer * @page_size: the page size of the SPI NOR * @addr_width: number of address bytes * @erase_opcode: the opcode for erasing a sector @@ -344,12 +344,12 @@ struct spi_nor_flash_parameter; * @read_dummy: the dummy needed by the read operation * @program_opcode: the program opcode * @sst_write_second: used by the SST write operation - * @flags: flag options for the current SPI-NOR (SNOR_F_*) + * @flags: flag options for the current SPI NOR (SNOR_F_*) * @read_proto: the SPI protocol for read operations * @write_proto: the SPI protocol for write operations * @reg_proto: the SPI protocol for read_reg/write_reg/erase operations * @controller_ops: SPI NOR controller driver specific operations. - * @params: [FLASH-SPECIFIC] SPI-NOR flash parameters and settings. + * @params: [FLASH-SPECIFIC] SPI NOR flash parameters and settings. * The structure includes legacy flash parameters and * settings that can be overwritten by the spi_nor_fixups * hooks, or dynamically when parsing the SFDP tables. -- cgit v1.2.3 From 91710728d1725de51d06b40674abf6e860d592c7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 27 May 2020 22:11:13 +0200 Subject: locking: Introduce local_lock() preempt_disable() and local_irq_disable/save() are in principle per CPU big kernel locks. This has several downsides: - The protection scope is unknown - Violation of protection rules is hard to detect by instrumentation - For PREEMPT_RT such sections, unless in low level critical code, can violate the preemptability constraints. To address this PREEMPT_RT introduced the concept of local_locks which are strictly per CPU. The lock operations map to preempt_disable(), local_irq_disable/save() and the enabling counterparts on non RT enabled kernels. If lockdep is enabled local locks gain a lock map which tracks the usage context. This will catch cases where an area is protected by preempt_disable() but the access also happens from interrupt context. local locks have identified quite a few such issues over the years, the most recent example is: b7d5dc21072cd ("random: add a spinlock_t to struct batched_entropy") Aside of the lockdep coverage this also improves code readability as it precisely annotates the protection scope. PREEMPT_RT substitutes these local locks with 'sleeping' spinlocks to protect such sections while maintaining preemtability and CPU locality. local locks can replace: - preempt_enable()/disable() pairs - local_irq_disable/enable() pairs - local_irq_save/restore() pairs They are also used to replace code which implicitly disables preemption like: - get_cpu()/put_cpu() - get_cpu_var()/put_cpu_var() with PREEMPT_RT friendly constructs. Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200527201119.1692513-2-bigeasy@linutronix.de --- include/linux/local_lock.h | 54 ++++++++++++++++++++++ include/linux/local_lock_internal.h | 90 +++++++++++++++++++++++++++++++++++++ 2 files changed, 144 insertions(+) create mode 100644 include/linux/local_lock.h create mode 100644 include/linux/local_lock_internal.h (limited to 'include/linux') diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h new file mode 100644 index 000000000000..e55010fa7329 --- /dev/null +++ b/include/linux/local_lock.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_LOCAL_LOCK_H +#define _LINUX_LOCAL_LOCK_H + +#include + +/** + * local_lock_init - Runtime initialize a lock instance + */ +#define local_lock_init(lock) __local_lock_init(lock) + +/** + * local_lock - Acquire a per CPU local lock + * @lock: The lock variable + */ +#define local_lock(lock) __local_lock(lock) + +/** + * local_lock_irq - Acquire a per CPU local lock and disable interrupts + * @lock: The lock variable + */ +#define local_lock_irq(lock) __local_lock_irq(lock) + +/** + * local_lock_irqsave - Acquire a per CPU local lock, save and disable + * interrupts + * @lock: The lock variable + * @flags: Storage for interrupt flags + */ +#define local_lock_irqsave(lock, flags) \ + __local_lock_irqsave(lock, flags) + +/** + * local_unlock - Release a per CPU local lock + * @lock: The lock variable + */ +#define local_unlock(lock) __local_unlock(lock) + +/** + * local_unlock_irq - Release a per CPU local lock and enable interrupts + * @lock: The lock variable + */ +#define local_unlock_irq(lock) __local_unlock_irq(lock) + +/** + * local_unlock_irqrestore - Release a per CPU local lock and restore + * interrupt flags + * @lock: The lock variable + * @flags: Interrupt flags to restore + */ +#define local_unlock_irqrestore(lock, flags) \ + __local_unlock_irqrestore(lock, flags) + +#endif diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h new file mode 100644 index 000000000000..4a8795b21d77 --- /dev/null +++ b/include/linux/local_lock_internal.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_LOCAL_LOCK_H +# error "Do not include directly, include linux/local_lock.h" +#endif + +#include +#include + +typedef struct { +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; + struct task_struct *owner; +#endif +} local_lock_t; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define LL_DEP_MAP_INIT(lockname) \ + .dep_map = { \ + .name = #lockname, \ + .wait_type_inner = LD_WAIT_CONFIG, \ + } +#else +# define LL_DEP_MAP_INIT(lockname) +#endif + +#define INIT_LOCAL_LOCK(lockname) { LL_DEP_MAP_INIT(lockname) } + +#define __local_lock_init(lock) \ +do { \ + static struct lock_class_key __key; \ + \ + debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ + lockdep_init_map_wait(&(lock)->dep_map, #lock, &__key, 0, LD_WAIT_CONFIG);\ +} while (0) + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static inline void local_lock_acquire(local_lock_t *l) +{ + lock_map_acquire(&l->dep_map); + DEBUG_LOCKS_WARN_ON(l->owner); + l->owner = current; +} + +static inline void local_lock_release(local_lock_t *l) +{ + DEBUG_LOCKS_WARN_ON(l->owner != current); + l->owner = NULL; + lock_map_release(&l->dep_map); +} + +#else /* CONFIG_DEBUG_LOCK_ALLOC */ +static inline void local_lock_acquire(local_lock_t *l) { } +static inline void local_lock_release(local_lock_t *l) { } +#endif /* !CONFIG_DEBUG_LOCK_ALLOC */ + +#define __local_lock(lock) \ + do { \ + preempt_disable(); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_lock_irq(lock) \ + do { \ + local_irq_disable(); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_lock_irqsave(lock, flags) \ + do { \ + local_irq_save(flags); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_unlock(lock) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + preempt_enable(); \ + } while (0) + +#define __local_unlock_irq(lock) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + local_irq_enable(); \ + } while (0) + +#define __local_unlock_irqrestore(lock, flags) \ + do { \ + local_lock_release(this_cpu_ptr(lock)); \ + local_irq_restore(flags); \ + } while (0) -- cgit v1.2.3 From cfa6705d89b6562f79c40c249f8d94073c4276e4 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 27 May 2020 22:11:14 +0200 Subject: radix-tree: Use local_lock for protection The radix-tree and idr preload mechanisms use preempt_disable() to protect the complete operation between xxx_preload() and xxx_preload_end(). As the code inside the preempt disabled section acquires regular spinlocks, which are converted to 'sleeping' spinlocks on a PREEMPT_RT kernel and eventually calls into a memory allocator, this conflicts with the RT semantics. Convert it to a local_lock which allows RT kernels to substitute them with a real per CPU lock. On non RT kernels this maps to preempt_disable() as before, but provides also lockdep coverage of the critical region. No functional change. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200527201119.1692513-3-bigeasy@linutronix.de --- include/linux/idr.h | 2 +- include/linux/radix-tree.h | 11 ++++++++++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index ac6e946b6767..3ade03e5c7af 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -171,7 +171,7 @@ static inline bool idr_is_empty(const struct idr *idr) */ static inline void idr_preload_end(void) { - preempt_enable(); + local_unlock(&radix_tree_preloads.lock); } /** diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 63e62372443a..c2a9f7c90727 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -16,11 +16,20 @@ #include #include #include +#include /* Keep unconverted code working */ #define radix_tree_root xarray #define radix_tree_node xa_node +struct radix_tree_preload { + local_lock_t lock; + unsigned nr; + /* nodes->parent points to next preallocated node */ + struct radix_tree_node *nodes; +}; +DECLARE_PER_CPU(struct radix_tree_preload, radix_tree_preloads); + /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: @@ -245,7 +254,7 @@ int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); static inline void radix_tree_preload_end(void) { - preempt_enable(); + local_unlock(&radix_tree_preloads.lock); } void __rcu **idr_get_free(struct radix_tree_root *root, -- cgit v1.2.3 From b01b2141999936ac3e4746b7f76c0f204ae4b445 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 27 May 2020 22:11:15 +0200 Subject: mm/swap: Use local_lock for protection The various struct pagevec per CPU variables are protected by disabling either preemption or interrupts across the critical sections. Inside these sections spinlocks have to be acquired. These spinlocks are regular spinlock_t types which are converted to "sleeping" spinlocks on PREEMPT_RT enabled kernels. Obviously sleeping locks cannot be acquired in preemption or interrupt disabled sections. local locks provide a trivial way to substitute preempt and interrupt disable instances. On a non PREEMPT_RT enabled kernel local_lock() maps to preempt_disable() and local_lock_irq() to local_irq_disable(). Create lru_rotate_pvecs containing the pagevec and the locallock. Create lru_pvecs containing the remaining pagevecs and the locallock. Add lru_add_drain_cpu_zone() which is used from compact_zone() to avoid exporting the pvec structure. Change the relevant call sites to acquire these locks instead of using preempt_disable() / get_cpu() / get_cpu_var() and local_irq_disable() / local_irq_save(). There is neither a functional change nor a change in the generated binary code for non PREEMPT_RT enabled non-debug kernels. When lockdep is enabled local locks have lockdep maps embedded. These allow lockdep to validate the protections, i.e. inappropriate usage of a preemption only protected sections would result in a lockdep warning while the same problem would not be noticed with a plain preempt_disable() based protection. local locks also improve readability as they provide a named scope for the protections while preempt/interrupt disable are opaque scopeless. Finally local locks allow PREEMPT_RT to substitute them with real locking primitives to ensure the correctness of operation in a fully preemptible kernel. [ bigeasy: Adopted to use local_lock ] Signed-off-by: Ingo Molnar Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20200527201119.1692513-4-bigeasy@linutronix.de --- include/linux/swap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index e1bbf7a16b27..25181d2dd0b9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -337,6 +337,7 @@ extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); +extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); -- cgit v1.2.3 From 4b44a21dd640b692d4e9b12d3e37c24825f90baa Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 26 May 2020 18:11:02 +0200 Subject: irq_work, smp: Allow irq_work on call_single_queue Currently irq_work_queue_on() will issue an unconditional arch_send_call_function_single_ipi() and has the handler do irq_work_run(). This is unfortunate in that it makes the IPI handler look at a second cacheline and it misses the opportunity to avoid the IPI. Instead note that struct irq_work and struct __call_single_data are very similar in layout, so use a few bits in the flags word to encode a type and stick the irq_work on the call_single_queue list. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200526161908.011635912@infradead.org --- include/linux/irq_work.h | 7 ++++++- include/linux/smp.h | 23 ++++++++++++++++++++++- 2 files changed, 28 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 3b752e80c017..f23a359c8f46 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -13,6 +13,8 @@ * busy NULL, 2 -> {free, claimed} : callback in progress, can be claimed */ +/* flags share CSD_FLAG_ space */ + #define IRQ_WORK_PENDING BIT(0) #define IRQ_WORK_BUSY BIT(1) @@ -23,9 +25,12 @@ #define IRQ_WORK_CLAIMED (IRQ_WORK_PENDING | IRQ_WORK_BUSY) +/* + * structure shares layout with single_call_data_t. + */ struct irq_work { - atomic_t flags; struct llist_node llnode; + atomic_t flags; void (*func)(struct irq_work *); }; diff --git a/include/linux/smp.h b/include/linux/smp.h index cbc9162689d0..45ad6e30f398 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -16,17 +16,38 @@ typedef void (*smp_call_func_t)(void *info); typedef bool (*smp_cond_func_t)(int cpu, void *info); + +enum { + CSD_FLAG_LOCK = 0x01, + + /* IRQ_WORK_flags */ + + CSD_TYPE_ASYNC = 0x00, + CSD_TYPE_SYNC = 0x10, + CSD_TYPE_IRQ_WORK = 0x20, + CSD_FLAG_TYPE_MASK = 0xF0, +}; + +/* + * structure shares (partial) layout with struct irq_work + */ struct __call_single_data { struct llist_node llist; + unsigned int flags; smp_call_func_t func; void *info; - unsigned int flags; }; /* Use __aligned() to avoid to use 2 cache lines for 1 csd */ typedef struct __call_single_data call_single_data_t __aligned(sizeof(struct __call_single_data)); +/* + * Enqueue a llist_node on the call_single_queue; be very careful, read + * flush_smp_call_function_queue() in detail. + */ +extern void __smp_call_single_queue(int cpu, struct llist_node *node); + /* total number of cpus in this system (may exceed NR_CPUS) */ extern unsigned int total_cpus; -- cgit v1.2.3 From a148866489fbe243c936fe43e4525d8dbfa0318f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 26 May 2020 18:11:04 +0200 Subject: sched: Replace rq::wake_list The recent commit: 90b5363acd47 ("sched: Clean up scheduler_ipi()") got smp_call_function_single_async() subtly wrong. Even though it will return -EBUSY when trying to re-use a csd, that condition is not atomic and still requires external serialization. The change in ttwu_queue_remote() got this wrong. While on first reading ttwu_queue_remote() has an atomic test-and-set that appears to serialize the use, the matching 'release' is not in the right place to actually guarantee this serialization. The actual race is vs the sched_ttwu_pending() call in the idle loop; that can run the wakeup-list without consuming the CSD. Instead of trying to chain the lists, merge them. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200526161908.129371594@infradead.org --- include/linux/sched.h | 1 + include/linux/smp.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ebc68706152a..e0f5f41cf2ee 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -654,6 +654,7 @@ struct task_struct { #ifdef CONFIG_SMP struct llist_node wake_entry; + unsigned int wake_entry_type; int on_cpu; #ifdef CONFIG_THREAD_INFO_IN_TASK /* Current CPU: */ diff --git a/include/linux/smp.h b/include/linux/smp.h index 45ad6e30f398..84f90e24ed6f 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -25,6 +25,7 @@ enum { CSD_TYPE_ASYNC = 0x00, CSD_TYPE_SYNC = 0x10, CSD_TYPE_IRQ_WORK = 0x20, + CSD_TYPE_TTWU = 0x30, CSD_FLAG_TYPE_MASK = 0xF0, }; -- cgit v1.2.3 From 6db96e5810e0a6a345b7d78549de7676ae5b2662 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 13 Apr 2020 10:46:03 +0800 Subject: mmc: host: Introduce the request_atomic() for the host The SD host controller can process one request in the atomic context if the card is nonremovable, which means we can submit next request in the irq hard handler when using the MMC host software queue to reduce the latency. Thus this patch adds a new API request_atomic() for the host controller, as well as adding support for host software queue to submit a request by the new request_atomic() API. Moreover there is an unusual case that the card is busy when trying to send a command, and we can not polling the card status in interrupt context by using request_atomic() to dispatch requests. Thus we should queue a work to try again in the non-atomic context in case the host releases the busy signal later. Suggested-by: Adrian Hunter Acked-by: Adrian Hunter Signed-off-by: Baolin Wang Link: https://lore.kernel.org/r/a344e27e506cb2329073cbd5cf65e15cc3cbeba9.1586744073.git.baolin.wang7@gmail.com Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index c318fb5b6a94..d4a50e5dc111 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -92,6 +92,9 @@ struct mmc_host_ops { int err); void (*pre_req)(struct mmc_host *host, struct mmc_request *req); void (*request)(struct mmc_host *host, struct mmc_request *req); + /* Submit one request to host in atomic context. */ + int (*request_atomic)(struct mmc_host *host, + struct mmc_request *req); /* * Avoid calling the next three functions too often or in a "fast -- cgit v1.2.3 From 064f7e58ee42372be05ec87fdf57864c7475ba93 Mon Sep 17 00:00:00 2001 From: Krishna Konda Date: Fri, 1 May 2020 19:23:01 +0530 Subject: mmc: core: expose info about enhanced rpmb support Following eMMC JEDEC JESD84-B51 standard, an enhanced form of rpmb is supported. What this enhanced mode supports is in addition to be able to write one rpmb or two rpmb frames at a time, 32 frames can be written at a time. Expose this information present in ext csd field so that the user space application that wants to make use of this can do so. Signed-off-by: Krishna Konda Signed-off-by: Veerabhadrarao Badiganti Link: https://lore.kernel.org/r/1588341189-4371-1-git-send-email-vbadigan@codeaurora.org Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 1 + include/linux/mmc/mmc.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index cf3780a6ccc4..7d46411ffaa2 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -48,6 +48,7 @@ struct mmc_ext_csd { u8 sec_feature_support; u8 rel_sectors; u8 rel_param; + bool enhanced_rpmb_supported; u8 part_config; u8 cache_ctrl; u8 rst_n_function; diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 4b85ef05a906..d9a65c6a8816 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -325,6 +325,7 @@ static inline bool mmc_ready_for_data(u32 status) */ #define EXT_CSD_WR_REL_PARAM_EN (1<<2) +#define EXT_CSD_WR_REL_PARAM_EN_RPMB_REL_WR (1<<4) #define EXT_CSD_BOOT_WP_B_PWR_WP_DIS (0x40) #define EXT_CSD_BOOT_WP_B_PERM_WP_DIS (0x10) -- cgit v1.2.3 From 30e1028dcef9ac981c20df83983e0e77a4df2dc4 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 2 May 2020 16:28:25 +0200 Subject: mmc: sdhci-esdhc: update contact email The 'pengutronix' address is defunct for years. Use the proper contact address. Signed-off-by: Wolfram Sang Acked-by: Adrian Hunter Link: https://lore.kernel.org/r/20200502142840.19418-1-wsa@kernel.org Signed-off-by: Ulf Hansson --- include/linux/platform_data/mmc-esdhc-imx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h index 0434f68eda86..cba1184b364c 100644 --- a/include/linux/platform_data/mmc-esdhc-imx.h +++ b/include/linux/platform_data/mmc-esdhc-imx.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright 2010 Wolfram Sang + * Copyright 2010 Wolfram Sang */ #ifndef __ASM_ARCH_IMX_ESDHC_H -- cgit v1.2.3 From f4f20d6897b1c047c5d38b2cfc50928e83d8fd83 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 14:22:18 -0500 Subject: memstick: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200507192218.GA16315@embeddedor Signed-off-by: Ulf Hansson --- include/linux/memstick.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memstick.h b/include/linux/memstick.h index 216a713bef7f..da4c65f9435f 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -288,7 +288,7 @@ struct memstick_host { int (*set_param)(struct memstick_host *host, enum memstick_param param, int value); - unsigned long private[0] ____cacheline_aligned; + unsigned long private[] ____cacheline_aligned; }; struct memstick_driver { -- cgit v1.2.3 From 1be64c7963f89afbd6f96f27effea20900650dfe Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 8 May 2020 13:29:02 +0200 Subject: mmc: host: Drop redundant MMC_CAP_ERASE The MMC_CAP_ERASE bit is no longer used by the mmc core as erase, discard and trim operations are now always supported. Therefore, drop the bit and move all mmc hosts away from using it. Signed-off-by: Ulf Hansson Reviewed-by: Rui Miguel Silva Link: https://lore.kernel.org/r/20200508112902.23575-1-ulf.hansson@linaro.org Reviewed-by: Linus Walleij --- include/linux/mmc/host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index d4a50e5dc111..7149bab555d7 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -321,7 +321,6 @@ struct mmc_host { #define MMC_CAP_AGGRESSIVE_PM (1 << 7) /* Suspend (e)MMC/SD at idle */ #define MMC_CAP_NONREMOVABLE (1 << 8) /* Nonremovable e.g. eMMC */ #define MMC_CAP_WAIT_WHILE_BUSY (1 << 9) /* Waits while card is busy */ -#define MMC_CAP_ERASE (1 << 10) /* Allow erase/trim commands */ #define MMC_CAP_3_3V_DDR (1 << 11) /* Host supports eMMC DDR 3.3V */ #define MMC_CAP_1_8V_DDR (1 << 12) /* Host supports eMMC DDR 1.8V */ #define MMC_CAP_1_2V_DDR (1 << 13) /* Host supports eMMC DDR 1.2V */ -- cgit v1.2.3 From 991f5c4dd2422881c933ec3c7c19f3a2a1858cc4 Mon Sep 17 00:00:00 2001 From: Angelo Dureghello Date: Mon, 18 May 2020 21:17:39 +0200 Subject: m68k: mcf5441x: add support for esdhc mmc controller Add support for sdhci-edshc mmc controller. Signed-off-by: Angelo Dureghello Acked-by: Greg Ungerer Link: https://lore.kernel.org/r/20200518191742.1251440-1-angelo.dureghello@timesys.com Signed-off-by: Ulf Hansson --- include/linux/platform_data/mmc-esdhc-mcf.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/linux/platform_data/mmc-esdhc-mcf.h (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-esdhc-mcf.h b/include/linux/platform_data/mmc-esdhc-mcf.h new file mode 100644 index 000000000000..85cb786a62fe --- /dev/null +++ b/include/linux/platform_data/mmc-esdhc-mcf.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_PLATFORM_DATA_MCF_ESDHC_H__ +#define __LINUX_PLATFORM_DATA_MCF_ESDHC_H__ + +enum cd_types { + ESDHC_CD_NONE, /* no CD, neither controller nor gpio */ + ESDHC_CD_CONTROLLER, /* mmc controller internal CD */ + ESDHC_CD_PERMANENT, /* no CD, card permanently wired to host */ +}; + +struct mcf_esdhc_platform_data { + int max_bus_width; + int cd_type; +}; + +#endif /* __LINUX_PLATFORM_DATA_MCF_ESDHC_H__ */ -- cgit v1.2.3 From 4bc90f492230af6661bc2021dddd501f7c842334 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:02 +0200 Subject: mmc: sdio: Fix macro name for Marvell device with ID 0x9134 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Marvell SDIO device ID 0x9134 is used in SDIO Common CIS (Card Information Structure) and not in SDIO wlan function (with ID 1). SDIO Common CIS is accessed by function ID 0. So change this misleading macro name to SDIO_DEVICE_ID_MARVELL_8887_F0 as it does not refer to wlan function. It refers to function 0. Wlan module on this SDIO card is available at function ID 1 and is identified by different SDIO device ID 0x9135. Kernel quirks for SDIO devices are matched against device ID from SDIO Common CIS. Therefore device ID used in quirk is correct, just has misleading name. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-2-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 2e9a6e4634eb..96f43e0dc78f 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -59,7 +59,7 @@ #define SDIO_DEVICE_ID_MARVELL_8688WLAN 0x9104 #define SDIO_DEVICE_ID_MARVELL_8688BT 0x9105 #define SDIO_DEVICE_ID_MARVELL_8797_F0 0x9128 -#define SDIO_DEVICE_ID_MARVELL_8887WLAN 0x9134 +#define SDIO_DEVICE_ID_MARVELL_8887_F0 0x9134 #define SDIO_VENDOR_ID_MEDIATEK 0x037a -- cgit v1.2.3 From b75b7ca7c27dfd61dba368f390b7d4dc20b3a8cb Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Mon, 25 Nov 2019 13:24:03 -0600 Subject: fs: remove dio_end_io() Since we removed the last user of dio_end_io(), remove the helper function dio_end_io(). Reviewed-by: Nikolay Borisov Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Goldwyn Rodrigues Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 366c533d30cd..e84623d5e173 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3187,8 +3187,6 @@ enum { DIO_SKIP_HOLES = 0x02, }; -void dio_end_io(struct bio *bio); - ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, -- cgit v1.2.3 From dc35ada4251f183137ee3a524543c9329d7a4fa2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 15:41:23 +0200 Subject: block: fix a warning when blkdev.h is included for !CONFIG_BLOCK builds disk_start_io_acct and disk_end_io_acct need at least a struct gendisk forward declaration, but for weird historic reasons much of blkdev.h is stubbed out for CONFIG_BLOCK=n. Fix this by stubbing more out for now, but eventually this header will need a massive cleanup. Fixes: 956d510ee78 ("block: add disk/bio-based accounting helpers") Reported-by: Stephen Rothwell Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6f7ff0fa8fcf..8fd900998b4e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1892,12 +1892,12 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } +#ifdef CONFIG_BLOCK unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op); void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); -#ifdef CONFIG_BLOCK /** * bio_start_io_acct - start I/O accounting for bio based drivers * @bio: bio to start account for -- cgit v1.2.3 From 1597b374af22266266e1e20612208c4b11359ad4 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 28 May 2020 17:28:04 +0300 Subject: hwmon: Add notification support For hwmon drivers using the hwmon_device_register_with_info() API, it is desirable to have a generic notification mechanism available. This mechanism can be used to notify userspace as well as the thermal subsystem if the driver experiences any events, such as warning or critical alarms. Implement hwmon_notify_event() to provide this mechanism. The function generates a sysfs event and a udev event. If the device is registered with the thermal subsystem and the event is associated with a temperature sensor, also notify the thermal subsystem that a thermal event occurred. Signed-off-by: Guenter Roeck Signed-off-by: Serge Semin Cc: Maxim Kaurkin Cc: Alexey Malahov Cc: Thomas Bogendoerfer Cc: Arnd Bergmann Cc: Rob Herring Cc: linux-mips@vger.kernel.org Cc: devicetree@vger.kernel.org Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 5e609f25878c..363d4a814aa1 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -436,6 +436,9 @@ devm_hwmon_device_register_with_info(struct device *dev, void hwmon_device_unregister(struct device *dev); void devm_hwmon_device_unregister(struct device *dev); +int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel); + /** * hwmon_is_bad_char - Is the char invalid in a hwmon name * @ch: the char to be considered -- cgit v1.2.3 From 7df915e540ec51ce9ac5f2d2d9801d0356b617da Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 25 May 2020 14:05:04 +0200 Subject: i2c: avoid confusing naming in header i2c_client pointers are usually named 'client'. Use it here to get rid of the ambiguity of 'dev->dev'. Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 49d29054e657..c10617bb980a 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -351,14 +351,14 @@ static inline struct i2c_client *kobj_to_i2c_client(struct kobject *kobj) return to_i2c_client(dev); } -static inline void *i2c_get_clientdata(const struct i2c_client *dev) +static inline void *i2c_get_clientdata(const struct i2c_client *client) { - return dev_get_drvdata(&dev->dev); + return dev_get_drvdata(&client->dev); } -static inline void i2c_set_clientdata(struct i2c_client *dev, void *data) +static inline void i2c_set_clientdata(struct i2c_client *client, void *data) { - dev_set_drvdata(&dev->dev, data); + dev_set_drvdata(&client->dev, data); } /* I2C slave support */ -- cgit v1.2.3 From 655078f5f5286fe0ab38e90c4695001a0e15e9dd Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Wed, 13 May 2020 20:55:57 +0200 Subject: kobject: increase allowed number of uevent variables SBS battery driver exposes 32 power supply properties now, which will result in uevent failure on (un)plugging the battery. Other drivers (e.g. bq27xxx) are also coming close to this limit, so increase it. Acked-by: Greg Kroah-Hartman Reviewed-by: Emil Velikov Signed-off-by: Sebastian Reichel --- include/linux/kobject.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index e2ca0a292e21..75e822569e39 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -29,7 +29,7 @@ #include #define UEVENT_HELPER_PATH_LEN 256 -#define UEVENT_NUM_ENVP 32 /* number of env pointers */ +#define UEVENT_NUM_ENVP 64 /* number of env pointers */ #define UEVENT_BUFFER_SIZE 2048 /* buffer for the variables */ #ifdef CONFIG_UEVENT_HELPER -- cgit v1.2.3 From bac705abcf345c28e419157cfcd1c44032cc9db2 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Wed, 13 May 2020 20:55:58 +0200 Subject: power: supply: core: add capacity error margin property Add a property for reporting the error margin expected by fuel gauge chips. Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 1f60731ec7fe..453a85f25635 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -139,6 +139,7 @@ enum power_supply_property { POWER_SUPPLY_PROP_CAPACITY, /* in percents! */ POWER_SUPPLY_PROP_CAPACITY_ALERT_MIN, /* in percents! */ POWER_SUPPLY_PROP_CAPACITY_ALERT_MAX, /* in percents! */ + POWER_SUPPLY_PROP_CAPACITY_ERROR_MARGIN, /* in percents! */ POWER_SUPPLY_PROP_CAPACITY_LEVEL, POWER_SUPPLY_PROP_TEMP, POWER_SUPPLY_PROP_TEMP_MAX, -- cgit v1.2.3 From feabe49e46bb556b8d43e28d4a0d459940f7a5cb Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Wed, 13 May 2020 20:55:59 +0200 Subject: power: supply: core: add manufacture date properties Some smart batteries store their manufacture date, which is useful to identify the battery and/or to know about the cell quality. Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 453a85f25635..63ffe2a0a87b 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -159,6 +159,9 @@ enum power_supply_property { POWER_SUPPLY_PROP_PRECHARGE_CURRENT, POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT, POWER_SUPPLY_PROP_CALIBRATE, + POWER_SUPPLY_PROP_MANUFACTURE_YEAR, + POWER_SUPPLY_PROP_MANUFACTURE_MONTH, + POWER_SUPPLY_PROP_MANUFACTURE_DAY, /* Properties of type `const char *' */ POWER_SUPPLY_PROP_MODEL_NAME, POWER_SUPPLY_PROP_MANUFACTURER, -- cgit v1.2.3 From 601c2a543f02da484362b3ff9074b2cfe08750de Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Wed, 13 May 2020 20:56:00 +0200 Subject: power: supply: core: add POWER_SUPPLY_HEALTH_CALIBRATION_REQUIRED Some battery fuel gauges know when the battery needs to be recalibrated before providing usable values. This should be reported via the health property. Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 63ffe2a0a87b..ac1345a48ad0 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -61,6 +61,7 @@ enum { POWER_SUPPLY_HEALTH_WATCHDOG_TIMER_EXPIRE, POWER_SUPPLY_HEALTH_SAFETY_TIMER_EXPIRE, POWER_SUPPLY_HEALTH_OVERCURRENT, + POWER_SUPPLY_HEALTH_CALIBRATION_REQUIRED, }; enum { -- cgit v1.2.3 From db10538a4b997a77a1fd561adaaa58afc7dcfa2f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:18 +0200 Subject: tcp: add tcp_sock_set_cork Add a helper to directly set the TCP_CORK sockopt from kernel space without going through a fake uaccess. Cleanup the callers to avoid pointless wrappers now that this is a simple function call. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index bf44e85d709d..889eeb2256c2 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -497,4 +497,6 @@ static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen); +void tcp_sock_set_cork(struct sock *sk, bool on); + #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From 12abc5ee7873a085cc280240822b8ac53c86fecd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:19 +0200 Subject: tcp: add tcp_sock_set_nodelay Add a helper to directly set the TCP_NODELAY sockopt from kernel space without going through a fake uaccess. Cleanup the callers to avoid pointless wrappers now that this is a simple function call. Signed-off-by: Christoph Hellwig Acked-by: Sagi Grimberg Acked-by: Jason Gunthorpe Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 889eeb2256c2..9e42c7fe50a8 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -498,5 +498,6 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen); void tcp_sock_set_cork(struct sock *sk, bool on); +void tcp_sock_set_nodelay(struct sock *sk); #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From ddd061b8daed3ce0c01109a69c9a2a9f9669f01a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:20 +0200 Subject: tcp: add tcp_sock_set_quickack Add a helper to directly set the TCP_QUICKACK sockopt from kernel space without going through a fake uaccess. Cleanup the callers to avoid pointless wrappers now that this is a simple function call. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 9e42c7fe50a8..2eaf8320b9db 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -499,5 +499,6 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, void tcp_sock_set_cork(struct sock *sk, bool on); void tcp_sock_set_nodelay(struct sock *sk); +void tcp_sock_set_quickack(struct sock *sk, int val); #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From 557eadfcc5ee8f8fa98a795e05ed21db58a65db5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:21 +0200 Subject: tcp: add tcp_sock_set_syncnt Add a helper to directly set the TCP_SYNCNT sockopt from kernel space without going through a fake uaccess. Signed-off-by: Christoph Hellwig Acked-by: Sagi Grimberg Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 2eaf8320b9db..6aa4ae5ebf3d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -500,5 +500,6 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, void tcp_sock_set_cork(struct sock *sk, bool on); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); +int tcp_sock_set_syncnt(struct sock *sk, int val); #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From c488aeadcbd002a992593e6090d54e8ac27c4310 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:22 +0200 Subject: tcp: add tcp_sock_set_user_timeout Add a helper to directly set the TCP_USER_TIMEOUT sockopt from kernel space without going through a fake uaccess. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 6aa4ae5ebf3d..de682143efe4 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -501,5 +501,6 @@ void tcp_sock_set_cork(struct sock *sk, bool on); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); +void tcp_sock_set_user_timeout(struct sock *sk, u32 val); #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From 71c48eb81c9ecb6fed49dc33e7c9b621fdcb7bf8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:23 +0200 Subject: tcp: add tcp_sock_set_keepidle Add a helper to directly set the TCP_KEEP_IDLE sockopt from kernel space without going through a fake uaccess. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index de682143efe4..5724dd84a85e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -498,6 +498,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen); void tcp_sock_set_cork(struct sock *sk, bool on); +int tcp_sock_set_keepidle(struct sock *sk, int val); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); -- cgit v1.2.3 From d41ecaac903c9f4658a71d4e7a708673cfb5abba Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:24 +0200 Subject: tcp: add tcp_sock_set_keepintvl Add a helper to directly set the TCP_KEEPINTVL sockopt from kernel space without going through a fake uaccess. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 5724dd84a85e..1f9bada00faa 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -499,6 +499,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, void tcp_sock_set_cork(struct sock *sk, bool on); int tcp_sock_set_keepidle(struct sock *sk, int val); +int tcp_sock_set_keepintvl(struct sock *sk, int val); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); -- cgit v1.2.3 From 480aeb9639d6a077c611b303a22f9b1e5937d081 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 May 2020 07:12:25 +0200 Subject: tcp: add tcp_sock_set_keepcnt Add a helper to directly set the TCP_KEEPCNT sockopt from kernel space without going through a fake uaccess. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 1f9bada00faa..9aac824c523c 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -498,6 +498,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen); void tcp_sock_set_cork(struct sock *sk, bool on); +int tcp_sock_set_keepcnt(struct sock *sk, int val); int tcp_sock_set_keepidle(struct sock *sk, int val); int tcp_sock_set_keepintvl(struct sock *sk, int val); void tcp_sock_set_nodelay(struct sock *sk); -- cgit v1.2.3 From a8173820f441ab3e2a45c4bb66b70da9a57a349e Mon Sep 17 00:00:00 2001 From: Maulik Shah Date: Sat, 23 May 2020 22:41:10 +0530 Subject: gpio: gpiolib: Allow GPIO IRQs to lazy disable With 'commit 461c1a7d4733 ("gpiolib: override irq_enable/disable")' gpiolib overrides irqchip's irq_enable and irq_disable callbacks. If irq_disable callback is implemented then genirq takes unlazy path to disable irq. Underlying irqchip may not want to implement irq_disable callback to lazy disable irq when client drivers invokes disable_irq(). By overriding irq_disable callback, gpiolib ends up always unlazy disabling IRQ. Allow gpiolib to lazy disable IRQs by overriding irq_disable callback only if irqchip implemented irq_disable. In cases where irq_disable is not implemented irq_mask is overridden. Similarly override irq_enable callback only if irqchip implemented irq_enable otherwise irq_unmask is overridden. Fixes: 461c1a7d4733 ("gpiolib: override irq_enable/disable") Signed-off-by: Maulik Shah Tested-by: Hans Verkuil Link: https://lore.kernel.org/r/1590253873-11556-2-git-send-email-mkshah@codeaurora.org Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 8c41ae41b6bb..c8bcaf315d03 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -253,6 +253,19 @@ struct gpio_irq_chip { * Store old irq_chip irq_disable callback */ void (*irq_disable)(struct irq_data *data); + /** + * @irq_unmask: + * + * Store old irq_chip irq_unmask callback + */ + void (*irq_unmask)(struct irq_data *data); + + /** + * @irq_mask: + * + * Store old irq_chip irq_mask callback + */ + void (*irq_mask)(struct irq_data *data); }; /** -- cgit v1.2.3 From 95fc87b44104d9a524ff3e975bbfbd7c1f1a2dd5 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Fri, 29 May 2020 02:00:54 +0530 Subject: vfio: Selective dirty page tracking if IOMMU backed device pins pages Added a check such that only singleton IOMMU groups can pin pages. >From the point when vendor driver pins any pages, consider IOMMU group dirty page scope to be limited to pinned pages. To optimize to avoid walking list often, added flag pinned_page_dirty_scope to indicate if all of the vfio_groups for each vfio_domain in the domain_list dirty page scope is limited to pinned pages. This flag is updated on first pinned pages request for that IOMMU group and on attaching/detaching group. Signed-off-by: Kirti Wankhede Reviewed-by: Neo Jia Reviewed-by: Yan Zhao Signed-off-by: Alex Williamson --- include/linux/vfio.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 5d92ee15d098..38d3c6a8dc7e 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -76,7 +76,9 @@ struct vfio_iommu_driver_ops { struct iommu_group *group); void (*detach_group)(void *iommu_data, struct iommu_group *group); - int (*pin_pages)(void *iommu_data, unsigned long *user_pfn, + int (*pin_pages)(void *iommu_data, + struct iommu_group *group, + unsigned long *user_pfn, int npage, int prot, unsigned long *phys_pfn); int (*unpin_pages)(void *iommu_data, -- cgit v1.2.3 From 24c5efe41c29ee3e55bcf5a1c9f61ca8709622e8 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 22 May 2020 12:01:33 +1000 Subject: sunrpc: clean up properly in gss_mech_unregister() gss_mech_register() calls svcauth_gss_register_pseudoflavor() for each flavour, but gss_mech_unregister() does not call auth_domain_put(). This is unbalanced and makes it impossible to reload the module. Change svcauth_gss_register_pseudoflavor() to return the registered auth_domain, and save it for later release. Cc: stable@vger.kernel.org (v2.6.12+) Link: https://bugzilla.kernel.org/show_bug.cgi?id=206651 Signed-off-by: NeilBrown Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/gss_api.h | 1 + include/linux/sunrpc/svcauth_gss.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index bc07e51f20d1..bf4ac8a0268c 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -84,6 +84,7 @@ struct pf_desc { u32 service; char *name; char *auth_domain_name; + struct auth_domain *domain; bool datatouch; }; diff --git a/include/linux/sunrpc/svcauth_gss.h b/include/linux/sunrpc/svcauth_gss.h index ca39a388dc22..f09c82b0a7ae 100644 --- a/include/linux/sunrpc/svcauth_gss.h +++ b/include/linux/sunrpc/svcauth_gss.h @@ -20,7 +20,8 @@ int gss_svc_init(void); void gss_svc_shutdown(void); int gss_svc_init_net(struct net *net); void gss_svc_shutdown_net(struct net *net); -int svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name); +struct auth_domain *svcauth_gss_register_pseudoflavor(u32 pseudoflavor, + char *name); u32 svcauth_gss_flavor(struct auth_domain *dom); #endif /* _LINUX_SUNRPC_SVCAUTH_GSS_H */ -- cgit v1.2.3 From 6d3f922c46f2e91f63c92f8dd28381f097082912 Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Tue, 12 May 2020 15:53:21 +0300 Subject: opp: Add support for parsing interconnect bandwidth The OPP bindings now support bandwidth values, so add support to parse it from device tree and store it into the new dev_pm_opp_icc_bw struct, which is part of the dev_pm_opp. Signed-off-by: Georgi Djakov Reviewed-by: Matthias Kaehlcke [ Viresh: Create _read_bw() and use it, renamed _of_find_icc_paths() to dev_pm_opp_of_find_icc_paths(), exported it and made opp_table argument optional. Also drop the depends on from Kconfig. ] Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 747861816f4f..d5c4a329321d 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -41,6 +41,18 @@ struct dev_pm_opp_supply { unsigned long u_amp; }; +/** + * struct dev_pm_opp_icc_bw - Interconnect bandwidth values + * @avg: Average bandwidth corresponding to this OPP (in icc units) + * @peak: Peak bandwidth corresponding to this OPP (in icc units) + * + * This structure stores the bandwidth values for a single interconnect path. + */ +struct dev_pm_opp_icc_bw { + u32 avg; + u32 peak; +}; + /** * struct dev_pm_opp_info - OPP freq/voltage/current values * @rate: Target clk rate in hz @@ -360,6 +372,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpuma struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev); struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp); int of_get_required_opp_performance_state(struct device_node *np, int index); +int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table); void dev_pm_opp_of_register_em(struct cpumask *cpus); #else static inline int dev_pm_opp_of_add_table(struct device *dev) @@ -408,6 +421,11 @@ static inline int of_get_required_opp_performance_state(struct device_node *np, { return -ENOTSUPP; } + +static inline int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table) +{ + return -ENOTSUPP; +} #endif #endif /* __LINUX_OPP_H__ */ -- cgit v1.2.3 From 0430b1d5704b0f0f1d237236dde9c143f8669e49 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 18 May 2020 14:25:32 +0300 Subject: opp: Expose bandwidth information via debugfs Expose the bandwidth information as well via debugfs. Signed-off-by: Viresh Kumar Signed-off-by: Georgi Djakov --- include/linux/interconnect.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index 34e97231a6ab..1ad09efd296e 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -32,6 +32,7 @@ struct icc_path *of_icc_get_by_index(struct device *dev, int idx); void icc_put(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); void icc_set_tag(struct icc_path *path, u32 tag); +const char *icc_get_name(struct icc_path *path); #else @@ -65,6 +66,11 @@ static inline void icc_set_tag(struct icc_path *path, u32 tag) { } +static inline const char *icc_get_name(struct icc_path *path) +{ + return NULL; +} + #endif /* CONFIG_INTERCONNECT */ #endif /* __LINUX_INTERCONNECT_H */ -- cgit v1.2.3 From 2849beec3343343b293f33267affbdd7c3f42814 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:03 +0200 Subject: mmc: sdio: Change macro names for Marvell 8688 modules MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add underscore as separator in Marvell 8688 macro names for better readability and consistency. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-3-pali@kernel.org Signed-off-by: Ulf Hansson Acked-by: Ganapathi Bhat --- include/linux/mmc/sdio_ids.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 96f43e0dc78f..7e992a0e6cc0 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -56,8 +56,8 @@ #define SDIO_VENDOR_ID_MARVELL 0x02df #define SDIO_DEVICE_ID_MARVELL_LIBERTAS 0x9103 -#define SDIO_DEVICE_ID_MARVELL_8688WLAN 0x9104 -#define SDIO_DEVICE_ID_MARVELL_8688BT 0x9105 +#define SDIO_DEVICE_ID_MARVELL_8688_WLAN 0x9104 +#define SDIO_DEVICE_ID_MARVELL_8688_BT 0x9105 #define SDIO_DEVICE_ID_MARVELL_8797_F0 0x9128 #define SDIO_DEVICE_ID_MARVELL_8887_F0 0x9134 -- cgit v1.2.3 From 7d14c687376e6bd33cf42028300838466b95e765 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:04 +0200 Subject: mmc: sdio: Move SDIO IDs from mwifiex driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add _WLAN suffix to macro names for consistency with other Marvell macros. These IDs represents wlan function of combo bt/wlan cards. Other functions of these cards have different IDs. Signed-off-by: Pali Rohár Acked-by: Kalle Valo Link: https://lore.kernel.org/r/20200522144412.19712-4-pali@kernel.org Signed-off-by: Ulf Hansson Acked-by: Ganapathi Bhat --- include/linux/mmc/sdio_ids.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 7e992a0e6cc0..90361ea7f5ed 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -58,8 +58,18 @@ #define SDIO_DEVICE_ID_MARVELL_LIBERTAS 0x9103 #define SDIO_DEVICE_ID_MARVELL_8688_WLAN 0x9104 #define SDIO_DEVICE_ID_MARVELL_8688_BT 0x9105 +#define SDIO_DEVICE_ID_MARVELL_8786_WLAN 0x9116 +#define SDIO_DEVICE_ID_MARVELL_8787_WLAN 0x9119 #define SDIO_DEVICE_ID_MARVELL_8797_F0 0x9128 +#define SDIO_DEVICE_ID_MARVELL_8797_WLAN 0x9129 +#define SDIO_DEVICE_ID_MARVELL_8897_WLAN 0x912d #define SDIO_DEVICE_ID_MARVELL_8887_F0 0x9134 +#define SDIO_DEVICE_ID_MARVELL_8887_WLAN 0x9135 +#define SDIO_DEVICE_ID_MARVELL_8801_WLAN 0x9139 +#define SDIO_DEVICE_ID_MARVELL_8997_F0 0x9140 +#define SDIO_DEVICE_ID_MARVELL_8997_WLAN 0x9141 +#define SDIO_DEVICE_ID_MARVELL_8977_WLAN 0x9145 +#define SDIO_DEVICE_ID_MARVELL_8987_WLAN 0x9149 #define SDIO_VENDOR_ID_MEDIATEK 0x037a -- cgit v1.2.3 From 649c7d76d87ca2285a82a65d86d99ddb60571e20 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:05 +0200 Subject: mmc: sdio: Move SDIO IDs from btmrvl driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define appropriate macro names for consistency with other Marvell macros. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-5-pali@kernel.org Signed-off-by: Ulf Hansson Acked-by: Ganapathi Bhat --- include/linux/mmc/sdio_ids.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 90361ea7f5ed..1237e1048d06 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -60,16 +60,24 @@ #define SDIO_DEVICE_ID_MARVELL_8688_BT 0x9105 #define SDIO_DEVICE_ID_MARVELL_8786_WLAN 0x9116 #define SDIO_DEVICE_ID_MARVELL_8787_WLAN 0x9119 +#define SDIO_DEVICE_ID_MARVELL_8787_BT 0x911a +#define SDIO_DEVICE_ID_MARVELL_8787_BT_AMP 0x911b #define SDIO_DEVICE_ID_MARVELL_8797_F0 0x9128 #define SDIO_DEVICE_ID_MARVELL_8797_WLAN 0x9129 +#define SDIO_DEVICE_ID_MARVELL_8797_BT 0x912a #define SDIO_DEVICE_ID_MARVELL_8897_WLAN 0x912d +#define SDIO_DEVICE_ID_MARVELL_8897_BT 0x912e #define SDIO_DEVICE_ID_MARVELL_8887_F0 0x9134 #define SDIO_DEVICE_ID_MARVELL_8887_WLAN 0x9135 +#define SDIO_DEVICE_ID_MARVELL_8887_BT 0x9136 #define SDIO_DEVICE_ID_MARVELL_8801_WLAN 0x9139 #define SDIO_DEVICE_ID_MARVELL_8997_F0 0x9140 #define SDIO_DEVICE_ID_MARVELL_8997_WLAN 0x9141 +#define SDIO_DEVICE_ID_MARVELL_8997_BT 0x9142 #define SDIO_DEVICE_ID_MARVELL_8977_WLAN 0x9145 +#define SDIO_DEVICE_ID_MARVELL_8977_BT 0x9146 #define SDIO_DEVICE_ID_MARVELL_8987_WLAN 0x9149 +#define SDIO_DEVICE_ID_MARVELL_8987_BT 0x914a #define SDIO_VENDOR_ID_MEDIATEK 0x037a -- cgit v1.2.3 From baaa110dcacfd704d182a275c4307baecb81423b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:06 +0200 Subject: mmc: sdio: Move SDIO IDs from btmtksdio driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define appropriate macro names for consistency with other macros. Signed-off-by: Pali Rohár Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20200522144412.19712-6-pali@kernel.org Signed-off-by: Ulf Hansson Acked-by: Ganapathi Bhat --- include/linux/mmc/sdio_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 1237e1048d06..c9aca57d4dea 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -80,6 +80,8 @@ #define SDIO_DEVICE_ID_MARVELL_8987_BT 0x914a #define SDIO_VENDOR_ID_MEDIATEK 0x037a +#define SDIO_DEVICE_ID_MEDIATEK_MT7663 0x7663 +#define SDIO_DEVICE_ID_MEDIATEK_MT7668 0x7668 #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 -- cgit v1.2.3 From b8c26a9663e1d888bbf4e14d3a62d033f286623e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:07 +0200 Subject: mmc: sdio: Move SDIO IDs from smssdio driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define appropriate macro names for consistency with other Siano macros. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-7-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index c9aca57d4dea..9ec675a7ac37 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -88,6 +88,11 @@ #define SDIO_DEVICE_ID_SIANO_NICE 0x0202 #define SDIO_DEVICE_ID_SIANO_VEGA_A0 0x0300 #define SDIO_DEVICE_ID_SIANO_VENICE 0x0301 +#define SDIO_DEVICE_ID_SIANO_MING 0x0302 +#define SDIO_DEVICE_ID_SIANO_PELE 0x0500 +#define SDIO_DEVICE_ID_SIANO_RIO 0x0600 +#define SDIO_DEVICE_ID_SIANO_DENVER_2160 0x0700 +#define SDIO_DEVICE_ID_SIANO_DENVER_1530 0x0800 #define SDIO_DEVICE_ID_SIANO_NOVA_A0 0x1100 #define SDIO_DEVICE_ID_SIANO_STELLAR 0x5347 -- cgit v1.2.3 From ecc2f3962587aed327ccd3c32e99ccfc9e744fa0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:08 +0200 Subject: mmc: sdio: Move SDIO IDs from ath6kl driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Also replace generic MANUFACTURER macros by proper SDIO IDs macros. Check for "AR6003 or later" is slightly modified to use SDIO device IDs. This allows removal of all custom MANUFACTURER macros from ath6kl. Signed-off-by: Pali Rohár Acked-by: Kalle Valo Link: https://lore.kernel.org/r/20200522144412.19712-8-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 9ec675a7ac37..95b67ab7d06a 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -24,6 +24,16 @@ /* * Vendors and devices. Sort key: vendor first, device next. */ + +#define SDIO_VENDOR_ID_ATHEROS 0x0271 +#define SDIO_DEVICE_ID_ATHEROS_AR6003_00 0x0300 +#define SDIO_DEVICE_ID_ATHEROS_AR6003_01 0x0301 +#define SDIO_DEVICE_ID_ATHEROS_AR6004_00 0x0400 +#define SDIO_DEVICE_ID_ATHEROS_AR6004_01 0x0401 +#define SDIO_DEVICE_ID_ATHEROS_AR6004_02 0x0402 +#define SDIO_DEVICE_ID_ATHEROS_AR6004_18 0x0418 +#define SDIO_DEVICE_ID_ATHEROS_AR6004_19 0x0419 + #define SDIO_VENDOR_ID_BROADCOM 0x02d0 #define SDIO_DEVICE_ID_BROADCOM_43143 0xa887 #define SDIO_DEVICE_ID_BROADCOM_43241 0x4324 -- cgit v1.2.3 From 4dc28c948f480c5004613aab153c7160bd4f29ce Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:09 +0200 Subject: mmc: sdio: Move SDIO IDs from ath10k driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Also replace generic MANUFACTURER macros by proper SDIO IDs macros. Checks for device IDs are slightly modified to use SDIO device IDs. This allows removal of all custom MANUFACTURER macros from ath10k. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-9-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 95b67ab7d06a..2894f7739acc 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -33,6 +33,8 @@ #define SDIO_DEVICE_ID_ATHEROS_AR6004_02 0x0402 #define SDIO_DEVICE_ID_ATHEROS_AR6004_18 0x0418 #define SDIO_DEVICE_ID_ATHEROS_AR6004_19 0x0419 +#define SDIO_DEVICE_ID_ATHEROS_AR6005 0x050A +#define SDIO_DEVICE_ID_ATHEROS_QCA9377 0x0701 #define SDIO_VENDOR_ID_BROADCOM 0x02d0 #define SDIO_DEVICE_ID_BROADCOM_43143 0xa887 -- cgit v1.2.3 From 8baa6d1bce05cf26eec6b43bcd428735f33cb60e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:10 +0200 Subject: mmc: sdio: Move SDIO IDs from b43-sdio driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define appropriate macro names for consistency with other macros. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-10-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 2894f7739acc..8e7a0683b927 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -25,6 +25,9 @@ * Vendors and devices. Sort key: vendor first, device next. */ +#define SDIO_VENDOR_ID_CGUYS 0x0092 +#define SDIO_DEVICE_ID_CGUYS_EW_CG1102GC 0x0004 + #define SDIO_VENDOR_ID_ATHEROS 0x0271 #define SDIO_DEVICE_ID_ATHEROS_AR6003_00 0x0300 #define SDIO_DEVICE_ID_ATHEROS_AR6003_01 0x0301 @@ -37,6 +40,7 @@ #define SDIO_DEVICE_ID_ATHEROS_QCA9377 0x0701 #define SDIO_VENDOR_ID_BROADCOM 0x02d0 +#define SDIO_DEVICE_ID_BROADCOM_NINTENDO_WII 0x044b #define SDIO_DEVICE_ID_BROADCOM_43143 0xa887 #define SDIO_DEVICE_ID_BROADCOM_43241 0x4324 #define SDIO_DEVICE_ID_BROADCOM_4329 0x4329 -- cgit v1.2.3 From 1eb911258805695c8f85795d3d4cdbd1e84fc2d9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:11 +0200 Subject: mmc: sdio: Fix Cypress SDIO IDs macros in common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All macro names for SDIO device IDs are prefixed by vendor name to which device ID belongs. So for consistency add Broadcom string vendor prefix to all Cypress macro names as they belong to SDIO Broadcom vendor ID. Change also Cypress 43012 value from decimal do hexadecimal notation to be consistent with all other values. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-11-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 8e7a0683b927..b19200aea56a 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -58,9 +58,9 @@ #define SDIO_DEVICE_ID_BROADCOM_4354 0x4354 #define SDIO_DEVICE_ID_BROADCOM_4356 0x4356 #define SDIO_DEVICE_ID_BROADCOM_4359 0x4359 -#define SDIO_DEVICE_ID_CYPRESS_4373 0x4373 -#define SDIO_DEVICE_ID_CYPRESS_43012 43012 -#define SDIO_DEVICE_ID_CYPRESS_89359 0x4355 +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_4373 0x4373 +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43012 0xa804 +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_89359 0x4355 #define SDIO_VENDOR_ID_INTEL 0x0089 #define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX 0x1402 -- cgit v1.2.3 From 798dd3c311f6c862719a3fc71c3c14eba192c64e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 22 May 2020 16:44:12 +0200 Subject: mmc: sdio: Sort all SDIO IDs in common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix ordering of SDIO IDs to conform to the comment above, which says vendor first, device next. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200522144412.19712-12-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 43 ++++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index b19200aea56a..15ed8ce9d394 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -25,9 +25,23 @@ * Vendors and devices. Sort key: vendor first, device next. */ +#define SDIO_VENDOR_ID_STE 0x0020 +#define SDIO_DEVICE_ID_STE_CW1200 0x2280 + +#define SDIO_VENDOR_ID_INTEL 0x0089 +#define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX 0x1402 +#define SDIO_DEVICE_ID_INTEL_IWMC3200WIFI 0x1403 +#define SDIO_DEVICE_ID_INTEL_IWMC3200TOP 0x1404 +#define SDIO_DEVICE_ID_INTEL_IWMC3200GPS 0x1405 +#define SDIO_DEVICE_ID_INTEL_IWMC3200BT 0x1406 +#define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX_2G5 0x1407 + #define SDIO_VENDOR_ID_CGUYS 0x0092 #define SDIO_DEVICE_ID_CGUYS_EW_CG1102GC 0x0004 +#define SDIO_VENDOR_ID_TI 0x0097 +#define SDIO_DEVICE_ID_TI_WL1271 0x4076 + #define SDIO_VENDOR_ID_ATHEROS 0x0271 #define SDIO_DEVICE_ID_ATHEROS_AR6003_00 0x0300 #define SDIO_DEVICE_ID_ATHEROS_AR6003_01 0x0301 @@ -41,34 +55,26 @@ #define SDIO_VENDOR_ID_BROADCOM 0x02d0 #define SDIO_DEVICE_ID_BROADCOM_NINTENDO_WII 0x044b -#define SDIO_DEVICE_ID_BROADCOM_43143 0xa887 #define SDIO_DEVICE_ID_BROADCOM_43241 0x4324 #define SDIO_DEVICE_ID_BROADCOM_4329 0x4329 #define SDIO_DEVICE_ID_BROADCOM_4330 0x4330 #define SDIO_DEVICE_ID_BROADCOM_4334 0x4334 -#define SDIO_DEVICE_ID_BROADCOM_43340 0xa94c -#define SDIO_DEVICE_ID_BROADCOM_43341 0xa94d #define SDIO_DEVICE_ID_BROADCOM_4335_4339 0x4335 #define SDIO_DEVICE_ID_BROADCOM_4339 0x4339 -#define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 -#define SDIO_DEVICE_ID_BROADCOM_43364 0xa9a4 -#define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 #define SDIO_DEVICE_ID_BROADCOM_4345 0x4345 -#define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_DEVICE_ID_BROADCOM_4354 0x4354 +#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_89359 0x4355 #define SDIO_DEVICE_ID_BROADCOM_4356 0x4356 #define SDIO_DEVICE_ID_BROADCOM_4359 0x4359 #define SDIO_DEVICE_ID_BROADCOM_CYPRESS_4373 0x4373 #define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43012 0xa804 -#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_89359 0x4355 - -#define SDIO_VENDOR_ID_INTEL 0x0089 -#define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX 0x1402 -#define SDIO_DEVICE_ID_INTEL_IWMC3200WIFI 0x1403 -#define SDIO_DEVICE_ID_INTEL_IWMC3200TOP 0x1404 -#define SDIO_DEVICE_ID_INTEL_IWMC3200GPS 0x1405 -#define SDIO_DEVICE_ID_INTEL_IWMC3200BT 0x1406 -#define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX_2G5 0x1407 +#define SDIO_DEVICE_ID_BROADCOM_43143 0xa887 +#define SDIO_DEVICE_ID_BROADCOM_43340 0xa94c +#define SDIO_DEVICE_ID_BROADCOM_43341 0xa94d +#define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 +#define SDIO_DEVICE_ID_BROADCOM_43364 0xa9a4 +#define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 +#define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_VENDOR_ID_MARVELL 0x02df #define SDIO_DEVICE_ID_MARVELL_LIBERTAS 0x9103 @@ -112,12 +118,7 @@ #define SDIO_DEVICE_ID_SIANO_NOVA_A0 0x1100 #define SDIO_DEVICE_ID_SIANO_STELLAR 0x5347 -#define SDIO_VENDOR_ID_TI 0x0097 -#define SDIO_DEVICE_ID_TI_WL1271 0x4076 #define SDIO_VENDOR_ID_TI_WL1251 0x104c #define SDIO_DEVICE_ID_TI_WL1251 0x9066 -#define SDIO_VENDOR_ID_STE 0x0020 -#define SDIO_DEVICE_ID_STE_CW1200 0x2280 - #endif /* LINUX_MMC_SDIO_IDS_H */ -- cgit v1.2.3 From d58a2df3d8877b91ecbfb936a15da364251a228f Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Mon, 18 May 2020 16:45:02 +0200 Subject: serial: 8250: Support rs485 bus termination GPIO Commit e8759ad17d41 ("serial: uapi: Add support for bus termination") introduced the ability to enable rs485 bus termination from user space. So far the feature is only used by a single driver, 8250_exar.c, using a hardcoded GPIO pin specific to Siemens IOT2040 products. Provide for a more generic solution by allowing specification of an rs485 bus termination GPIO pin in the device tree: Amend the serial core to retrieve the GPIO from the device tree (or ACPI table) and amend the default ->rs485_config() callback for 8250 drivers to change the GPIO on request from user space. Perhaps 8250_exar.c can be converted to the generic approach in a follow-up patch. Signed-off-by: Lukas Wunner Reviewed-by: Andy Shevchenko Cc: Jan Kiszka Link: https://lore.kernel.org/r/94c6c800d1ca9fa04766dd1d43a8272c5ad4bedd.1589811297.git.lukas@wunner.de Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index b649a2b894e7..9fd550e7946a 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -251,6 +252,7 @@ struct uart_port { struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ struct serial_rs485 rs485; + struct gpio_desc *rs485_term_gpio; /* enable RS485 bus termination */ struct serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ }; -- cgit v1.2.3 From 5ace60859e84113b7a185c117fbf2c429d381b59 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 16 Mar 2020 11:22:24 +0100 Subject: i2c: smbus: Add a way to instantiate SPD EEPROMs automatically In simple cases we can instantiate SPD EEPROMs on the SMBus automatically. Start with just DDR2, DDR3 and DDR4 on x86 for now, and only for systems with no more than 4 memory slots. These limitations may be lifted later. Signed-off-by: Jean Delvare [wsa: minor change for new API] Signed-off-by: Wolfram Sang --- include/linux/i2c-smbus.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h index 8c5459034f92..1e4e0de4ef8b 100644 --- a/include/linux/i2c-smbus.h +++ b/include/linux/i2c-smbus.h @@ -2,7 +2,7 @@ /* * i2c-smbus.h - SMBus extensions to the I2C protocol * - * Copyright (C) 2010 Jean Delvare + * Copyright (C) 2010-2019 Jean Delvare */ #ifndef _LINUX_I2C_SMBUS_H @@ -39,4 +39,10 @@ static inline int of_i2c_setup_smbus_alert(struct i2c_adapter *adap) } #endif +#if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_DMI) +void i2c_register_spd(struct i2c_adapter *adap); +#else +static inline void i2c_register_spd(struct i2c_adapter *adap) { } +#endif + #endif /* _LINUX_I2C_SMBUS_H */ -- cgit v1.2.3 From 8baebfc2aca26e3fa67ab28343671b82be42b22c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 28 May 2020 02:41:03 +0300 Subject: regmap: add helper for per-port regfield initialization Similar to the standalone regfields, add an initializer for the users who need to set .id_size and .id_offset in order to use the regmap_fields_update_bits_base API. Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20200527234113.2491988-2-olteanv@gmail.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 40b07168fd8e..87703d105191 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1134,6 +1134,14 @@ struct reg_field { .msb = _msb, \ } +#define REG_FIELD_ID(_reg, _lsb, _msb, _size, _offset) { \ + .reg = _reg, \ + .lsb = _lsb, \ + .msb = _msb, \ + .id_size = _size, \ + .id_offset = _offset, \ + } + struct regmap_field *regmap_field_alloc(struct regmap *regmap, struct reg_field reg_field); void regmap_field_free(struct regmap_field *field); -- cgit v1.2.3 From fb01562e5a8a731bb1807eba0a9fadb355ca2277 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Thu, 23 Apr 2020 14:53:28 +0200 Subject: uacce: Remove mm_exit() op The mm_exit() op will be removed from the SVA API. When a process dies and its mm goes away, the IOMMU driver won't notify device drivers anymore. Drivers should expect to handle a lot more aborted DMA. On the upside, it does greatly simplify the queue management. The uacce_mm struct, that tracks all queues bound to an mm, was only used by the mm_exit() callback. Remove it. Signed-off-by: Jean-Philippe Brucker Acked-by: Jacob Pan Acked-by: Lu Baolu Acked-by: Zhangfei Gao Link: https://lore.kernel.org/r/20200423125329.782066-2-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- include/linux/uacce.h | 34 +++++++++------------------------- 1 file changed, 9 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uacce.h b/include/linux/uacce.h index 0e215e6d0534..454c2f6672d7 100644 --- a/include/linux/uacce.h +++ b/include/linux/uacce.h @@ -68,19 +68,21 @@ enum uacce_q_state { * @uacce: pointer to uacce * @priv: private pointer * @wait: wait queue head - * @list: index into uacce_mm - * @uacce_mm: the corresponding mm + * @list: index into uacce queues list * @qfrs: pointer of qfr regions * @state: queue state machine + * @pasid: pasid associated to the mm + * @handle: iommu_sva handle returned by iommu_sva_bind_device() */ struct uacce_queue { struct uacce_device *uacce; void *priv; wait_queue_head_t wait; struct list_head list; - struct uacce_mm *uacce_mm; struct uacce_qfile_region *qfrs[UACCE_MAX_REGION]; enum uacce_q_state state; + int pasid; + struct iommu_sva *handle; }; /** @@ -96,8 +98,8 @@ struct uacce_queue { * @cdev: cdev of the uacce * @dev: dev of the uacce * @priv: private pointer of the uacce - * @mm_list: list head of uacce_mm->list - * @mm_lock: lock for mm_list + * @queues: list of queues + * @queues_lock: lock for queues list * @inode: core vfs */ struct uacce_device { @@ -112,27 +114,9 @@ struct uacce_device { struct cdev *cdev; struct device dev; void *priv; - struct list_head mm_list; - struct mutex mm_lock; - struct inode *inode; -}; - -/** - * struct uacce_mm - keep track of queues bound to a process - * @list: index into uacce_device - * @queues: list of queues - * @mm: the mm struct - * @lock: protects the list of queues - * @pasid: pasid of the uacce_mm - * @handle: iommu_sva handle return from iommu_sva_bind_device - */ -struct uacce_mm { - struct list_head list; struct list_head queues; - struct mm_struct *mm; - struct mutex lock; - int pasid; - struct iommu_sva *handle; + struct mutex queues_lock; + struct inode *inode; }; #if IS_ENABLED(CONFIG_UACCE) -- cgit v1.2.3 From edcc40d2ab5f47f205c2dd2a9aeedd8c77de050a Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Thu, 23 Apr 2020 14:53:30 +0200 Subject: iommu: Remove iommu_sva_ops::mm_exit() After binding a device to an mm, device drivers currently need to register a mm_exit handler. This function is called when the mm exits, to gracefully stop DMA targeting the address space and flush page faults to the IOMMU. This is deemed too complex for the MMU release() notifier, which may be triggered by any mmput() invocation, from about 120 callsites [1]. The upcoming SVA module has an example of such complexity: the I/O Page Fault handler would need to call mmput_async() instead of mmput() after handling an IOPF, to avoid triggering the release() notifier which would in turn drain the IOPF queue and lock up. Another concern is the DMA stop function taking too long, up to several minutes [2]. For some mmput() callers this may disturb other users. For example, if the OOM killer picks the mm bound to a device as the victim and that mm's memory is locked, if the release() takes too long, it might choose additional innocent victims to kill. To simplify the MMU release notifier, don't forward the notification to device drivers. Since they don't stop DMA on mm exit anymore, the PASID lifetime is extended: (1) The device driver calls bind(). A PASID is allocated. Here any DMA fault is handled by mm, and on error we don't print anything to dmesg. Userspace can easily trigger errors by issuing DMA on unmapped buffers. (2) exit_mmap(), for example the process took a SIGKILL. This step doesn't happen during normal operations. Remove the pgd from the PASID table, since the page tables are about to be freed. Invalidate the IOTLBs. Here the device may still perform DMA on the address space. Incoming transactions are aborted but faults aren't printed out. ATS Translation Requests return Successful Translation Completions with R=W=0. PRI Page Requests return with Invalid Request. (3) The device driver stops DMA, possibly following release of a fd, and calls unbind(). PASID table is cleared, IOTLB invalidated if necessary. The page fault queues are drained, and the PASID is freed. If DMA for that PASID is still running here, something went seriously wrong and errors should be reported. For now remove iommu_sva_ops entirely. We might need to re-introduce them at some point, for example to notify device drivers of unhandled IOPF. [1] https://lore.kernel.org/linux-iommu/20200306174239.GM31668@ziepe.ca/ [2] https://lore.kernel.org/linux-iommu/4d68da96-0ad5-b412-5987-2f7a6aa796c3@amd.com/ Signed-off-by: Jean-Philippe Brucker Acked-by: Jacob Pan Acked-by: Lu Baolu Link: https://lore.kernel.org/r/20200423125329.782066-3-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 30 ------------------------------ 1 file changed, 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7cfd2dddb49d..08d3506172a1 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -53,8 +53,6 @@ struct iommu_fault_event; typedef int (*iommu_fault_handler_t)(struct iommu_domain *, struct device *, unsigned long, int, void *); -typedef int (*iommu_mm_exit_handler_t)(struct device *dev, struct iommu_sva *, - void *); typedef int (*iommu_dev_fault_handler_t)(struct iommu_fault *, void *); struct iommu_domain_geometry { @@ -171,25 +169,6 @@ enum iommu_dev_features { #define IOMMU_PASID_INVALID (-1U) -/** - * struct iommu_sva_ops - device driver callbacks for an SVA context - * - * @mm_exit: called when the mm is about to be torn down by exit_mmap. After - * @mm_exit returns, the device must not issue any more transaction - * with the PASID given as argument. - * - * The @mm_exit handler is allowed to sleep. Be careful about the - * locks taken in @mm_exit, because they might lead to deadlocks if - * they are also held when dropping references to the mm. Consider the - * following call chain: - * mutex_lock(A); mmput(mm) -> exit_mm() -> @mm_exit() -> mutex_lock(A) - * Using mmput_async() prevents this scenario. - * - */ -struct iommu_sva_ops { - iommu_mm_exit_handler_t mm_exit; -}; - #ifdef CONFIG_IOMMU_API /** @@ -616,7 +595,6 @@ struct iommu_fwspec { */ struct iommu_sva { struct device *dev; - const struct iommu_sva_ops *ops; }; int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, @@ -664,8 +642,6 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata); void iommu_sva_unbind_device(struct iommu_sva *handle); -int iommu_sva_set_ops(struct iommu_sva *handle, - const struct iommu_sva_ops *ops); int iommu_sva_get_pasid(struct iommu_sva *handle); #else /* CONFIG_IOMMU_API */ @@ -1069,12 +1045,6 @@ static inline void iommu_sva_unbind_device(struct iommu_sva *handle) { } -static inline int iommu_sva_set_ops(struct iommu_sva *handle, - const struct iommu_sva_ops *ops) -{ - return -EINVAL; -} - static inline int iommu_sva_get_pasid(struct iommu_sva *handle) { return IOMMU_PASID_INVALID; -- cgit v1.2.3 From aa2ff9dbaeddabb5ad166db5f9f1a0580a8bbba8 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 28 May 2020 17:45:02 +0200 Subject: regmap: provide helpers for simple bit operations In many instances regmap_update_bits() is used for simple bit setting and clearing. In these cases the last argument is redundant and we can hide it with a static inline function. This adds three new helpers for simple bit operations: set_bits, clear_bits and test_bits (the last one defined as a regular function). Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20200528154503.26304-2-brgl@bgdev.pl Signed-off-by: Mark Brown --- include/linux/regmap.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 40b07168fd8e..ddf0baff195d 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1111,6 +1111,21 @@ bool regmap_reg_in_ranges(unsigned int reg, const struct regmap_range *ranges, unsigned int nranges); +static inline int regmap_set_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + return regmap_update_bits_base(map, reg, bits, bits, + NULL, false, false); +} + +static inline int regmap_clear_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + return regmap_update_bits_base(map, reg, bits, 0, NULL, false, false); +} + +int regmap_test_bits(struct regmap *map, unsigned int reg, unsigned int bits); + /** * struct reg_field - Description of an register field * @@ -1410,6 +1425,27 @@ static inline int regmap_update_bits_base(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_set_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_clear_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_test_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_field_update_bits_base(struct regmap_field *field, unsigned int mask, unsigned int val, bool *change, bool async, bool force) -- cgit v1.2.3 From 4fda230ecddc2573ed88632e98b69b0b9b68c0ad Mon Sep 17 00:00:00 2001 From: Jon Derrick Date: Wed, 27 May 2020 10:56:16 -0600 Subject: iommu/vt-d: Allocate domain info for real DMA sub-devices Sub-devices of a real DMA device might exist on a separate segment than the real DMA device and its IOMMU. These devices should still have a valid device_domain_info, but the current dma alias model won't allocate info for the subdevice. This patch adds a segment member to struct device_domain_info and uses the sub-device's BDF so that these sub-devices won't alias to other devices. Fixes: 2b0140c69637e ("iommu/vt-d: Use pci_real_dma_dev() for mapping") Cc: stable@vger.kernel.org # v5.6+ Signed-off-by: Jon Derrick Acked-by: Lu Baolu Link: https://lore.kernel.org/r/20200527165617.297470-3-jonathan.derrick@intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 21633cee6331..4100bd224f5c 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -609,6 +609,7 @@ struct device_domain_info { struct list_head auxiliary_domains; /* auxiliary domains * attached to this device */ + u32 segment; /* PCI segment number */ u8 bus; /* PCI bus number */ u8 devfn; /* PCI devfn number */ u16 pfsid; /* SRIOV physical function source ID */ -- cgit v1.2.3 From 752db83a5dfd4fd3a0624b9ab440ed947fa003ca Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Fri, 29 May 2020 14:49:39 +0200 Subject: regulator: extract voltage balancing code to the separate function Move the coupled regulators voltage balancing code to the separate function and allow to call it from the custom regulator couplers. Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200529124940.10675-2-m.szyprowski@samsung.com Signed-off-by: Mark Brown --- include/linux/regulator/coupler.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/coupler.h b/include/linux/regulator/coupler.h index 0212d6255e4e..5f86824bd117 100644 --- a/include/linux/regulator/coupler.h +++ b/include/linux/regulator/coupler.h @@ -62,6 +62,8 @@ int regulator_get_voltage_rdev(struct regulator_dev *rdev); int regulator_set_voltage_rdev(struct regulator_dev *rdev, int min_uV, int max_uV, suspend_state_t state); +int regulator_do_balance_voltage(struct regulator_dev *rdev, + suspend_state_t state, bool skip_coupled); #else static inline int regulator_coupler_register(struct regulator_coupler *coupler) { @@ -92,6 +94,12 @@ static inline int regulator_set_voltage_rdev(struct regulator_dev *rdev, { return -EINVAL; } +static inline int regulator_do_balance_voltage(struct regulator_dev *rdev, + suspend_state_t state, + bool skip_coupled) +{ + return -EINVAL; +} #endif #endif -- cgit v1.2.3 From 9a7875461fd0427dc86e3a87e93bd5723679b8b1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 28 May 2020 16:45:14 +0200 Subject: PM: runtime: Replace pm_runtime_callbacks_present() The name of pm_runtime_callbacks_present() is confusing, because it suggests that the device has PM-runtime callbacks if 'true' is returned by that function, but in fact that may not be the case, so replace it with pm_runtime_has_no_callbacks() which is not ambiguous. No functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Ulf Hansson --- include/linux/pm_runtime.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 3bdcbce8141a..3dbc207bff53 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -102,9 +102,9 @@ static inline bool pm_runtime_enabled(struct device *dev) return !dev->power.disable_depth; } -static inline bool pm_runtime_callbacks_present(struct device *dev) +static inline bool pm_runtime_has_no_callbacks(struct device *dev) { - return !dev->power.no_callbacks; + return dev->power.no_callbacks; } static inline void pm_runtime_mark_last_busy(struct device *dev) -- cgit v1.2.3 From 7b11eab041dacfeaaa6d27d9183b247a995bc16d Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 29 May 2020 07:51:59 -0700 Subject: blk-mq: blk-mq: provide forced completion method Drivers may need to bypass error injection for error recovery. Rename __blk_mq_complete_request() to blk_mq_force_complete_rq() and export that function so drivers may skip potential fake timeouts after they've reclaimed lost requests. Signed-off-by: Keith Busch Reviewed-by: Daniel Wagner Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d7307795439a..856bb10993cf 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -494,6 +494,7 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); bool blk_mq_complete_request(struct request *rq); +void blk_mq_force_complete_rq(struct request *rq); bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs); bool blk_mq_queue_stopped(struct request_queue *q); -- cgit v1.2.3 From 5d9c305b8ea3fbc95bedfde01f7dd91e68082098 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 May 2020 15:53:08 +0200 Subject: blk-mq: remove the bio argument to ->prepare_request None of the I/O schedulers actually needs it. Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Bart Van Assche Reviewed-by: Daniel Wagner Signed-off-by: Jens Axboe --- include/linux/elevator.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 901bda352dcb..bacc40a0bdf3 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -39,7 +39,7 @@ struct elevator_mq_ops { void (*request_merged)(struct request_queue *, struct request *, enum elv_merge); void (*requests_merged)(struct request_queue *, struct request *, struct request *); void (*limit_depth)(unsigned int, struct blk_mq_alloc_data *); - void (*prepare_request)(struct request *, struct bio *bio); + void (*prepare_request)(struct request *); void (*finish_request)(struct request *); void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool); struct request *(*dispatch_request)(struct blk_mq_hw_ctx *); -- cgit v1.2.3 From bf0beec0607db3c6f6fb7bd2c6d503792b05cf3f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 29 May 2020 15:53:15 +0200 Subject: blk-mq: drain I/O when all CPUs in a hctx are offline Most of blk-mq drivers depend on managed IRQ's auto-affinity to setup up queue mapping. Thomas mentioned the following point[1]: "That was the constraint of managed interrupts from the very beginning: The driver/subsystem has to quiesce the interrupt line and the associated queue _before_ it gets shutdown in CPU unplug and not fiddle with it until it's restarted by the core when the CPU is plugged in again." However, current blk-mq implementation doesn't quiesce hw queue before the last CPU in the hctx is shutdown. Even worse, CPUHP_BLK_MQ_DEAD is a cpuhp state handled after the CPU is down, so there isn't any chance to quiesce the hctx before shutting down the CPU. Add new CPUHP_AP_BLK_MQ_ONLINE state to stop allocating from blk-mq hctxs where the last CPU goes away, and wait for completion of in-flight requests. This guarantees that there is no inflight I/O before shutting down the managed IRQ. Add a BLK_MQ_F_STACKING and set it for dm-rq and loop, so we don't need to wait for completion of in-flight requests from these drivers to avoid a potential dead-lock. It is safe to do this for stacking drivers as those do not use interrupts at all and their I/O completions are triggered by underlying devices I/O completion. [1] https://lore.kernel.org/linux-block/alpine.DEB.2.21.1904051331270.1802@nanos.tec.linutronix.de/ [hch: different retry mechanism, merged two patches, minor cleanups] Signed-off-by: Ming Lei Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Daniel Wagner Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 10 ++++++++++ include/linux/cpuhotplug.h | 1 + 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 856bb10993cf..d6fcae17da5a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -140,6 +140,8 @@ struct blk_mq_hw_ctx { */ atomic_t nr_active; + /** @cpuhp_online: List to store request if CPU is going to die */ + struct hlist_node cpuhp_online; /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; /** @kobj: Kernel object for sysfs. */ @@ -391,6 +393,11 @@ struct blk_mq_ops { enum { BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_SHARED = 1 << 1, + /* + * Set when this device requires underlying blk-mq device for + * completing IO: + */ + BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_BLOCKING = 1 << 5, BLK_MQ_F_NO_SCHED = 1 << 6, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, @@ -400,6 +407,9 @@ enum { BLK_MQ_S_TAG_ACTIVE = 1, BLK_MQ_S_SCHED_RESTART = 2, + /* hw queue is inactive after all its CPUs become offline */ + BLK_MQ_S_INACTIVE = 3, + BLK_MQ_MAX_DEPTH = 10240, BLK_MQ_CPU_WORK_BATCH = 8, diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 77d70b633531..24b3a77810b6 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -152,6 +152,7 @@ enum cpuhp_state { CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, CPUHP_AP_IRQ_AFFINITY_ONLINE, + CPUHP_AP_BLK_MQ_ONLINE, CPUHP_AP_ARM_MVEBU_SYNC_CLOCKS, CPUHP_AP_X86_INTEL_EPB_ONLINE, CPUHP_AP_PERF_ONLINE, -- cgit v1.2.3 From 5a892ff2facb4548c17c05931ed899038a0da63e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 May 2020 14:09:43 +0200 Subject: net: remove kernel_setsockopt No users left. Signed-off-by: Christoph Hellwig Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/linux/net.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 74ef5d7315f7..e10f378194a5 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -303,8 +303,6 @@ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags); int kernel_getsockname(struct socket *sock, struct sockaddr *addr); int kernel_getpeername(struct socket *sock, struct sockaddr *addr); -int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, - unsigned int optlen); int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, -- cgit v1.2.3 From a7868323c2638a7c6c5b30b37831b73cbdf0dc15 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 29 May 2020 08:24:10 -0500 Subject: exec: Add a per bprm->file version of per_clear There is a small bug in the code that recomputes parts of bprm->cred for every bprm->file. The code never recomputes the part of clear_dangerous_personality_flags it is responsible for. Which means that in practice if someone creates a sgid script the interpreter will not be able to use any of: READ_IMPLIES_EXEC ADDR_NO_RANDOMIZE ADDR_COMPAT_LAYOUT MMAP_PAGE_ZERO. This accentially clearing of personality flags probably does not matter in practice because no one has complained but it does make the code more difficult to understand. Further remaining bug compatible prevents the recomputation from being removed and replaced by simply computing bprm->cred once from the final bprm->file. Making this change removes the last behavior difference between computing bprm->creds from the final file and recomputing bprm->cred several times. Which allows this behavior change to be justified for it's own reasons, and for any but hunts looking into why the behavior changed to wind up here instead of in the code that will follow that computes bprm->cred from the final bprm->file. This small logic bug appears to have existed since the code started clearing dangerous personality bits. History Tree: git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git Fixes: 1bb0fa189c6a ("[PATCH] NX: clean up legacy binary support") Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 5 +++++ include/linux/lsm_hooks.h | 2 ++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 7fc05929c967..50025ead0b72 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -55,6 +55,11 @@ struct linux_binprm { struct file * file; struct cred *cred; /* new credentials */ int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ + /* + * bits to clear in current->personality + * recalculated for each bprm->file. + */ + unsigned int pf_per_clear; unsigned int per_clear; /* bits to clear in current->personality */ int argc, envc; const char * filename; /* Name of binary as seen by procps */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d618ecc4d660..f68076d440f3 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -55,6 +55,8 @@ * transitions between security domains). * The hook must set @bprm->active_secureexec to 1 if AT_SECURE should be set to * request libc enable secure mode. + * The hook must add to @bprm->pf_per_clear any personality flags that + * should be cleared from current->personality. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. * @bprm_check_security: -- cgit v1.2.3 From 56305aa9b6fab91a5555a45796b79c1b0a6353d1 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 29 May 2020 22:00:54 -0500 Subject: exec: Compute file based creds only once Move the computation of creds from prepare_binfmt into begin_new_exec so that the creds need only be computed once. This is just code reorganization no semantic changes of any kind are made. Moving the computation is safe. I have looked through the kernel and verified none of the binfmts look at bprm->cred directly, and that there are no helpers that look at bprm->cred indirectly. Which means that it is not a problem to compute the bprm->cred later in the execution flow as it is not used until it becomes current->cred. A new function bprm_creds_from_file is added to contain the work that needs to be done. bprm_creds_from_file first computes which file bprm->executable or most likely bprm->file that the bprm->creds will be computed from. The funciton bprm_fill_uid is updated to receive the file instead of accessing bprm->file. The now unnecessary work needed to reset the bprm->cred->euid, and bprm->cred->egid is removed from brpm_fill_uid. A small comment to document that bprm_fill_uid now only deals with the work to handle suid and sgid files. The default case is already heandled by prepare_exec_creds. The function security_bprm_repopulate_creds is renamed security_bprm_creds_from_file and now is explicitly passed the file from which to compute the creds. The documentation of the bprm_creds_from_file security hook is updated to explain when the hook is called and what it needs to do. The file is passed from cap_bprm_creds_from_file into get_file_caps so that the caps are computed for the appropriate file. The now unnecessary work in cap_bprm_creds_from_file to reset the ambient capabilites has been removed. A small comment to document that the work of cap_bprm_creds_from_file is to read capabilities from the files secureity attribute and derive capabilities from the fact the user had uid 0 has been added. Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 14 ++------------ include/linux/lsm_hook_defs.h | 2 +- include/linux/lsm_hooks.h | 22 +++++++++++----------- include/linux/security.h | 9 +++++---- 4 files changed, 19 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 50025ead0b72..aece1b340e7d 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -29,13 +29,8 @@ struct linux_binprm { /* Should an execfd be passed to userspace? */ have_execfd:1, - /* It is safe to use the creds of a script (see binfmt_misc) */ - preserve_creds:1, - /* - * True if most recent call to security_bprm_set_creds - * resulted in elevated privileges. - */ - active_secureexec:1, + /* Use the creds of a script (see binfmt_misc) */ + execfd_creds:1, /* * Set by bprm_creds_for_exec hook to indicate a * privilege-gaining exec has happened. Used to set @@ -55,11 +50,6 @@ struct linux_binprm { struct file * file; struct cred *cred; /* new credentials */ int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ - /* - * bits to clear in current->personality - * recalculated for each bprm->file. - */ - unsigned int pf_per_clear; unsigned int per_clear; /* bits to clear in current->personality */ int argc, envc; const char * filename; /* Name of binary as seen by procps */ diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 1e295ba12c0d..adbc6603abba 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -50,7 +50,7 @@ LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) -LSM_HOOK(int, 0, bprm_repopulate_creds, struct linux_binprm *bprm) +LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, struct file *file) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index f68076d440f3..c523c18efa0e 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -44,18 +44,18 @@ * request libc enable secure mode. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. - * @bprm_repopulate_creds: - * Assuming that the relevant bits of @bprm->cred->security have been - * previously set, examine @bprm->file and regenerate them. This is - * so that the credentials derived from the interpreter the code is - * actually going to run are used rather than credentials derived - * from a script. This done because the interpreter binary needs to - * reopen script, and may end up opening something completely different. - * This hook may also optionally check permissions (e.g. for - * transitions between security domains). - * The hook must set @bprm->active_secureexec to 1 if AT_SECURE should be set to + * @bprm_creds_from_file: + * If @file is setpcap, suid, sgid or otherwise marked to change + * privilege upon exec, update @bprm->cred to reflect that change. + * This is called after finding the binary that will be executed. + * without an interpreter. This ensures that the credentials will not + * be derived from a script that the binary will need to reopen, which + * when reopend may end up being a completely different file. This + * hook may also optionally check permissions (e.g. for transitions + * between security domains). + * The hook must set @bprm->secureexec to 1 if AT_SECURE should be set to * request libc enable secure mode. - * The hook must add to @bprm->pf_per_clear any personality flags that + * The hook must add to @bprm->per_clear any personality flags that * should be cleared from current->personality. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. diff --git a/include/linux/security.h b/include/linux/security.h index 6dcec9375e8f..8444fae7c5b9 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -140,7 +140,7 @@ extern int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); -extern int cap_bprm_repopulate_creds(struct linux_binprm *bprm); +extern int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file); extern int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); extern int cap_inode_removexattr(struct dentry *dentry, const char *name); @@ -277,7 +277,7 @@ int security_syslog(int type); int security_settime64(const struct timespec64 *ts, const struct timezone *tz); int security_vm_enough_memory_mm(struct mm_struct *mm, long pages); int security_bprm_creds_for_exec(struct linux_binprm *bprm); -int security_bprm_repopulate_creds(struct linux_binprm *bprm); +int security_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file); int security_bprm_check(struct linux_binprm *bprm); void security_bprm_committing_creds(struct linux_binprm *bprm); void security_bprm_committed_creds(struct linux_binprm *bprm); @@ -575,9 +575,10 @@ static inline int security_bprm_creds_for_exec(struct linux_binprm *bprm) return 0; } -static inline int security_bprm_repopulate_creds(struct linux_binprm *bprm) +static inline int security_bprm_creds_from_file(struct linux_binprm *bprm, + struct file *file) { - return cap_bprm_repopulate_creds(bprm); + return cap_bprm_creds_from_file(bprm, file); } static inline int security_bprm_check(struct linux_binprm *bprm) -- cgit v1.2.3 From 2553f421f44f4db7579f202b79b69046b579c7b5 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Wed, 27 May 2020 23:16:02 -0700 Subject: net/mlx5: cmd: Fix memset with byte count warning Fix sparse warning: drivers/net/ethernet/mellanox/mlx5/core/cmd.c:1949:15: warning: memset with byte count of 271720 mlx5_cmd_stats array is too big to be held inline in mlx5_cmd. Allocate it separately. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6aa6bbd60559..13c0e4556eda 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -298,7 +298,7 @@ struct mlx5_cmd { struct mlx5_cmd_debug dbg; struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES]; int checksum_disabled; - struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX]; + struct mlx5_cmd_stats *stats; }; struct mlx5_port_caps { -- cgit v1.2.3 From 44345c4c130ee3df9b9fbc366d59ab3ac707d7f8 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 29 May 2020 00:47:12 -0700 Subject: net/mlx5: IPSec: Fix incorrect type for spi spi is __be32, fix that. Fixes sparse warning: drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c:74:64 warning: incorrect type Signed-off-by: Saeed Mahameed --- include/linux/mlx5/accel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index b919d143a9a6..96ebaa94a92e 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -76,7 +76,7 @@ struct aes_gcm_keymat { struct mlx5_accel_esp_xfrm_attrs { enum mlx5_accel_esp_action action; u32 esn; - u32 spi; + __be32 spi; u32 seq; u32 tfc_pad; u32 flags; -- cgit v1.2.3 From 563ca40ddf400dbf8c6254077f9b6887101d0f08 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 8 May 2020 09:16:02 -0700 Subject: pstore/platform: Switch pstore_info::name to const In order to more cleanly pass around backend names, make the "name" member const. This means the module param needs to be dynamic (technically, it was before, so this actually cleans up a minor memory leak if a backend was specified and then gets unloaded.) Link: https://lore.kernel.org/lkml/20200510202436.63222-3-keescook@chromium.org/ Signed-off-by: Kees Cook --- include/linux/pstore.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index e779441e6d26..f6f22b13e04f 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -170,7 +170,7 @@ struct pstore_record { */ struct pstore_info { struct module *owner; - char *name; + const char *name; struct semaphore buf_lock; char *buf; -- cgit v1.2.3 From 6d3cf962dd1a95df868c547b090bfc4c7977f4be Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 15 May 2020 11:05:43 -0700 Subject: printk: Collapse shutdown types into a single dump reason To turn the KMSG_DUMP_* reasons into a more ordered list, collapse the redundant KMSG_DUMP_(RESTART|HALT|POWEROFF) reasons into KMSG_DUMP_SHUTDOWN. The current users already don't meaningfully distinguish between them, so there's no need to, as discussed here: https://lore.kernel.org/lkml/CA+CK2bAPv5u1ih5y9t5FUnTyximtFCtDYXJCpuyjOyHNOkRdqw@mail.gmail.com/ Link: https://lore.kernel.org/lkml/20200515184434.8470-2-keescook@chromium.org/ Reviewed-by: Pavel Tatashin Reviewed-by: Petr Mladek Acked-by: Michael Ellerman (powerpc) Signed-off-by: Kees Cook --- include/linux/kmsg_dump.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 2e7a1e032c71..3f82b5cb2d82 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -25,9 +25,7 @@ enum kmsg_dump_reason { KMSG_DUMP_PANIC, KMSG_DUMP_OOPS, KMSG_DUMP_EMERG, - KMSG_DUMP_RESTART, - KMSG_DUMP_HALT, - KMSG_DUMP_POWEROFF, + KMSG_DUMP_SHUTDOWN, }; /** -- cgit v1.2.3 From b1f6f161b236d0e5a9222fb8b482e65aaff13689 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Tue, 5 May 2020 11:45:06 -0400 Subject: printk: honor the max_reason field in kmsg_dumper kmsg_dump() allows to dump kmesg buffer for various system events: oops, panic, reboot, etc. It provides an interface to register a callback call for clients, and in that callback interface there is a field "max_reason", but it was getting ignored when set to any "reason" higher than KMSG_DUMP_OOPS unless "always_kmsg_dump" was passed as kernel parameter. Allow clients to actually control their "max_reason", and keep the current behavior when "max_reason" is not set. Signed-off-by: Pavel Tatashin Link: https://lore.kernel.org/lkml/20200515184434.8470-3-keescook@chromium.org/ Reviewed-by: Petr Mladek Signed-off-by: Kees Cook --- include/linux/kmsg_dump.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 3f82b5cb2d82..9826014771ab 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -26,6 +26,7 @@ enum kmsg_dump_reason { KMSG_DUMP_OOPS, KMSG_DUMP_EMERG, KMSG_DUMP_SHUTDOWN, + KMSG_DUMP_MAX }; /** -- cgit v1.2.3 From fb13cb8a0482105a415e24042209d02a684255e2 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 7 May 2020 19:36:22 -0700 Subject: printk: Introduce kmsg_dump_reason_str() The pstore subsystem already had a private version of this function. With the coming addition of the pstore/zone driver, this needs to be shared. As it really should live with printk, move it there instead. Link: https://lore.kernel.org/lkml/20200515184434.8470-4-keescook@chromium.org/ Acked-by: Petr Mladek Acked-by: Sergey Senozhatsky Reviewed-by: Pavel Tatashin Signed-off-by: Kees Cook --- include/linux/kmsg_dump.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 9826014771ab..3378bcbe585e 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -70,6 +70,8 @@ void kmsg_dump_rewind(struct kmsg_dumper *dumper); int kmsg_dump_register(struct kmsg_dumper *dumper); int kmsg_dump_unregister(struct kmsg_dumper *dumper); + +const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason); #else static inline void kmsg_dump(enum kmsg_dump_reason reason) { @@ -111,6 +113,11 @@ static inline int kmsg_dump_unregister(struct kmsg_dumper *dumper) { return -EINVAL; } + +static inline const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) +{ + return "Disabled"; +} #endif #endif /* _LINUX_KMSG_DUMP_H */ -- cgit v1.2.3 From 3524e688b8ee50b0edc76f0e020727eb6c684dbc Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Tue, 5 May 2020 11:45:07 -0400 Subject: pstore/platform: Pass max_reason to kmesg dump Add a new member to struct pstore_info for passing information about kmesg dump maximum reason. This allows a finer control of what kmesg dumps are sent to pstore storage backends. Those backends that do not explicitly set this field (keeping it equal to 0), get the default behavior: store only Oopses and Panics, or everything if the printk.always_kmsg_dump boot param is set. Signed-off-by: Pavel Tatashin Link: https://lore.kernel.org/lkml/20200515184434.8470-5-keescook@chromium.org/ Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index f6f22b13e04f..eb93a54cff31 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -96,6 +96,12 @@ struct pstore_record { * * @read_mutex: serializes @open, @read, @close, and @erase callbacks * @flags: bitfield of frontends the backend can accept writes for + * @max_reason: Used when PSTORE_FLAGS_DMESG is set. Contains the + * kmsg_dump_reason enum value. KMSG_DUMP_UNDEF means + * "use existing kmsg_dump() filtering, based on the + * printk.always_kmsg_dump boot param" (which is either + * KMSG_DUMP_OOPS when false, or KMSG_DUMP_MAX when + * true); see printk.always_kmsg_dump for more details. * @data: backend-private pointer passed back during callbacks * * Callbacks: @@ -179,6 +185,7 @@ struct pstore_info { struct mutex read_mutex; int flags; + int max_reason; void *data; int (*open)(struct pstore_info *psi); -- cgit v1.2.3 From 791205e3ec6081a8da6f00621e3453d622dc41e7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 13 May 2020 14:35:03 -0700 Subject: pstore/ram: Introduce max_reason and convert dump_oops Now that pstore_register() can correctly pass max_reason to the kmesg dump facility, introduce a new "max_reason" module parameter and "max-reason" Device Tree field. The "dump_oops" module parameter and "dump-oops" Device Tree field are now considered deprecated, but are now automatically converted to their corresponding max_reason values when present, though the new max_reason setting has precedence. For struct ramoops_platform_data, the "dump_oops" member is entirely replaced by a new "max_reason" member, with the only existing user updated in place. Additionally remove the "reason" filter logic from ramoops_pstore_write(), as that is not specifically needed anymore, though technically this is a change in behavior for any ramoops users also setting the printk.always_kmsg_dump boot param, which will cause ramoops to behave as if max_reason was set to KMSG_DUMP_MAX. Co-developed-by: Pavel Tatashin Signed-off-by: Pavel Tatashin Link: https://lore.kernel.org/lkml/20200515184434.8470-6-keescook@chromium.org/ Signed-off-by: Kees Cook --- include/linux/pstore_ram.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 9cb9b9067298..9f16afec7290 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -133,7 +133,7 @@ struct ramoops_platform_data { unsigned long console_size; unsigned long ftrace_size; unsigned long pmsg_size; - int dump_oops; + int max_reason; u32 flags; struct persistent_ram_ecc_info ecc_info; }; -- cgit v1.2.3 From d26c3321fe18dc74517dc1f518d584aa33b0a851 Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:54:56 +0800 Subject: pstore/zone: Introduce common layer to manage storage zones Implement a common set of APIs needed to support pstore storage zones, based on how ramoops is designed. This will be used by pstore/blk with the intention of migrating pstore/ram in the future. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-2-keescook@chromium.org/ Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore_zone.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 include/linux/pstore_zone.h (limited to 'include/linux') diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h new file mode 100644 index 000000000000..eb005d9ae40c --- /dev/null +++ b/include/linux/pstore_zone.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __PSTORE_ZONE_H_ +#define __PSTORE_ZONE_H_ + +#include + +typedef ssize_t (*pstore_zone_read_op)(char *, size_t, loff_t); +typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); +/** + * struct pstore_zone_info - pstore/zone back-end driver structure + * + * @owner: Module which is responsible for this back-end driver. + * @name: Name of the back-end driver. + * @total_size: The total size in bytes pstore/zone can use. It must be greater + * than 4096 and be multiple of 4096. + * @kmsg_size: The size of oops/panic zone. Zero means disabled, otherwise, + * it must be multiple of SECTOR_SIZE(512 Bytes). + * @max_reason: Maximum kmsg dump reason to store. + * @read: The general read operation. Both of the function parameters + * @size and @offset are relative value to storage. + * On success, the number of bytes should be returned, others + * means error. + * @write: The same as @read. + * @panic_write:The write operation only used for panic case. It's optional + * if you do not care panic log. The parameters and return value + * are the same as @read. + */ +struct pstore_zone_info { + struct module *owner; + const char *name; + + unsigned long total_size; + unsigned long kmsg_size; + int max_reason; + pstore_zone_read_op read; + pstore_zone_write_op write; + pstore_zone_write_op panic_write; +}; + +extern int register_pstore_zone(struct pstore_zone_info *info); +extern void unregister_pstore_zone(struct pstore_zone_info *info); + +#endif -- cgit v1.2.3 From 17639f67c1d61aba3c05e7703f75cd468f9d484f Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:54:57 +0800 Subject: pstore/blk: Introduce backend for block devices pstore/blk is similar to pstore/ram, but uses a block device as the storage rather than persistent ram. The pstore/blk backend solves two common use-cases that used to preclude using pstore/ram: - not all devices have a battery that could be used to persist regular RAM across power failures. - most embedded intelligent equipment have no persistent ram, which increases costs, instead preferring cheaper solutions, like block devices. pstore/blk provides separate configurations for the end user and for the block drivers. User configuration determines how pstore/blk operates, such as record sizes, max kmsg dump reasons, etc. These can be set by Kconfig and/or module parameters, but module parameter have priority over Kconfig. Driver configuration covers all the details about the target block device, such as total size of the device and how to perform read/write operations. These are provided by block drivers, calling pstore_register_blkdev(), including an optional panic_write callback used to bypass regular IO APIs in an effort to avoid potentially destabilized kernel code during a panic. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-3-keescook@chromium.org/ Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore_blk.h | 51 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 include/linux/pstore_blk.h (limited to 'include/linux') diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h new file mode 100644 index 000000000000..4501977b1336 --- /dev/null +++ b/include/linux/pstore_blk.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __PSTORE_BLK_H_ +#define __PSTORE_BLK_H_ + +#include +#include +#include + +/** + * typedef pstore_blk_panic_write_op - panic write operation to block device + * + * @buf: the data to write + * @start_sect: start sector to block device + * @sects: sectors count on buf + * + * Return: On success, zero should be returned. Others mean error. + * + * Panic write to block device must be aligned to SECTOR_SIZE. + */ +typedef int (*pstore_blk_panic_write_op)(const char *buf, sector_t start_sect, + sector_t sects); + +/** + * struct pstore_blk_info - pstore/blk registration details + * + * @major: Which major device number to support with pstore/blk + * @flags: The supported PSTORE_FLAGS_* from linux/pstore.h. + * @panic_write:The write operation only used for the panic case. + * This can be NULL, but is recommended to avoid losing + * crash data if the kernel's IO path or work queues are + * broken during a panic. + * @devt: The dev_t that pstore/blk has attached to. + * @nr_sects: Number of sectors on @devt. + * @start_sect: Starting sector on @devt. + */ +struct pstore_blk_info { + unsigned int major; + unsigned int flags; + pstore_blk_panic_write_op panic_write; + + /* Filled in by pstore/blk after registration. */ + dev_t devt; + sector_t nr_sects; + sector_t start_sect; +}; + +int register_pstore_blk(struct pstore_blk_info *info); +void unregister_pstore_blk(unsigned int major); + +#endif -- cgit v1.2.3 From 0dc068265a1c5923ffebf40388fbe93050a77ad1 Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:54:59 +0800 Subject: pstore/zone,blk: Add support for pmsg frontend Add pmsg support to pstore/blk (through pstore/zone). To enable, pmsg_size must be greater than 0 and a multiple of 4096. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-4-keescook@chromium.org/ Co-developed-by: Colin Ian King Signed-off-by: Colin Ian King Link: https://lore.kernel.org/lkml/20200512171932.222102-1-colin.king@canonical.com Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore_zone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h index eb005d9ae40c..29c367a3bd80 100644 --- a/include/linux/pstore_zone.h +++ b/include/linux/pstore_zone.h @@ -17,6 +17,7 @@ typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); * @kmsg_size: The size of oops/panic zone. Zero means disabled, otherwise, * it must be multiple of SECTOR_SIZE(512 Bytes). * @max_reason: Maximum kmsg dump reason to store. + * @pmsg_size: The size of pmsg zone which is the same as @kmsg_size. * @read: The general read operation. Both of the function parameters * @size and @offset are relative value to storage. * On success, the number of bytes should be returned, others @@ -33,6 +34,7 @@ struct pstore_zone_info { unsigned long total_size; unsigned long kmsg_size; int max_reason; + unsigned long pmsg_size; pstore_zone_read_op read; pstore_zone_write_op write; pstore_zone_write_op panic_write; -- cgit v1.2.3 From cc9c4d1b5597167f8e8c92f6b61e1cda6d01884d Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:55:00 +0800 Subject: pstore/zone,blk: Add console frontend support Support backend for console. To enable console backend, just make console_size be greater than 0 and a multiple of 4096. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-5-keescook@chromium.org/ Signed-off-by: Kees Cook --- include/linux/pstore_zone.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h index 29c367a3bd80..904ee67f4ba2 100644 --- a/include/linux/pstore_zone.h +++ b/include/linux/pstore_zone.h @@ -18,11 +18,12 @@ typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); * it must be multiple of SECTOR_SIZE(512 Bytes). * @max_reason: Maximum kmsg dump reason to store. * @pmsg_size: The size of pmsg zone which is the same as @kmsg_size. + * @console_size:The size of console zone which is the same as @kmsg_size. * @read: The general read operation. Both of the function parameters * @size and @offset are relative value to storage. * On success, the number of bytes should be returned, others * means error. - * @write: The same as @read. + * @write: The same as @read, but -EBUSY means try to write again later. * @panic_write:The write operation only used for panic case. It's optional * if you do not care panic log. The parameters and return value * are the same as @read. @@ -35,6 +36,7 @@ struct pstore_zone_info { unsigned long kmsg_size; int max_reason; unsigned long pmsg_size; + unsigned long console_size; pstore_zone_read_op read; pstore_zone_write_op write; pstore_zone_write_op panic_write; -- cgit v1.2.3 From 34327e9fd213414b35eb70aa512c4e39b2095907 Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:55:01 +0800 Subject: pstore/zone,blk: Add ftrace frontend support Support backend for ftrace. To enable ftrace backend, just make ftrace_size be greater than 0 and a multiple of 4096. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-6-keescook@chromium.org/ Co-developed-by: Colin Ian King Signed-off-by: Colin Ian King Link: https://lore.kernel.org/lkml/20200512170719.221514-1-colin.king@canonical.com Signed-off-by: Kees Cook --- include/linux/pstore_zone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h index 904ee67f4ba2..6f16b0dd834a 100644 --- a/include/linux/pstore_zone.h +++ b/include/linux/pstore_zone.h @@ -19,6 +19,7 @@ typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); * @max_reason: Maximum kmsg dump reason to store. * @pmsg_size: The size of pmsg zone which is the same as @kmsg_size. * @console_size:The size of console zone which is the same as @kmsg_size. + * @ftrace_size:The size of ftrace zone which is the same as @kmsg_size. * @read: The general read operation. Both of the function parameters * @size and @offset are relative value to storage. * On success, the number of bytes should be returned, others @@ -37,6 +38,7 @@ struct pstore_zone_info { int max_reason; unsigned long pmsg_size; unsigned long console_size; + unsigned long ftrace_size; pstore_zone_read_op read; pstore_zone_write_op write; pstore_zone_write_op panic_write; -- cgit v1.2.3 From 9630a055256de420d528ecde9f35902a9dcd8750 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 19 May 2020 15:00:35 +0200 Subject: mtd: rawnand: Stop using nand_release() This helper is not very useful and very often people get confused: they use nand_release() instead of nand_cleanup(). Now that all drivers have been converted to do not use nand_release() anymore, let's remove this helper. Signed-off-by: Miquel Raynal Cc: Jonathan Corbet Link: https://lore.kernel.org/linux-mtd/20200519130035.1883-63-miquel.raynal@bootlin.com --- include/linux/mtd/bbm.h | 2 +- include/linux/mtd/rawnand.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/bbm.h b/include/linux/mtd/bbm.h index 886e30441c90..d890805f5494 100644 --- a/include/linux/mtd/bbm.h +++ b/include/linux/mtd/bbm.h @@ -98,7 +98,7 @@ struct nand_bbt_descr { /* * Flag set by nand_create_default_bbt_descr(), marking that the nand_bbt_descr - * was allocated dynamicaly and must be freed in nand_release(). Has no meaning + * was allocated dynamicaly and must be freed in nand_cleanup(). Has no meaning * in nand_chip.bbt_options. */ #define NAND_BBT_DYNAMICSTRUCT 0x80000000 diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 2804c13e5662..b0b358908a47 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1398,8 +1398,6 @@ void nand_wait_ready(struct nand_chip *chip); * sucessful nand_scan(). */ void nand_cleanup(struct nand_chip *chip); -/* Unregister the MTD device and calls nand_cleanup() */ -void nand_release(struct nand_chip *chip); /* * External helper for controller drivers that have to implement the WAITRDY -- cgit v1.2.3 From f66a6fd0dc7cc49c891a167937e161114f48a62e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 26 May 2020 21:56:14 +0200 Subject: mtd: rawnand: Avoid a typedef In new code, the use of typedef is discouraged. Turn this one in the raw NAND core into a regular enumeration. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200526195633.11543-3-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 6 +++--- include/linux/platform_data/mtd-davinci.h | 2 +- include/linux/platform_data/mtd-nand-s3c2410.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index b0b358908a47..8f662df02fdd 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -83,14 +83,14 @@ struct nand_chip; /* * Constants for ECC_MODES */ -typedef enum { +enum nand_ecc_mode { NAND_ECC_NONE, NAND_ECC_SOFT, NAND_ECC_HW, NAND_ECC_HW_SYNDROME, NAND_ECC_HW_OOB_FIRST, NAND_ECC_ON_DIE, -} nand_ecc_modes_t; +}; enum nand_ecc_algo { NAND_ECC_UNKNOWN, @@ -362,7 +362,7 @@ static const struct nand_ecc_caps __name = { \ * @write_oob: function to write chip OOB data */ struct nand_ecc_ctrl { - nand_ecc_modes_t mode; + enum nand_ecc_mode mode; enum nand_ecc_algo algo; int steps; int size; diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h index 08e639e047e5..03e92c71b3fa 100644 --- a/include/linux/platform_data/mtd-davinci.h +++ b/include/linux/platform_data/mtd-davinci.h @@ -68,7 +68,7 @@ struct davinci_nand_pdata { /* platform_data */ * Newer ones also support 4-bit ECC, but are awkward * using it with large page chips. */ - nand_ecc_modes_t ecc_mode; + enum nand_ecc_mode ecc_mode; u8 ecc_bits; /* e.g. NAND_BUSWIDTH_16 */ diff --git a/include/linux/platform_data/mtd-nand-s3c2410.h b/include/linux/platform_data/mtd-nand-s3c2410.h index deb849bcf0ec..08675b16f9e1 100644 --- a/include/linux/platform_data/mtd-nand-s3c2410.h +++ b/include/linux/platform_data/mtd-nand-s3c2410.h @@ -49,7 +49,7 @@ struct s3c2410_platform_nand { unsigned int ignore_unset_ecc:1; - nand_ecc_modes_t ecc_mode; + enum nand_ecc_mode ecc_mode; int nr_sets; struct s3c2410_nand_set *sets; -- cgit v1.2.3 From 74e24cd2376d9cc4cfc6edad8610780b79fd5def Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 26 May 2020 21:56:15 +0200 Subject: mtd: rawnand: Drop OOB_FIRST placement scheme This scheme has been introduced for the Davinci controller and means that the OOB area must be read *before* the rest of the data. This has nothing to do with the ECC in OOB placement as it could be understood and most importantly, there is no point in having this function out of the Davinci NAND controller driver. A DT property for this scheme has been added but never used, even by the Davinci driver which only uses this scheme to change the default nand_read_page(). Move the main read_page() helper into the Davinci driver and remove the remaining boilerplate. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200526195633.11543-4-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 8f662df02fdd..605d64ead3a8 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -88,7 +88,6 @@ enum nand_ecc_mode { NAND_ECC_SOFT, NAND_ECC_HW, NAND_ECC_HW_SYNDROME, - NAND_ECC_HW_OOB_FIRST, NAND_ECC_ON_DIE, }; -- cgit v1.2.3 From 86f2b225adf4ecd2edfdc8541a7342645556ac3b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 26 May 2020 21:56:18 +0200 Subject: mtd: rawnand: Add an invalid ECC mode to discriminate with valid ones NAND ECC modes (or providers) have their own enumeration but, unlike their algorithms counterpart, there is no invalid or uninitialized value to discriminate between an error and having chosen a no-ECC situation. Add an "invalid" entry for this purpose. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200526195633.11543-7-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 605d64ead3a8..65b1c1c18b41 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -84,6 +84,7 @@ struct nand_chip; * Constants for ECC_MODES */ enum nand_ecc_mode { + NAND_ECC_INVALID, NAND_ECC_NONE, NAND_ECC_SOFT, NAND_ECC_HW, -- cgit v1.2.3 From 372b38ea5911fc2500f0291b00140e80a26c0e36 Mon Sep 17 00:00:00 2001 From: Tova Mussai Date: Thu, 28 May 2020 21:34:26 +0200 Subject: ieee80211: definitions for reduced neighbor reports Add the necessary definitions to parse reduced neighbor report elements. Signed-off-by: Tova Mussai [change struct name, remove IEEE80211_MIN_AP_NEIGHBOR_INFO_SIZE] Link: https://lore.kernel.org/r/20200528213443.4f9154461c06.I518d9898ad982f838112ea9ca14a20d6bbb16394@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 0320ca4c7d28..c29184bf9416 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2754,6 +2754,8 @@ enum ieee80211_eid { WLAN_EID_QUIET_CHANNEL = 198, WLAN_EID_OPMODE_NOTIF = 199, + WLAN_EID_REDUCED_NEIGHBOR_REPORT = 201, + WLAN_EID_S1G_BCN_COMPAT = 213, WLAN_EID_S1G_SHORT_BCN_INTERVAL = 214, WLAN_EID_S1G_CAPABILITIES = 217, @@ -3675,4 +3677,30 @@ static inline bool for_each_element_completed(const struct element *element, #define WLAN_RSNX_CAPA_PROTECTED_TWT BIT(4) #define WLAN_RSNX_CAPA_SAE_H2E BIT(5) +/* + * reduced neighbor report, based on Draft P802.11ax_D5.0, + * section 9.4.2.170 + */ +#define IEEE80211_AP_INFO_TBTT_HDR_TYPE 0x03 +#define IEEE80211_AP_INFO_TBTT_HDR_FILTERED 0x04 +#define IEEE80211_AP_INFO_TBTT_HDR_COLOC 0x08 +#define IEEE80211_AP_INFO_TBTT_HDR_COUNT 0xF0 +#define IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM 8 +#define IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM 12 + +#define IEEE80211_RNR_TBTT_PARAMS_OCT_RECOMMENDED 0x01 +#define IEEE80211_RNR_TBTT_PARAMS_SAME_SSID 0x02 +#define IEEE80211_RNR_TBTT_PARAMS_MULTI_BSSID 0x04 +#define IEEE80211_RNR_TBTT_PARAMS_TRANSMITTED_BSSID 0x08 +#define IEEE80211_RNR_TBTT_PARAMS_COLOC_ESS 0x10 +#define IEEE80211_RNR_TBTT_PARAMS_PROBE_ACTIVE 0x20 +#define IEEE80211_RNR_TBTT_PARAMS_COLOC_AP 0x40 + +struct ieee80211_neighbor_ap_info { + u8 tbtt_info_hdr; + u8 tbtt_info_len; + u8 op_class; + u8 channel; +} __packed; + #endif /* LINUX_IEEE80211_H */ -- cgit v1.2.3 From 821273a5a502eebaae005557907d122d1e9b7b98 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 28 May 2020 21:34:27 +0200 Subject: ieee80211: add code to obtain and parse 6 GHz operation field Add some code to obtain and parse the 6 GHz operation field inside the HE operation element. While at it, fix the required length using sizeof() the new struct, which is 5 instead of 4 now. Link: https://lore.kernel.org/r/20200528213443.42ca72c45ca9.Id74bc1b03da9ea6574f9bc70deeb60dfc1634359@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 51 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index c29184bf9416..2bd9e757167d 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2209,6 +2209,28 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 +/** + * ieee80211_he_6ghz_oper - HE 6 GHz operation Information field + * @primary: primary channel + * @control: control flags + * @ccfs0: channel center frequency segment 0 + * @ccfs1: channel center frequency segment 1 + * @minrate: minimum rate (in 1 Mbps units) + */ +struct ieee80211_he_6ghz_oper { + u8 primary; +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH 0x3 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ 0 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ 1 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ 2 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ 3 +#define IEEE80211_HE_6GHZ_OPER_CTRL_DUP_BEACON 0x4 + u8 control; + u8 ccfs0; + u8 ccfs1; + u8 minrate; +} __packed; + /* * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size * @he_oper_ie: byte data of the He Operations IE, stating from the byte @@ -2235,7 +2257,7 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) oper_len++; if (he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO) - oper_len += 4; + oper_len += sizeof(struct ieee80211_he_6ghz_oper); /* Add the first byte (extension ID) to the total length */ oper_len++; @@ -2243,6 +2265,34 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) return oper_len; } +/** + * ieee80211_he_6ghz_oper - obtain 6 GHz operation field + * @he_oper: HE operation element (must be pre-validated for size) + * but may be %NULL + * + * Return: a pointer to the 6 GHz operation field, or %NULL + */ +static inline const struct ieee80211_he_6ghz_oper * +ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) +{ + const u8 *ret = (void *)&he_oper->optional; + u32 he_oper_params; + + if (!he_oper) + return NULL; + + he_oper_params = le32_to_cpu(he_oper->he_oper_params); + + if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)) + return NULL; + if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) + ret += 3; + if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) + ret++; + + return (void *)ret; +} + /* HE Spatial Reuse defines */ #define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT 0x4 #define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT 0x8 -- cgit v1.2.3 From 8b30808d9be4183fab17f0b0e68eea88c94ff15a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 28 May 2020 21:34:28 +0200 Subject: ieee80211: add HE ext EIDs and 6 GHz capability defines Add the HE extended element IDs and the definitions for the HE 6 GHz band capabilities element, from Draft 5.0. Link: https://lore.kernel.org/r/20200528213443.1a6689fe093f.Ifdc5400fb01779351354daf38663ebeea03c9ad9@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2bd9e757167d..9580dfd9e2d1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2839,9 +2839,19 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_UORA = 37, WLAN_EID_EXT_HE_MU_EDCA = 38, WLAN_EID_EXT_HE_SPR = 39, + WLAN_EID_EXT_NDP_FEEDBACK_REPORT_PARAMSET = 41, + WLAN_EID_EXT_BSS_COLOR_CHG_ANN = 42, + WLAN_EID_EXT_QUIET_TIME_PERIOD_SETUP = 43, + WLAN_EID_EXT_ESS_REPORT = 45, + WLAN_EID_EXT_OPS = 46, + WLAN_EID_EXT_HE_BSS_LOAD = 47, WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME = 52, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION = 55, WLAN_EID_EXT_NON_INHERITANCE = 56, + WLAN_EID_EXT_KNOWN_BSSID = 57, + WLAN_EID_EXT_SHORT_SSID_LIST = 58, + WLAN_EID_EXT_HE_6GHZ_CAPA = 59, + WLAN_EID_EXT_UL_MU_POWER_CAPA = 60, }; /* Action category code */ @@ -3384,6 +3394,24 @@ struct ieee80211_tspec_ie { __le16 medium_time; } __packed; +struct ieee80211_he_6ghz_capa { + /* uses IEEE80211_HE_6GHZ_CAP_* below */ + __le16 capa; +} __packed; + +/* HE 6 GHz band capabilities */ +/* uses enum ieee80211_min_mpdu_spacing values */ +#define IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START 0x0007 +/* uses enum ieee80211_vht_max_ampdu_length_exp values */ +#define IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP 0x0038 +/* uses IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_* values */ +#define IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN 0x00c0 +/* WLAN_HT_CAP_SM_PS_* values */ +#define IEEE80211_HE_6GHZ_CAP_SM_PS 0x0600 +#define IEEE80211_HE_6GHZ_CAP_RD_RESPONDER 0x0800 +#define IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS 0x1000 +#define IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS 0x2000 + /** * ieee80211_get_qos_ctl - get pointer to qos control bytes * @hdr: the frame -- cgit v1.2.3 From 3b3ec3d52e8f72ec8c40477b96f23440a89000be Mon Sep 17 00:00:00 2001 From: Shaul Triebitz Date: Thu, 28 May 2020 21:34:37 +0200 Subject: mac80211: check the correct bit for EMA AP An AP supporting EMA (Enhanced Multi-BSSID advertisement) should set bit 83 in the extended capabilities IE (9.4.2.26 in the 802.11ax D5 spec). So the *3rd* bit of the 10th byte should be checked. Also, in one place, the wrong byte was checked. (cfg80211_find_ie returns a pointer to the beginning of the IE, so the data really starts at ie[2], so the 10th byte should be ie[12]. To avoid this confusion, use cfg80211_find_elem instead). Signed-off-by: Shaul Triebitz Link: https://lore.kernel.org/r/20200528213443.4316121fa2a3.I9745582f8d41ad8e689dac0fefcd70b276d7c1ea@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 9580dfd9e2d1..1ecfd19f836d 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -3082,7 +3082,7 @@ enum ieee80211_tdls_actioncode { #define WLAN_EXT_CAPA10_OBSS_NARROW_BW_RU_TOLERANCE_SUPPORT BIT(7) /* Defines support for enhanced multi-bssid advertisement*/ -#define WLAN_EXT_CAPA11_EMA_SUPPORT BIT(1) +#define WLAN_EXT_CAPA11_EMA_SUPPORT BIT(3) /* TDLS specific payload type in the LLC/SNAP header */ #define WLAN_TDLS_SNAP_RFTYPE 0x2 -- cgit v1.2.3 From 3f19b2ab97a97b413c24b66c67ae16daa4f56c35 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 1 Dec 2017 11:40:16 +0000 Subject: vfs, afs, ext4: Make the inode hash table RCU searchable Make the inode hash table RCU searchable so that searches that want to access or modify an inode without taking a ref on that inode can do so without taking the inode hash table lock. The main thing this requires is some RCU annotation on the list manipulation operations. Inodes are already freed by RCU in most cases. Users of this interface must take care as the inode may be still under construction or may be being torn down around them. There are at least three instances where this can be of use: (1) Testing whether the inode number iunique() is going to return is currently unique (the iunique_lock is still held). (2) Ext4 date stamp updating. (3) AFS callback breaking. Signed-off-by: David Howells Acked-by: Konstantin Khlebnikov cc: linux-ext4@vger.kernel.org cc: linux-afs@lists.infradead.org --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 45cc10cdf6dd..5f9b2bb4b44f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3070,6 +3070,9 @@ extern struct inode *find_inode_nowait(struct super_block *, int (*match)(struct inode *, unsigned long, void *), void *data); +extern struct inode *find_inode_rcu(struct super_block *, unsigned long, + int (*)(struct inode *, void *), void *); +extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC -- cgit v1.2.3 From 335426c6dcdd338d6b7c939c2da15fc9c5dd4959 Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:55:03 +0800 Subject: pstore/zone: Provide way to skip "broken" zone for MTD devices One requirement to support MTD devices in pstore/zone is having a way to declare certain regions as broken. Add this support to pstore/zone. The MTD driver should return -ENOMSG when encountering a bad region, which tells pstore/zone to skip and try the next one. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-8-keescook@chromium.org/ Co-developed-by: Colin Ian King Signed-off-by: Colin Ian King Link: //lore.kernel.org/lkml/20200512173801.222666-1-colin.king@canonical.com Signed-off-by: Kees Cook --- include/linux/pstore_blk.h | 3 ++- include/linux/pstore_zone.h | 12 ++++++++---- 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h index 4501977b1336..ccba8c068752 100644 --- a/include/linux/pstore_blk.h +++ b/include/linux/pstore_blk.h @@ -14,7 +14,8 @@ * @start_sect: start sector to block device * @sects: sectors count on buf * - * Return: On success, zero should be returned. Others mean error. + * Return: On success, zero should be returned. Others excluding -ENOMSG + * mean error. -ENOMSG means to try next zone. * * Panic write to block device must be aligned to SECTOR_SIZE. */ diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h index 6f16b0dd834a..e79a18e41064 100644 --- a/include/linux/pstore_zone.h +++ b/include/linux/pstore_zone.h @@ -23,11 +23,15 @@ typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); * @read: The general read operation. Both of the function parameters * @size and @offset are relative value to storage. * On success, the number of bytes should be returned, others - * means error. - * @write: The same as @read, but -EBUSY means try to write again later. + * mean error. + * @write: The same as @read, but the following error number: + * -EBUSY means try to write again later. + * -ENOMSG means to try next zone. * @panic_write:The write operation only used for panic case. It's optional - * if you do not care panic log. The parameters and return value - * are the same as @read. + * if you do not care panic log. The parameters are relative + * value to storage. + * On success, the number of bytes should be returned, others + * excluding -ENOMSG mean error. -ENOMSG means to try next zone. */ struct pstore_zone_info { struct module *owner; -- cgit v1.2.3 From 1525fb3bb6d69028b3941d34363397c28345ffab Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:55:04 +0800 Subject: pstore/blk: Provide way to query pstore configuration In order to configure itself, the MTD backend needs to be able to query the current pstore configuration. Introduce pstore_blk_get_config() for this purpose. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-9-keescook@chromium.org/ Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore_blk.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h index ccba8c068752..0c40774e71e0 100644 --- a/include/linux/pstore_blk.h +++ b/include/linux/pstore_blk.h @@ -49,4 +49,32 @@ struct pstore_blk_info { int register_pstore_blk(struct pstore_blk_info *info); void unregister_pstore_blk(unsigned int major); +/** + * struct pstore_blk_config - the pstore_blk backend configuration + * + * @device: Name of the desired block device + * @max_reason: Maximum kmsg dump reason to store to block device + * @kmsg_size: Total size of for kmsg dumps + * @pmsg_size: Total size of the pmsg storage area + * @console_size: Total size of the console storage area + * @ftrace_size: Total size for ftrace logging data (for all CPUs) + */ +struct pstore_blk_config { + char device[80]; + enum kmsg_dump_reason max_reason; + unsigned long kmsg_size; + unsigned long pmsg_size; + unsigned long console_size; + unsigned long ftrace_size; +}; + +/** + * pstore_blk_get_config - get a copy of the pstore_blk backend configuration + * + * @info: The sturct pstore_blk_config to be filled in + * + * Failure returns negative error code, and success returns 0. + */ +int pstore_blk_get_config(struct pstore_blk_config *info); + #endif -- cgit v1.2.3 From 7dcb7848ba110ff192efc917d1a6de66b4c9ca4f Mon Sep 17 00:00:00 2001 From: WeiXiong Liao Date: Wed, 25 Mar 2020 16:55:05 +0800 Subject: pstore/blk: Support non-block storage devices Add support for non-block devices (e.g. MTD). A non-block driver calls pstore_blk_register_device() to register iself. In addition, pstore/zone is updated to handle non-block devices, where an erase must be done before a write. Without this, there is no way to remove records stored to an MTD. Signed-off-by: WeiXiong Liao Link: https://lore.kernel.org/lkml/20200511233229.27745-10-keescook@chromium.org/ Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore_blk.h | 38 ++++++++++++++++++++++++++++++++++++++ include/linux/pstore_zone.h | 6 ++++++ 2 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h index 0c40774e71e0..61e914522b01 100644 --- a/include/linux/pstore_blk.h +++ b/include/linux/pstore_blk.h @@ -49,6 +49,44 @@ struct pstore_blk_info { int register_pstore_blk(struct pstore_blk_info *info); void unregister_pstore_blk(unsigned int major); +/** + * struct pstore_device_info - back-end pstore/blk driver structure. + * + * @total_size: The total size in bytes pstore/blk can use. It must be greater + * than 4096 and be multiple of 4096. + * @flags: Refer to macro starting with PSTORE_FLAGS defined in + * linux/pstore.h. It means what front-ends this device support. + * Zero means all backends for compatible. + * @read: The general read operation. Both of the function parameters + * @size and @offset are relative value to bock device (not the + * whole disk). + * On success, the number of bytes should be returned, others + * means error. + * @write: The same as @read, but the following error number: + * -EBUSY means try to write again later. + * -ENOMSG means to try next zone. + * @erase: The general erase operation for device with special removing + * job. Both of the function parameters @size and @offset are + * relative value to storage. + * Return 0 on success and others on failure. + * @panic_write:The write operation only used for panic case. It's optional + * if you do not care panic log. The parameters are relative + * value to storage. + * On success, the number of bytes should be returned, others + * excluding -ENOMSG mean error. -ENOMSG means to try next zone. + */ +struct pstore_device_info { + unsigned long total_size; + unsigned int flags; + pstore_zone_read_op read; + pstore_zone_write_op write; + pstore_zone_erase_op erase; + pstore_zone_write_op panic_write; +}; + +int register_pstore_device(struct pstore_device_info *dev); +void unregister_pstore_device(struct pstore_device_info *dev); + /** * struct pstore_blk_config - the pstore_blk backend configuration * diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h index e79a18e41064..1e35eaa33e5e 100644 --- a/include/linux/pstore_zone.h +++ b/include/linux/pstore_zone.h @@ -7,6 +7,7 @@ typedef ssize_t (*pstore_zone_read_op)(char *, size_t, loff_t); typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); +typedef ssize_t (*pstore_zone_erase_op)(size_t, loff_t); /** * struct pstore_zone_info - pstore/zone back-end driver structure * @@ -27,6 +28,10 @@ typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); * @write: The same as @read, but the following error number: * -EBUSY means try to write again later. * -ENOMSG means to try next zone. + * @erase: The general erase operation for device with special removing + * job. Both of the function parameters @size and @offset are + * relative value to storage. + * Return 0 on success and others on failure. * @panic_write:The write operation only used for panic case. It's optional * if you do not care panic log. The parameters are relative * value to storage. @@ -45,6 +50,7 @@ struct pstore_zone_info { unsigned long ftrace_size; pstore_zone_read_op read; pstore_zone_write_op write; + pstore_zone_erase_op erase; pstore_zone_write_op panic_write; }; -- cgit v1.2.3 From 0958f0cefede403037653e44de0e3332d10b0e1a Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 25 May 2020 16:41:19 +0200 Subject: KVM: introduce kvm_read_guest_offset_cached() We already have kvm_write_guest_offset_cached(), introduce read analogue. Signed-off-by: Vitaly Kuznetsov Message-Id: <20200525144125.143875-5-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 161684696610..f43b59b1294c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -734,6 +734,9 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); +int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, unsigned int offset, + unsigned long len); int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, -- cgit v1.2.3 From 97e27aaa9a2cbd6238c66b3251d397e0eacc9968 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 19 Mar 2020 23:45:01 -0400 Subject: ceph: add read/write latency metric support Calculate the latency for OSD read requests. Add a new r_end_stamp field to struct ceph_osd_request that will hold the time of that the reply was received. Use that to calculate the RTT for each call, and divide the sum of those by number of calls to get averate RTT. Keep a tally of RTT for OSD writes and number of calls to track average latency of OSD writes. URL: https://tracker.ceph.com/issues/43215 Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 9d9f745b98a1..734f7c6a9f56 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -213,6 +214,8 @@ struct ceph_osd_request { /* internal */ unsigned long r_stamp; /* jiffies, send or check time */ unsigned long r_start_stamp; /* jiffies */ + ktime_t r_start_latency; /* ktime_t */ + ktime_t r_end_latency; /* ktime_t */ int r_attempts; u32 r_map_dne_bound; -- cgit v1.2.3 From 53ab8e7cd2d47594e68951994ac083d30f82fce4 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:51:38 -0500 Subject: libceph, rbd: replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/mon_client.h | 2 +- include/linux/crush/crush.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index dbb8a6959a73..ce4ffeb384d7 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -19,7 +19,7 @@ struct ceph_monmap { struct ceph_fsid fsid; u32 epoch; u32 num_mon; - struct ceph_entity_inst mon_inst[0]; + struct ceph_entity_inst mon_inst[]; }; struct ceph_mon_client; diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 54741295c70b..38b0e4d50ed9 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -87,7 +87,7 @@ struct crush_rule_mask { struct crush_rule { __u32 len; struct crush_rule_mask mask; - struct crush_rule_step steps[0]; + struct crush_rule_step steps[]; }; #define crush_rule_size(len) (sizeof(struct crush_rule) + \ -- cgit v1.2.3 From 8a4b863c876d9f135fa00cfe65774c3740970303 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 19 May 2020 16:46:47 +0200 Subject: libceph: add non-asserting rbtree insertion helper Needed for the next commit and useful for ceph_pg_pool_info tree as well. I'm leaving the asserting helper in for now, but we should look at getting rid of it in the future. Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 525b7c3f1c81..4b5a47bcaba4 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -188,7 +188,7 @@ static inline int calc_pages_for(u64 off, u64 len) #define RB_CMP3WAY(a, b) ((a) < (b) ? -1 : (a) > (b)) #define DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, cmpexp, keyexp, nodefld) \ -static void insert_##name(struct rb_root *root, type *t) \ +static bool __insert_##name(struct rb_root *root, type *t) \ { \ struct rb_node **n = &root->rb_node; \ struct rb_node *parent = NULL; \ @@ -206,11 +206,17 @@ static void insert_##name(struct rb_root *root, type *t) \ else if (cmp > 0) \ n = &(*n)->rb_right; \ else \ - BUG(); \ + return false; \ } \ \ rb_link_node(&t->nodefld, parent, n); \ rb_insert_color(&t->nodefld, root); \ + return true; \ +} \ +static void __maybe_unused insert_##name(struct rb_root *root, type *t) \ +{ \ + if (!__insert_##name(root, t)) \ + BUG(); \ } \ static void erase_##name(struct rb_root *root, type *t) \ { \ -- cgit v1.2.3 From 86403a92c3c5c6c395983fdbfc5e2f29dc39279b Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 19 May 2020 17:09:52 +0200 Subject: libceph: decode CRUSH device/bucket types and names These would be matched with the provided client location to calculate the locality value. Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/crush/crush.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 38b0e4d50ed9..33c16f2de7f6 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -301,6 +301,12 @@ struct crush_map { __u32 *choose_tries; #else + /* device/bucket type id -> type name (CrushWrapper::type_map) */ + struct rb_root type_names; + + /* device/bucket id -> name (CrushWrapper::name_map) */ + struct rb_root names; + /* CrushWrapper::choose_args */ struct rb_root choose_args; #endif @@ -342,4 +348,10 @@ struct crush_work { struct crush_work_bucket **work; /* Per-bucket working store */ }; +#ifdef __KERNEL__ +/* osdmap.c */ +void clear_crush_names(struct rb_root *root); +void clear_choose_args(struct crush_map *c); +#endif + #endif -- cgit v1.2.3 From 45e6aa9f5592cd127367074f4822039cd8a825c3 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 22 May 2020 15:24:53 +0200 Subject: libceph: crush_location infrastructure Allow expressing client's location in terms of CRUSH hierarchy as a set of (bucket type name, bucket name) pairs. The userspace syntax "crush_location = key1=value1 key2=value2" is incompatible with mount options and needed adaptation. Key-value pairs are separated by '|' and we use ':' instead of '=' to separate keys from values. So for: crush_location = host=foo rack=bar one would write: crush_location=host:foo|rack:bar As in userspace, "multipath" locations are supported, so indicating locality for parallel hierarchies is possible: crush_location=rack:foo1|rack:foo2|datacenter:bar Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 1 + include/linux/ceph/osdmap.h | 16 +++++++++++++++- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 4b5a47bcaba4..4733959f1ec7 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -64,6 +64,7 @@ struct ceph_options { int num_mon; char *name; struct ceph_crypto_key *key; + struct rb_root crush_locs; }; /* diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 5e601975745f..8c9d18cc9f45 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -302,9 +302,23 @@ bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap, int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap, const struct ceph_pg *raw_pgid); +struct crush_loc { + char *cl_type_name; + char *cl_name; +}; + +struct crush_loc_node { + struct rb_node cl_node; + struct crush_loc cl_loc; /* pointers into cl_data */ + char cl_data[]; +}; + +int ceph_parse_crush_location(char *crush_location, struct rb_root *locs); +int ceph_compare_crush_locs(struct rb_root *locs1, struct rb_root *locs2); +void ceph_clear_crush_locs(struct rb_root *locs); + extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id); - extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id); extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name); u64 ceph_pg_pool_flags(struct ceph_osdmap *map, u64 id); -- cgit v1.2.3 From 117d96a04f007ce8fc2e292369056c3bd09f6f63 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sat, 23 May 2020 11:45:48 +0200 Subject: libceph: support for balanced and localized reads OSD-side issues with reads from replica have been resolved in Octopus. Reading from replica should be safe wrt. unstable or uncommitted state now, so add support for balanced and localized reads. There are two cases when a read from replica can't be served: - OSD may silently drop the request, expecting the client to notice that the acting set has changed and resend via the usual means (handled with t->used_replica) - OSD may return EAGAIN, expecting the client to resend to the primary, ignoring replica read flags (see handle_reply()) Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/osd_client.h | 1 + include/linux/ceph/osdmap.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 734f7c6a9f56..671fb93e8c60 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -165,6 +165,7 @@ struct ceph_osd_request_target { bool recovery_deletes; unsigned int flags; /* CEPH_OSD_FLAG_* */ + bool used_replica; bool paused; u32 epoch; diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 8c9d18cc9f45..3f4498fef6ad 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -317,6 +317,9 @@ int ceph_parse_crush_location(char *crush_location, struct rb_root *locs); int ceph_compare_crush_locs(struct rb_root *locs1, struct rb_root *locs2); void ceph_clear_crush_locs(struct rb_root *locs); +int ceph_get_crush_locality(struct ceph_osdmap *osdmap, int id, + struct rb_root *locs); + extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id); extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id); -- cgit v1.2.3 From 8ad44d5e0d1eda7e4a0ed382174888476dc81789 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sat, 23 May 2020 11:47:33 +0200 Subject: libceph: read_from_replica option Expose replica reads through read_from_replica=balance and read_from_replica=localize. The default is to read from primary (read_from_replica=no). Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 4733959f1ec7..2247e71beb83 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -53,6 +53,8 @@ struct ceph_options { unsigned long osd_keepalive_timeout; /* jiffies */ unsigned long osd_request_timeout; /* jiffies */ + u32 osd_req_flags; /* CEPH_OSD_FLAG_*, applied to each OSD request */ + /* * any type that can't be simply compared or doesn't need * to be compared should go beyond this point, -- cgit v1.2.3 From d43be2554b58621a21cb5f54b32db2263b3008b6 Mon Sep 17 00:00:00 2001 From: Bernard Zhao Date: Mon, 27 Apr 2020 01:05:23 -0700 Subject: drivers: video: hdmi: cleanup coding style in video a bit Eliminate the magic numbers, add vendor infoframe size macro like other hdmi modules. Signed-off-by: Bernard Zhao Cc: Uma Shankar Cc: Ville Syrjala Cc: Shashank Sharma Cc: Laurent Pinchart Cc: Daniel Vetter Cc: opensource.kernel@vivo.com [b.zolnierkie: add "hdmi" to the patch summary] [b.zolnierkie: fix "vender" -> vendor" typo in the patch description] Signed-off-by: Bartlomiej Zolnierkiewicz Link: https://patchwork.freedesktop.org/patch/msgid/20200427080530.3234-1-bernard@vivo.com --- include/linux/hdmi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 9613d796cfb1..ff25aeb95ee4 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -57,6 +57,7 @@ enum hdmi_infoframe_type { #define HDMI_SPD_INFOFRAME_SIZE 25 #define HDMI_AUDIO_INFOFRAME_SIZE 10 #define HDMI_DRM_INFOFRAME_SIZE 26 +#define HDMI_VENDOR_INFOFRAME_SIZE 4 #define HDMI_INFOFRAME_SIZE(type) \ (HDMI_INFOFRAME_HEADER_SIZE + HDMI_ ## type ## _INFOFRAME_SIZE) -- cgit v1.2.3 From c39ba6b3a8d47be07c180f857564a25a0356d336 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Mon, 1 Jun 2020 08:44:39 +0000 Subject: workqueue: fix a piece of comment about reserved bits for work flags 8a2e8e5dec7e("workqueue: fix cwq->nr_active underflow") allocated one more bit from the work flags, and it updated partial of the comments (128 bytes -> 256 bytes), but it failed to update the info about the number of reserved bits. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 8b505d22fc0e..26de0cae2a0a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -62,7 +62,7 @@ enum { WORK_CPU_UNBOUND = NR_CPUS, /* - * Reserve 7 bits off of pwq pointer w/ debugobjects turned off. + * Reserve 8 bits off of pwq pointer w/ debugobjects turned off. * This makes pwqs aligned to 256 bytes and allows 15 workqueue * flush colors. */ -- cgit v1.2.3 From abb30460bda232f304f642510adc8c6576ea51ea Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 1 Jun 2020 10:02:01 -0600 Subject: block: mark bio_wouldblock_error() bio with BIO_QUIET We really don't care about triggering buffer errors for this condition. This avoids a spew of: Buffer I/O error on dev sdc, logical block 785929, async page read Buffer I/O error on dev sdc, logical block 759095, async page read Buffer I/O error on dev sdc, logical block 766922, async page read Buffer I/O error on dev sdc, logical block 17659, async page read Buffer I/O error on dev sdc, logical block 637571, async page read Buffer I/O error on dev sdc, logical block 39241, async page read Buffer I/O error on dev sdc, logical block 397241, async page read Buffer I/O error on dev sdc, logical block 763992, async page read from -EAGAIN conditions on request allocation for async reads. Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 941378ec5b39..683ff5fd8871 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -417,6 +417,7 @@ static inline void bio_io_error(struct bio *bio) static inline void bio_wouldblock_error(struct bio *bio) { + bio_set_flag(bio, BIO_QUIET); bio->bi_status = BLK_STS_AGAIN; bio_endio(bio); } -- cgit v1.2.3 From 708b2000362476c9c7a3571c0cc774dffb91836a Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Tue, 26 May 2020 16:18:29 -0700 Subject: PCI/AER: Remove HEST/FIRMWARE_FIRST parsing for AER ownership Commit c100beb9ccfb ("PCI/AER: Use only _OSC to determine AER ownership") removed the use of HEST in determining AER ownership, but the AER driver still used HEST to verify AER ownership in some of its APIs. Per the ACPI spec v6.3, sec 18.3.2.4, some HEST table entries contain a FIRMWARE_FIRST bit, but that bit does not tell us anything about ownership of the AER capability. Remove parsing of HEST to look for FIRMWARE_FIRST. Add pcie_aer_is_native() for the places that need to know whether the OS owns the AER capability. [bhelgaas: commit log, reorder patch, remove unused __aer_firmware_first] Link: https://lore.kernel.org/r/9a37f53a4e6ff4942ff8e18dbb20b00e16c47341.1590534843.git.sathyanarayanan.kuppuswamy@linux.intel.com Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 83ce1cdf5676..43f265830eca 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -420,8 +420,6 @@ struct pci_dev { * mappings to make sure they cannot access arbitrary memory. */ unsigned int untrusted:1; - unsigned int __aer_firmware_first_valid:1; - unsigned int __aer_firmware_first:1; unsigned int broken_intx_masking:1; /* INTx masking can't be used */ unsigned int io_window_1k:1; /* Intel bridge 1K I/O windows */ unsigned int irq_managed:1; -- cgit v1.2.3 From bfad978116c2aa3b693701059923de4561196f9b Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 28 May 2020 17:45:02 +0200 Subject: regmap: provide helpers for simple bit operations In many instances regmap_update_bits() is used for simple bit setting and clearing. In these cases the last argument is redundant and we can hide it with a static inline function. This adds three new helpers for simple bit operations: set_bits, clear_bits and test_bits (the last one defined as a regular function). Signed-off-by: Bartosz Golaszewski Signed-off-by: David S. Miller --- include/linux/regmap.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 40b07168fd8e..ddf0baff195d 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1111,6 +1111,21 @@ bool regmap_reg_in_ranges(unsigned int reg, const struct regmap_range *ranges, unsigned int nranges); +static inline int regmap_set_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + return regmap_update_bits_base(map, reg, bits, bits, + NULL, false, false); +} + +static inline int regmap_clear_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + return regmap_update_bits_base(map, reg, bits, 0, NULL, false, false); +} + +int regmap_test_bits(struct regmap *map, unsigned int reg, unsigned int bits); + /** * struct reg_field - Description of an register field * @@ -1410,6 +1425,27 @@ static inline int regmap_update_bits_base(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_set_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_clear_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_test_bits(struct regmap *map, + unsigned int reg, unsigned int bits) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_field_update_bits_base(struct regmap_field *field, unsigned int mask, unsigned int val, bool *change, bool async, bool force) -- cgit v1.2.3 From d3798acc094c8ff2406e9acc7a9b2c09da994616 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 29 May 2020 20:31:37 +0200 Subject: libceph: support for alloc hint flags Allow indicating future I/O pattern via flags. This is supported since Kraken (and bluestore persists flags together with expected_object_size and expected_write_size). Signed-off-by: Ilya Dryomov Reviewed-by: Jason Dillaman --- include/linux/ceph/osd_client.h | 4 +++- include/linux/ceph/rados.h | 14 ++++++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 671fb93e8c60..c60b59e9291b 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -136,6 +136,7 @@ struct ceph_osd_req_op { struct { u64 expected_object_size; u64 expected_write_size; + u32 flags; /* CEPH_OSD_OP_ALLOC_HINT_FLAG_* */ } alloc_hint; struct { u64 snapid; @@ -472,7 +473,8 @@ extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req, unsigned int which, u64 expected_object_size, - u64 expected_write_size); + u64 expected_write_size, + u32 flags); extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 88ed3c5c04c5..3a518fd0eaad 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -464,6 +464,19 @@ enum { const char *ceph_osd_watch_op_name(int o); +enum { + CEPH_OSD_ALLOC_HINT_FLAG_SEQUENTIAL_WRITE = 1, + CEPH_OSD_ALLOC_HINT_FLAG_RANDOM_WRITE = 2, + CEPH_OSD_ALLOC_HINT_FLAG_SEQUENTIAL_READ = 4, + CEPH_OSD_ALLOC_HINT_FLAG_RANDOM_READ = 8, + CEPH_OSD_ALLOC_HINT_FLAG_APPEND_ONLY = 16, + CEPH_OSD_ALLOC_HINT_FLAG_IMMUTABLE = 32, + CEPH_OSD_ALLOC_HINT_FLAG_SHORTLIVED = 64, + CEPH_OSD_ALLOC_HINT_FLAG_LONGLIVED = 128, + CEPH_OSD_ALLOC_HINT_FLAG_COMPRESSIBLE = 256, + CEPH_OSD_ALLOC_HINT_FLAG_INCOMPRESSIBLE = 512, +}; + enum { CEPH_OSD_BACKOFF_OP_BLOCK = 1, CEPH_OSD_BACKOFF_OP_ACK_BLOCK = 2, @@ -517,6 +530,7 @@ struct ceph_osd_op { struct { __le64 expected_object_size; __le64 expected_write_size; + __le32 flags; /* CEPH_OSD_OP_ALLOC_HINT_FLAG_* */ } __attribute__ ((packed)) alloc_hint; struct { __le64 snapid; -- cgit v1.2.3 From 457f44363a8894135c85b7a9afd2bd8196db24ab Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 29 May 2020 00:54:20 -0700 Subject: bpf: Implement BPF ring buffer and verifier support for it This commit adds a new MPSC ring buffer implementation into BPF ecosystem, which allows multiple CPUs to submit data to a single shared ring buffer. On the consumption side, only single consumer is assumed. Motivation ---------- There are two distinctive motivators for this work, which are not satisfied by existing perf buffer, which prompted creation of a new ring buffer implementation. - more efficient memory utilization by sharing ring buffer across CPUs; - preserving ordering of events that happen sequentially in time, even across multiple CPUs (e.g., fork/exec/exit events for a task). These two problems are independent, but perf buffer fails to satisfy both. Both are a result of a choice to have per-CPU perf ring buffer. Both can be also solved by having an MPSC implementation of ring buffer. The ordering problem could technically be solved for perf buffer with some in-kernel counting, but given the first one requires an MPSC buffer, the same solution would solve the second problem automatically. Semantics and APIs ------------------ Single ring buffer is presented to BPF programs as an instance of BPF map of type BPF_MAP_TYPE_RINGBUF. Two other alternatives considered, but ultimately rejected. One way would be to, similar to BPF_MAP_TYPE_PERF_EVENT_ARRAY, make BPF_MAP_TYPE_RINGBUF could represent an array of ring buffers, but not enforce "same CPU only" rule. This would be more familiar interface compatible with existing perf buffer use in BPF, but would fail if application needed more advanced logic to lookup ring buffer by arbitrary key. HASH_OF_MAPS addresses this with current approach. Additionally, given the performance of BPF ringbuf, many use cases would just opt into a simple single ring buffer shared among all CPUs, for which current approach would be an overkill. Another approach could introduce a new concept, alongside BPF map, to represent generic "container" object, which doesn't necessarily have key/value interface with lookup/update/delete operations. This approach would add a lot of extra infrastructure that has to be built for observability and verifier support. It would also add another concept that BPF developers would have to familiarize themselves with, new syntax in libbpf, etc. But then would really provide no additional benefits over the approach of using a map. BPF_MAP_TYPE_RINGBUF doesn't support lookup/update/delete operations, but so doesn't few other map types (e.g., queue and stack; array doesn't support delete, etc). The approach chosen has an advantage of re-using existing BPF map infrastructure (introspection APIs in kernel, libbpf support, etc), being familiar concept (no need to teach users a new type of object in BPF program), and utilizing existing tooling (bpftool). For common scenario of using a single ring buffer for all CPUs, it's as simple and straightforward, as would be with a dedicated "container" object. On the other hand, by being a map, it can be combined with ARRAY_OF_MAPS and HASH_OF_MAPS map-in-maps to implement a wide variety of topologies, from one ring buffer for each CPU (e.g., as a replacement for perf buffer use cases), to a complicated application hashing/sharding of ring buffers (e.g., having a small pool of ring buffers with hashed task's tgid being a look up key to preserve order, but reduce contention). Key and value sizes are enforced to be zero. max_entries is used to specify the size of ring buffer and has to be a power of 2 value. There are a bunch of similarities between perf buffer (BPF_MAP_TYPE_PERF_EVENT_ARRAY) and new BPF ring buffer semantics: - variable-length records; - if there is no more space left in ring buffer, reservation fails, no blocking; - memory-mappable data area for user-space applications for ease of consumption and high performance; - epoll notifications for new incoming data; - but still the ability to do busy polling for new data to achieve the lowest latency, if necessary. BPF ringbuf provides two sets of APIs to BPF programs: - bpf_ringbuf_output() allows to *copy* data from one place to a ring buffer, similarly to bpf_perf_event_output(); - bpf_ringbuf_reserve()/bpf_ringbuf_commit()/bpf_ringbuf_discard() APIs split the whole process into two steps. First, a fixed amount of space is reserved. If successful, a pointer to a data inside ring buffer data area is returned, which BPF programs can use similarly to a data inside array/hash maps. Once ready, this piece of memory is either committed or discarded. Discard is similar to commit, but makes consumer ignore the record. bpf_ringbuf_output() has disadvantage of incurring extra memory copy, because record has to be prepared in some other place first. But it allows to submit records of the length that's not known to verifier beforehand. It also closely matches bpf_perf_event_output(), so will simplify migration significantly. bpf_ringbuf_reserve() avoids the extra copy of memory by providing a memory pointer directly to ring buffer memory. In a lot of cases records are larger than BPF stack space allows, so many programs have use extra per-CPU array as a temporary heap for preparing sample. bpf_ringbuf_reserve() avoid this needs completely. But in exchange, it only allows a known constant size of memory to be reserved, such that verifier can verify that BPF program can't access memory outside its reserved record space. bpf_ringbuf_output(), while slightly slower due to extra memory copy, covers some use cases that are not suitable for bpf_ringbuf_reserve(). The difference between commit and discard is very small. Discard just marks a record as discarded, and such records are supposed to be ignored by consumer code. Discard is useful for some advanced use-cases, such as ensuring all-or-nothing multi-record submission, or emulating temporary malloc()/free() within single BPF program invocation. Each reserved record is tracked by verifier through existing reference-tracking logic, similar to socket ref-tracking. It is thus impossible to reserve a record, but forget to submit (or discard) it. bpf_ringbuf_query() helper allows to query various properties of ring buffer. Currently 4 are supported: - BPF_RB_AVAIL_DATA returns amount of unconsumed data in ring buffer; - BPF_RB_RING_SIZE returns the size of ring buffer; - BPF_RB_CONS_POS/BPF_RB_PROD_POS returns current logical possition of consumer/producer, respectively. Returned values are momentarily snapshots of ring buffer state and could be off by the time helper returns, so this should be used only for debugging/reporting reasons or for implementing various heuristics, that take into account highly-changeable nature of some of those characteristics. One such heuristic might involve more fine-grained control over poll/epoll notifications about new data availability in ring buffer. Together with BPF_RB_NO_WAKEUP/BPF_RB_FORCE_WAKEUP flags for output/commit/discard helpers, it allows BPF program a high degree of control and, e.g., more efficient batched notifications. Default self-balancing strategy, though, should be adequate for most applications and will work reliable and efficiently already. Design and implementation ------------------------- This reserve/commit schema allows a natural way for multiple producers, either on different CPUs or even on the same CPU/in the same BPF program, to reserve independent records and work with them without blocking other producers. This means that if BPF program was interruped by another BPF program sharing the same ring buffer, they will both get a record reserved (provided there is enough space left) and can work with it and submit it independently. This applies to NMI context as well, except that due to using a spinlock during reservation, in NMI context, bpf_ringbuf_reserve() might fail to get a lock, in which case reservation will fail even if ring buffer is not full. The ring buffer itself internally is implemented as a power-of-2 sized circular buffer, with two logical and ever-increasing counters (which might wrap around on 32-bit architectures, that's not a problem): - consumer counter shows up to which logical position consumer consumed the data; - producer counter denotes amount of data reserved by all producers. Each time a record is reserved, producer that "owns" the record will successfully advance producer counter. At that point, data is still not yet ready to be consumed, though. Each record has 8 byte header, which contains the length of reserved record, as well as two extra bits: busy bit to denote that record is still being worked on, and discard bit, which might be set at commit time if record is discarded. In the latter case, consumer is supposed to skip the record and move on to the next one. Record header also encodes record's relative offset from the beginning of ring buffer data area (in pages). This allows bpf_ringbuf_commit()/bpf_ringbuf_discard() to accept only the pointer to the record itself, without requiring also the pointer to ring buffer itself. Ring buffer memory location will be restored from record metadata header. This significantly simplifies verifier, as well as improving API usability. Producer counter increments are serialized under spinlock, so there is a strict ordering between reservations. Commits, on the other hand, are completely lockless and independent. All records become available to consumer in the order of reservations, but only after all previous records where already committed. It is thus possible for slow producers to temporarily hold off submitted records, that were reserved later. Reservation/commit/consumer protocol is verified by litmus tests in Documentation/litmus-test/bpf-rb. One interesting implementation bit, that significantly simplifies (and thus speeds up as well) implementation of both producers and consumers is how data area is mapped twice contiguously back-to-back in the virtual memory. This allows to not take any special measures for samples that have to wrap around at the end of the circular buffer data area, because the next page after the last data page would be first data page again, and thus the sample will still appear completely contiguous in virtual memory. See comment and a simple ASCII diagram showing this visually in bpf_ringbuf_area_alloc(). Another feature that distinguishes BPF ringbuf from perf ring buffer is a self-pacing notifications of new data being availability. bpf_ringbuf_commit() implementation will send a notification of new record being available after commit only if consumer has already caught up right up to the record being committed. If not, consumer still has to catch up and thus will see new data anyways without needing an extra poll notification. Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c) show that this allows to achieve a very high throughput without having to resort to tricks like "notify only every Nth sample", which are necessary with perf buffer. For extreme cases, when BPF program wants more manual control of notifications, commit/discard/output helpers accept BPF_RB_NO_WAKEUP and BPF_RB_FORCE_WAKEUP flags, which give full control over notifications of data availability, but require extra caution and diligence in using this API. Comparison to alternatives -------------------------- Before considering implementing BPF ring buffer from scratch existing alternatives in kernel were evaluated, but didn't seem to meet the needs. They largely fell into few categores: - per-CPU buffers (perf, ftrace, etc), which don't satisfy two motivations outlined above (ordering and memory consumption); - linked list-based implementations; while some were multi-producer designs, consuming these from user-space would be very complicated and most probably not performant; memory-mapping contiguous piece of memory is simpler and more performant for user-space consumers; - io_uring is SPSC, but also requires fixed-sized elements. Naively turning SPSC queue into MPSC w/ lock would have subpar performance compared to locked reserve + lockless commit, as with BPF ring buffer. Fixed sized elements would be too limiting for BPF programs, given existing BPF programs heavily rely on variable-sized perf buffer already; - specialized implementations (like a new printk ring buffer, [0]) with lots of printk-specific limitations and implications, that didn't seem to fit well for intended use with BPF programs. [0] https://lwn.net/Articles/779550/ Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200529075424.3139988-2-andriin@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 13 +++++++++++++ include/linux/bpf_types.h | 1 + include/linux/bpf_verifier.h | 4 ++++ 3 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index efe8836b5c48..e5884f7f801c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -90,6 +90,8 @@ struct bpf_map_ops { int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); + __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, + struct poll_table_struct *pts); }; struct bpf_map_memory { @@ -244,6 +246,9 @@ enum bpf_arg_type { ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ + ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ + ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ + ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ }; /* type of values returned from helper functions */ @@ -255,6 +260,7 @@ enum bpf_return_type { RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */ RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */ + RET_PTR_TO_ALLOC_MEM_OR_NULL, /* returns a pointer to dynamically allocated memory or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -322,6 +328,8 @@ enum bpf_reg_type { PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ PTR_TO_BTF_ID, /* reg points to kernel struct */ PTR_TO_BTF_ID_OR_NULL, /* reg points to kernel struct or NULL */ + PTR_TO_MEM, /* reg points to valid memory region */ + PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -1611,6 +1619,11 @@ extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_event_output_data_proto; +extern const struct bpf_func_proto bpf_ringbuf_output_proto; +extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; +extern const struct bpf_func_proto bpf_ringbuf_submit_proto; +extern const struct bpf_func_proto bpf_ringbuf_discard_proto; +extern const struct bpf_func_proto bpf_ringbuf_query_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 29d22752fc87..fa8e1b552acd 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -118,6 +118,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) #if defined(CONFIG_BPF_JIT) BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index ea833087e853..ca08db4ffb5f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -54,6 +54,8 @@ struct bpf_reg_state { u32 btf_id; /* for PTR_TO_BTF_ID */ + u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */ + /* Max size from any of the above. */ unsigned long raw; }; @@ -63,6 +65,8 @@ struct bpf_reg_state { * offset, so they can share range knowledge. * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we * came from, when one is tested for != NULL. + * For PTR_TO_MEM_OR_NULL this is used to identify memory allocation + * for the purpose of tracking that it's freed. * For PTR_TO_SOCKET this is used to share which pointers retain the * same reference to the socket, to determine proper reference freeing. */ -- cgit v1.2.3 From fbee97feed9b3e4acdf9590e1f6b4a2eefecfffe Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 29 May 2020 16:07:13 -0600 Subject: bpf: Add support to attach bpf program to a devmap entry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern Signed-off-by: Alexei Starovoitov Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e5884f7f801c..e042311f991f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1250,6 +1250,7 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); +bool dev_map_can_have_prog(struct bpf_map *map); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); void __cpu_map_flush(void); @@ -1363,6 +1364,10 @@ static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map { return NULL; } +static inline bool dev_map_can_have_prog(struct bpf_map *map) +{ + return false; +} static inline void __dev_flush(void) { -- cgit v1.2.3 From e91de6afa81c10e9f855c5695eb9a53168d96b73 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 29 May 2020 16:06:59 -0700 Subject: bpf: Fix running sk_skb program types with ktls KTLS uses a stream parser to collect TLS messages and send them to the upper layer tls receive handler. This ensures the tls receiver has a full TLS header to parse when it is run. However, when a socket has BPF_SK_SKB_STREAM_VERDICT program attached before KTLS is enabled we end up with two stream parsers running on the same socket. The result is both try to run on the same socket. First the KTLS stream parser runs and calls read_sock() which will tcp_read_sock which in turn calls tcp_rcv_skb(). This dequeues the skb from the sk_receive_queue. When this is done KTLS code then data_ready() callback which because we stacked KTLS on top of the bpf stream verdict program has been replaced with sk_psock_start_strp(). This will in turn kick the stream parser again and eventually do the same thing KTLS did above calling into tcp_rcv_skb() and dequeuing a skb from the sk_receive_queue. At this point the data stream is broke. Part of the stream was handled by the KTLS side some other bytes may have been handled by the BPF side. Generally this results in either missing data or more likely a "Bad Message" complaint from the kTLS receive handler as the BPF program steals some bytes meant to be in a TLS header and/or the TLS header length is no longer correct. We've already broke the idealized model where we can stack ULPs in any order with generic callbacks on the TX side to handle this. So in this patch we do the same thing but for RX side. We add a sk_psock_strp_enabled() helper so TLS can learn a BPF verdict program is running and add a tls_sw_has_ctx_rx() helper so BPF side can learn there is a TLS ULP on the socket. Then on BPF side we omit calling our stream parser to avoid breaking the data stream for the KTLS receiver. Then on the KTLS side we call BPF_SK_SKB_STREAM_VERDICT once the KTLS receiver is done with the packet but before it posts the msg to userspace. This gives us symmetry between the TX and RX halfs and IMO makes it usable again. On the TX side we process packets in this order BPF -> TLS -> TCP and on the receive side in the reverse order TCP -> TLS -> BPF. Discovered while testing OpenSSL 3.0 Alpha2.0 release. Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/159079361946.5745.605854335665044485.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov --- include/linux/skmsg.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index ad31c9fb7158..08674cd14d5a 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -437,4 +437,12 @@ static inline void psock_progs_drop(struct sk_psock_progs *progs) psock_set_prog(&progs->skb_verdict, NULL); } +int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb); + +static inline bool sk_psock_strp_enabled(struct sk_psock *psock) +{ + if (!psock) + return false; + return psock->parser.enabled; +} #endif /* _LINUX_SKMSG_H */ -- cgit v1.2.3 From 958a3f2d2aff896ae2a622878e456114f4a4cd15 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 31 May 2020 17:42:55 +0200 Subject: bpf: Use tracing helpers for lsm programs Currenty lsm uses bpf_tracing_func_proto helpers which do not include stack trace or perf event output. It's useful to have those for bpftrace lsm support [1]. Using tracing_prog_func_proto helpers for lsm programs. [1] https://github.com/iovisor/bpftrace/pull/1347 Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Cc: KP Singh Link: https://lore.kernel.org/bpf/20200531154255.896551-1-jolsa@kernel.org --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e042311f991f..07052d44bca1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1633,6 +1633,9 @@ extern const struct bpf_func_proto bpf_ringbuf_query_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); +const struct bpf_func_proto *tracing_prog_func_proto( + enum bpf_func_id func_id, const struct bpf_prog *prog); + /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); -- cgit v1.2.3 From a3fd7ceee05431d2c51ed86c6cae015d236a51f0 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sun, 31 May 2020 10:28:36 +0200 Subject: net: Introduce netns_bpf for BPF programs attached to netns In order to: (1) attach more than one BPF program type to netns, or (2) support attaching BPF programs to netns with bpf_link, or (3) support multi-prog attach points for netns we will need to keep more state per netns than a single pointer like we have now for BPF flow dissector program. Prepare for the above by extracting netns_bpf that is part of struct net, for storing all state related to BPF programs attached to netns. Turn flow dissector callbacks for querying/attaching/detaching a program into generic ones that operate on netns_bpf. Next patch will move the generic callbacks into their own module. This is similar to how it is organized for cgroup with cgroup_bpf. Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Cc: Stanislav Fomichev Link: https://lore.kernel.org/bpf/20200531082846.2117903-3-jakub@cloudflare.com --- include/linux/bpf-netns.h | 56 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/skbuff.h | 26 ---------------------- 2 files changed, 56 insertions(+), 26 deletions(-) create mode 100644 include/linux/bpf-netns.h (limited to 'include/linux') diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h new file mode 100644 index 000000000000..f3aec3d79824 --- /dev/null +++ b/include/linux/bpf-netns.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BPF_NETNS_H +#define _BPF_NETNS_H + +#include +#include + +enum netns_bpf_attach_type { + NETNS_BPF_INVALID = -1, + NETNS_BPF_FLOW_DISSECTOR = 0, + MAX_NETNS_BPF_ATTACH_TYPE +}; + +static inline enum netns_bpf_attach_type +to_netns_bpf_attach_type(enum bpf_attach_type attach_type) +{ + switch (attach_type) { + case BPF_FLOW_DISSECTOR: + return NETNS_BPF_FLOW_DISSECTOR; + default: + return NETNS_BPF_INVALID; + } +} + +/* Protects updates to netns_bpf */ +extern struct mutex netns_bpf_mutex; + +union bpf_attr; +struct bpf_prog; + +#ifdef CONFIG_NET +int netns_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); +int netns_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog); +int netns_bpf_prog_detach(const union bpf_attr *attr); +#else +static inline int netns_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EOPNOTSUPP; +} + +static inline int netns_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} + +static inline int netns_bpf_prog_detach(const union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} +#endif + +#endif /* _BPF_NETNS_H */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 531843952809..a0d5c2760103 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1283,32 +1283,6 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); -#ifdef CONFIG_NET -int skb_flow_dissector_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr); -int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, - struct bpf_prog *prog); - -int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr); -#else -static inline int skb_flow_dissector_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr) -{ - return -EOPNOTSUPP; -} - -static inline int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, - struct bpf_prog *prog) -{ - return -EOPNOTSUPP; -} - -static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) -{ - return -EOPNOTSUPP; -} -#endif - struct bpf_flow_dissector; bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags); -- cgit v1.2.3 From 7f045a49fee04b5662cbdeaf0838f9322ae8c63a Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sun, 31 May 2020 10:28:38 +0200 Subject: bpf: Add link-based BPF program attachment to network namespace Extend bpf() syscall subcommands that operate on bpf_link, that is LINK_CREATE, LINK_UPDATE, OBJ_GET_INFO, to accept attach types tied to network namespaces (only flow dissector at the moment). Link-based and prog-based attachment can be used interchangeably, but only one can exist at a time. Attempts to attach a link when a prog is already attached directly, and the other way around, will be met with -EEXIST. Attempts to detach a program when link exists result in -EINVAL. Attachment of multiple links of same attach type to one netns is not supported with the intention to lift the restriction when a use-case presents itself. Because of that link create returns -E2BIG when trying to create another netns link, when one already exists. Link-based attachments to netns don't keep a netns alive by holding a ref to it. Instead links get auto-detached from netns when the latter is being destroyed, using a pernet pre_exit callback. When auto-detached, link lives in defunct state as long there are open FDs for it. -ENOLINK is returned if a user tries to update a defunct link. Because bpf_link to netns doesn't hold a ref to struct net, special care is taken when releasing, updating, or filling link info. The netns might be getting torn down when any of these link operations are in progress. That is why auto-detach and update/release/fill_info are synchronized by the same mutex. Also, link ops have to always check if auto-detach has not happened yet and if netns is still alive (refcnt > 0). Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200531082846.2117903-5-jakub@cloudflare.com --- include/linux/bpf-netns.h | 8 ++++++++ include/linux/bpf_types.h | 3 +++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h index f3aec3d79824..4052d649f36d 100644 --- a/include/linux/bpf-netns.h +++ b/include/linux/bpf-netns.h @@ -34,6 +34,8 @@ int netns_bpf_prog_query(const union bpf_attr *attr, int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int netns_bpf_prog_detach(const union bpf_attr *attr); +int netns_bpf_link_create(const union bpf_attr *attr, + struct bpf_prog *prog); #else static inline int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -51,6 +53,12 @@ static inline int netns_bpf_prog_detach(const union bpf_attr *attr) { return -EOPNOTSUPP; } + +static inline int netns_bpf_link_create(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif #endif /* _BPF_NETNS_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index fa8e1b552acd..a18ae82a298a 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -126,3 +126,6 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) #endif BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) +#ifdef CONFIG_NET +BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns) +#endif -- cgit v1.2.3 From a865e420b9561235851c3f5d483c82ef389d29bd Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 6 Apr 2020 08:42:55 -0400 Subject: virtio: force spec specified alignment on types The ring element addresses are passed between components with different alignments assumptions. Thus, if guest/userspace selects a pointer and host then gets and dereferences it, we might need to decrease the compiler-selected alignment to prevent compiler on the host from assuming pointer is aligned. This actually triggers on ARM with -mabi=apcs-gnu - which is a deprecated configuration, but it seems safer to handle this generally. Note that userspace that allocates the memory is actually OK and does not need to be fixed, but userspace that gets it from guest or another process does need to be fixed. The later doesn't generally talk to the kernel so while it might be buggy it's not talking to the kernel in the buggy way - it's just using the header in the buggy way - so fixing header and asking userspace to recompile is the best we can do. I verified that the produced kernel binary on x86 is exactly identical before and after the change. Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/linux/vringh.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 9e2763d7c159..59bd50f99291 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -105,9 +105,9 @@ struct vringh_kiov { /* Helpers for userspace vrings. */ int vringh_init_user(struct vringh *vrh, u64 features, unsigned int num, bool weak_barriers, - struct vring_desc __user *desc, - struct vring_avail __user *avail, - struct vring_used __user *used); + vring_desc_t __user *desc, + vring_avail_t __user *avail, + vring_used_t __user *used); static inline void vringh_iov_init(struct vringh_iov *iov, struct iovec *iovec, unsigned num) -- cgit v1.2.3 From 25de110d148666752dc0e0da7a0b69de31cd7098 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 2 Jun 2020 12:08:39 +0200 Subject: irq_work: Define irq_work_single() on !CONFIG_IRQ_WORK too Some SMP platforms don't have CONFIG_IRQ_WORK defined, resulting in a link error at build time. Define a stub and clean up the prototype definitions. Reported-by: kbuild test robot Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/irq_work.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index f23a359c8f46..2735da5f839e 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -58,9 +58,11 @@ void irq_work_sync(struct irq_work *work); void irq_work_run(void); bool irq_work_needs_cpu(void); +void irq_work_single(void *arg); #else static inline bool irq_work_needs_cpu(void) { return false; } static inline void irq_work_run(void) { } +static inline void irq_work_single(void *arg) { } #endif #endif /* _LINUX_IRQ_WORK_H */ -- cgit v1.2.3 From ef3534a94fdbdeab4c89d18d0164be2ad5d6dbb7 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Tue, 2 Jun 2020 09:42:08 +0530 Subject: hw-breakpoints: Fix build warnings with clang kbuild test robot reported some build warnings in the hw_breakpoint code when compiled with clang[1]. Some of them were introduced by the recent powerpc change to add arch_reserve_bp_slot() and arch_release_bp_slot(). Fix them all. kernel/events/hw_breakpoint.c:71:12: warning: no previous prototype for function 'hw_breakpoint_weight' kernel/events/hw_breakpoint.c:216:12: warning: no previous prototype for function 'arch_reserve_bp_slot' kernel/events/hw_breakpoint.c:221:13: warning: no previous prototype for function 'arch_release_bp_slot' kernel/events/hw_breakpoint.c:228:13: warning: no previous prototype for function 'arch_unregister_hw_breakpoint' [1]: https://lore.kernel.org/linuxppc-dev/202005192233.oi9CjRtA%25lkp@intel.com/ Fixes: 29da4f91c0c1 ("powerpc/watchpoint: Don't allow concurrent perf and ptrace events") Reported-by: kbuild test robot Signed-off-by: Ravi Bangoria [mpe: Drop extern, flesh out change log, add Fixes tag] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200602041208.128913-1-ravi.bangoria@linux.ibm.com --- include/linux/hw_breakpoint.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index 6058c3844a76..d7d4250cd1e4 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -80,6 +80,10 @@ extern int dbg_reserve_bp_slot(struct perf_event *bp); extern int dbg_release_bp_slot(struct perf_event *bp); extern int reserve_bp_slot(struct perf_event *bp); extern void release_bp_slot(struct perf_event *bp); +int hw_breakpoint_weight(struct perf_event *bp); +int arch_reserve_bp_slot(struct perf_event *bp); +void arch_release_bp_slot(struct perf_event *bp); +void arch_unregister_hw_breakpoint(struct perf_event *bp); extern void flush_ptrace_hw_breakpoint(struct task_struct *tsk); -- cgit v1.2.3 From c893de12e1ef17b581eb2cf8fc9018ec0cbd07df Mon Sep 17 00:00:00 2001 From: Wei Li Date: Thu, 21 May 2020 15:21:25 +0800 Subject: kdb: Remove the misfeature 'KDBFLAGS' Currently, 'KDBFLAGS' is an internal variable of kdb, it is combined by 'KDBDEBUG' and state flags. It will be shown only when 'KDBDEBUG' is set, and the user can define an environment variable named 'KDBFLAGS' too. These are puzzling indeed. After communication with Daniel, it seems that 'KDBFLAGS' is a misfeature. So let's replace 'KDBFLAGS' with 'KDBDEBUG' to just show the value we wrote into. After this modification, we can use `md4c1 kdb_flags` instead, to observe the state flags. Suggested-by: Daniel Thompson Signed-off-by: Wei Li Link: https://lore.kernel.org/r/20200521072125.21103-1-liwei391@huawei.com [daniel.thompson@linaro.org: Make kdb_flags unsigned to avoid arithmetic right shift] Signed-off-by: Daniel Thompson --- include/linux/kdb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 24cd447659e0..0125a677b67f 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -125,7 +125,7 @@ extern const char *kdb_diemsg; #define KDB_FLAG_NO_I8042 (1 << 7) /* No i8042 chip is available, do * not use keyboard */ -extern int kdb_flags; /* Global flags, see kdb_state for per cpu state */ +extern unsigned int kdb_flags; /* Global flags, see kdb_state for per cpu state */ extern void kdb_save_flags(void); extern void kdb_restore_flags(void); -- cgit v1.2.3 From 735e4ae5ba28c886d249ad04d3c8cc097dad6336 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 1 Jun 2020 21:45:36 -0700 Subject: vfs: track per-sb writeback errors and report them to syncfs Patch series "vfs: have syncfs() return error when there are writeback errors", v6. Currently, syncfs does not return errors when one of the inodes fails to be written back. It will return errors based on the legacy AS_EIO and AS_ENOSPC flags when syncing out the block device fails, but that's not particularly helpful for filesystems that aren't backed by a blockdev. It's also possible for a stray sync to lose those errors. The basic idea in this set is to track writeback errors at the superblock level, so that we can quickly and easily check whether something bad happened without having to fsync each file individually. syncfs is then changed to reliably report writeback errors after they occur, much in the same fashion as fsync does now. This patch (of 2): Usually we suggest that applications call fsync when they want to ensure that all data written to the file has made it to the backing store, but that can be inefficient when there are a lot of open files. Calling syncfs on the filesystem can be more efficient in some situations, but the error reporting doesn't currently work the way most people expect. If a single inode on a filesystem reports a writeback error, syncfs won't necessarily return an error. syncfs only returns an error if __sync_blockdev fails, and on some filesystems that's a no-op. It would be better if syncfs reported an error if there were any writeback failures. Then applications could call syncfs to see if there are any errors on any open files, and could then call fsync on all of the other descriptors to figure out which one failed. This patch adds a new errseq_t to struct super_block, and has mapping_set_error also record writeback errors there. To report those errors, we also need to keep an errseq_t in struct file to act as a cursor. This patch adds a dedicated field for that purpose, which slots nicely into 4 bytes of padding at the end of struct file on x86_64. An earlier version of this patch used an O_PATH file descriptor to cue the kernel that the open file should track the superblock error and not the inode's writeback error. I think that API is just too weird though. This is simpler and should make syncfs error reporting "just work" even if someone is multiplexing fsync and syncfs on the same fds. Signed-off-by: Jeff Layton Signed-off-by: Andrew Morton Reviewed-by: Jan Kara Cc: Andres Freund Cc: Matthew Wilcox Cc: Al Viro Cc: Christoph Hellwig Cc: Dave Chinner Cc: David Howells Link: http://lkml.kernel.org/r/20200428135155.19223-1-jlayton@kernel.org Link: http://lkml.kernel.org/r/20200428135155.19223-2-jlayton@kernel.org Signed-off-by: Linus Torvalds --- include/linux/fs.h | 16 ++++++++++++++++ include/linux/pagemap.h | 5 ++++- 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 45cc10cdf6dd..f2fb5b7406b9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -976,6 +976,7 @@ struct file { #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; errseq_t f_wb_err; + errseq_t f_sb_err; /* for syncfs */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ @@ -1520,6 +1521,9 @@ struct super_block { /* Being remounted read-only */ int s_readonly_remount; + /* per-sb errseq_t for reporting writeback errors via syncfs */ + errseq_t s_wb_err; + /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; @@ -2827,6 +2831,18 @@ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) return errseq_sample(&mapping->wb_err); } +/** + * file_sample_sb_err - sample the current errseq_t to test for later errors + * @mapping: mapping to be sampled + * + * Grab the most current superblock-level errseq_t value for the given + * struct file. + */ +static inline errseq_t file_sample_sb_err(struct file *file) +{ + return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); +} + static inline int filemap_nr_thps(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a8f7bd8ea1c6..d4409b13747e 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -51,7 +51,10 @@ static inline void mapping_set_error(struct address_space *mapping, int error) return; /* Record in wb_err for checkers using errseq_t based tracking */ - filemap_set_wb_err(mapping, error); + __filemap_set_wb_err(mapping, error); + + /* Record it in superblock */ + errseq_set(&mapping->host->i_sb->s_wb_err, error); /* Record it in flags for now, for legacy callers */ if (error == -ENOSPC) -- cgit v1.2.3 From cee9a0c4e84db024d692d6b5c18f65465eb06905 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:46:07 -0700 Subject: mm: move readahead prototypes from mm.h Patch series "Change readahead API", v11. This series adds a readahead address_space operation to replace the readpages operation. The key difference is that pages are added to the page cache as they are allocated (and then looked up by the filesystem) instead of passing them on a list to the readpages operation and having the filesystem add them to the page cache. It's a net reduction in code for each implementation, more efficient than walking a list, and solves the direct-write vs buffered-read problem reported by yu kuai at http://lkml.kernel.org/r/20200116063601.39201-1-yukuai3@huawei.com The only unconverted filesystems are those which use fscache. Their conversion is pending Dave Howells' rewrite which will make the conversion substantially easier. This should be completed by the end of the year. I want to thank the reviewers/testers; Dave Chinner, John Hubbard, Eric Biggers, Johannes Thumshirn, Dave Sterba, Zi Yan, Christoph Hellwig and Miklos Szeredi have done a marvellous job of providing constructive criticism. These patches pass an xfstests run on ext4, xfs & btrfs with no regressions that I can tell (some of the tests seem a little flaky before and remain flaky afterwards). This patch (of 25): The readahead code is part of the page cache so should be found in the pagemap.h file. force_page_cache_readahead is only used within mm, so move it to mm/internal.h instead. Remove the parameter names where they add no value, and rename the ones which were actively misleading. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski Reviewed-by: Johannes Thumshirn Cc: Chao Yu Cc: Cong Wang Cc: Darrick J. Wong Cc: Dave Chinner Cc: Eric Biggers Cc: Gao Xiang Cc: Jaegeuk Kim Cc: Joseph Qi Cc: Junxiao Bi Cc: Michal Hocko Cc: Zi Yan Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-1-willy@infradead.org Link: http://lkml.kernel.org/r/20200414150233.24495-2-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 19 ------------------- include/linux/pagemap.h | 8 ++++++++ 2 files changed, 8 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f3fe7371855c..92704fde6475 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2612,25 +2612,6 @@ extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); int __must_check write_one_page(struct page *page); void task_dirty_inc(struct task_struct *tsk); -/* readahead.c */ -#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) - -int force_page_cache_readahead(struct address_space *mapping, struct file *filp, - pgoff_t offset, unsigned long nr_to_read); - -void page_cache_sync_readahead(struct address_space *mapping, - struct file_ra_state *ra, - struct file *filp, - pgoff_t offset, - unsigned long size); - -void page_cache_async_readahead(struct address_space *mapping, - struct file_ra_state *ra, - struct file *filp, - struct page *pg, - pgoff_t offset, - unsigned long size); - extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d4409b13747e..8c081cda4b35 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -618,6 +618,14 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec); +#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) + +void page_cache_sync_readahead(struct address_space *, struct file_ra_state *, + struct file *, pgoff_t index, unsigned long req_count); +void page_cache_async_readahead(struct address_space *, struct file_ra_state *, + struct file *, struct page *, pgoff_t index, + unsigned long req_count); + /* * Like add_to_page_cache_locked, but used to add newly allocated pages: * the page is new, so we can just run __SetPageLocked() against it. -- cgit v1.2.3 From 042124cc64c33555deba0b11c6e0c612ae7a8653 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:46:21 -0700 Subject: mm: add new readahead_control API Filesystems which implement the upcoming ->readahead method will get their pages by calling readahead_page() or readahead_page_batch(). These functions support large pages, even though none of the filesystems to be converted do yet. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski Cc: Chao Yu Cc: Cong Wang Cc: Darrick J. Wong Cc: Dave Chinner Cc: Eric Biggers Cc: Gao Xiang Cc: Jaegeuk Kim Cc: John Hubbard Cc: Joseph Qi Cc: Junxiao Bi Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Thumshirn Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-6-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 140 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 140 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8c081cda4b35..c3bf73263ec9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -642,6 +642,146 @@ static inline int add_to_page_cache(struct page *page, return error; } +/** + * struct readahead_control - Describes a readahead request. + * + * A readahead request is for consecutive pages. Filesystems which + * implement the ->readahead method should call readahead_page() or + * readahead_page_batch() in a loop and attempt to start I/O against + * each page in the request. + * + * Most of the fields in this struct are private and should be accessed + * by the functions below. + * + * @file: The file, used primarily by network filesystems for authentication. + * May be NULL if invoked internally by the filesystem. + * @mapping: Readahead this filesystem object. + */ +struct readahead_control { + struct file *file; + struct address_space *mapping; +/* private: use the readahead_* accessors instead */ + pgoff_t _index; + unsigned int _nr_pages; + unsigned int _batch_count; +}; + +/** + * readahead_page - Get the next page to read. + * @rac: The current readahead request. + * + * Context: The page is locked and has an elevated refcount. The caller + * should decreases the refcount once the page has been submitted for I/O + * and unlock the page once all I/O to that page has completed. + * Return: A pointer to the next page, or %NULL if we are done. + */ +static inline struct page *readahead_page(struct readahead_control *rac) +{ + struct page *page; + + BUG_ON(rac->_batch_count > rac->_nr_pages); + rac->_nr_pages -= rac->_batch_count; + rac->_index += rac->_batch_count; + + if (!rac->_nr_pages) { + rac->_batch_count = 0; + return NULL; + } + + page = xa_load(&rac->mapping->i_pages, rac->_index); + VM_BUG_ON_PAGE(!PageLocked(page), page); + rac->_batch_count = hpage_nr_pages(page); + + return page; +} + +static inline unsigned int __readahead_batch(struct readahead_control *rac, + struct page **array, unsigned int array_sz) +{ + unsigned int i = 0; + XA_STATE(xas, &rac->mapping->i_pages, 0); + struct page *page; + + BUG_ON(rac->_batch_count > rac->_nr_pages); + rac->_nr_pages -= rac->_batch_count; + rac->_index += rac->_batch_count; + rac->_batch_count = 0; + + xas_set(&xas, rac->_index); + rcu_read_lock(); + xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(PageTail(page), page); + array[i++] = page; + rac->_batch_count += hpage_nr_pages(page); + + /* + * The page cache isn't using multi-index entries yet, + * so the xas cursor needs to be manually moved to the + * next index. This can be removed once the page cache + * is converted. + */ + if (PageHead(page)) + xas_set(&xas, rac->_index + rac->_batch_count); + + if (i == array_sz) + break; + } + rcu_read_unlock(); + + return i; +} + +/** + * readahead_page_batch - Get a batch of pages to read. + * @rac: The current readahead request. + * @array: An array of pointers to struct page. + * + * Context: The pages are locked and have an elevated refcount. The caller + * should decreases the refcount once the page has been submitted for I/O + * and unlock the page once all I/O to that page has completed. + * Return: The number of pages placed in the array. 0 indicates the request + * is complete. + */ +#define readahead_page_batch(rac, array) \ + __readahead_batch(rac, array, ARRAY_SIZE(array)) + +/** + * readahead_pos - The byte offset into the file of this readahead request. + * @rac: The readahead request. + */ +static inline loff_t readahead_pos(struct readahead_control *rac) +{ + return (loff_t)rac->_index * PAGE_SIZE; +} + +/** + * readahead_length - The number of bytes in this readahead request. + * @rac: The readahead request. + */ +static inline loff_t readahead_length(struct readahead_control *rac) +{ + return (loff_t)rac->_nr_pages * PAGE_SIZE; +} + +/** + * readahead_index - The index of the first page in this readahead request. + * @rac: The readahead request. + */ +static inline pgoff_t readahead_index(struct readahead_control *rac) +{ + return rac->_index; +} + +/** + * readahead_count - The number of pages in this readahead request. + * @rac: The readahead request. + */ +static inline unsigned int readahead_count(struct readahead_control *rac) +{ + return rac->_nr_pages; +} + static inline unsigned long dir_pages(struct inode *inode) { return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> -- cgit v1.2.3 From 8151b4c8bee43cea7a28cb0300123df90880e60c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:46:44 -0700 Subject: mm: add readahead address space operation This replaces ->readpages with a saner interface: - Return void instead of an ignored error code. - Page cache is already populated with locked pages when ->readahead is called. - New arguments can be passed to the implementation without changing all the filesystems that use a common helper function like mpage_readahead(). Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski Cc: Chao Yu Cc: Cong Wang Cc: Darrick J. Wong Cc: Dave Chinner Cc: Eric Biggers Cc: Gao Xiang Cc: Jaegeuk Kim Cc: Joseph Qi Cc: Junxiao Bi Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Thumshirn Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-12-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f2fb5b7406b9..1434ed801b80 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -292,6 +292,7 @@ enum positive_aop_returns { struct page; struct address_space; struct writeback_control; +struct readahead_control; /* * Write life time hint values. @@ -375,6 +376,7 @@ struct address_space_operations { */ int (*readpages)(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages); + void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, -- cgit v1.2.3 From 2c684234d36f7e8c80414e4a772911d407e821fa Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:46:51 -0700 Subject: mm: add page_cache_readahead_unbounded ext4 and f2fs have duplicated the guts of the readahead code so they can read past i_size. Instead, separate out the guts of the readahead code so they can call it directly. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Tested-by: Eric Biggers Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski Reviewed-by: Eric Biggers Cc: Chao Yu Cc: Cong Wang Cc: Darrick J. Wong Cc: Dave Chinner Cc: Gao Xiang Cc: Jaegeuk Kim Cc: John Hubbard Cc: Joseph Qi Cc: Junxiao Bi Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Thumshirn Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-14-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c3bf73263ec9..c6348c50136f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -625,6 +625,9 @@ void page_cache_sync_readahead(struct address_space *, struct file_ra_state *, void page_cache_async_readahead(struct address_space *, struct file_ra_state *, struct file *, struct page *, pgoff_t index, unsigned long req_count); +void page_cache_readahead_unbounded(struct address_space *, struct file *, + pgoff_t index, unsigned long nr_to_read, + unsigned long lookahead_count); /* * Like add_to_page_cache_locked, but used to add newly allocated pages: -- cgit v1.2.3 From d4388340ae0bc8397ef5b24342279f7739982918 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:47:02 -0700 Subject: fs: convert mpage_readpages to mpage_readahead Implement the new readahead aop and convert all callers (block_dev, exfat, ext2, fat, gfs2, hpfs, isofs, jfs, nilfs2, ocfs2, omfs, qnx6, reiserfs & udf). The callers are all trivial except for GFS2 & OCFS2. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: Junxiao Bi # ocfs2 Reviewed-by: Joseph Qi # ocfs2 Reviewed-by: Dave Chinner Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski Cc: Chao Yu Cc: Cong Wang Cc: Darrick J. Wong Cc: Eric Biggers Cc: Gao Xiang Cc: Jaegeuk Kim Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Thumshirn Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-17-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/mpage.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mpage.h b/include/linux/mpage.h index 001f1fcf9836..f4f5e90a6844 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -13,9 +13,9 @@ #ifdef CONFIG_BLOCK struct writeback_control; +struct readahead_control; -int mpage_readpages(struct address_space *mapping, struct list_head *pages, - unsigned nr_pages, get_block_t get_block); +void mpage_readahead(struct readahead_control *, get_block_t get_block); int mpage_readpage(struct page *page, get_block_t get_block); int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); -- cgit v1.2.3 From 9d24a13a93d995e4c980fdaa389aa3e2f1ea0b12 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:47:34 -0700 Subject: iomap: convert from readpages to readahead Use the new readahead operation in iomap. Convert XFS and ZoneFS to use it. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Reviewed-by: William Kucharski Cc: Chao Yu Cc: Cong Wang Cc: Dave Chinner Cc: Eric Biggers Cc: Gao Xiang Cc: Jaegeuk Kim Cc: John Hubbard Cc: Joseph Qi Cc: Junxiao Bi Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Thumshirn Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-26-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/iomap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 8b09463dae0d..bc20bd04c2a2 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -155,8 +155,7 @@ loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); int iomap_readpage(struct page *page, const struct iomap_ops *ops); -int iomap_readpages(struct address_space *mapping, struct list_head *pages, - unsigned nr_pages, const struct iomap_ops *ops); +void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); int iomap_set_page_dirty(struct page *page); int iomap_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count); -- cgit v1.2.3 From b03143accd9274d9e024da42ed5857a71a6b6a27 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 1 Jun 2020 21:47:38 -0700 Subject: include/linux/pagemap.h: introduce attach/detach_page_private MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Introduce attach/detach_page_private to cleanup code". This patch (of 10): The logic in attach_page_buffers and __clear_page_buffers are quite paired, but 1. they are located in different files. 2. attach_page_buffers is implemented in buffer_head.h, so it could be used by other files. But __clear_page_buffers is static function in buffer.c and other potential users can't call the function, md-bitmap even copied the function. So, introduce the new attach/detach_page_private to replace them. With the new pair of function, we will remove the usage of attach_page_buffers and __clear_page_buffers in next patches. Thanks for suggestions about the function name from Alexander Viro, Andreas Grünbacher, Christoph Hellwig and Matthew Wilcox. Suggested-by: Matthew Wilcox Signed-off-by: Guoqing Jiang Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: "Darrick J. Wong" Cc: William Kucharski Cc: "Kirill A. Shutemov" Cc: Andreas Gruenbacher Cc: Yang Shi Cc: Yafang Shao Cc: Song Liu Cc: Chris Mason Cc: Josef Bacik Cc: David Sterba Cc: Alexander Viro Cc: Jaegeuk Kim Cc: Chao Yu Cc: Christoph Hellwig Cc: Anton Altaparmakov Cc: Mike Marshall Cc: Martin Brandenburg Cc: Thomas Gleixner Cc: Sebastian Andrzej Siewior Cc: Roman Gushchin Cc: Andreas Dilger Cc: Chao Yu Cc: Dave Chinner Link: http://lkml.kernel.org/r/20200517214718.468-1-guoqing.jiang@cloud.ionos.com Link: http://lkml.kernel.org/r/20200517214718.468-2-guoqing.jiang@cloud.ionos.com Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c6348c50136f..8e085713150c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -208,6 +208,43 @@ static inline int page_cache_add_speculative(struct page *page, int count) return __page_cache_add_speculative(page, count); } +/** + * attach_page_private - Attach private data to a page. + * @page: Page to attach data to. + * @data: Data to attach to page. + * + * Attaching private data to a page increments the page's reference count. + * The data must be detached before the page will be freed. + */ +static inline void attach_page_private(struct page *page, void *data) +{ + get_page(page); + set_page_private(page, (unsigned long)data); + SetPagePrivate(page); +} + +/** + * detach_page_private - Detach private data from a page. + * @page: Page to detach data from. + * + * Removes the data that was previously attached to the page and decrements + * the refcount on the page. + * + * Return: Data that was attached to the page. + */ +static inline void *detach_page_private(struct page *page) +{ + void *data = (void *)page_private(page); + + if (!PagePrivate(page)) + return NULL; + ClearPagePrivate(page); + set_page_private(page, 0); + put_page(page); + + return data; +} + #ifdef CONFIG_NUMA extern struct page *__page_cache_alloc(gfp_t gfp); #else -- cgit v1.2.3 From 7b59435a2afed12dc9b2ec1b930efa2e94f1c397 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 1 Jun 2020 21:48:03 -0700 Subject: buffer_head.h: remove attach_page_buffers All the callers have replaced attach_page_buffers with the new function attach_page_private, so remove it. Signed-off-by: Guoqing Jiang Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Thomas Gleixner Cc: Sebastian Andrzej Siewior Cc: Roman Gushchin Cc: Andreas Dilger Link: http://lkml.kernel.org/r/20200517214718.468-10-guoqing.jiang@cloud.ionos.com Signed-off-by: Linus Torvalds --- include/linux/buffer_head.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 15b765a181b8..22fb11e2d2e0 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -272,14 +272,6 @@ void buffer_init(void); * inline definitions */ -static inline void attach_page_buffers(struct page *page, - struct buffer_head *head) -{ - get_page(page); - SetPagePrivate(page); - set_page_private(page, (unsigned long)head); -} - static inline void get_bh(struct buffer_head *bh) { atomic_inc(&bh->b_count); -- cgit v1.2.3 From 60e65a6f42d0af33fa7361bd8723adc70539121b Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 1 Jun 2020 21:48:09 -0700 Subject: mm_types.h: change set_page_private to inline function Change it to inline function to make callers use the proper argument. And no need for it to be macro per Andrew's comment [1]. [1] https://lore.kernel.org/lkml/20200518221235.1fa32c38e5766113f78e3f0d@linux-foundation.org/ Signed-off-by: Guoqing Jiang Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Link: http://lkml.kernel.org/r/20200525203149.18802-1-guoqing.jiang@cloud.ionos.com Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4aba6c0c2ba8..ef6d3aface8a 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -240,7 +240,11 @@ static inline atomic_t *compound_pincount_ptr(struct page *page) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) #define page_private(page) ((page)->private) -#define set_page_private(page, v) ((page)->private = (v)) + +static inline void set_page_private(struct page *page, unsigned long private) +{ + page->private = private; +} struct page_frag_cache { void * va; -- cgit v1.2.3 From a37b0715ddf3007734c4e2424c14bc7efcdd1190 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 1 Jun 2020 21:48:18 -0700 Subject: mm/writeback: replace PF_LESS_THROTTLE with PF_LOCAL_THROTTLE PF_LESS_THROTTLE exists for loop-back nfsd (and a similar need in the loop block driver and callers of prctl(PR_SET_IO_FLUSHER)), where a daemon needs to write to one bdi (the final bdi) in order to free up writes queued to another bdi (the client bdi). The daemon sets PF_LESS_THROTTLE and gets a larger allowance of dirty pages, so that it can still dirty pages after other processses have been throttled. The purpose of this is to avoid deadlock that happen when the PF_LESS_THROTTLE process must write for any dirty pages to be freed, but it is being thottled and cannot write. This approach was designed when all threads were blocked equally, independently on which device they were writing to, or how fast it was. Since that time the writeback algorithm has changed substantially with different threads getting different allowances based on non-trivial heuristics. This means the simple "add 25%" heuristic is no longer reliable. The important issue is not that the daemon needs a *larger* dirty page allowance, but that it needs a *private* dirty page allowance, so that dirty pages for the "client" bdi that it is helping to clear (the bdi for an NFS filesystem or loop block device etc) do not affect the throttling of the daemon writing to the "final" bdi. This patch changes the heuristic so that the task is not throttled when the bdi it is writing to has a dirty page count below below (or equal to) the free-run threshold for that bdi. This ensures it will always be able to have some pages in flight, and so will not deadlock. In a steady-state, it is expected that PF_LOCAL_THROTTLE tasks might still be throttled by global threshold, but that is acceptable as it is only the deadlock state that is interesting for this flag. This approach of "only throttle when target bdi is busy" is consistent with the other use of PF_LESS_THROTTLE in current_may_throttle(), were it causes attention to be focussed only on the target bdi. So this patch - renames PF_LESS_THROTTLE to PF_LOCAL_THROTTLE, - removes the 25% bonus that that flag gives, and - If PF_LOCAL_THROTTLE is set, don't delay at all unless the global and the local free-run thresholds are exceeded. Note that previously realtime threads were treated the same as PF_LESS_THROTTLE threads. This patch does *not* change the behvaiour for real-time threads, so it is now different from the behaviour of nfsd and loop tasks. I don't know what is wanted for realtime. [akpm@linux-foundation.org: coding style fixes] Signed-off-by: NeilBrown Signed-off-by: Andrew Morton Reviewed-by: Jan Kara Acked-by: Chuck Lever [nfsd] Cc: Christoph Hellwig Cc: Michal Hocko Cc: Trond Myklebust Link: http://lkml.kernel.org/r/87ftbf7gs3.fsf@notabene.neil.brown.name Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4418f5cb8324..12ef0c753284 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1481,7 +1481,8 @@ extern struct pid *cad_pid; #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocation requests will inherit GFP_NOFS */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocation requests will inherit GFP_NOIO */ -#define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ +#define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to, + * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ -- cgit v1.2.3 From 8d92890bd6b8502d6aee4b37430ae6444ade7a8c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 1 Jun 2020 21:48:21 -0700 Subject: mm/writeback: discard NR_UNSTABLE_NFS, use NR_WRITEBACK instead After an NFS page has been written it is considered "unstable" until a COMMIT request succeeds. If the COMMIT fails, the page will be re-written. These "unstable" pages are currently accounted as "reclaimable", either in WB_RECLAIMABLE, or in NR_UNSTABLE_NFS which is included in a 'reclaimable' count. This might have made sense when sending the COMMIT required a separate action by the VFS/MM (e.g. releasepage() used to send a COMMIT). However now that all writes generated by ->writepages() will automatically be followed by a COMMIT (since commit 919e3bd9a875 ("NFS: Ensure we commit after writeback is complete")) it makes more sense to treat them as writeback pages. So this patch removes NR_UNSTABLE_NFS and accounts unstable pages in NR_WRITEBACK and WB_WRITEBACK. A particular effect of this change is that when wb_check_background_flush() calls wb_over_bg_threshold(), the latter will report 'true' a lot less often as the 'unstable' pages are no longer considered 'dirty' (as there is nothing that writeback can do about them anyway). Currently wb_check_background_flush() will trigger writeback to NFS even when there are relatively few dirty pages (if there are lots of unstable pages), this can result in small writes going to the server (10s of Kilobytes rather than a Megabyte) which hurts throughput. With this patch, there are fewer writes which are each larger on average. Where the NR_UNSTABLE_NFS count was included in statistics virtual-files, the entry is retained, but the value is hard-coded as zero. static trace points and warning printks which mentioned this counter no longer report it. [akpm@linux-foundation.org: re-layout comment] [akpm@linux-foundation.org: fix printk warning] Signed-off-by: NeilBrown Signed-off-by: Andrew Morton Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig Acked-by: Trond Myklebust Acked-by: Michal Hocko [mm] Cc: Christoph Hellwig Cc: Chuck Lever Link: http://lkml.kernel.org/r/87d06j7gqa.fsf@notabene.neil.brown.name Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1b9de7d220fb..a89f47515eb1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -193,7 +193,6 @@ enum node_stat_item { NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, - NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ -- cgit v1.2.3 From 91429023342789a89f4b6ae95b47a7df71ab6d95 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Mon, 1 Jun 2020 21:48:27 -0700 Subject: mm/gup: introduce pin_user_pages_unlocked Introduce pin_user_pages_unlocked(), which is nearly identical to the get_user_pages_unlocked() that it wraps, except that it sets FOLL_PIN and rejects FOLL_GET. Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Andy Walls Cc: Mauro Carvalho Chehab Link: http://lkml.kernel.org/r/20200518012157.1178336-2-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 92704fde6475..ebbb0acbeee2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1713,6 +1713,8 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); +long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, + struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); -- cgit v1.2.3 From 4b4bb6bb451c8b0c1cbc38fa20a89a3988aa4e0b Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Mon, 1 Jun 2020 21:49:13 -0700 Subject: mm/swapfile.c: classify SWAP_MAP_XXX to make it more readable swap_info_struct->swap_map[] encodes some flag and count. And to do some condition check, it also introduces some special values. Currently those macros are defined with some magic order, which makes audience hard to understand the exact meaning. This patch split those macros into three categories: flag special value for first swap_map special value for continued swap_map May this help audiences a little. [akpm@linux-foundation.org: tweak capitalization in comments] Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Link: http://lkml.kernel.org/r/20200501015259.32237-1-richard.weiyang@gmail.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index e1bbf7a16b27..873bf5206afb 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -183,12 +183,17 @@ enum { #define SWAP_CLUSTER_MAX 32UL #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX -#define SWAP_MAP_MAX 0x3e /* Max duplication count, in first swap_map */ -#define SWAP_MAP_BAD 0x3f /* Note pageblock is bad, in first swap_map */ +/* Bit flag in swap_map */ #define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */ -#define SWAP_CONT_MAX 0x7f /* Max count, in each swap_map continuation */ -#define COUNT_CONTINUED 0x80 /* See swap_map continuation for full count */ -#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs, in first swap_map */ +#define COUNT_CONTINUED 0x80 /* Flag swap_map continuation for full count */ + +/* Special value in first swap_map */ +#define SWAP_MAP_MAX 0x3e /* Max count */ +#define SWAP_MAP_BAD 0x3f /* Note page is bad */ +#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */ + +/* Special value in each swap_map continuation */ +#define SWAP_CONT_MAX 0x7f /* Max count */ /* * We use this to track usage of a cluster. A cluster is a block of swap disk -- cgit v1.2.3 From 490705888107c3edf8c264ec930909107f76a984 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 1 Jun 2020 21:49:22 -0700 Subject: swap: reduce lock contention on swap cache from swap slots allocation In some swap scalability test, it is found that there are heavy lock contention on swap cache even if we have split one swap cache radix tree per swap device to one swap cache radix tree every 64 MB trunk in commit 4b3ef9daa4fc ("mm/swap: split swap cache into 64MB trunks"). The reason is as follow. After the swap device becomes fragmented so that there's no free swap cluster, the swap device will be scanned linearly to find the free swap slots. swap_info_struct->cluster_next is the next scanning base that is shared by all CPUs. So nearby free swap slots will be allocated for different CPUs. The probability for multiple CPUs to operate on the same 64 MB trunk is high. This causes the lock contention on the swap cache. To solve the issue, in this patch, for SSD swap device, a percpu version next scanning base (cluster_next_cpu) is added. Every CPU will use its own per-cpu next scanning base. And after finishing scanning a 64MB trunk, the per-cpu scanning base will be changed to the beginning of another randomly selected 64MB trunk. In this way, the probability for multiple CPUs to operate on the same 64 MB trunk is reduced greatly. Thus the lock contention is reduced too. For HDD, because sequential access is more important for IO performance, the original shared next scanning base is used. To test the patch, we have run 16-process pmbench memory benchmark on a 2-socket server machine with 48 cores. One ram disk is configured as the swap device per socket. The pmbench working-set size is much larger than the available memory so that swapping is triggered. The memory read/write ratio is 80/20 and the accessing pattern is random. In the original implementation, the lock contention on the swap cache is heavy. The perf profiling data of the lock contention code path is as following, _raw_spin_lock_irq.add_to_swap_cache.add_to_swap.shrink_page_list: 7.91 _raw_spin_lock_irqsave.__remove_mapping.shrink_page_list: 7.11 _raw_spin_lock.swapcache_free_entries.free_swap_slot.__swap_entry_free: 2.51 _raw_spin_lock_irqsave.swap_cgroup_record.mem_cgroup_uncharge_swap: 1.66 _raw_spin_lock_irq.shrink_inactive_list.shrink_lruvec.shrink_node: 1.29 _raw_spin_lock.free_pcppages_bulk.drain_pages_zone.drain_pages: 1.03 _raw_spin_lock_irq.shrink_active_list.shrink_lruvec.shrink_node: 0.93 After applying this patch, it becomes, _raw_spin_lock.swapcache_free_entries.free_swap_slot.__swap_entry_free: 3.58 _raw_spin_lock_irq.shrink_inactive_list.shrink_lruvec.shrink_node: 2.3 _raw_spin_lock_irqsave.swap_cgroup_record.mem_cgroup_uncharge_swap: 2.26 _raw_spin_lock_irq.shrink_active_list.shrink_lruvec.shrink_node: 1.8 _raw_spin_lock.free_pcppages_bulk.drain_pages_zone.drain_pages: 1.19 The lock contention on the swap cache is almost eliminated. And the pmbench score increases 18.5%. The swapin throughput increases 18.7% from 2.96 GB/s to 3.51 GB/s. While the swapout throughput increases 18.5% from 2.99 GB/s to 3.54 GB/s. We need really fast disk to show the benefit. I have tried this on 2 Intel P3600 NVMe disks. The performance improvement is only about 1%. The improvement should be better on the faster disks, such as Intel Optane disk. [ying.huang@intel.com: fix cluster_next_cpu allocation and freeing, per Daniel] Link: http://lkml.kernel.org/r/20200525002648.336325-1-ying.huang@intel.com [ying.huang@intel.com: v4] Link: http://lkml.kernel.org/r/20200529010840.928819-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Cc: Michal Hocko Cc: Minchan Kim Cc: Tim Chen Cc: Hugh Dickins Link: http://lkml.kernel.org/r/20200520031502.175659-1-ying.huang@intel.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 873bf5206afb..6c23a6a14012 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -252,6 +252,7 @@ struct swap_info_struct { unsigned int inuse_pages; /* number of those currently in use */ unsigned int cluster_next; /* likely index for next allocation */ unsigned int cluster_nr; /* countdown to next cluster search */ + unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ -- cgit v1.2.3 From 251af0cda614e5ad6bfda059bd120aed7432891d Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Mon, 1 Jun 2020 21:49:29 -0700 Subject: include/linux/swap.h: delete meaningless __add_to_swap_cache() declaration Since commit 8d93b41c09d1 ("mm: Convert add_to_swap_cache to XArray"), __add_to_swap_cache and add_to_swap_cache are combined into one function. There is no __add_to_swap_cache() anymore. Signed-off-by: Miaohe Lin Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Reviewed-by: "Huang, Ying" Link: http://lkml.kernel.org/r/1590810326-2493-1-git-send-email-linmiaohe@huawei.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6c23a6a14012..68ef7638311f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -414,7 +414,6 @@ extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); extern int add_to_swap(struct page *page); extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); -extern int __add_to_swap_cache(struct page *page, swp_entry_t entry); extern void __delete_from_swap_cache(struct page *, swp_entry_t entry); extern void delete_from_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); -- cgit v1.2.3 From d1663a907bd348f912b7f7088e83ca1b6fd3309f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 1 Jun 2020 21:49:49 -0700 Subject: mm/memcg: move cgroup high memory limit setting into struct page_counter High memory limit is currently recorded directly in struct mem_cgroup. We are about to add a high limit for swap, move the field to struct page_counter and add some helpers. Signed-off-by: Jakub Kicinski Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Chris Down Cc: Hugh Dickins Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200527195846.102707-4-kuba@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 --- include/linux/page_counter.h | 8 ++++++++ 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 977edd3b7bd8..95a09a7ec412 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -215,9 +215,6 @@ struct mem_cgroup { struct page_counter kmem; struct page_counter tcpmem; - /* Upper bound of normal memory consumption range */ - unsigned long high; - /* Range enforcement for interrupt charges */ struct work_struct high_work; diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index bab7e57f659b..85bd413e784e 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -10,6 +10,7 @@ struct page_counter { atomic_long_t usage; unsigned long min; unsigned long low; + unsigned long high; unsigned long max; struct page_counter *parent; @@ -55,6 +56,13 @@ bool page_counter_try_charge(struct page_counter *counter, void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages); void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages); + +static inline void page_counter_set_high(struct page_counter *counter, + unsigned long nr_pages) +{ + WRITE_ONCE(counter->high, nr_pages); +} + int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages); int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages); -- cgit v1.2.3 From 4b82ab4f28836646eca12cb37f408568d3cdc5c3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 1 Jun 2020 21:49:52 -0700 Subject: mm/memcg: automatically penalize tasks with high swap use Add a memory.swap.high knob, which can be used to protect the system from SWAP exhaustion. The mechanism used for penalizing is similar to memory.high penalty (sleep on return to user space). That is not to say that the knob itself is equivalent to memory.high. The objective is more to protect the system from potentially buggy tasks consuming a lot of swap and impacting other tasks, or even bringing the whole system to stand still with complete SWAP exhaustion. Hopefully without the need to find per-task hard limits. Slowing misbehaving tasks down gradually allows user space oom killers or other protection mechanisms to react. oomd and earlyoom already do killing based on swap exhaustion, and memory.swap.high protection will help implement such userspace oom policies more reliably. We can use one counter for number of pages allocated under pressure to save struct task space and avoid two separate hierarchy walks on the hot path. The exact overage is calculated on return to user space, anyway. Take the new high limit into account when determining if swap is "full". Borrowing the explanation from Johannes: The idea behind "swap full" is that as long as the workload has plenty of swap space available and it's not changing its memory contents, it makes sense to generously hold on to copies of data in the swap device, even after the swapin. A later reclaim cycle can drop the page without any IO. Trading disk space for IO. But the only two ways to reclaim a swap slot is when they're faulted in and the references go away, or by scanning the virtual address space like swapoff does - which is very expensive (one could argue it's too expensive even for swapoff, it's often more practical to just reboot). So at some point in the fill level, we have to start freeing up swap slots on fault/swapin. Otherwise we could eventually run out of swap slots while they're filled with copies of data that is also in RAM. We don't want to OOM a workload because its available swap space is filled with redundant cache. Signed-off-by: Jakub Kicinski Signed-off-by: Andrew Morton Acked-by: Johannes Weiner Cc: Tejun Heo Cc: Chris Down Cc: Shakeel Butt Cc: Michal Hocko Cc: Hugh Dickins Link: http://lkml.kernel.org/r/20200527195846.102707-5-kuba@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 95a09a7ec412..bfe9533bb67e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -45,6 +45,7 @@ enum memcg_memory_event { MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, + MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, -- cgit v1.2.3 From 1494e0c38ee903e83aefb58caf54a9217273d49a Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 1 Jun 2020 21:49:58 -0700 Subject: x86: mm: ptdump: calculate effective permissions correctly Patch series "Fix W+X debug feature on x86" Jan alerted me[1] that the W+X detection debug feature was broken in x86 by my change[2] to switch x86 to use the generic ptdump infrastructure. Fundamentally the approach of trying to move the calculation of effective permissions into note_page() was broken because note_page() is only called for 'leaf' entries and the effective permissions are passed down via the internal nodes of the page tree. The solution I've taken here is to create a new (optional) callback which is called for all nodes of the page tree and therefore can calculate the effective permissions. Secondly on some configurations (32 bit with PAE) "unsigned long" is not large enough to store the table entries. The fix here is simple - let's just use a u64. [1] https://lore.kernel.org/lkml/d573dc7e-e742-84de-473d-f971142fa319@suse.com/ [2] 2ae27137b2db ("x86: mm: convert dump_pagetables to use walk_page_range") This patch (of 2): By switching the x86 page table dump code to use the generic code the effective permissions are no longer calculated correctly because the note_page() function is only called for *leaf* entries. To calculate the actual effective permissions it is necessary to observe the full hierarchy of the page tree. Introduce a new callback for ptdump which is called for every entry and can therefore update the prot_levels array correctly. note_page() can then simply access the appropriate element in the array. [steven.price@arm.com: make the assignment conditional on val != 0] Link: http://lkml.kernel.org/r/430c8ab4-e7cd-6933-dde6-087fac6db872@arm.com Fixes: 2ae27137b2db ("x86: mm: convert dump_pagetables to use walk_page_range") Reported-by: Jan Beulich Signed-off-by: Steven Price Signed-off-by: Andrew Morton Cc: Qian Cai Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Link: http://lkml.kernel.org/r/20200521152308.33096-1-steven.price@arm.com Link: http://lkml.kernel.org/r/20200521152308.33096-2-steven.price@arm.com Signed-off-by: Linus Torvalds --- include/linux/ptdump.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ptdump.h b/include/linux/ptdump.h index a67065c403c3..ac01502763bf 100644 --- a/include/linux/ptdump.h +++ b/include/linux/ptdump.h @@ -14,6 +14,7 @@ struct ptdump_state { /* level is 0:PGD to 4:PTE, or -1 if unknown */ void (*note_page)(struct ptdump_state *st, unsigned long addr, int level, unsigned long val); + void (*effective_prot)(struct ptdump_state *st, int level, u64 val); const struct ptdump_range *range; }; -- cgit v1.2.3 From 99395ee3f7b4accc3a16a6aa4c2abb3774fc33ca Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 1 Jun 2020 21:50:01 -0700 Subject: mm: ptdump: expand type of 'val' in note_page() The page table entry is passed in the 'val' argument to note_page(), however this was previously an "unsigned long" which is fine on 64-bit platforms. But for 32 bit x86 it is not always big enough to contain a page table entry which may be 64 bits. Change the type to u64 to ensure that it is always big enough. [akpm@linux-foundation.org: fix riscv] Reported-by: Jan Beulich Signed-off-by: Steven Price Signed-off-by: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Link: http://lkml.kernel.org/r/20200521152308.33096-3-steven.price@arm.com Signed-off-by: Linus Torvalds --- include/linux/ptdump.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptdump.h b/include/linux/ptdump.h index ac01502763bf..2a3a95586425 100644 --- a/include/linux/ptdump.h +++ b/include/linux/ptdump.h @@ -13,7 +13,7 @@ struct ptdump_range { struct ptdump_state { /* level is 0:PGD to 4:PTE, or -1 if unknown */ void (*note_page)(struct ptdump_state *st, unsigned long addr, - int level, unsigned long val); + int level, u64 val); void (*effective_prot)(struct ptdump_state *st, int level, u64 val); const struct ptdump_range *range; }; -- cgit v1.2.3 From 4926627793c0a7e7db2bc674e1d06777e86d8dab Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:50:45 -0700 Subject: mm: remove __get_vm_area Switch the two remaining callers to use __get_vm_area_caller instead. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-9-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index a95d3cc74d79..ff69d1e037ca 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -161,8 +161,6 @@ static inline size_t get_vm_area_size(const struct vm_struct *area) extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags); extern struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller); -extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, - unsigned long start, unsigned long end); extern struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, -- cgit v1.2.3 From 8b136018da7bf49b988a24064fc45c290baffd93 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:50:53 -0700 Subject: mm: rename CONFIG_PGTABLE_MAPPING to CONFIG_ZSMALLOC_PGTABLE_MAPPING Rename the Kconfig variable to clarify the scope. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Minchan Kim Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-11-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/zsmalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 2219cce81ca4..0fdbf653b173 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -20,7 +20,7 @@ * zsmalloc mapping modes * * NOTE: These only make a difference when a mapped object spans pages. - * They also have no effect when PGTABLE_MAPPING is selected. + * They also have no effect when ZSMALLOC_PGTABLE_MAPPING is selected. */ enum zs_mapmode { ZS_MM_RW, /* normal read-write mapping */ -- cgit v1.2.3 From ed1f324c5fed06c91f30a36aedb66f34244ab86e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:19 -0700 Subject: mm: remove map_vm_range Switch all callers to map_kernel_range, which symmetric to the unmap side (as well as the _noflush versions). Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-17-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index ff69d1e037ca..a1e9bdc3ad9e 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -168,11 +168,11 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size, extern struct vm_struct *remove_vm_area(const void *addr); extern struct vm_struct *find_vm_area(const void *addr); -extern int map_vm_area(struct vm_struct *area, pgprot_t prot, - struct page **pages); #ifdef CONFIG_MMU extern int map_kernel_range_noflush(unsigned long start, unsigned long size, pgprot_t prot, struct page **pages); +int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot, + struct page **pages); extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size); extern void unmap_kernel_range(unsigned long addr, unsigned long size); static inline void set_vm_flush_reset_perms(void *addr) @@ -189,14 +189,12 @@ map_kernel_range_noflush(unsigned long start, unsigned long size, { return size >> PAGE_SHIFT; } +#define map_kernel_range map_kernel_range_noflush static inline void unmap_kernel_range_noflush(unsigned long addr, unsigned long size) { } -static inline void -unmap_kernel_range(unsigned long addr, unsigned long size) -{ -} +#define unmap_kernel_range unmap_kernel_range_noflush static inline void set_vm_flush_reset_perms(void *addr) { } -- cgit v1.2.3 From d4efd79a81abc7096a418ee3103f261cfb6ab634 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:27 -0700 Subject: mm: remove the prot argument from vm_map_ram This is always PAGE_KERNEL - for long term mappings with other properties vmap should be used. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-19-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index a1e9bdc3ad9e..5488cea5ef11 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -88,8 +88,7 @@ struct vmap_area { * Highlevel APIs for driver use */ extern void vm_unmap_ram(const void *mem, unsigned int count); -extern void *vm_map_ram(struct page **pages, unsigned int count, - int node, pgprot_t prot); +extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); #ifdef CONFIG_MMU -- cgit v1.2.3 From 88dca4ca5a93d2c09e5bbc6a62fbfc3af83c4fca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:40 -0700 Subject: mm: remove the pgprot argument to __vmalloc The pgprot argument to __vmalloc is always PAGE_KERNEL now, so remove it. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Reviewed-by: Michael Kelley [hyperv] Acked-by: Gao Xiang [erofs] Acked-by: Peter Zijlstra (Intel) Acked-by: Wei Liu Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-22-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 5488cea5ef11..1c278e030599 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -110,7 +110,7 @@ extern void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags); extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); -extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot); +extern void *__vmalloc(unsigned long size, gfp_t gfp_mask); extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, -- cgit v1.2.3 From 4d39d7285f45cc6c72b850f040d3addd626658e4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:49 -0700 Subject: mm: remove both instances of __vmalloc_node_flags The real version just had a few callers that can open code it and remove one layer of indirection. The nommu stub was public but only had a single caller, so remove it and avoid a CONFIG_MMU ifdef in vmalloc.h. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-24-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 1c278e030599..91d143783458 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -115,17 +115,8 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller); -#ifndef CONFIG_MMU -extern void *__vmalloc_node_flags(unsigned long size, int node, gfp_t flags); -static inline void *__vmalloc_node_flags_caller(unsigned long size, int node, - gfp_t flags, void *caller) -{ - return __vmalloc_node_flags(size, node, flags); -} -#else extern void *__vmalloc_node_flags_caller(unsigned long size, int node, gfp_t flags, void *caller); -#endif extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); -- cgit v1.2.3 From 2b9059489c839e67ca9254913325e18cea11a980 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:53 -0700 Subject: mm: remove __vmalloc_node_flags_caller Just use __vmalloc_node instead which gets and extra argument. To be able to to use __vmalloc_node in all caller make it available outside of vmalloc and implement it in nommu.c. [akpm@linux-foundation.org: fix nommu build] Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200414131348.444715-25-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 91d143783458..964d58a060ca 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -115,8 +115,8 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller); -extern void *__vmalloc_node_flags_caller(unsigned long size, - int node, gfp_t flags, void *caller); +void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, + int node, const void *caller); extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); -- cgit v1.2.3 From 041de93ff86fc500aa73e5360039c95f4d31b95f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:52:02 -0700 Subject: mm: remove vmalloc_user_node_flags Open code it in __bpf_map_area_alloc, which is the only caller. Also clean up __bpf_map_area_alloc to have a single vmalloc call with slightly different flags instead of the current two different calls. For this to compile for the nommu case add a __vmalloc_node_range stub to nommu.c. [akpm@linux-foundation.org: fix nommu.c build] Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200414131348.444715-27-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 964d58a060ca..3332926295d4 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -106,7 +106,6 @@ extern void *vzalloc(unsigned long size); extern void *vmalloc_user(unsigned long size); extern void *vmalloc_node(unsigned long size, int node); extern void *vzalloc_node(unsigned long size, int node); -extern void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags); extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); -- cgit v1.2.3 From d8626138009ba58ae2c22356966c2edaa1f1c3b5 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 1 Jun 2020 21:52:18 -0700 Subject: mm: add functions to track page directory modifications Patch series "mm: Get rid of vmalloc_sync_(un)mappings()", v3. After the recent issue with vmalloc and tracing code[1] on x86 and a long history of previous issues related to the vmalloc_sync_mappings() interface, I thought the time has come to remove it. Please see [2], [3], and [4] for some other issues in the past. The patches add tracking of page-table directory changes to the vmalloc and ioremap code. Depending on which page-table levels changes have been made, a new per-arch function is called: arch_sync_kernel_mappings(). On x86-64 with 4-level paging, this function will not be called more than 64 times in a systems runtime (because vmalloc-space takes 64 PGD entries which are only populated, but never cleared). As a side effect this also allows to get rid of vmalloc faults on x86, making it safe to touch vmalloc'ed memory in the page-fault handler. Note that this potentially includes per-cpu memory. This patch (of 7): Add page-table allocation functions which will keep track of changed directory entries. They are needed for new PGD, P4D, PUD, and PMD entries and will be used in vmalloc and ioremap code to decide whether any changes in the kernel mappings need to be synchronized between page-tables in the system. Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: "H . Peter Anvin" Cc: Dave Hansen Cc: "Rafael J. Wysocki" Cc: Arnd Bergmann Cc: Steven Rostedt (VMware) Cc: Vlastimil Babka Cc: Michal Hocko Cc: Matthew Wilcox (Oracle) Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20200515140023.25469-1-joro@8bytes.org Link: http://lkml.kernel.org/r/20200515140023.25469-2-joro@8bytes.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ebbb0acbeee2..fda41eb7f1c8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2091,13 +2091,54 @@ static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address); } + +static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, + unsigned long address, + pgtbl_mod_mask *mod_mask) + +{ + if (unlikely(pgd_none(*pgd))) { + if (__p4d_alloc(mm, pgd, address)) + return NULL; + *mod_mask |= PGTBL_PGD_MODIFIED; + } + + return p4d_offset(pgd, address); +} + #endif /* !__ARCH_HAS_5LEVEL_HACK */ +static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(p4d_none(*p4d))) { + if (__pud_alloc(mm, p4d, address)) + return NULL; + *mod_mask |= PGTBL_P4D_MODIFIED; + } + + return pud_offset(p4d, address); +} + static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } + +static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(pud_none(*pud))) { + if (__pmd_alloc(mm, pud, address)) + return NULL; + *mod_mask |= PGTBL_PUD_MODIFIED; + } + + return pmd_offset(pud, address); +} #endif /* CONFIG_MMU */ #if USE_SPLIT_PTE_PTLOCKS @@ -2213,6 +2254,11 @@ static inline void pgtable_pte_page_dtor(struct page *page) ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) +#define pte_alloc_kernel_track(pmd, address, mask) \ + ((unlikely(pmd_none(*(pmd))) && \ + (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ + NULL: pte_offset_kernel(pmd, address)) + #if USE_SPLIT_PMD_PTLOCKS static struct page *pmd_to_page(pmd_t *pmd) -- cgit v1.2.3 From 2ba3e6947aed9bb9575eb1603c0ac6e39185d32a Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 1 Jun 2020 21:52:22 -0700 Subject: mm/vmalloc: track which page-table levels were modified Track at which levels in the page-table entries were modified by vmap/vunmap. After the page-table has been modified, use that information do decide whether the new arch_sync_kernel_mappings() needs to be called. [akpm@linux-foundation.org: map_kernel_range_noflush() needs the arch_sync_kernel_mappings() call] Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: Dave Hansen Cc: "H . Peter Anvin" Cc: Ingo Molnar Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Vlastimil Babka Link: http://lkml.kernel.org/r/20200515140023.25469-3-joro@8bytes.org Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3332926295d4..0efc35dc5b25 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -133,6 +133,22 @@ extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, void vmalloc_sync_mappings(void); void vmalloc_sync_unmappings(void); +/* + * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values + * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() + * needs to be called. + */ +#ifndef ARCH_PAGE_TABLE_SYNC_MASK +#define ARCH_PAGE_TABLE_SYNC_MASK 0 +#endif + +/* + * There is no default implementation for arch_sync_kernel_mappings(). It is + * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK + * is 0. + */ +void arch_sync_kernel_mappings(unsigned long start, unsigned long end); + /* * Lowlevel-APIs (not for driver use!) */ -- cgit v1.2.3 From 73f693c3a705756032c2863bfb37570276902d7d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 1 Jun 2020 21:52:36 -0700 Subject: mm: remove vmalloc_sync_(un)mappings() These functions are not needed anymore because the vmalloc and ioremap mappings are now synchronized when they are created or torn down. Remove all callers and function definitions. Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Tested-by: Steven Rostedt (VMware) Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: Dave Hansen Cc: "H . Peter Anvin" Cc: Ingo Molnar Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: "Rafael J. Wysocki" Cc: Thomas Gleixner Cc: Vlastimil Babka Link: http://lkml.kernel.org/r/20200515140023.25469-7-joro@8bytes.org Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 0efc35dc5b25..48bb681e6c2a 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -130,8 +130,6 @@ extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); -void vmalloc_sync_mappings(void); -void vmalloc_sync_unmappings(void); /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values -- cgit v1.2.3 From 836e66c218f355ec01ba57671c85abf32961dcea Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 2 Jun 2020 16:58:32 +0200 Subject: bpf: Fix up bpf_skb_adjust_room helper's skb csum setting Lorenz recently reported: In our TC classifier cls_redirect [0], we use the following sequence of helper calls to decapsulate a GUE (basically IP + UDP + custom header) encapsulated packet: bpf_skb_adjust_room(skb, -encap_len, BPF_ADJ_ROOM_MAC, BPF_F_ADJ_ROOM_FIXED_GSO) bpf_redirect(skb->ifindex, BPF_F_INGRESS) It seems like some checksums of the inner headers are not validated in this case. For example, a TCP SYN packet with invalid TCP checksum is still accepted by the network stack and elicits a SYN ACK. [...] That is, we receive the following packet from the driver: | ETH | IP | UDP | GUE | IP | TCP | skb->ip_summed == CHECKSUM_UNNECESSARY ip_summed is CHECKSUM_UNNECESSARY because our NICs do rx checksum offloading. On this packet we run skb_adjust_room_mac(-encap_len), and get the following: | ETH | IP | TCP | skb->ip_summed == CHECKSUM_UNNECESSARY Note that ip_summed is still CHECKSUM_UNNECESSARY. After bpf_redirect()'ing into the ingress, we end up in tcp_v4_rcv(). There, skb_checksum_init() is turned into a no-op due to CHECKSUM_UNNECESSARY. The bpf_skb_adjust_room() helper is not aware of protocol specifics. Internally, it handles the CHECKSUM_COMPLETE case via skb_postpull_rcsum(), but that does not cover CHECKSUM_UNNECESSARY. In this case skb->csum_level of the original skb prior to bpf_skb_adjust_room() call was 0, that is, covering UDP. Right now there is no way to adjust the skb->csum_level. NICs that have checksum offload disabled (CHECKSUM_NONE) or that support CHECKSUM_COMPLETE are not affected. Use a safe default for CHECKSUM_UNNECESSARY by resetting to CHECKSUM_NONE and add a flag to the helper called BPF_F_ADJ_ROOM_NO_CSUM_RESET that allows users from opting out. Opting out is useful for the case where we don't remove/add full protocol headers, or for the case where a user wants to adjust the csum level manually e.g. through bpf_csum_level() helper that is added in subsequent patch. The bpf_skb_proto_{4_to_6,6_to_4}() for NAT64/46 translation from the BPF bpf_skb_change_proto() helper uses bpf_skb_net_hdr_{push,pop}() pair internally as well but doesn't change layers, only transitions between v4 to v6 and vice versa, therefore no adoption is required there. [0] https://lore.kernel.org/bpf/20200424185556.7358-1-lmb@cloudflare.com/ Fixes: 2be7e212d541 ("bpf: add bpf_skb_adjust_room helper") Reported-by: Lorenz Bauer Reported-by: Alan Maguire Signed-off-by: Daniel Borkmann Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Reviewed-by: Alan Maguire Link: https://lore.kernel.org/bpf/CACAyw9-uU_52esMd1JjuA80fRPHJv5vsSg8GnfW3t_qDU4aVKQ@mail.gmail.com/ Link: https://lore.kernel.org/bpf/11a90472e7cce83e76ddbfce81fdfce7bfc68808.1591108731.git.daniel@iogearbox.net --- include/linux/skbuff.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a0d5c2760103..0c0377fc00c2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3919,6 +3919,14 @@ static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) } } +static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) +{ + if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + skb->ip_summed = CHECKSUM_NONE; + skb->csum_level = 0; + } +} + /* Check if we need to perform checksum complete validation. * * Returns true if checksum complete is needed, false otherwise -- cgit v1.2.3 From 1f55b7ab907d373581e9abf3fc4b24ed19cf831f Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 28 May 2020 16:45:50 -0300 Subject: RDMA/mlx4: Remove FMR support for memory registration HCA's that are driven by mlx4 driver support FRWR method to register memory. Remove the ancient and unsafe FMR method. Link: https://lore.kernel.org/r/8-v3-f58e6669d5d3+2cf-fmr_removal_jgg@mellanox.com Reviewed-by: Max Gurtovoy Signed-off-by: Max Gurtovoy Signed-off-by: Jason Gunthorpe --- include/linux/mlx4/device.h | 22 ++-------------------- 1 file changed, 2 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 20372de0b587..06e066e04a4b 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -573,7 +573,6 @@ struct mlx4_caps { int reserved_eqs; int num_comp_vectors; int num_mpts; - int max_fmr_maps; int num_mtts; int fmr_reserved_mtts; int reserved_mtts; @@ -707,17 +706,6 @@ struct mlx4_mw { int enabled; }; -struct mlx4_fmr { - struct mlx4_mr mr; - struct mlx4_mpt_entry *mpt; - __be64 *mtts; - dma_addr_t dma_handle; - int max_pages; - int max_maps; - int maps; - u8 page_shift; -}; - struct mlx4_uar { unsigned long pfn; int index; @@ -1412,14 +1400,6 @@ int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx); int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index); void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan); -int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list, - int npages, u64 iova, u32 *lkey, u32 *rkey); -int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages, - int max_maps, u8 page_shift, struct mlx4_fmr *fmr); -int mlx4_fmr_enable(struct mlx4_dev *dev, struct mlx4_fmr *fmr); -void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr, - u32 *lkey, u32 *rkey); -int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr); int mlx4_SYNC_TPT(struct mlx4_dev *dev); int mlx4_test_interrupt(struct mlx4_dev *dev, int vector); int mlx4_test_async(struct mlx4_dev *dev); @@ -1522,6 +1502,8 @@ int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port); int mlx4_vf_get_enable_smi_admin(struct mlx4_dev *dev, int slave, int port); int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port, int enable); + +struct mlx4_mpt_entry; int mlx4_mr_hw_get_mpt(struct mlx4_dev *dev, struct mlx4_mr *mmr, struct mlx4_mpt_entry ***mpt_entry); int mlx4_mr_hw_write_mpt(struct mlx4_dev *dev, struct mlx4_mr *mmr, -- cgit v1.2.3 From 649392bf75a423287a9c4936b341677f12e8cf0b Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 28 May 2020 16:45:54 -0300 Subject: RDMA: Remove 'max_fmr' Now that FMR support is gone, this attribute can be deleted from all places. Link: https://lore.kernel.org/r/12-v3-f58e6669d5d3+2cf-fmr_removal_jgg@mellanox.com Reviewed-by: Max Gurtovoy Reviewed-by: Bernard Metzler Signed-off-by: Jason Gunthorpe --- include/linux/qed/qed_rdma_if.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index 74efca15fde7..c90276cda5c1 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -91,7 +91,6 @@ struct qed_rdma_device { u64 max_mr_size; u32 max_cqe; u32 max_mw; - u32 max_fmr; u32 max_mr_mw_fmr_pbl; u64 max_mr_mw_fmr_size; u32 max_pd; -- cgit v1.2.3 From 6a45b0e2589fafd7fc501a5fbd0ab56689a08124 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Thu, 28 May 2020 16:58:43 +0200 Subject: gpiolib: Introduce gpiochip_irqchip_add_domain() The function connects an IRQ domain to a gpiochip and reuses gpiochip_to_irq() which is provided by gpiolib. gpiochip_irqchip_* and regmap_irq partially provide the same functionality. This function will help to connect just the minimal functionality of the gpiochip_irqchip which is needed to work together with regmap-irq. Signed-off-by: Michael Walle Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200528145845.31436-2-michael@walle.cc Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index c8bcaf315d03..c4f272af7af5 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -612,6 +612,9 @@ int gpiochip_irqchip_add_key(struct gpio_chip *gc, bool gpiochip_irqchip_irq_valid(const struct gpio_chip *gc, unsigned int offset); +int gpiochip_irqchip_add_domain(struct gpio_chip *gc, + struct irq_domain *domain); + #ifdef CONFIG_LOCKDEP /* -- cgit v1.2.3 From ebe363197e525ffbd279c729421f6f6c24d8d681 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Thu, 28 May 2020 16:58:44 +0200 Subject: gpio: add a reusable generic gpio_chip using regmap There are quite a lot simple GPIO controller which are using regmap to access the hardware. This driver tries to be a base to unify existing code into one place. This won't cover everything but it should be a good starting point. It does not implement its own irq_chip because there is already a generic one for regmap based devices. Instead, the irq_chip will be instantiated in the parent driver and its irq domain will be associate to this driver. For now it consists of the usual registers, like set (and an optional clear) data register, an input register and direction registers. Out-of-the-box, it supports consecutive register mappings and mappings where the registers have gaps between them with a linear mapping between GPIO offset and bit position. For weirder mappings the user can register its own .xlate(). Signed-off-by: Michael Walle Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200528145845.31436-3-michael@walle.cc Signed-off-by: Linus Walleij --- include/linux/gpio/regmap.h | 86 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) create mode 100644 include/linux/gpio/regmap.h (limited to 'include/linux') diff --git a/include/linux/gpio/regmap.h b/include/linux/gpio/regmap.h new file mode 100644 index 000000000000..4c1e6b34e824 --- /dev/null +++ b/include/linux/gpio/regmap.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _LINUX_GPIO_REGMAP_H +#define _LINUX_GPIO_REGMAP_H + +struct device; +struct gpio_regmap; +struct irq_domain; +struct regmap; + +#define GPIO_REGMAP_ADDR_ZERO ((unsigned long)(-1)) +#define GPIO_REGMAP_ADDR(addr) ((addr) ? : GPIO_REGMAP_ADDR_ZERO) + +/** + * struct gpio_regmap_config - Description of a generic regmap gpio_chip. + * @parent: The parent device + * @regmap: The regmap used to access the registers + * given, the name of the device is used + * @label: (Optional) Descriptive name for GPIO controller. + * If not given, the name of the device is used. + * @ngpio: Number of GPIOs + * @names: (Optional) Array of names for gpios + * @reg_dat_base: (Optional) (in) register base address + * @reg_set_base: (Optional) set register base address + * @reg_clr_base: (Optional) clear register base address + * @reg_dir_in_base: (Optional) in setting register base address + * @reg_dir_out_base: (Optional) out setting register base address + * @reg_stride: (Optional) May be set if the registers (of the + * same type, dat, set, etc) are not consecutive. + * @ngpio_per_reg: Number of GPIOs per register + * @irq_domain: (Optional) IRQ domain if the controller is + * interrupt-capable + * @reg_mask_xlate: (Optional) Translates base address and GPIO + * offset to a register/bitmask pair. If not + * given the default gpio_regmap_simple_xlate() + * is used. + * + * The ->reg_mask_xlate translates a given base address and GPIO offset to + * register and mask pair. The base address is one of the given register + * base addresses in this structure. + * + * Although all register base addresses are marked as optional, there are + * several rules: + * 1. if you only have @reg_dat_base set, then it is input-only + * 2. if you only have @reg_set_base set, then it is output-only + * 3. if you have either @reg_dir_in_base or @reg_dir_out_base set, then + * you have to set both @reg_dat_base and @reg_set_base + * 4. if you have @reg_set_base set, you may also set @reg_clr_base to have + * two different registers for setting and clearing the output. This is + * also valid for the output-only case. + * 5. @reg_dir_in_base and @reg_dir_out_base are exclusive; is there really + * hardware which has redundant registers? + * + * Note: All base addresses may have the special value %GPIO_REGMAP_ADDR_ZERO + * which forces the address to the value 0. + */ +struct gpio_regmap_config { + struct device *parent; + struct regmap *regmap; + + const char *label; + int ngpio; + const char *const *names; + + unsigned int reg_dat_base; + unsigned int reg_set_base; + unsigned int reg_clr_base; + unsigned int reg_dir_in_base; + unsigned int reg_dir_out_base; + int reg_stride; + int ngpio_per_reg; + struct irq_domain *irq_domain; + + int (*reg_mask_xlate)(struct gpio_regmap *gpio, unsigned int base, + unsigned int offset, unsigned int *reg, + unsigned int *mask); +}; + +struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config); +void gpio_regmap_unregister(struct gpio_regmap *gpio); +struct gpio_regmap *devm_gpio_regmap_register(struct device *dev, + const struct gpio_regmap_config *config); +void gpio_regmap_set_drvdata(struct gpio_regmap *gpio, void *data); +void *gpio_regmap_get_drvdata(struct gpio_regmap *gpio); + +#endif /* _LINUX_GPIO_REGMAP_H */ -- cgit v1.2.3 From a645a89d9a780a8fbb6e283f84fc91ad538c2edc Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 2 Jun 2020 15:55:48 +0300 Subject: RDMA/mlx5: Return ECE DC support The DC QPs are many-to-one QP types that means that first connection will establish ECE options that coming connections should follow. Due to this property, the ECE code was removed between first [1] and second [2] ECE submissions. This patch returns the dropped code, because ECE is a property of a connection and like any other connection users are needed to manage this data. Allow them to set ECE parameter for DC too and avoid need of having compatibility flag for the DC ECE. [1] https://lore.kernel.org/linux-rdma/20200523132243.817936-1-leon@kernel.org/ [2] https://lore.kernel.org/linux-rdma/20200525174401.71152-1-leon@kernel.org/ Link: https://lore.kernel.org/r/20200602125548.172654-4-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4d2e36dd2c6b..116bd9bb347f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3690,7 +3690,8 @@ struct mlx5_ifc_dctc_bits { u8 ecn[0x2]; u8 dscp[0x6]; - u8 reserved_at_1c0[0x40]; + u8 reserved_at_1c0[0x20]; + u8 ece[0x20]; }; enum { @@ -7940,7 +7941,7 @@ struct mlx5_ifc_create_dct_out_bits { u8 reserved_at_40[0x8]; u8 dctn[0x18]; - u8 reserved_at_60[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_create_dct_in_bits { -- cgit v1.2.3 From 5ea75ae6ae60d13dfa35fd5d2e2a81824cba6662 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 18 Feb 2020 17:30:05 -0500 Subject: user_regset_copyout_zero(): use clear_user() that's the only caller of __clear_user() in generic code, and it's not hot enough to bother with skipping access_ok(). Signed-off-by: Al Viro --- include/linux/regset.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h index bf0243779738..46d6ae68c455 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -320,7 +320,7 @@ static inline int user_regset_copyout_zero(unsigned int *pos, if (*kbuf) { memset(*kbuf, 0, copy); *kbuf += copy; - } else if (__clear_user(*ubuf, copy)) + } else if (clear_user(*ubuf, copy)) return -EFAULT; else *ubuf += copy; -- cgit v1.2.3 From 376a34efa4eeb699d285c1a741b186d44b44c429 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Wed, 3 Jun 2020 15:56:30 -0700 Subject: mm/gup: refactor and de-duplicate gup_fast() code There were two nearly identical sets of code for gup_fast() style of walking the page tables with interrupts disabled. This has lead to the usual maintenance problems that arise from having duplicated code. There is already a core internal routine in gup.c for gup_fast(), so just enhance it very slightly: allow skipping the fall-back to "slow" (regular) get_user_pages(), via the new FOLL_FAST_ONLY flag. Then, just call internal_get_user_pages_fast() from __get_user_pages_fast(), and adjust the API to match pre-existing API behavior. There is a change in behavior from this refactoring: the nested form of interrupt disabling is used in all gup_fast() variants now. That's because there is only one place that interrupt disabling for page walking is done, and so the safer form is required. This should, if anything, eliminate possible (rare) bugs, because the non-nested form of enabling interrupts was fragile at best. [jhubbard@nvidia.com: fixup] Link: http://lkml.kernel.org/r/20200521233841.1279742-1-jhubbard@nvidia.com Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Reviewed-by: Chris Wilson Cc: Daniel Vetter Cc: David Airlie Cc: Jani Nikula Cc: "Joonas Lahtinen" Cc: Matthew Auld Cc: Matthew Wilcox Cc: Rodrigo Vivi Cc: Souptick Joarder Cc: Tvrtko Ursulin Link: http://lkml.kernel.org/r/20200519002124.2025955-3-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7e07f4f490cb..e6b884715da1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2816,6 +2816,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ #define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */ +#define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */ /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each -- cgit v1.2.3 From 104acc327648b347d1716374586803e82fa1dc95 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Wed, 3 Jun 2020 15:56:34 -0700 Subject: mm/gup: introduce pin_user_pages_fast_only() This is the FOLL_PIN equivalent of __get_user_pages_fast(), except with a more descriptive name, and gup_flags instead of a boolean "write" in the argument list. Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Reviewed-by: Chris Wilson Cc: Daniel Vetter Cc: David Airlie Cc: Jani Nikula Cc: "Joonas Lahtinen" Cc: Matthew Auld Cc: Matthew Wilcox Cc: Rodrigo Vivi Cc: Souptick Joarder Cc: Tvrtko Ursulin Link: http://lkml.kernel.org/r/20200519002124.2025955-4-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e6b884715da1..6c236c5b0015 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1827,6 +1827,8 @@ extern int mprotect_fixup(struct vm_area_struct *vma, */ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); +int pin_user_pages_fast_only(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); /* * per-process(per-mm_struct) statistics. */ -- cgit v1.2.3 From 47227d27e2fcb01a9e8f5958d8997cf47a820afc Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Wed, 3 Jun 2020 15:56:46 -0700 Subject: string.h: fix incompatibility between FORTIFY_SOURCE and KASAN The memcmp KASAN self-test fails on a kernel with both KASAN and FORTIFY_SOURCE. When FORTIFY_SOURCE is on, a number of functions are replaced with fortified versions, which attempt to check the sizes of the operands. However, these functions often directly invoke __builtin_foo() once they have performed the fortify check. Using __builtins may bypass KASAN checks if the compiler decides to inline it's own implementation as sequence of instructions, rather than emit a function call that goes out to a KASAN-instrumented implementation. Why is only memcmp affected? ============================ Of the string and string-like functions that kasan_test tests, only memcmp is replaced by an inline sequence of instructions in my testing on x86 with gcc version 9.2.1 20191008 (Ubuntu 9.2.1-9ubuntu2). I believe this is due to compiler heuristics. For example, if I annotate kmalloc calls with the alloc_size annotation (and disable some fortify compile-time checking!), the compiler will replace every memset except the one in kmalloc_uaf_memset with inline instructions. (I have some WIP patches to add this annotation.) Does this affect other functions in string.h? ============================================= Yes. Anything that uses __builtin_* rather than __real_* could be affected. This looks like: - strncpy - strcat - strlen - strlcpy maybe, under some circumstances? - strncat under some circumstances - memset - memcpy - memmove - memcmp (as noted) - memchr - strcpy Whether a function call is emitted always depends on the compiler. Most bugs should get caught by FORTIFY_SOURCE, but the missed memcmp test shows that this is not always the case. Isn't FORTIFY_SOURCE disabled with KASAN? ========================================- The string headers on all arches supporting KASAN disable fortify with kasan, but only when address sanitisation is _also_ disabled. For example from x86: #if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) /* * For files that are not instrumented (e.g. mm/slub.c) we * should use not instrumented version of mem* functions. */ #define memcpy(dst, src, len) __memcpy(dst, src, len) #define memmove(dst, src, len) __memmove(dst, src, len) #define memset(s, c, n) __memset(s, c, n) #ifndef __NO_FORTIFY #define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ #endif #endif This comes from commit 6974f0c4555e ("include/linux/string.h: add the option of fortified string.h functions"), and doesn't work when KASAN is enabled and the file is supposed to be sanitised - as with test_kasan.c I'm pretty sure this is not wrong, but not as expansive it should be: * we shouldn't use __builtin_memcpy etc in files where we don't have instrumentation - it could devolve into a function call to memcpy, which will be instrumented. Rather, we should use __memcpy which by convention is not instrumented. * we also shouldn't be using __builtin_memcpy when we have a KASAN instrumented file, because it could be replaced with inline asm that will not be instrumented. What is correct behaviour? ========================== Firstly, there is some overlap between fortification and KASAN: both provide some level of _runtime_ checking. Only fortify provides compile-time checking. KASAN and fortify can pick up different things at runtime: - Some fortify functions, notably the string functions, could easily be modified to consider sub-object sizes (e.g. members within a struct), and I have some WIP patches to do this. KASAN cannot detect these because it cannot insert poision between members of a struct. - KASAN can detect many over-reads/over-writes when the sizes of both operands are unknown, which fortify cannot. So there are a couple of options: 1) Flip the test: disable fortify in santised files and enable it in unsanitised files. This at least stops us missing KASAN checking, but we lose the fortify checking. 2) Make the fortify code always call out to real versions. Do this only for KASAN, for fear of losing the inlining opportunities we get from __builtin_*. (We can't use kasan_check_{read,write}: because the fortify functions are _extern inline_, you can't include _static_ inline functions without a compiler warning. kasan_check_{read,write} are static inline so we can't use them even when they would otherwise be suitable.) Take approach 2 and call out to real versions when KASAN is enabled. Use __underlying_foo to distinguish from __real_foo: __real_foo always refers to the kernel's implementation of foo, __underlying_foo could be either the kernel implementation or the __builtin_foo implementation. This is sometimes enough to make the memcmp test succeed with FORTIFY_SOURCE enabled. It is at least enough to get the function call into the module. One more fix is needed to make it reliable: see the next patch. Fixes: 6974f0c4555e ("include/linux/string.h: add the option of fortified string.h functions") Signed-off-by: Daniel Axtens Signed-off-by: Andrew Morton Tested-by: David Gow Reviewed-by: Dmitry Vyukov Cc: Daniel Micay Cc: Andrey Ryabinin Cc: Alexander Potapenko Link: http://lkml.kernel.org/r/20200423154503.5103-3-dja@axtens.net Signed-off-by: Linus Torvalds --- include/linux/string.h | 60 ++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 48 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 6dfbb2efa815..9b7a0632e87a 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -272,6 +272,31 @@ void __read_overflow3(void) __compiletime_error("detected read beyond size of ob void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) + +#ifdef CONFIG_KASAN +extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); +extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); +extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); +extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); +extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); +extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); +extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); +#else +#define __underlying_memchr __builtin_memchr +#define __underlying_memcmp __builtin_memcmp +#define __underlying_memcpy __builtin_memcpy +#define __underlying_memmove __builtin_memmove +#define __underlying_memset __builtin_memset +#define __underlying_strcat __builtin_strcat +#define __underlying_strcpy __builtin_strcpy +#define __underlying_strlen __builtin_strlen +#define __underlying_strncat __builtin_strncat +#define __underlying_strncpy __builtin_strncpy +#endif + __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -279,14 +304,14 @@ __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) __write_overflow(); if (p_size < size) fortify_panic(__func__); - return __builtin_strncpy(p, q, size); + return __underlying_strncpy(p, q, size); } __FORTIFY_INLINE char *strcat(char *p, const char *q) { size_t p_size = __builtin_object_size(p, 0); if (p_size == (size_t)-1) - return __builtin_strcat(p, q); + return __underlying_strcat(p, q); if (strlcat(p, q, p_size) >= p_size) fortify_panic(__func__); return p; @@ -300,7 +325,7 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p) /* Work around gcc excess stack consumption issue */ if (p_size == (size_t)-1 || (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) - return __builtin_strlen(p); + return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) fortify_panic(__func__); @@ -333,7 +358,7 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) __write_overflow(); if (len >= p_size) fortify_panic(__func__); - __builtin_memcpy(p, q, len); + __underlying_memcpy(p, q, len); p[len] = '\0'; } return ret; @@ -346,12 +371,12 @@ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __builtin_strncat(p, q, count); + return __underlying_strncat(p, q, count); p_len = strlen(p); copy_len = strnlen(q, count); if (p_size < p_len + copy_len + 1) fortify_panic(__func__); - __builtin_memcpy(p + p_len, q, copy_len); + __underlying_memcpy(p + p_len, q, copy_len); p[p_len + copy_len] = '\0'; return p; } @@ -363,7 +388,7 @@ __FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) __write_overflow(); if (p_size < size) fortify_panic(__func__); - return __builtin_memset(p, c, size); + return __underlying_memset(p, c, size); } __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) @@ -378,7 +403,7 @@ __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) } if (p_size < size || q_size < size) fortify_panic(__func__); - return __builtin_memcpy(p, q, size); + return __underlying_memcpy(p, q, size); } __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) @@ -393,7 +418,7 @@ __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) } if (p_size < size || q_size < size) fortify_panic(__func__); - return __builtin_memmove(p, q, size); + return __underlying_memmove(p, q, size); } extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); @@ -419,7 +444,7 @@ __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) } if (p_size < size || q_size < size) fortify_panic(__func__); - return __builtin_memcmp(p, q, size); + return __underlying_memcmp(p, q, size); } __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) @@ -429,7 +454,7 @@ __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) __read_overflow(); if (p_size < size) fortify_panic(__func__); - return __builtin_memchr(p, c, size); + return __underlying_memchr(p, c, size); } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); @@ -460,11 +485,22 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q) size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __builtin_strcpy(p, q); + return __underlying_strcpy(p, q); memcpy(p, q, strlen(q) + 1); return p; } +/* Don't use these outside the FORITFY_SOURCE implementation */ +#undef __underlying_memchr +#undef __underlying_memcmp +#undef __underlying_memcpy +#undef __underlying_memmove +#undef __underlying_memset +#undef __underlying_strcat +#undef __underlying_strcpy +#undef __underlying_strlen +#undef __underlying_strncat +#undef __underlying_strncpy #endif /** -- cgit v1.2.3 From 574c1ae66c12410a08aeef8474936baa50e0371d Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 3 Jun 2020 15:56:49 -0700 Subject: mm: clarify __GFP_MEMALLOC usage It seems that the existing documentation is not explicit about the expected usage and potential risks enough. While it is calls out that users have to free memory when using this flag it is not really apparent that users have to careful to not deplete memory reserves and that they should implement some sort of throttling wrt. freeing process. This is partly based on Neil's explanation [1]. Let's also call out that a pre allocated pool allocator should be considered. [1] http://lkml.kernel.org/r/877dz0yxoa.fsf@notabene.neil.brown.name [akpm@linux-foundation.org: coding style fixes] [mhocko@kernel.org: update] Link: http://lkml.kernel.org/r/20200406070137.GC19426@dhcp22.suse.cz Signed-off-by: Michal Hocko Signed-off-by: Andrew Morton Cc: David Rientjes Cc: Joel Fernandes Cc: Neil Brown Cc: Paul E. McKenney Cc: John Hubbard Link: http://lkml.kernel.org/r/20200403083543.11552-2-mhocko@kernel.org Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 4aba4c86c626..fab6d486cbb7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -110,6 +110,11 @@ struct vm_area_struct; * the caller guarantees the allocation will allow more memory to be freed * very shortly e.g. process exiting or swapping. Users either should * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). + * Users of this flag have to be extremely careful to not deplete the reserve + * completely and implement a throttling mechanism which controls the + * consumption of the reserve based on the amount of freed memory. + * Usage of a pre-allocated pool (e.g. mempool) should be always considered + * before using this flag. * * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. * This takes precedence over the %__GFP_MEMALLOC flag if both are set. -- cgit v1.2.3 From 6f24fbd38c4e05f7905814791806c01dc6c4b9de Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:56:57 -0700 Subject: mm: make early_pfn_to_nid() and related defintions close to each other early_pfn_to_nid() and its helper __early_pfn_to_nid() are spread around include/linux/mm.h, include/linux/mmzone.h and mm/page_alloc.c. Drop unused stub for __early_pfn_to_nid() and move its actual generic implementation close to its users. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Reviewed-by: Baoquan He Cc: Brian Cain Cc: Catalin Marinas Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-3-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- include/linux/mmzone.h | 9 --------- 2 files changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6c236c5b0015..4288e6993dc8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2445,9 +2445,9 @@ extern void sparse_memory_present_with_active_regions(int nid); #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) -static inline int __early_pfn_to_nid(unsigned long pfn, - struct mminit_pfnnid_cache *state) +static inline int early_pfn_to_nid(unsigned long pfn) { + BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); return 0; } #else diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fdd9beb5efed..c3a77eb85b42 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1080,15 +1080,6 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #include #endif -#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \ - !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) -static inline unsigned long early_pfn_to_nid(unsigned long pfn) -{ - BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); - return 0; -} -#endif - #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif -- cgit v1.2.3 From 3f08a302f533f74ad2e909e7a61274aa7eebc0ab Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:57:02 -0700 Subject: mm: remove CONFIG_HAVE_MEMBLOCK_NODE_MAP option CONFIG_HAVE_MEMBLOCK_NODE_MAP is used to differentiate initialization of nodes and zones structures between the systems that have region to node mapping in memblock and those that don't. Currently all the NUMA architectures enable this option and for the non-NUMA systems we can presume that all the memory belongs to node 0 and therefore the compile time configuration option is not required. The remaining few architectures that use DISCONTIGMEM without NUMA are easily updated to use memblock_add_node() instead of memblock_add() and thus have proper correspondence of memblock regions to NUMA nodes. Still, free_area_init_node() must have a backward compatible version because its semantics with and without CONFIG_HAVE_MEMBLOCK_NODE_MAP is different. Once all the architectures will use the new semantics, the entire compatibility layer can be dropped. To avoid addition of extra run time memory to store node id for architectures that keep memblock but have only a single node, the node id field of the memblock_region is guarded by CONFIG_NEED_MULTIPLE_NODES and the corresponding accessors presume that in those cases it is always 0. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Acked-by: Catalin Marinas [arm64] Cc: Baoquan He Cc: Brian Cain Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-4-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 8 +++----- include/linux/mm.h | 12 ++---------- include/linux/mmzone.h | 2 +- 3 files changed, 6 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 6bc37a731d27..45abfc54da37 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -50,7 +50,7 @@ struct memblock_region { phys_addr_t base; phys_addr_t size; enum memblock_flags flags; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +#ifdef CONFIG_NEED_MULTIPLE_NODES int nid; #endif }; @@ -215,7 +215,6 @@ static inline bool memblock_is_nomap(struct memblock_region *m) return m->flags & MEMBLOCK_NOMAP; } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, @@ -234,7 +233,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, #define for_each_mem_pfn_range(i, nid, p_start, p_end, p_nid) \ for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \ i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid)) -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, @@ -310,10 +308,10 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ nid, flags, p_start, p_end, p_nid) -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid); +#ifdef CONFIG_NEED_MULTIPLE_NODES static inline void memblock_set_region_node(struct memblock_region *r, int nid) { r->nid = nid; @@ -332,7 +330,7 @@ static inline int memblock_get_region_node(const struct memblock_region *r) { return 0; } -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +#endif /* CONFIG_NEED_MULTIPLE_NODES */ /* Flags for memblock allocation APIs */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) diff --git a/include/linux/mm.h b/include/linux/mm.h index 4288e6993dc8..5f15d8723167 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2401,9 +2401,8 @@ static inline unsigned long get_num_physpages(void) return phys_pages; } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* - * With CONFIG_HAVE_MEMBLOCK_NODE_MAP set, an architecture may initialise its + * Using memblock node mappings, an architecture may initialise its * zones, allocate the backing mem_map and account for memory holes in a more * architecture independent manner. This is a substitute for creating the * zone_sizes[] and zholes_size[] arrays and passing them to @@ -2424,9 +2423,6 @@ static inline unsigned long get_num_physpages(void) * registered physical page range. Similarly * sparse_memory_present_with_active_regions() calls memory_present() for * each range when SPARSEMEM is enabled. - * - * See mm/page_alloc.c for more information on each function exposed by - * CONFIG_HAVE_MEMBLOCK_NODE_MAP. */ extern void free_area_init_nodes(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); @@ -2441,13 +2437,9 @@ extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); extern void sparse_memory_present_with_active_regions(int nid); -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ - -#if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ - !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) +#ifndef CONFIG_NEED_MULTIPLE_NODES static inline int early_pfn_to_nid(unsigned long pfn) { - BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); return 0; } #else diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c3a77eb85b42..0c575c3d7feb 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -876,7 +876,7 @@ extern int movable_zone; #ifdef CONFIG_HIGHMEM static inline int zone_movable_is_highmem(void) { -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +#ifdef CONFIG_NEED_MULTIPLE_NODES return movable_zone == ZONE_HIGHMEM; #else return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM; -- cgit v1.2.3 From fa3354e4ea39e97af906c05551a36396541d70b4 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:57:06 -0700 Subject: mm: free_area_init: use maximal zone PFNs rather than zone sizes Currently, architectures that use free_area_init() to initialize memory map and node and zone structures need to calculate zone and hole sizes. We can use free_area_init_nodes() instead and let it detect the zone boundaries while the architectures will only have to supply the possible limits for the zones. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Reviewed-by: Baoquan He Cc: Brian Cain Cc: Catalin Marinas Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-5-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5f15d8723167..788704977de0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2329,7 +2329,7 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void free_area_init(unsigned long * zones_size); +extern void free_area_init(unsigned long * max_zone_pfn); extern void __init free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); extern void free_initmem(void); -- cgit v1.2.3 From 9691a071aa26a21fc8dac804a2b98d3c24f76f9a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:57:10 -0700 Subject: mm: use free_area_init() instead of free_area_init_nodes() free_area_init() has effectively became a wrapper for free_area_init_nodes() and there is no point of keeping it. Still free_area_init() name is shorter and more general as it does not imply necessity to initialize multiple nodes. Rename free_area_init_nodes() to free_area_init(), update the callers and drop old version of free_area_init(). Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Reviewed-by: Baoquan He Acked-by: Catalin Marinas Cc: Brian Cain Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-6-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 788704977de0..ff2c19e14c1e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2329,7 +2329,6 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void free_area_init(unsigned long * max_zone_pfn); extern void __init free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); extern void free_initmem(void); @@ -2410,21 +2409,21 @@ static inline unsigned long get_num_physpages(void) * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling - * free_area_init_nodes() passing in the PFN each zone ends at. At a basic + * free_area_init() passing in the PFN each zone ends at. At a basic * usage, an architecture is expected to do something like * * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid) - * free_area_init_nodes(max_zone_pfns); + * free_area_init(max_zone_pfns); * * free_bootmem_with_active_regions() calls free_bootmem_node() for each * registered physical page range. Similarly * sparse_memory_present_with_active_regions() calls memory_present() for * each range when SPARSEMEM is enabled. */ -extern void free_area_init_nodes(unsigned long *max_zone_pfn); +void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, unsigned long end_pfn); -- cgit v1.2.3 From 51930df5801e4da60e962ea52b811634d257a148 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:58:03 -0700 Subject: mm: free_area_init: allow defining max_zone_pfn in descending order Some architectures (e.g. ARC) have the ZONE_HIGHMEM zone below the ZONE_NORMAL. Allowing free_area_init() parse max_zone_pfn array even it is sorted in descending order allows using free_area_init() on such architectures. Add top -> down traversal of max_zone_pfn array in free_area_init() and use the latter in ARC node/zone initialization. [rppt@kernel.org: ARC fix] Link: http://lkml.kernel.org/r/20200504153901.GM14260@kernel.org [rppt@linux.ibm.com: arc: free_area_init(): take into account PAE40 mode] Link: http://lkml.kernel.org/r/20200507205900.GH683243@linux.ibm.com [akpm@linux-foundation.org: declare arch_has_descending_max_zone_pfns()] Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Reviewed-by: Baoquan He Cc: Brian Cain Cc: Catalin Marinas Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Cc: Guenter Roeck Link: http://lkml.kernel.org/r/20200412194859.12663-18-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ff2c19e14c1e..21cf171ae9de 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2473,6 +2473,7 @@ extern void setup_per_cpu_pageset(void); extern int min_free_kbytes; extern int watermark_boost_factor; extern int watermark_scale_factor; +extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; -- cgit v1.2.3 From bc9331a19d758706493cbebba67ca70382edddac Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:58:09 -0700 Subject: mm: rename free_area_init_node() to free_area_init_memoryless_node() free_area_init_node() is only used by x86 to initialize a memory-less nodes. Make its name reflect this and drop all the function parameters except node ID as they are anyway zero. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Cc: Baoquan He Cc: Brian Cain Cc: Catalin Marinas Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-19-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 21cf171ae9de..0d998c84231c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2329,8 +2329,7 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void __init free_area_init_node(int nid, unsigned long * zones_size, - unsigned long zone_start_pfn, unsigned long *zholes_size); +extern void __init free_area_init_memoryless_node(int nid); extern void free_initmem(void); /* @@ -2402,10 +2401,8 @@ static inline unsigned long get_num_physpages(void) /* * Using memblock node mappings, an architecture may initialise its - * zones, allocate the backing mem_map and account for memory holes in a more - * architecture independent manner. This is a substitute for creating the - * zone_sizes[] and zholes_size[] arrays and passing them to - * free_area_init_node() + * zones, allocate the backing mem_map and account for memory holes in an + * architecture independent manner. * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling -- cgit v1.2.3 From 4ca7be24eeb3198dffdae9472d7464c8b8cadadb Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 3 Jun 2020 15:58:45 -0700 Subject: mm/page_alloc.c: remove unused free_bootmem_with_active_regions Since commit 397dc00e249ec64e10 ("mips: sgi-ip27: switch from DISCONTIGMEM to SPARSEMEM"), the last caller of free_bootmem_with_active_regions() was gone. Now no user calls it any more. Let's remove it. Signed-off-by: Baoquan He Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Acked-by: Michal Hocko Link: http://lkml.kernel.org/r/20200402143455.5145-1-bhe@redhat.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0d998c84231c..4141ebcb3a65 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2415,8 +2415,6 @@ static inline unsigned long get_num_physpages(void) * memblock_add_node(base, size, nid) * free_area_init(max_zone_pfns); * - * free_bootmem_with_active_regions() calls free_bootmem_node() for each - * registered physical page range. Similarly * sparse_memory_present_with_active_regions() calls memory_present() for * each range when SPARSEMEM is enabled. */ @@ -2429,8 +2427,6 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn, extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); -extern void free_bootmem_with_active_regions(int nid, - unsigned long max_low_pfn); extern void sparse_memory_present_with_active_regions(int nid); #ifndef CONFIG_NEED_MULTIPLE_NODES -- cgit v1.2.3 From 97a225e69a1f880886f33d2e65a7ace13f152caa Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 3 Jun 2020 15:59:01 -0700 Subject: mm/page_alloc: integrate classzone_idx and high_zoneidx classzone_idx is just different name for high_zoneidx now. So, integrate them and add some comment to struct alloc_context in order to reduce future confusion about the meaning of this variable. The accessor, ac_classzone_idx() is also removed since it isn't needed after integration. In addition to integration, this patch also renames high_zoneidx to highest_zoneidx since it represents more precise meaning. Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Reviewed-by: Baoquan He Acked-by: Vlastimil Babka Acked-by: David Rientjes Cc: Johannes Weiner Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Ye Xiaolong Link: http://lkml.kernel.org/r/1587095923-7515-3-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 9 +++++---- include/linux/mmzone.h | 12 ++++++------ 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 4b898cdbdf05..3ed2f22b588a 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -97,7 +97,7 @@ extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, struct page **page); extern void reset_isolation_suitable(pg_data_t *pgdat); extern enum compact_result compaction_suitable(struct zone *zone, int order, - unsigned int alloc_flags, int classzone_idx); + unsigned int alloc_flags, int highest_zoneidx); extern void defer_compaction(struct zone *zone, int order); extern bool compaction_deferred(struct zone *zone, int order); @@ -182,7 +182,7 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, extern int kcompactd_run(int nid); extern void kcompactd_stop(int nid); -extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx); +extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx); #else static inline void reset_isolation_suitable(pg_data_t *pgdat) @@ -190,7 +190,7 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat) } static inline enum compact_result compaction_suitable(struct zone *zone, int order, - int alloc_flags, int classzone_idx) + int alloc_flags, int highest_zoneidx) { return COMPACT_SKIPPED; } @@ -232,7 +232,8 @@ static inline void kcompactd_stop(int nid) { } -static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) +static inline void wakeup_kcompactd(pg_data_t *pgdat, + int order, int highest_zoneidx) { } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0c575c3d7feb..cd8bd5f90552 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -699,13 +699,13 @@ typedef struct pglist_data { struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ int kswapd_order; - enum zone_type kswapd_classzone_idx; + enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; - enum zone_type kcompactd_classzone_idx; + enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; #endif @@ -783,15 +783,15 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat) void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, - enum zone_type classzone_idx); + enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, - int classzone_idx, unsigned int alloc_flags, + int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx, + unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx); + unsigned long mark, int highest_zoneidx); enum memmap_context { MEMMAP_EARLY, MEMMAP_HOTPLUG, -- cgit v1.2.3 From 01c0bfe061f309b848d51619f20495ee2acd7727 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 3 Jun 2020 15:59:08 -0700 Subject: mm: rename gfpflags_to_migratetype to gfp_migratetype for same convention Pageblock migrate type is encoded in GFP flags, just as zone_type and zonelist. Currently we use gfp_zone() and gfp_zonelist() to extract related information, it would be proper to use the same naming convention for migrate type. Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Reviewed-by: Pankaj Gupta Link: http://lkml.kernel.org/r/20200329080823.7735-1-richard.weiyang@gmail.com Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fab6d486cbb7..67a0774e080b 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -312,7 +312,7 @@ struct vm_area_struct; #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 -static inline int gfpflags_to_migratetype(const gfp_t gfp_flags) +static inline int gfp_migratetype(const gfp_t gfp_flags) { VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); -- cgit v1.2.3 From ae70eddd5633fc71dccf210f237c5aefc96f4332 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 3 Jun 2020 15:59:17 -0700 Subject: mm/page_alloc: restrict and formalize compound_page_dtors[] Restrict elements in compound_page_dtors[] array per NR_COMPOUND_DTORS and explicitly position them according to enum compound_dtor_id. This improves protection against possible misalignment between compound_page_dtors[] and enum compound_dtor_id later on. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Link: http://lkml.kernel.org/r/1589795958-19317-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 4141ebcb3a65..32f3c17715ac 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -867,7 +867,7 @@ enum compound_dtor_id { #endif NR_COMPOUND_DTORS, }; -extern compound_page_dtor * const compound_page_dtors[]; +extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS]; static inline void set_compound_page_dtor(struct page *page, enum compound_dtor_id compound_dtor) -- cgit v1.2.3 From 3d060856adfc59afb9d029c233141334cfaba418 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Wed, 3 Jun 2020 15:59:24 -0700 Subject: mm: initialize deferred pages with interrupts enabled Initializing struct pages is a long task and keeping interrupts disabled for the duration of this operation introduces a number of problems. 1. jiffies are not updated for long period of time, and thus incorrect time is reported. See proposed solution and discussion here: lkml/20200311123848.118638-1-shile.zhang@linux.alibaba.com 2. It prevents farther improving deferred page initialization by allowing intra-node multi-threading. We are keeping interrupts disabled to solve a rather theoretical problem that was never observed in real world (See 3a2d7fa8a3d5). Let's keep interrupts enabled. In case we ever encounter a scenario where an interrupt thread wants to allocate large amount of memory this early in boot we can deal with that by growing zone (see deferred_grow_zone()) by the needed amount before starting deferred_init_memmap() threads. Before: [ 1.232459] node 0 initialised, 12058412 pages in 1ms After: [ 1.632580] node 0 initialised, 12051227 pages in 436ms Fixes: 3a2d7fa8a3d5 ("mm: disable interrupts while initializing deferred pages") Reported-by: Shile Zhang Signed-off-by: Pavel Tatashin Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Reviewed-by: David Hildenbrand Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Dan Williams Cc: James Morris Cc: Kirill Tkhai Cc: Sasha Levin Cc: Yiqian Wei Cc: [4.17+] Link: http://lkml.kernel.org/r/20200403140952.17177-3-pasha.tatashin@soleen.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index cd8bd5f90552..2f79ff4477ba 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -680,6 +680,8 @@ typedef struct pglist_data { /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. + * Also synchronizes pgdat->first_deferred_pfn during deferred page + * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG -- cgit v1.2.3 From f1b192b117cd418bacf42a9583d7a01855a18fe5 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:35 -0700 Subject: padata: initialize earlier padata will soon initialize the system's struct pages in parallel, so it needs to be ready by page_alloc_init_late(). The error return from padata_driver_init() triggers an initcall warning, so add a warning to padata_init() to avoid silent failure. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-3-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/padata.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index 693cae9bfe66..d50bd1a7756f 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -166,6 +166,12 @@ struct padata_instance { #define PADATA_INVALID 4 }; +#ifdef CONFIG_PADATA +extern void __init padata_init(void); +#else +static inline void __init padata_init(void) {} +#endif + extern struct padata_instance *padata_alloc_possible(const char *name); extern void padata_free(struct padata_instance *pinst); extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst); -- cgit v1.2.3 From 4611ce22468895acd61fee9ac1da810d60617d9a Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:39 -0700 Subject: padata: allocate work structures for parallel jobs from a pool padata allocates per-CPU, per-instance work structs for parallel jobs. A do_parallel call assigns a job to a sequence number and hashes the number to a CPU, where the job will eventually run using the corresponding work. This approach fit with how padata used to bind a job to each CPU round-robin, makes less sense after commit bfde23ce200e6 ("padata: unbind parallel jobs from specific CPUs") because a work isn't bound to a particular CPU anymore, and isn't needed at all for multithreaded jobs because they don't have sequence numbers. Replace the per-CPU works with a preallocated pool, which allows sharing them between existing padata users and the upcoming multithreaded user. The pool will also facilitate setting NUMA-aware concurrency limits with later users. The pool is sized according to the number of possible CPUs. With this limit, MAX_OBJ_NUM no longer makes sense, so remove it. If the global pool is exhausted, a parallel job is run in the current task instead to throttle a system trying to do too much in parallel. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-4-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/padata.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index d50bd1a7756f..b4da88f8588c 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -24,7 +24,6 @@ * @list: List entry, to attach to the padata lists. * @pd: Pointer to the internal control structure. * @cb_cpu: Callback cpu for serializatioon. - * @cpu: Cpu for parallelization. * @seq_nr: Sequence number of the parallelized data object. * @info: Used to pass information from the parallel to the serial function. * @parallel: Parallel execution function. @@ -34,7 +33,6 @@ struct padata_priv { struct list_head list; struct parallel_data *pd; int cb_cpu; - int cpu; unsigned int seq_nr; int info; void (*parallel)(struct padata_priv *padata); @@ -68,15 +66,11 @@ struct padata_serial_queue { /** * struct padata_parallel_queue - The percpu padata parallel queue * - * @parallel: List to wait for parallelization. * @reorder: List to wait for reordering after parallel processing. - * @work: work struct for parallelization. * @num_obj: Number of objects that are processed by this cpu. */ struct padata_parallel_queue { - struct padata_list parallel; struct padata_list reorder; - struct work_struct work; atomic_t num_obj; }; @@ -111,7 +105,7 @@ struct parallel_data { struct padata_parallel_queue __percpu *pqueue; struct padata_serial_queue __percpu *squeue; atomic_t refcnt; - atomic_t seq_nr; + unsigned int seq_nr; unsigned int processed; int cpu; struct padata_cpumask cpumask; -- cgit v1.2.3 From 004ed42638f4428e70ead59d170f3d17ff761a0f Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:43 -0700 Subject: padata: add basic support for multithreaded jobs Sometimes the kernel doesn't take full advantage of system memory bandwidth, leading to a single CPU spending excessive time in initialization paths where the data scales with memory size. Multithreading naturally addresses this problem. Extend padata, a framework that handles many parallel yet singlethreaded jobs, to also handle multithreaded jobs by adding support for splitting up the work evenly, specifying a minimum amount of work that's appropriate for one helper thread to do, load balancing between helpers, and coordinating them. This is inspired by work from Pavel Tatashin and Steve Sistare. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-5-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/padata.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index b4da88f8588c..7302efff5e65 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -4,6 +4,9 @@ * * Copyright (C) 2008, 2009 secunet Security Networks AG * Copyright (C) 2008, 2009 Steffen Klassert + * + * Copyright (c) 2020 Oracle and/or its affiliates. + * Author: Daniel Jordan */ #ifndef PADATA_H @@ -130,6 +133,31 @@ struct padata_shell { struct list_head list; }; +/** + * struct padata_mt_job - represents one multithreaded job + * + * @thread_fn: Called for each chunk of work that a padata thread does. + * @fn_arg: The thread function argument. + * @start: The start of the job (units are job-specific). + * @size: size of this node's work (units are job-specific). + * @align: Ranges passed to the thread function fall on this boundary, with the + * possible exceptions of the beginning and end of the job. + * @min_chunk: The minimum chunk size in job-specific units. This allows + * the client to communicate the minimum amount of work that's + * appropriate for one worker thread to do at once. + * @max_threads: Max threads to use for the job, actual number may be less + * depending on task size and minimum chunk size. + */ +struct padata_mt_job { + void (*thread_fn)(unsigned long start, unsigned long end, void *arg); + void *fn_arg; + unsigned long start; + unsigned long size; + unsigned long align; + unsigned long min_chunk; + int max_threads; +}; + /** * struct padata_instance - The overall control structure. * @@ -173,6 +201,7 @@ extern void padata_free_shell(struct padata_shell *ps); extern int padata_do_parallel(struct padata_shell *ps, struct padata_priv *padata, int *cb_cpu); extern void padata_do_serial(struct padata_priv *padata); +extern void __init padata_do_multithreaded(struct padata_mt_job *job); extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, cpumask_var_t cpumask); extern int padata_start(struct padata_instance *pinst); -- cgit v1.2.3 From ecd096506922332fdb36ff1211e03601befe6e18 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:55 -0700 Subject: mm: make deferred init's max threads arch-specific Using padata during deferred init has only been tested on x86, so for now limit it to this architecture. If another arch wants this, it can find the max thread limit that's best for it and override deferred_page_init_max_threads(). Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-8-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 45abfc54da37..807ab9daf0cd 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -273,6 +273,9 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, #define for_each_free_mem_pfn_range_in_zone_from(i, zone, p_start, p_end) \ for (; i != U64_MAX; \ __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end)) + +int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask); + #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /** -- cgit v1.2.3 From ae94da898133947c2d1f005da10838478e4548db Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 3 Jun 2020 16:00:34 -0700 Subject: hugetlbfs: add arch_hugetlb_valid_size Patch series "Clean up hugetlb boot command line processing", v4. Longpeng(Mike) reported a weird message from hugetlb command line processing and proposed a solution [1]. While the proposed patch does address the specific issue, there are other related issues in command line processing. As hugetlbfs evolved, updates to command line processing have been made to meet immediate needs and not necessarily in a coordinated manner. The result is that some processing is done in arch specific code, some is done in arch independent code and coordination is problematic. Semantics can vary between architectures. The patch series does the following: - Define arch specific arch_hugetlb_valid_size routine used to validate passed huge page sizes. - Move hugepagesz= command line parsing out of arch specific code and into an arch independent routine. - Clean up command line processing to follow desired semantics and document those semantics. [1] https://lore.kernel.org/linux-mm/20200305033014.1152-1-longpeng2@huawei.com This patch (of 3): The architecture independent routine hugetlb_default_setup sets up the default huge pages size. It has no way to verify if the passed value is valid, so it accepts it and attempts to validate at a later time. This requires undocumented cooperation between the arch specific and arch independent code. For architectures that support more than one huge page size, provide a routine arch_hugetlb_valid_size to validate a huge page size. hugetlb_default_setup can use this to validate passed values. arch_hugetlb_valid_size will also be used in a subsequent patch to move processing of the "hugepagesz=" in arch specific code to a common routine in arch independent code. Signed-off-by: Mike Kravetz Signed-off-by: Andrew Morton Acked-by: Gerald Schaefer [s390] Acked-by: Will Deacon Cc: Catalin Marinas Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: David S. Miller Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Dave Hansen Cc: Jonathan Corbet Cc: Longpeng Cc: Christophe Leroy Cc: Randy Dunlap Cc: Mina Almasry Cc: Peter Xu Cc: Nitesh Narayan Lal Cc: Anders Roxell Cc: "Aneesh Kumar K.V" Cc: Qian Cai Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200428205614.246260-1-mike.kravetz@oracle.com Link: http://lkml.kernel.org/r/20200428205614.246260-2-mike.kravetz@oracle.com Link: http://lkml.kernel.org/r/20200417185049.275845-1-mike.kravetz@oracle.com Link: http://lkml.kernel.org/r/20200417185049.275845-2-mike.kravetz@oracle.com Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 43a1cef8f0f1..2eb15f5ab01e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -521,6 +521,7 @@ int __init alloc_bootmem_huge_page(struct hstate *h); void __init hugetlb_bad_size(void); void __init hugetlb_add_hstate(unsigned order); +bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); #ifndef HUGE_MAX_HSTATE -- cgit v1.2.3 From 359f25443a8dada0fb709dd044a422017031790f Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 3 Jun 2020 16:00:38 -0700 Subject: hugetlbfs: move hugepagesz= parsing to arch independent code Now that architectures provide arch_hugetlb_valid_size(), parsing of "hugepagesz=" can be done in architecture independent code. Create a single routine to handle hugepagesz= parsing and remove all arch specific routines. We can also remove the interface hugetlb_bad_size() as this is no longer used outside arch independent code. This also provides consistent behavior of hugetlbfs command line options. The hugepagesz= option should only be specified once for a specific size, but some architectures allow multiple instances. This appears to be more of an oversight when code was added by some architectures to set up ALL huge pages sizes. Signed-off-by: Mike Kravetz Signed-off-by: Andrew Morton Tested-by: Sandipan Das Reviewed-by: Peter Xu Acked-by: Mina Almasry Acked-by: Gerald Schaefer [s390] Acked-by: Will Deacon Cc: Albert Ou Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Dave Hansen Cc: David S. Miller Cc: Heiko Carstens Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Longpeng Cc: Nitesh Narayan Lal Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Randy Dunlap Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Anders Roxell Cc: "Aneesh Kumar K.V" Cc: Qian Cai Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200417185049.275845-3-mike.kravetz@oracle.com Link: http://lkml.kernel.org/r/20200428205614.246260-3-mike.kravetz@oracle.com Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2eb15f5ab01e..0c13706054ef 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -519,7 +519,6 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping, int __init __alloc_bootmem_huge_page(struct hstate *h); int __init alloc_bootmem_huge_page(struct hstate *h); -void __init hugetlb_bad_size(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); -- cgit v1.2.3 From b0eae98c66fe4ccac3a5a79a1479c057f2c7cdd7 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 3 Jun 2020 16:01:01 -0700 Subject: mm/hugetlb: define a generic fallback for is_hugepage_only_range() There are multiple similar definitions for is_hugepage_only_range() on various platforms. Lets just add it's generic fallback definition for platforms that do not override. This help reduce code duplication. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Acked-by: Mike Kravetz Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Tony Luck Cc: Fenghua Yu Cc: Thomas Bogendoerfer Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Yoshinori Sato Cc: Rich Felker Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Link: http://lkml.kernel.org/r/1588907271-11920-3-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0c13706054ef..bf97b17ab206 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -591,6 +591,15 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h) #include +#ifndef is_hugepage_only_range +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, unsigned long len) +{ + return 0; +} +#define is_hugepage_only_range is_hugepage_only_range +#endif + #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, struct page *page, int writable) -- cgit v1.2.3 From 5be993432821750f382809df5e20bf4c129b24f7 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 3 Jun 2020 16:01:05 -0700 Subject: mm/hugetlb: define a generic fallback for arch_clear_hugepage_flags() There are multiple similar definitions for arch_clear_hugepage_flags() on various platforms. Lets just add it's generic fallback definition for platforms that do not override. This help reduce code duplication. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Acked-by: Mike Kravetz Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Tony Luck Cc: Fenghua Yu Cc: Thomas Bogendoerfer Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Yoshinori Sato Cc: Rich Felker Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Link: http://lkml.kernel.org/r/1588907271-11920-4-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index bf97b17ab206..2e66b71c1236 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -600,6 +600,11 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, #define is_hugepage_only_range is_hugepage_only_range #endif +#ifndef arch_clear_hugepage_flags +static inline void arch_clear_hugepage_flags(struct page *page) { } +#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#endif + #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, struct page *page, int writable) -- cgit v1.2.3 From ff45fc3ca0f3c38e752d75f71b8d8efcf409e42d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 3 Jun 2020 16:01:09 -0700 Subject: mm: simplify calling a compound page destructor None of the three callers of get_compound_page_dtor() want to know the value; they just want to call the function. Replace it with destroy_compound_page() which calls the dtor for them. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: Anshuman Khandual Reviewed-by: David Hildenbrand Acked-by: Kirill A. Shutemov Link: http://lkml.kernel.org/r/20200517105051.9352-1-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 32f3c17715ac..ff73187c3fd4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -876,10 +876,10 @@ static inline void set_compound_page_dtor(struct page *page, page[1].compound_dtor = compound_dtor; } -static inline compound_page_dtor *get_compound_page_dtor(struct page *page) +static inline void destroy_compound_page(struct page *page) { VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page); - return compound_page_dtors[page[1].compound_dtor]; + compound_page_dtors[page[1].compound_dtor](page); } static inline unsigned int compound_order(struct page *page) -- cgit v1.2.3 From 1f318a9b0dc3990490e98eef48f21e6f15185781 Mon Sep 17 00:00:00 2001 From: Jaewon Kim Date: Wed, 3 Jun 2020 16:01:15 -0700 Subject: mm/vmscan: count layzfree pages and fix nr_isolated_* mismatch Fix an nr_isolate_* mismatch problem between cma and dirty lazyfree pages. If try_to_unmap_one is used for reclaim and it detects a dirty lazyfree page, then the lazyfree page is changed to a normal anon page having SwapBacked by commit 802a3a92ad7a ("mm: reclaim MADV_FREE pages"). Even with the change, reclaim context correctly counts isolated files because it uses is_file_lru to distinguish file. And the change to anon is not happened if try_to_unmap_one is used for migration. So migration context like compaction also correctly counts isolated files even though it uses page_is_file_lru insted of is_file_lru. Recently page_is_file_cache was renamed to page_is_file_lru by commit 9de4f22a60f7 ("mm: code cleanup for MADV_FREE"). But the nr_isolate_* mismatch problem happens on cma alloc. There is reclaim_clean_pages_from_list which is being used only by cma. It was introduced by commit 02c6de8d757c ("mm: cma: discard clean pages during contiguous allocation instead of migration") to reclaim clean file pages without migration. The cma alloc uses both reclaim_clean_pages_from_list and migrate_pages, and it uses page_is_file_lru to count isolated files. If there are dirty lazyfree pages allocated from cma memory region, the pages are counted as isolated file at the beginging but are counted as isolated anon after finished. Mem-Info: Node 0 active_anon:3045904kB inactive_anon:611448kB active_file:14892kB inactive_file:205636kB unevictable:10416kB isolated(anon):0kB isolated(file):37664kB mapped:630216kB dirty:384kB writeback:0kB shmem:42576kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no Like log above, there were too much isolated files, 37664kB, which triggers too_many_isolated in reclaim even when there is no actually isolated file in system wide. It could be reproducible by running two programs, writing on MADV_FREE page and doing cma alloc, respectively. Although isolated anon is 0, I found that the internal value of isolated anon was the negative value of isolated file. Fix this by compensating the isolated count for both LRU lists. Count non-discarded lazyfree pages in shrink_page_list, then compensate the counted number in reclaim_clean_pages_from_list. Reported-by: Yong-Taek Lee Suggested-by: Minchan Kim Signed-off-by: Jaewon Kim Signed-off-by: Andrew Morton Acked-by: Minchan Kim Cc: Mel Gorman Cc: Johannes Weiner Cc: Marek Szyprowski Cc: Michal Nazarewicz Cc: Shaohua Li Link: http://lkml.kernel.org/r/20200426011718.30246-1-jaewon31.kim@samsung.com Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 292485f3d24d..10cc932e209a 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -29,6 +29,7 @@ struct reclaim_stat { unsigned nr_activate[2]; unsigned nr_ref_keep; unsigned nr_unmap_fail; + unsigned nr_lazyfree_fail; }; enum writeback_stat_item { -- cgit v1.2.3 From 3fba69a56e16e8dcf182fe6ca77735dd65a898aa Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:31 -0700 Subject: mm: memcontrol: drop @compound parameter from memcg charging API The memcg charging API carries a boolean @compound parameter that tells whether the page we're dealing with is a hugepage. mem_cgroup_commit_charge() has another boolean @lrucare that indicates whether the page needs LRU locking or not while charging. The majority of callsites know those parameters at compile time, which results in a lot of naked "false, false" argument lists. This makes for cryptic code and is a breeding ground for subtle mistakes. Thankfully, the huge page state can be inferred from the page itself and doesn't need to be passed along. This is safe because charging completes before the page is published and somebody may split it. Simplify the callsites by removing @compound, and let memcg infer the state by using hpage_nr_pages() unconditionally. That function does PageTransHuge() to identify huge pages, which also helpfully asserts that nobody passes in tail pages by accident. The following patches will introduce a new charging API, best not to carry over unnecessary weight. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Alex Shi Reviewed-by: Joonsoo Kim Reviewed-by: Shakeel Butt Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-4-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index bfe9533bb67e..fc400002c7be 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -359,15 +359,12 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound); + gfp_t gfp_mask, struct mem_cgroup **memcgp); int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound); + gfp_t gfp_mask, struct mem_cgroup **memcgp); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound); -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, - bool compound); + bool lrucare); +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -849,8 +846,7 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp, - bool compound) + struct mem_cgroup **memcgp) { *memcgp = NULL; return 0; @@ -859,8 +855,7 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, static inline int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp, - bool compound) + struct mem_cgroup **memcgp) { *memcgp = NULL; return 0; @@ -868,13 +863,12 @@ static inline int mem_cgroup_try_charge_delay(struct page *page, static inline void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound) + bool lrucare) { } static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg, - bool compound) + struct mem_cgroup *memcg) { } -- cgit v1.2.3 From 6caa6a0703e03236f46461342e31ca53d0e3c091 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:38 -0700 Subject: mm: memcontrol: move out cgroup swaprate throttling The cgroup swaprate throttling is about matching new anon allocations to the rate of available IO when that is being throttled. It's the io controller hooking into the VM, rather than a memory controller thing. Rename mem_cgroup_throttle_swaprate() to cgroup_throttle_swaprate(), and drop the @memcg argument which is only used to check whether the preceding page charge has succeeded and the fault is proceeding. We could decouple the call from mem_cgroup_try_charge() here as well, but that would cause unnecessary churn: the following patches convert all callsites to a new charge API and we'll decouple as we go along. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Alex Shi Reviewed-by: Joonsoo Kim Reviewed-by: Shakeel Butt Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-5-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/swap.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index e92176fc8824..6cea1eb97d45 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -651,11 +651,9 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -extern void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node, - gfp_t gfp_mask); +extern void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); #else -static inline void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, - int node, gfp_t gfp_mask) +static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { } #endif -- cgit v1.2.3 From 3fea5a499d57dec46043fcdb08e38eac1767bb0d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:41 -0700 Subject: mm: memcontrol: convert page cache to a new mem_cgroup_charge() API The try/commit/cancel protocol that memcg uses dates back to when pages used to be uncharged upon removal from the page cache, and thus couldn't be committed before the insertion had succeeded. Nowadays, pages are uncharged when they are physically freed; it doesn't matter whether the insertion was successful or not. For the page cache, the transaction dance has become unnecessary. Introduce a mem_cgroup_charge() function that simply charges a newly allocated page to a cgroup and sets up page->mem_cgroup in one single step. If the insertion fails, the caller doesn't have to do anything but free/put the page. Then switch the page cache over to this new API. Subsequent patches will also convert anon pages, but it needs a bit more prep work. Right now, memcg depends on page->mapping being already set up at the time of charging, so that it can maintain its own MEMCG_CACHE and MEMCG_RSS counters. For anon, page->mapping is set under the same pte lock under which the page is publishd, so a single charge point that can block doesn't work there just yet. The following prep patches will replace the private memcg counters with the generic vmstat counters, thus removing the page->mapping dependency, then complete the transition to the new single-point charge API and delete the old transactional scheme. v2: leave shmem swapcache when charging fails to avoid double IO (Joonsoo) v3: rebase on preceeding shmem simplification patch Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Alex Shi Cc: Hugh Dickins Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-6-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index fc400002c7be..898925bdd676 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -365,6 +365,10 @@ int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare); void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); + +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, + bool lrucare); + void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -872,6 +876,12 @@ static inline void mem_cgroup_cancel_charge(struct page *page, { } +static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask, bool lrucare) +{ + return 0; +} + static inline void mem_cgroup_uncharge(struct page *page) { } -- cgit v1.2.3 From 9da7b5216869f80e91f78403a57c72b42357758c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:51 -0700 Subject: mm: memcontrol: prepare cgroup vmstat infrastructure for native anon counters Anonymous compound pages can be mapped by ptes, which means that if we want to track NR_MAPPED_ANON, NR_ANON_THPS on a per-cgroup basis, we have to be prepared to see tail pages in our accounting functions. Make mod_lruvec_page_state() and lock_page_memcg() deal with tail pages correctly, namely by redirecting to the head page which has the page->mem_cgroup set up. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-9-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 898925bdd676..8f00dd755818 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -709,16 +709,17 @@ static inline void mod_lruvec_state(struct lruvec *lruvec, static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { + struct page *head = compound_head(page); /* rmap on tail pages */ pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; /* Untracked pages have no memcg, no lruvec. Update only the node */ - if (!page->mem_cgroup) { + if (!head->mem_cgroup) { __mod_node_page_state(pgdat, idx, val); return; } - lruvec = mem_cgroup_lruvec(page->mem_cgroup, pgdat); + lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat); __mod_lruvec_state(lruvec, idx, val); } -- cgit v1.2.3 From 0d1c20722ab333ac0ac03ae2188922c1021d3abc Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:54 -0700 Subject: mm: memcontrol: switch to native NR_FILE_PAGES and NR_SHMEM counters Memcg maintains private MEMCG_CACHE and NR_SHMEM counters. This divergence from the generic VM accounting means unnecessary code overhead, and creates a dependency for memcg that page->mapping is set up at the time of charging, so that page types can be told apart. Convert the generic accounting sites to mod_lruvec_page_state and friends to maintain the per-cgroup vmstat counters of NR_FILE_PAGES and NR_SHMEM. The page is already locked in these places, so page->mem_cgroup is stable; we only need minimal tweaks of two mem_cgroup_migrate() calls to ensure it's set up in time. Then replace MEMCG_CACHE with NR_FILE_PAGES and delete the private NR_SHMEM accounting sites. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-10-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8f00dd755818..f6ea68ceed2c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_CACHE = NR_VM_NODE_STAT_ITEMS, - MEMCG_RSS, + MEMCG_RSS = NR_VM_NODE_STAT_ITEMS, MEMCG_RSS_HUGE, MEMCG_SWAP, MEMCG_SOCK, -- cgit v1.2.3 From be5d0a74c62d8da43f9526a5b08cdd18e2bbc37a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:57 -0700 Subject: mm: memcontrol: switch to native NR_ANON_MAPPED counter Memcg maintains a private MEMCG_RSS counter. This divergence from the generic VM accounting means unnecessary code overhead, and creates a dependency for memcg that page->mapping is set up at the time of charging, so that page types can be told apart. Convert the generic accounting sites to mod_lruvec_page_state and friends to maintain the per-cgroup vmstat counter of NR_ANON_MAPPED. We use lock_page_memcg() to stabilize page->mem_cgroup during rmap changes, the same way we do for NR_FILE_MAPPED. With the previous patch removing MEMCG_CACHE and the private NR_SHMEM counter, this patch finally eliminates the need to have page->mapping set up at charge time. However, we need to have page->mem_cgroup set up by the time rmap runs and does the accounting, so switch the commit and the rmap callbacks around. v2: fix temporary accounting bug by switching rmap<->commit (Joonsoo) Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Alex Shi Cc: Hugh Dickins Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-11-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f6ea68ceed2c..acacc3018957 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_RSS = NR_VM_NODE_STAT_ITEMS, - MEMCG_RSS_HUGE, + MEMCG_RSS_HUGE = NR_VM_NODE_STAT_ITEMS, MEMCG_SWAP, MEMCG_SOCK, /* XXX: why are these zone and not node counters? */ -- cgit v1.2.3 From 468c398233da208521a0f84c2068012a66a7489d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:01 -0700 Subject: mm: memcontrol: switch to native NR_ANON_THPS counter With rmap memcg locking already in place for NR_ANON_MAPPED, it's just a small step to remove the MEMCG_RSS_HUGE wart and switch memcg to the native NR_ANON_THPS accounting sites. [hannes@cmpxchg.org: fixes] Link: http://lkml.kernel.org/r/20200512121750.GA397968@cmpxchg.org Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Tested-by: Naresh Kamboju Reviewed-by: Joonsoo Kim Acked-by: Randy Dunlap [build-tested] Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-12-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index acacc3018957..63a31a6c3c69 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_RSS_HUGE = NR_VM_NODE_STAT_ITEMS, - MEMCG_SWAP, + MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, /* XXX: why are these zone and not node counters? */ MEMCG_KERNEL_STACK_KB, -- cgit v1.2.3 From 9d82c69438d0dff8809061edbcce43a5a4bcf09f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:04 -0700 Subject: mm: memcontrol: convert anon and file-thp to new mem_cgroup_charge() API With the page->mapping requirement gone from memcg, we can charge anon and file-thp pages in one single step, right after they're allocated. This removes two out of three API calls - especially the tricky commit step that needed to happen at just the right time between when the page is "set up" and when it's "published" - somewhat vague and fluid concepts that varied by page type. All we need is a freshly allocated page and a memcg context to charge. v2: prevent double charges on pre-allocated hugepages in khugepaged [hannes@cmpxchg.org: Fix crash - *hpage could be ERR_PTR instead of NULL] Link: http://lkml.kernel.org/r/20200512215813.GA487759@cmpxchg.org Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Cc: Qian Cai Link: http://lkml.kernel.org/r/20200508183105.225460-13-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ff73187c3fd4..4ef044fa09fa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -501,7 +501,6 @@ struct vm_fault { pte_t orig_pte; /* Value of PTE at the time of fault */ struct page *cow_page; /* Page handler may use for COW fault */ - struct mem_cgroup *memcg; /* Cgroup cow_page belongs to */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by @@ -946,8 +945,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, - struct page *page); +vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page); vm_fault_t finish_fault(struct vm_fault *vmf); vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif -- cgit v1.2.3 From f0e45fb4da29746a116e810eb91423ccfa4830fc Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:07 -0700 Subject: mm: memcontrol: drop unused try/commit/cancel charge API There are no more users. RIP in peace. [arnd@arndb.de: fix an unused-function warning] Link: http://lkml.kernel.org/r/20200528095640.151454-1-arnd@arndb.de Signed-off-by: Johannes Weiner Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-14-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 36 ------------------------------------ 1 file changed, 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 63a31a6c3c69..46620c6343ef 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -355,14 +355,6 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); -int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp); -int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp); -void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare); -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); - int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, bool lrucare); @@ -846,34 +838,6 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( return MEMCG_PROT_NONE; } -static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, - struct mem_cgroup **memcgp) -{ - *memcgp = NULL; - return 0; -} - -static inline int mem_cgroup_try_charge_delay(struct page *page, - struct mm_struct *mm, - gfp_t gfp_mask, - struct mem_cgroup **memcgp) -{ - *memcgp = NULL; - return 0; -} - -static inline void mem_cgroup_commit_charge(struct page *page, - struct mem_cgroup *memcg, - bool lrucare) -{ -} - -static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg) -{ -} - static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, bool lrucare) { -- cgit v1.2.3 From eccb52e7880973f221ab2606e4d22ce04d96a1a9 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:11 -0700 Subject: mm: memcontrol: prepare swap controller setup for integration A few cleanups to streamline the swap controller setup: - Replace the do_swap_account flag with cgroup_memory_noswap. This brings it in line with other functionality that is usually available unless explicitly opted out of - nosocket, nokmem. - Remove the really_do_swap_account flag that stores the boot option and is later used to switch the do_swap_account. It's not clear why this indirection is/was necessary. Use do_swap_account directly. - Minor coding style polishing Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-15-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 46620c6343ef..96257f995caa 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -558,7 +558,7 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); #ifdef CONFIG_MEMCG_SWAP -extern int do_swap_account; +extern bool cgroup_memory_noswap; #endif struct mem_cgroup *lock_page_memcg(struct page *page); -- cgit v1.2.3 From d9eb1ea2bf8734afd8ec7d995270437a7242f82b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:24 -0700 Subject: mm: memcontrol: delete unused lrucare handling Swapin faults were the last event to charge pages after they had already been put on the LRU list. Now that we charge directly on swapin, the lrucare portion of the charge code is unused. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Cc: Shakeel Butt Link: http://lkml.kernel.org/r/20200508183105.225460-19-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 96257f995caa..d5bf3b5bfe6d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -355,8 +355,7 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - bool lrucare); +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -839,7 +838,7 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( } static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, bool lrucare) + gfp_t gfp_mask) { return 0; } -- cgit v1.2.3 From 497a6c1b09902b22ceccc0f25ba4dd623e1ddb7d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:34 -0700 Subject: mm: keep separate anon and file statistics on page reclaim activity Having statistics on pages scanned and pages reclaimed for both anon and file pages makes it easier to evaluate changes to LRU balancing. While at it, clean up the stat-keeping mess for isolation, putback, reclaim stats etc. a bit: first the physical LRU operation (isolation and putback), followed by vmstats, reclaim_stats, and then vm events. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-3-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index ffef0f279747..24fc7c3ae7d6 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -35,6 +35,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGSCAN_KSWAPD, PGSCAN_DIRECT, PGSCAN_DIRECT_THROTTLE, + PGSCAN_ANON, + PGSCAN_FILE, + PGSTEAL_ANON, + PGSTEAL_FILE, #ifdef CONFIG_NUMA PGSCAN_ZONE_RECLAIM_FAILED, #endif -- cgit v1.2.3 From 6058eaec816f29fbe33c9d35694614c9a4ed75ba Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:40 -0700 Subject: mm: fold and remove lru_cache_add_anon() and lru_cache_add_file() They're the same function, and for the purpose of all callers they are equivalent to lru_cache_add(). [akpm@linux-foundation.org: fix it for local_lock changes] Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Rik van Riel Acked-by: Michal Hocko Acked-by: Minchan Kim Cc: Joonsoo Kim Link: http://lkml.kernel.org/r/20200520232525.798933-5-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6cea1eb97d45..217bc8e13feb 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -335,8 +335,6 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ extern void lru_cache_add(struct page *); -extern void lru_cache_add_anon(struct page *page); -extern void lru_cache_add_file(struct page *page); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); extern void activate_page(struct page *); -- cgit v1.2.3 From 1431d4d11abb265e79cd44bed2f5ea93f1bcc57b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:53 -0700 Subject: mm: base LRU balancing on an explicit cost model Currently, scan pressure between the anon and file LRU lists is balanced based on a mixture of reclaim efficiency and a somewhat vague notion of "value" of having certain pages in memory over others. That concept of value is problematic, because it has caused us to count any event that remotely makes one LRU list more or less preferrable for reclaim, even when these events are not directly comparable and impose very different costs on the system. One example is referenced file pages that we still deactivate and referenced anonymous pages that we actually rotate back to the head of the list. There is also conceptual overlap with the LRU algorithm itself. By rotating recently used pages instead of reclaiming them, the algorithm already biases the applied scan pressure based on page value. Thus, when rebalancing scan pressure due to rotations, we should think of reclaim cost, and leave assessing the page value to the LRU algorithm. Lastly, considering both value-increasing as well as value-decreasing events can sometimes cause the same type of event to be counted twice, i.e. how rotating a page increases the LRU value, while reclaiming it succesfully decreases the value. In itself this will balance out fine, but it quietly skews the impact of events that are only recorded once. The abstract metric of "value", the murky relationship with the LRU algorithm, and accounting both negative and positive events make the current pressure balancing model hard to reason about and modify. This patch switches to a balancing model of accounting the concrete, actually observed cost of reclaiming one LRU over another. For now, that cost includes pages that are scanned but rotated back to the list head. Subsequent patches will add consideration for IO caused by refaulting of recently evicted pages. Replace struct zone_reclaim_stat with two cost counters in the lruvec, and make everything that affects cost go through a new lru_note_cost() function. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Acked-by: Michal Hocko Cc: Joonsoo Kim Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-9-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 21 +++++++-------------- include/linux/swap.h | 2 ++ 2 files changed, 9 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2f79ff4477ba..e57248ccb63d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -242,19 +242,6 @@ static inline bool is_active_lru(enum lru_list lru) return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } -struct zone_reclaim_stat { - /* - * The pageout code in vmscan.c keeps track of how many of the - * mem/swap backed and file backed pages are referenced. - * The higher the rotated/scanned ratio, the more valuable - * that cache is. - * - * The anon LRU stats live in [0], file LRU stats in [1] - */ - unsigned long recent_rotated[2]; - unsigned long recent_scanned[2]; -}; - enum lruvec_flags { LRUVEC_CONGESTED, /* lruvec has many dirty pages * backed by a congested BDI @@ -263,7 +250,13 @@ enum lruvec_flags { struct lruvec { struct list_head lists[NR_LRU_LISTS]; - struct zone_reclaim_stat reclaim_stat; + /* + * These track the cost of reclaiming one LRU - file or anon - + * over the other. As the observed cost of reclaiming one LRU + * increases, the reclaim scan balance tips toward the other. + */ + unsigned long anon_cost; + unsigned long file_cost; /* Evictions & activations on the inactive file list */ atomic_long_t inactive_age; /* Refaults at the time of last reclaim cycle */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 217bc8e13feb..ce3c55747006 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -334,6 +334,8 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ +extern void lru_note_cost(struct lruvec *lruvec, bool file, + unsigned int nr_pages); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); -- cgit v1.2.3 From 314b57fb0460001a090b35ff8be987f2c868ad3c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:03:03 -0700 Subject: mm: balance LRU lists based on relative thrashing Since the LRUs were split into anon and file lists, the VM has been balancing between page cache and anonymous pages based on per-list ratios of scanned vs. rotated pages. In most cases that tips page reclaim towards the list that is easier to reclaim and has the fewest actively used pages, but there are a few problems with it: 1. Refaults and LRU rotations are weighted the same way, even though one costs IO and the other costs a bit of CPU. 2. The less we scan an LRU list based on already observed rotations, the more we increase the sampling interval for new references, and rotations become even more likely on that list. This can enter a death spiral in which we stop looking at one list completely until the other one is all but annihilated by page reclaim. Since commit a528910e12ec ("mm: thrash detection-based file cache sizing") we have refault detection for the page cache. Along with swapin events, they are good indicators of when the file or anon list, respectively, is too small for its workingset and needs to grow. For example, if the page cache is thrashing, the cache pages need more time in memory, while there may be colder pages on the anonymous list. Likewise, if swapped pages are faulting back in, it indicates that we reclaim anonymous pages too aggressively and should back off. Replace LRU rotations with refaults and swapins as the basis for relative reclaim cost of the two LRUs. This will have the VM target list balances that incur the least amount of IO on aggregate. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-12-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/swap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index ce3c55747006..0b71bf75fb67 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -334,8 +334,7 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ -extern void lru_note_cost(struct lruvec *lruvec, bool file, - unsigned int nr_pages); +extern void lru_note_cost(struct page *); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); -- cgit v1.2.3 From 7cf111bc39f6792abedcdfbc4e6291a5603b0ef0 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:03:06 -0700 Subject: mm: vmscan: determine anon/file pressure balance at the reclaim root We split the LRU lists into anon and file, and we rebalance the scan pressure between them when one of them begins thrashing: if the file cache experiences workingset refaults, we increase the pressure on anonymous pages; if the workload is stalled on swapins, we increase the pressure on the file cache instead. With cgroups and their nested LRU lists, we currently don't do this correctly. While recursive cgroup reclaim establishes a relative LRU order among the pages of all involved cgroups, LRU pressure balancing is done on an individual cgroup LRU level. As a result, when one cgroup is thrashing on the filesystem cache while a sibling may have cold anonymous pages, pressure doesn't get equalized between them. This patch moves LRU balancing decision to the root of reclaim - the same level where the LRU order is established. It does this by tracking LRU cost recursively, so that every level of the cgroup tree knows the aggregate LRU cost of all memory within its domain. When the page scanner calculates the scan balance for any given individual cgroup's LRU list, it uses the values from the ancestor cgroup that initiated the reclaim cycle. If one sibling is then thrashing on the cache, it will tip the pressure balance inside its ancestors, and the next hierarchical reclaim iteration will go more after the anon pages in the tree. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-13-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d5bf3b5bfe6d..e77197a62809 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1242,6 +1242,19 @@ static inline void dec_lruvec_page_state(struct page *page, mod_lruvec_page_state(page, idx, -1); } +static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) +{ + struct mem_cgroup *memcg; + + memcg = lruvec_memcg(lruvec); + if (!memcg) + return NULL; + memcg = parent_mem_cgroup(memcg); + if (!memcg) + return NULL; + return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); +} + #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); -- cgit v1.2.3 From 96f8bf4fb1dd2656ae3e92326be9ebf003bbfd45 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:03:09 -0700 Subject: mm: vmscan: reclaim writepage is IO cost The VM tries to balance reclaim pressure between anon and file so as to reduce the amount of IO incurred due to the memory shortage. It already counts refaults and swapins, but in addition it should also count writepage calls during reclaim. For swap, this is obvious: it's IO that wouldn't have occurred if the anonymous memory hadn't been under memory pressure. From a relative balancing point of view this makes sense as well: even if anon is cold and reclaimable, a cache that isn't thrashing may have equally cold pages that don't require IO to reclaim. For file writeback, it's trickier: some of the reclaim writepage IO would have likely occurred anyway due to dirty expiration. But not all of it - premature writeback reduces batching and generates additional writes. Since the flushers are already woken up by the time the VM starts writing cache pages one by one, let's assume that we'e likely causing writes that wouldn't have happened without memory pressure. In addition, the per-page cost of IO would have probably been much cheaper if written in larger batches from the flusher thread rather than the single-page-writes from kswapd. For our purposes - getting the trend right to accelerate convergence on a stable state that doesn't require paging at all - this is sufficiently accurate. If we later wanted to optimize for sustained thrashing, we can still refine the measurements. Count all writepage calls from kswapd as IO cost toward the LRU that the page belongs to. Why do this dynamically? Don't we know in advance that anon pages require IO to reclaim, and so could build in a static bias? First, scanning is not the same as reclaiming. If all the anon pages are referenced, we may not swap for a while just because we're scanning the anon list. During this time, however, it's important that we age anonymous memory and the page cache at the same rate so that their hot-cold gradients are comparable. Everything else being equal, we still want to reclaim the coldest memory overall. Second, we keep copies in swap unless the page changes. If there is swap-backed data that's mostly read (tmpfs file) and has been swapped out before, we can reclaim it without incurring additional IO. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-14-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/swap.h | 4 +++- include/linux/vmstat.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 0b71bf75fb67..4c5974bb9ba9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -334,7 +334,9 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ -extern void lru_note_cost(struct page *); +extern void lru_note_cost(struct lruvec *lruvec, bool file, + unsigned int nr_pages); +extern void lru_note_cost_page(struct page *); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 10cc932e209a..3d12c34cd42a 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -26,6 +26,7 @@ struct reclaim_stat { unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; + unsigned nr_pageout; unsigned nr_activate[2]; unsigned nr_ref_keep; unsigned nr_unmap_fail; -- cgit v1.2.3 From 8cbd54f52997f43be3d09acd9fa9a10d202c5374 Mon Sep 17 00:00:00 2001 From: chenqiwu Date: Wed, 3 Jun 2020 16:03:28 -0700 Subject: include/linux/memblock.h: fix minor typo and unclear comment Fix a minor typo "usabe->usable" for the current discription of member variable "memory" in struct memblock. BTW, I think it's unclear the member variable "base" in struct memblock_type is currently described as the physical address of memory region, change it to base address of the region is clearer since the variable is decorated as phys_addr_t. Signed-off-by: chenqiwu Signed-off-by: Andrew Morton Reviewed-by: Mike Rapoport Link: http://lkml.kernel.org/r/1588846952-32166-1-git-send-email-qiwuchen55@gmail.com Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 807ab9daf0cd..017fae833d4a 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -41,7 +41,7 @@ enum memblock_flags { /** * struct memblock_region - represents a memory region - * @base: physical address of the region + * @base: base address of the region * @size: size of the region * @flags: memory region attributes * @nid: NUMA node id @@ -75,7 +75,7 @@ struct memblock_type { * struct memblock - memblock allocator metadata * @bottom_up: is bottom up direction? * @current_limit: physical address of the current allocation limit - * @memory: usabe memory regions + * @memory: usable memory regions * @reserved: reserved memory regions * @physmem: all physical memory */ -- cgit v1.2.3 From 4301efa4c7cca11556dd89899eee066d49b47bf7 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 21 Apr 2020 10:54:44 +0200 Subject: writeback: Export inode_io_list_del() Ext4 needs to remove inode from writeback lists after it is out of visibility of its journalling machinery (which can still dirty the inode). Export inode_io_list_del() for it. Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20200421085445.5731-3-jack@suse.cz Signed-off-by: Theodore Ts'o --- include/linux/writeback.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index a19d845dd7eb..902aa317621b 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -197,6 +197,7 @@ void wakeup_flusher_threads(enum wb_reason reason); void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason); void inode_wait_for_writeback(struct inode *inode); +void inode_io_list_del(struct inode *inode); /* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode(struct inode *inode) -- cgit v1.2.3 From 44ebcd06bbb3ab3ee446b933800aca32fc4ca9b1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 May 2020 09:30:10 +0200 Subject: fs: mark __generic_block_fiemap static There is no caller left outside of ioctl.c. Signed-off-by: Christoph Hellwig Reviewed-by: Ritesh Harjani Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20200523073016.2944131-4-hch@lst.de Signed-off-by: Theodore Ts'o --- include/linux/fs.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..3104c6f7527b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3299,10 +3299,6 @@ static inline int vfs_fstat(int fd, struct kstat *stat) extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); -extern int __generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, - loff_t start, loff_t len, - get_block_t *get_block); extern int generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, get_block_t *get_block); -- cgit v1.2.3 From 10c5db286452b8c60e8f58e9a4c1cbc5a91e4e5b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 May 2020 09:30:11 +0200 Subject: fs: move the fiemap definitions out of fs.h No need to pull the fiemap definitions into almost every file in the kernel build. Signed-off-by: Christoph Hellwig Reviewed-by: Ritesh Harjani Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20200523073016.2944131-5-hch@lst.de Signed-off-by: Theodore Ts'o --- include/linux/fiemap.h | 24 ++++++++++++++++++++++++ include/linux/fs.h | 19 +------------------ 2 files changed, 25 insertions(+), 18 deletions(-) create mode 100644 include/linux/fiemap.h (limited to 'include/linux') diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h new file mode 100644 index 000000000000..240d4f7d9116 --- /dev/null +++ b/include/linux/fiemap.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FIEMAP_H +#define _LINUX_FIEMAP_H 1 + +#include +#include + +struct fiemap_extent_info { + unsigned int fi_flags; /* Flags as passed from user */ + unsigned int fi_extents_mapped; /* Number of mapped extents */ + unsigned int fi_extents_max; /* Size of fiemap_extent array */ + struct fiemap_extent __user *fi_extents_start; /* Start of + fiemap_extent array */ +}; + +int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, + u64 phys, u64 len, u32 flags); +int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); + +int generic_block_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo, u64 start, u64 len, + get_block_t *get_block); + +#endif /* _LINUX_FIEMAP_H 1 */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 3104c6f7527b..09bcd329c062 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -24,7 +24,6 @@ #include #include #include -#include #include #include #include @@ -48,6 +47,7 @@ struct backing_dev_info; struct bdi_writeback; struct bio; struct export_operations; +struct fiemap_extent_info; struct hd_geometry; struct iovec; struct kiocb; @@ -1745,19 +1745,6 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, extern void inode_init_owner(struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); -/* - * VFS FS_IOC_FIEMAP helper definitions. - */ -struct fiemap_extent_info { - unsigned int fi_flags; /* Flags as passed from user */ - unsigned int fi_extents_mapped; /* Number of mapped extents */ - unsigned int fi_extents_max; /* Size of fiemap_extent array */ - struct fiemap_extent __user *fi_extents_start; /* Start of - fiemap_extent array */ -}; -int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, - u64 phys, u64 len, u32 flags); -int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); /* * This is the "filldir" function type, used by readdir() to let @@ -3299,10 +3286,6 @@ static inline int vfs_fstat(int fd, struct kstat *stat) extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); -extern int generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, u64 start, - u64 len, get_block_t *get_block); - extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); -- cgit v1.2.3 From 2732881894714f545ffac42dad7ba7730069874d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 May 2020 09:30:12 +0200 Subject: iomap: fix the iomap_fiemap prototype iomap_fiemap should take u64 start and len arguments, just like the ->fiemap prototype. Signed-off-by: Christoph Hellwig Reviewed-by: Ritesh Harjani Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20200523073016.2944131-6-hch@lst.de Signed-off-by: Theodore Ts'o --- include/linux/iomap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 8b09463dae0d..63db02528b70 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -178,7 +178,7 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, - loff_t start, loff_t len, const struct iomap_ops *ops); + u64 start, u64 len, const struct iomap_ops *ops); loff_t iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops); loff_t iomap_seek_data(struct inode *inode, loff_t offset, -- cgit v1.2.3 From cddf8a2c4a8286ae60fc866eab59c8bc524e93a0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 May 2020 09:30:13 +0200 Subject: fs: move fiemap range validation into the file systems instances Replace fiemap_check_flags with a fiemap_prep helper that also takes the inode and mapped range, and performs the sanity check and truncation previously done in fiemap_check_range. This way the validation is inside the file system itself and thus properly works for the stacked overlayfs case as well. Signed-off-by: Christoph Hellwig Reviewed-by: Amir Goldstein Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20200523073016.2944131-7-hch@lst.de Signed-off-by: Theodore Ts'o --- include/linux/fiemap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h index 240d4f7d9116..4e624c466583 100644 --- a/include/linux/fiemap.h +++ b/include/linux/fiemap.h @@ -13,9 +13,10 @@ struct fiemap_extent_info { fiemap_extent array */ }; +int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 *len, u32 supported_flags); int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, u64 phys, u64 len, u32 flags); -int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); int generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, -- cgit v1.2.3 From df820f8de4e481222b17f9bcee7b909ae8167529 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 4 Jun 2020 10:48:19 +0200 Subject: ovl: make private mounts longterm Overlayfs is using clone_private_mount() to create internal mounts for underlying layers. These are used for operations requiring a path, such as dentry_open(). Since these private mounts are not in any namespace they are treated as short term, "detached" mounts and mntput() involves taking the global mount_lock, which can result in serious cacheline pingpong. Make these private mounts longterm instead, which trade the penalty on mntput() for a slightly longer shutdown time due to an added RCU grace period when putting these mounts. Introduce a new helper kern_unmount_many() that can take care of multiple longterm mounts with a single RCU grace period. Cc: Al Viro Signed-off-by: Miklos Szeredi --- include/linux/mount.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index bf8cc4108b8f..8de95a0bec8d 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -109,4 +109,6 @@ extern unsigned int sysctl_mount_max; extern bool path_is_mountpoint(const struct path *path); +extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num); + #endif /* _LINUX_MOUNT_H */ -- cgit v1.2.3 From d56f5136b01020155b6b0a29f69d924687529bee Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 4 Jun 2020 15:16:52 +0200 Subject: KVM: let kvm_destroy_vm_debugfs clean up vCPU debugfs directories After commit 63d0434 ("KVM: x86: move kvm_create_vcpu_debugfs after last failure point") we are creating the pre-vCPU debugfs files after the creation of the vCPU file descriptor. This makes it possible for userspace to reach kvm_vcpu_release before kvm_create_vcpu_debugfs has finished. The vcpu->debugfs_dentry then does not have any associated inode anymore, and this causes a NULL-pointer dereference in debugfs_create_file. The solution is simply to avoid removing the files; they are cleaned up when the VM file descriptor is closed (and that must be after KVM_CREATE_VCPU returns). We can stop storing the dentry in struct kvm_vcpu too, because it is not needed anywhere after kvm_create_vcpu_debugfs returns. Reported-by: syzbot+705f4401d5a93a59b87d@syzkaller.appspotmail.com Fixes: 63d04348371b ("KVM: x86: move kvm_create_vcpu_debugfs after last failure point") Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f43b59b1294c..d38d6b9c24be 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -318,7 +318,6 @@ struct kvm_vcpu { bool preempted; bool ready; struct kvm_vcpu_arch arch; - struct dentry *debugfs_dentry; }; static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) @@ -888,7 +887,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS -void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu); +void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry); #endif int kvm_arch_hardware_enable(void); -- cgit v1.2.3 From c25a26e653a61b93339dcd1b734c889df60b3eef Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 29 May 2020 16:03:00 +0800 Subject: vdpa: introduce get_vq_notification method This patch introduces a new method in the vdpa_config_ops which reports the physical address and the size of the doorbell for a specific virtqueue. This will be used by the future patches that maps doorbell to userspace. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20200529080303.15449-4-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 5453af87a33e..239db794357c 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -17,6 +17,16 @@ struct vdpa_callback { void *private; }; +/** + * vDPA notification area + * @addr: base address of the notification area + * @size: size of the notification area + */ +struct vdpa_notification_area { + resource_size_t addr; + resource_size_t size; +}; + /** * vDPA device - representation of a vDPA device * @dev: underlying device @@ -73,6 +83,10 @@ struct vdpa_device { * @vdev: vdpa device * @idx: virtqueue index * Returns virtqueue state (last_avail_idx) + * @get_vq_notification: Get the notification area for a virtqueue + * @vdev: vdpa device + * @idx: virtqueue index + * Returns the notifcation area * @get_vq_align: Get the virtqueue align requirement * for the device * @vdev: vdpa device @@ -162,6 +176,8 @@ struct vdpa_config_ops { bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx); int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, u64 state); u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx); + struct vdpa_notification_area + (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); -- cgit v1.2.3 From aa218795cb5fd583c94fc838dc76b7379dc4976a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 7 May 2020 16:01:30 +0200 Subject: mm: Allow to offline unmovable PageOffline() pages via MEM_GOING_OFFLINE virtio-mem wants to allow to offline memory blocks of which some parts were unplugged (allocated via alloc_contig_range()), especially, to later offline and remove completely unplugged memory blocks. The important part is that PageOffline() has to remain set until the section is offline, so these pages will never get accessed (e.g., when dumping). The pages should not be handed back to the buddy (which would require clearing PageOffline() and result in issues if offlining fails and the pages are suddenly in the buddy). Let's allow to do that by allowing to isolate any PageOffline() page when offlining. This way, we can reach the memory hotplug notifier MEM_GOING_OFFLINE, where the driver can signal that he is fine with offlining this page by dropping its reference count. PageOffline() pages with a reference count of 0 can then be skipped when offlining the pages (like if they were free, however they are not in the buddy). Anybody who uses PageOffline() pages and does not agree to offline them (e.g., Hyper-V balloon, XEN balloon, VMWare balloon for 2MB pages) will not decrement the reference count and make offlining fail when trying to migrate such an unmovable page. So there should be no observable change. Same applies to balloon compaction users (movable PageOffline() pages), the pages will simply be migrated. Note 1: If offlining fails, a driver has to increment the reference count again in MEM_CANCEL_OFFLINE. Note 2: A driver that makes use of this has to be aware that re-onlining the memory block has to be handled by hooking into onlining code (online_page_callback_t), resetting the page PageOffline() and not giving them to the buddy. Reviewed-by: Alexander Duyck Acked-by: Michal Hocko Tested-by: Pankaj Gupta Acked-by: Andrew Morton Cc: Andrew Morton Cc: Juergen Gross Cc: Konrad Rzeszutek Wilk Cc: Pavel Tatashin Cc: Alexander Duyck Cc: Vlastimil Babka Cc: Johannes Weiner Cc: Anthony Yznaga Cc: Michal Hocko Cc: Oscar Salvador Cc: Mel Gorman Cc: Mike Rapoport Cc: Dan Williams Cc: Anshuman Khandual Cc: Qian Cai Cc: Pingfan Liu Signed-off-by: David Hildenbrand Link: https://lore.kernel.org/r/20200507140139.17083-7-david@redhat.com Signed-off-by: Michael S. Tsirkin --- include/linux/page-flags.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 222f6f7b2bb3..6be1aa559b1e 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -777,6 +777,16 @@ PAGE_TYPE_OPS(Buddy, buddy) * not onlined when onlining the section). * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. + * + * If a driver wants to allow to offline unmovable PageOffline() pages without + * putting them back to the buddy, it can do so via the memory notifier by + * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the + * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() + * pages (now with a reference count of zero) are treated like free pages, + * allowing the containing memory block to get offlined. A driver that + * relies on this feature is aware that re-onlining the memory block will + * require to re-set the pages PageOffline() and not giving them to the + * buddy via online_page_callback_t. */ PAGE_TYPE_OPS(Offline, offline) -- cgit v1.2.3 From 08b3acd7a68fc17902e1cb6b146389322840deab Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 7 May 2020 16:01:32 +0200 Subject: mm/memory_hotplug: Introduce offline_and_remove_memory() virtio-mem wants to offline and remove a memory block once it unplugged all subblocks (e.g., using alloc_contig_range()). Let's provide an interface to do that from a driver. virtio-mem already supports to offline partially unplugged memory blocks. Offlining a fully unplugged memory block will not require to migrate any pages. All unplugged subblocks are PageOffline() and have a reference count of 0 - so offlining code will simply skip them. All we need is an interface to offline and remove the memory from kernel module context, where we don't have access to the memory block devices (esp. find_memory_block() and device_offline()) and the device hotplug lock. To keep things simple, allow to only work on a single memory block. Acked-by: Michal Hocko Tested-by: Pankaj Gupta Acked-by: Andrew Morton Cc: Andrew Morton Cc: David Hildenbrand Cc: Oscar Salvador Cc: Michal Hocko Cc: Pavel Tatashin Cc: Wei Yang Cc: Dan Williams Cc: Qian Cai Signed-off-by: David Hildenbrand Link: https://lore.kernel.org/r/20200507140139.17083-9-david@redhat.com Signed-off-by: Michael S. Tsirkin --- include/linux/memory_hotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 93d9ada74ddd..cb7499843f5c 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -319,6 +319,7 @@ extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern int remove_memory(int nid, u64 start, u64 size); extern void __remove_memory(int nid, u64 start, u64 size); +extern int offline_and_remove_memory(int nid, u64 start, u64 size); #else static inline bool is_mem_section_removable(unsigned long pfn, -- cgit v1.2.3 From 6501bf87602f799b7e502014f8bc0aa58b868277 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Wed, 3 Jun 2020 16:49:46 +0200 Subject: u64_stats: Document writer non-preemptibility requirement MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The u64_stats mechanism uses sequence counters to protect against 64-bit values tearing on 32-bit architectures. Updating such statistics is a sequence counter write side critical section. Preemption must be disabled before entering this seqcount write critical section. Failing to do so, the seqcount read side can preempt the write side section and spin for the entire scheduler tick. If that reader belongs to a real-time scheduling class, it can spin forever and the kernel will livelock. Document this statistics update side non-preemptibility requirement. Reword the introductory paragraph to highlight u64_stats raison d'être: 64-bit values tearing protection on 32-bit architectures. Divide documentation on a basis of internal design vs. usage constraints. Reword the u64_stats header file top comment to always mention "Reader" or "Writer" at the start of each bullet point, making it easier to follow which side each point is actually for. Clarify the statement "whole thing is a NOOP on 64bit arches or UP kernels". For 32-bit UP kernels, preemption is always disabled for the statistics read side section. Signed-off-by: Ahmed S. Darwish Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/linux/u64_stats_sync.h | 43 ++++++++++++++++++++++-------------------- 1 file changed, 23 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 9de5c10293f5..c6abb79501b3 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -3,33 +3,36 @@ #define _LINUX_U64_STATS_SYNC_H /* - * To properly implement 64bits network statistics on 32bit and 64bit hosts, - * we provide a synchronization point, that is a noop on 64bit or UP kernels. + * Protect against 64-bit values tearing on 32-bit architectures. This is + * typically used for statistics read/update in different subsystems. * * Key points : - * 1) Use a seqcount on SMP 32bits, with low overhead. - * 2) Whole thing is a noop on 64bit arches or UP kernels. - * 3) Write side must ensure mutual exclusion or one seqcount update could + * + * - Use a seqcount on 32-bit SMP, only disable preemption for 32-bit UP. + * - The whole thing is a no-op on 64-bit architectures. + * + * Usage constraints: + * + * 1) Write side must ensure mutual exclusion, or one seqcount update could * be lost, thus blocking readers forever. - * If this synchronization point is not a mutex, but a spinlock or - * spinlock_bh() or disable_bh() : - * 3.1) Write side should not sleep. - * 3.2) Write side should not allow preemption. - * 3.3) If applicable, interrupts should be disabled. * - * 4) If reader fetches several counters, there is no guarantee the whole values - * are consistent (remember point 1) : this is a noop on 64bit arches anyway) + * 2) Write side must disable preemption, or a seqcount reader can preempt the + * writer and also spin forever. + * + * 3) Write side must use the _irqsave() variant if other writers, or a reader, + * can be invoked from an IRQ context. * - * 5) readers are allowed to sleep or be preempted/interrupted : They perform - * pure reads. But if they have to fetch many values, it's better to not allow - * preemptions/interruptions to avoid many retries. + * 4) If reader fetches several counters, there is no guarantee the whole values + * are consistent w.r.t. each other (remember point #2: seqcounts are not + * used for 64bit architectures). * - * 6) If counter might be written by an interrupt, readers should block interrupts. - * (On UP, there is no seqcount_t protection, a reader allowing interrupts could - * read partial values) + * 5) Readers are allowed to sleep or be preempted/interrupted: they perform + * pure reads. * - * 7) For irq and softirq uses, readers can use u64_stats_fetch_begin_irq() and - * u64_stats_fetch_retry_irq() helpers + * 6) Readers must use both u64_stats_fetch_{begin,retry}_irq() if the stats + * might be updated from a hardirq or softirq context (remember point #1: + * seqcounts are not used for UP kernels). 32-bit UP stat readers could read + * corrupted 64-bit values otherwise. * * Usage : * -- cgit v1.2.3 From a1c979f330cb82cae7a3b19464f9815e43060fe3 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 27 May 2020 07:04:46 -0400 Subject: dm bufio: delete unused and inefficient dm_bufio_discard_buffers There is no user for this interface. If in future it is needed it can be reimplemented to walk the rbtree of buffers instead of doing block-by-block lookups. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- include/linux/dm-bufio.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 07e1f163e299..5ec6bfbde9ae 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -123,13 +123,6 @@ int dm_bufio_issue_flush(struct dm_bufio_client *c); */ int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t count); -/* - * Free the specified range of buffers. If a buffer is held by other process, it - * is not freed. If a buffer is dirty, it is discarded without writeback. - * Finally, send the discard request to the device. - */ -int dm_bufio_discard_buffers(struct dm_bufio_client *c, sector_t block, sector_t count); - /* * Like dm_bufio_release but also move the buffer to the new * block. dm_bufio_write_dirty_buffers is needed to commit the new block. -- cgit v1.2.3 From 5ff3b30ab57da82d8db4f14662a2858cabfbc2c0 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 4 Jun 2020 16:46:04 -0700 Subject: kcov: collect coverage from interrupts This change extends kcov remote coverage support to allow collecting coverage from soft interrupts in addition to kernel background threads. To collect coverage from code that is executed in softirq context, a part of that code has to be annotated with kcov_remote_start/stop() in a similar way as how it is done for global kernel background threads. Then the handle used for the annotations has to be passed to the KCOV_REMOTE_ENABLE ioctl. Internally this patch adjusts the __sanitizer_cov_trace_pc() compiler inserted callback to not bail out when called from softirq context. kcov_remote_start/stop() are updated to save/restore the current per task kcov state in a per-cpu area (in case the softirq came when the kernel was already collecting coverage in task context). Coverage from softirqs is collected into pre-allocated per-cpu areas, whose size is controlled by the new CONFIG_KCOV_IRQ_AREA_SIZE. [andreyknvl@google.com: turn current->kcov_softirq into unsigned int to fix objtool warning] Link: http://lkml.kernel.org/r/841c778aa3849c5cb8c3761f56b87ce653a88671.1585233617.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Signed-off-by: Andrew Morton Reviewed-by: Dmitry Vyukov Cc: Alan Stern Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Greg Kroah-Hartman Cc: Marco Elver Link: http://lkml.kernel.org/r/469bd385c431d050bc38a593296eff4baae50666.1584655448.git.andreyknvl@google.com Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 57a5ce9f33c5..c5d96e3e7fff 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1247,6 +1247,9 @@ struct task_struct { /* KCOV sequence number: */ int kcov_sequence; + + /* Collect coverage from softirq context: */ + unsigned int kcov_softirq; #endif #ifdef CONFIG_MEMCG -- cgit v1.2.3 From f089dcc74226b874a4d4b122854e0dea91ff72d8 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 4 Jun 2020 16:47:08 -0700 Subject: mm: remove __ARCH_HAS_5LEVEL_HACK and include/asm-generic/5level-fixup.h There are no architectures that use include/asm-generic/5level-fixup.h therefore it can be removed along with __ARCH_HAS_5LEVEL_HACK define and the code it surrounds Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Brian Cain Cc: Catalin Marinas Cc: Christophe Leroy Cc: Fenghua Yu Cc: Geert Uytterhoeven Cc: Guan Xuetao Cc: James Morse Cc: Jonas Bonn Cc: Julien Thierry Cc: Ley Foon Tan Cc: Marc Zyngier Cc: Michael Ellerman Cc: Paul Mackerras Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Suzuki K Poulose Cc: Tony Luck Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200414153455.21744-15-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 66e0977f970a..e220ce5185ad 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2069,11 +2069,6 @@ int __pte_alloc_kernel(pmd_t *pmd); #if defined(CONFIG_MMU) -/* - * The following ifdef needed to get the 5level-fixup.h header to work. - * Remove it when 5level-fixup.h has been removed. - */ -#ifndef __ARCH_HAS_5LEVEL_HACK static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { @@ -2102,8 +2097,6 @@ static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, return p4d_offset(pgd, address); } -#endif /* !__ARCH_HAS_5LEVEL_HACK */ - static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, unsigned long address, pgtbl_mod_mask *mod_mask) -- cgit v1.2.3 From 525aaf9bad00e7454b9f9b3873e92795afb59f8e Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:47:30 -0700 Subject: arch/kmap: remove redundant arch specific kmaps MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The kmap code for all the architectures is almost 100% identical. Lift the common code to the core. Use ARCH_HAS_KMAP_FLUSH_TLB to indicate if an arch defines kmap_flush_tlb() and call if if needed. This also has the benefit of changing kmap() on a number of architectures to be an inline call rather than an actual function. Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200507150004.1423069-4-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index ea5cdbd8c2c3..fc3adc51254a 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -34,6 +34,24 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #ifdef CONFIG_HIGHMEM #include +#ifndef ARCH_HAS_KMAP_FLUSH_TLB +static inline void kmap_flush_tlb(unsigned long addr) { } +#endif + +void *kmap_high(struct page *page); +static inline void *kmap(struct page *page) +{ + void *addr; + + might_sleep(); + if (!PageHighMem(page)) + addr = page_address(page); + else + addr = kmap_high(page); + kmap_flush_tlb((unsigned long)addr); + return addr; +} + /* declarations for linux/mm/highmem.c */ unsigned int nr_free_highpages(void); extern atomic_long_t _totalhigh_pages; -- cgit v1.2.3 From e23c45976f82ac789469c37e4d5a72ea2ce30bba Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:47:34 -0700 Subject: arch/kunmap: remove duplicate kunmap implementations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All architectures do exactly the same thing for kunmap(); remove all the duplicate definitions and lift the call to the core. This also has the benefit of changing kmap_unmap() on a number of architectures to be an inline call rather than an actual function. [akpm@linux-foundation.org: fix CONFIG_HIGHMEM=n build on various architectures] Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200507150004.1423069-5-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index fc3adc51254a..216a647ed7db 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -52,6 +52,16 @@ static inline void *kmap(struct page *page) return addr; } +void kunmap_high(struct page *page); + +static inline void kunmap(struct page *page) +{ + might_sleep(); + if (!PageHighMem(page)) + return; + kunmap_high(page); +} + /* declarations for linux/mm/highmem.c */ unsigned int nr_free_highpages(void); extern atomic_long_t _totalhigh_pages; @@ -102,6 +112,10 @@ static inline void *kmap(struct page *page) return page_address(page); } +static inline void kunmap_high(struct page *page) +{ +} + static inline void kunmap(struct page *page) { } -- cgit v1.2.3 From 78b6d91ec7bbfc5bcc2dd05bb2cf13c9de1dc7cd Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:47:42 -0700 Subject: arch/kmap_atomic: consolidate duplicate code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Every arch has the same code to ensure atomic operations and a check for !HIGHMEM page. Remove the duplicate code by defining a core kmap_atomic() which only calls the arch specific kmap_atomic_high() when the page is high memory. [akpm@linux-foundation.org: coding style fixes] Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200507150004.1423069-7-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 216a647ed7db..d2209ae8be99 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -32,6 +32,7 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #include #ifdef CONFIG_HIGHMEM +extern void *kmap_atomic_high(struct page *page); #include #ifndef ARCH_HAS_KMAP_FLUSH_TLB @@ -62,6 +63,28 @@ static inline void kunmap(struct page *page) kunmap_high(page); } +/* + * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because + * no global lock is needed and because the kmap code must perform a global TLB + * invalidation when the kmap pool wraps. + * + * However when holding an atomic kmap is is not legal to sleep, so atomic + * kmaps are appropriate for short, tight code paths only. + * + * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap + * gives a more generic (and caching) interface. But kmap_atomic can + * be used in IRQ contexts, so in some (very limited) cases we need + * it. + */ +static inline void *kmap_atomic(struct page *page) +{ + preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); + return kmap_atomic_high(page); +} + /* declarations for linux/mm/highmem.c */ unsigned int nr_free_highpages(void); extern atomic_long_t _totalhigh_pages; -- cgit v1.2.3 From abca2500c0c1b20c3e552f259da4c4a99db3b4d1 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:47:46 -0700 Subject: arch/kunmap_atomic: consolidate duplicate code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Every single architecture (including !CONFIG_HIGHMEM) calls... pagefault_enable(); preempt_enable(); ... before returning from __kunmap_atomic(). Lift this code into the kunmap_atomic() macro. While we are at it rename __kunmap_atomic() to kunmap_atomic_high() to be consistent. [ira.weiny@intel.com: don't enable pagefault/preempt twice] Link: http://lkml.kernel.org/r/20200518184843.3029640-1-ira.weiny@intel.com [akpm@linux-foundation.org: coding style fixes] Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Guenter Roeck Link: http://lkml.kernel.org/r/20200507150004.1423069-8-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index d2209ae8be99..945b58d8a57b 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -33,6 +33,7 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #ifdef CONFIG_HIGHMEM extern void *kmap_atomic_high(struct page *page); +extern void kunmap_atomic_high(void *kvaddr); #include #ifndef ARCH_HAS_KMAP_FLUSH_TLB @@ -151,10 +152,12 @@ static inline void *kmap_atomic(struct page *page) } #define kmap_atomic_prot(page, prot) kmap_atomic(page) -static inline void __kunmap_atomic(void *addr) +static inline void kunmap_atomic_high(void *addr) { - pagefault_enable(); - preempt_enable(); + /* + * Nothing to do in the CONFIG_HIGHMEM=n case as kunmap_atomic() + * handles re-enabling faults + preemption + */ } #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) @@ -204,7 +207,9 @@ static inline void kmap_atomic_idx_pop(void) #define kunmap_atomic(addr) \ do { \ BUILD_BUG_ON(__same_type((addr), struct page *)); \ - __kunmap_atomic(addr); \ + kunmap_atomic_high(addr); \ + pagefault_enable(); \ + preempt_enable(); \ } while (0) -- cgit v1.2.3 From 20b271dfe9d932b02b067a1f7ba9805c5b8d79bd Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:47:58 -0700 Subject: arch/kmap: define kmap_atomic_prot() for all arch's MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To support kmap_atomic_prot(), all architectures need to support protections passed to their kmap_atomic_high() function. Pass protections into kmap_atomic_high() and change the name to kmap_atomic_high_prot() to match. Then define kmap_atomic_prot() as a core function which calls kmap_atomic_high_prot() when needed. Finally, redefine kmap_atomic() as a wrapper of kmap_atomic_prot() with the default kmap_prot exported by the architectures. Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200507150004.1423069-11-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 945b58d8a57b..9c559c670299 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -32,7 +32,7 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #include #ifdef CONFIG_HIGHMEM -extern void *kmap_atomic_high(struct page *page); +extern void *kmap_atomic_high_prot(struct page *page, pgprot_t prot); extern void kunmap_atomic_high(void *kvaddr); #include @@ -77,14 +77,15 @@ static inline void kunmap(struct page *page) * be used in IRQ contexts, so in some (very limited) cases we need * it. */ -static inline void *kmap_atomic(struct page *page) +static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); - return kmap_atomic_high(page); + return kmap_atomic_high_prot(page, prot); } +#define kmap_atomic(page) kmap_atomic_prot(page, kmap_prot) /* declarations for linux/mm/highmem.c */ unsigned int nr_free_highpages(void); -- cgit v1.2.3 From 7438f36310ddd9fe536fc7403187f63427cecaba Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:48:10 -0700 Subject: parisc/kmap: remove duplicate kmap code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit parisc reimplements the kmap calls except to flush its dcache. This is arguably an abuse of kmap but regardless it is messy and confusing. Remove the duplicate code and have parisc define ARCH_HAS_FLUSH_ON_KUNMAP for a kunmap_flush_on_unmap() architecture specific call to flush the cache. Suggested-by: Al Viro Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Christoph Hellwig Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200507150004.1423069-14-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 9c559c670299..091b32dff2d1 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -130,7 +130,6 @@ static inline struct page *kmap_to_page(void *addr) static inline unsigned long totalhigh_pages(void) { return 0UL; } -#ifndef ARCH_HAS_KMAP static inline void *kmap(struct page *page) { might_sleep(); @@ -143,6 +142,9 @@ static inline void kunmap_high(struct page *page) static inline void kunmap(struct page *page) { +#ifdef ARCH_HAS_FLUSH_ON_KUNMAP + kunmap_flush_on_unmap(page_address(page)); +#endif } static inline void *kmap_atomic(struct page *page) @@ -156,15 +158,17 @@ static inline void *kmap_atomic(struct page *page) static inline void kunmap_atomic_high(void *addr) { /* - * Nothing to do in the CONFIG_HIGHMEM=n case as kunmap_atomic() + * Mostly nothing to do in the CONFIG_HIGHMEM=n case as kunmap_atomic() * handles re-enabling faults + preemption */ +#ifdef ARCH_HAS_FLUSH_ON_KUNMAP + kunmap_flush_on_unmap(addr); +#endif } #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) #define kmap_flush_unused() do {} while(0) -#endif #endif /* CONFIG_HIGHMEM */ -- cgit v1.2.3 From 090e77e166334b83f555de408df64b9ab394ea08 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 4 Jun 2020 16:48:18 -0700 Subject: kmap: consolidate kmap_prot definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Most architectures define kmap_prot to be PAGE_KERNEL. Let sparc and xtensa define there own and define PAGE_KERNEL as the default if not overridden. [akpm@linux-foundation.org: coding style fixes] Suggested-by: Christoph Hellwig Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Cc: Al Viro Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian König Cc: Chris Zankel Cc: Daniel Vetter Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Max Filippov Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200507150004.1423069-16-ira.weiny@intel.com Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 091b32dff2d1..d6e82e3de027 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -40,6 +40,10 @@ extern void kunmap_atomic_high(void *kvaddr); static inline void kmap_flush_tlb(unsigned long addr) { } #endif +#ifndef kmap_prot +#define kmap_prot PAGE_KERNEL +#endif + void *kmap_high(struct page *page); static inline void *kmap(struct page *page) { -- cgit v1.2.3 From d4eaa2837851db2bfed572898bfc17f9a9f9151e Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 4 Jun 2020 16:48:21 -0700 Subject: mm: add kvfree_sensitive() for freeing sensitive data objects For kvmalloc'ed data object that contains sensitive information like cryptographic keys, we need to make sure that the buffer is always cleared before freeing it. Using memset() alone for buffer clearing may not provide certainty as the compiler may compile it away. To be sure, the special memzero_explicit() has to be used. This patch introduces a new kvfree_sensitive() for freeing those sensitive data objects allocated by kvmalloc(). The relevant places where kvfree_sensitive() can be used are modified to use it. Fixes: 4f0882491a14 ("KEYS: Avoid false positive ENOMEM error on key read") Suggested-by: Linus Torvalds Signed-off-by: Waiman Long Signed-off-by: Andrew Morton Reviewed-by: Eric Biggers Acked-by: David Howells Cc: Jarkko Sakkinen Cc: James Morris Cc: "Serge E. Hallyn" Cc: Joe Perches Cc: Matthew Wilcox Cc: David Rientjes Cc: Uladzislau Rezki Link: http://lkml.kernel.org/r/20200407200318.11711-1-longman@redhat.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e220ce5185ad..5bfc36320e3c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -776,6 +776,7 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) } extern void kvfree(const void *addr); +extern void kvfree_sensitive(const void *addr, size_t len); /* * Mapcount of compound page as a whole, does not include mapped sub-pages. -- cgit v1.2.3 From 04f3465c98665b7c5a3484d7194f1858954069f5 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 4 Jun 2020 16:48:31 -0700 Subject: mm/memory_hotplug: remove is_mem_section_removable() Fortunately, all users of is_mem_section_removable() are gone. Get rid of it, including some now unnecessary functions. Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Reviewed-by: Wei Yang Reviewed-by: Baoquan He Acked-by: Michal Hocko Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Oscar Salvador Link: http://lkml.kernel.org/r/20200407135416.24093-3-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 93d9ada74ddd..7dca9cd6076b 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -314,19 +314,12 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {} #ifdef CONFIG_MEMORY_HOTREMOVE -extern bool is_mem_section_removable(unsigned long pfn, unsigned long nr_pages); extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern int remove_memory(int nid, u64 start, u64 size); extern void __remove_memory(int nid, u64 start, u64 size); #else -static inline bool is_mem_section_removable(unsigned long pfn, - unsigned long nr_pages) -{ - return false; -} - static inline void try_offline_node(int nid) {} static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) -- cgit v1.2.3 From 7b7b27214bba1966772f9213cd2d8e5d67f8487f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 4 Jun 2020 16:48:41 -0700 Subject: mm/memory_hotplug: introduce add_memory_driver_managed() Patch series "mm/memory_hotplug: Interface to add driver-managed system ram", v4. kexec (via kexec_load()) can currently not properly handle memory added via dax/kmem, and will have similar issues with virtio-mem. kexec-tools will currently add all memory to the fixed-up initial firmware memmap. In case of dax/kmem, this means that - in contrast to a proper reboot - how that persistent memory will be used can no longer be configured by the kexec'd kernel. In case of virtio-mem it will be harmful, because that memory might contain inaccessible pieces that require coordination with hypervisor first. In both cases, we want to let the driver in the kexec'd kernel handle detecting and adding the memory, like during an ordinary reboot. Introduce add_memory_driver_managed(). More on the samentics are in patch #1. In the future, we might want to make this behavior configurable for dax/kmem- either by configuring it in the kernel (which would then also allow to configure kexec_file_load()) or in kexec-tools by also adding "System RAM (kmem)" memory from /proc/iomem to the fixed-up initial firmware memmap. More on the motivation can be found in [1] and [2]. [1] https://lkml.kernel.org/r/20200429160803.109056-1-david@redhat.com [2] https://lkml.kernel.org/r/20200430102908.10107-1-david@redhat.com This patch (of 3): Some device drivers rely on memory they managed to not get added to the initial (firmware) memmap as system RAM - so it's not used as initial system RAM by the kernel and the driver is under control. While this is the case during cold boot and after a reboot, kexec is not aware of that and might add such memory to the initial (firmware) memmap of the kexec kernel. We need ways to teach kernel and userspace that this system ram is different. For example, dax/kmem allows to decide at runtime if persistent memory is to be used as system ram. Another future user is virtio-mem, which has to coordinate with its hypervisor to deal with inaccessible parts within memory resources. We want to let users in the kernel (esp. kexec) but also user space (esp. kexec-tools) know that this memory has different semantics and needs to be handled differently: 1. Don't create entries in /sys/firmware/memmap/ 2. Name the memory resource "System RAM ($DRIVER)" (exposed via /proc/iomem) ($DRIVER might be "kmem", "virtio_mem"). 3. Flag the memory resource IORESOURCE_MEM_DRIVER_MANAGED /sys/firmware/memmap/ [1] represents the "raw firmware-provided memory map" because "on most architectures that firmware-provided memory map is modified afterwards by the kernel itself". The primary user is kexec on x86-64. Since commit d96ae5309165 ("memory-hotplug: create /sys/firmware/memmap entry for new memory"), we add all hotplugged memory to that firmware memmap - which makes perfect sense for traditional memory hotplug on x86-64, where real HW will also add hotplugged DIMMs to the firmware memmap. We replicate what the "raw firmware-provided memory map" looks like after hot(un)plug. To keep things simple, let the user provide the full resource name instead of only the driver name - this way, we don't have to manually allocate/craft strings for memory resources. Also use the resource name to make decisions, to avoid passing additional flags. In case the name isn't "System RAM", it's special. We don't have to worry about firmware_map_remove() on the removal path. If there is no entry, it will simply return with -EINVAL. We'll adapt dax/kmem in a follow-up patch. [1] https://www.kernel.org/doc/Documentation/ABI/testing/sysfs-firmware-memmap Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Acked-by: Pankaj Gupta Cc: Michal Hocko Cc: Pankaj Gupta Cc: Wei Yang Cc: Baoquan He Cc: Dave Hansen Cc: Eric Biederman Cc: Pavel Tatashin Cc: Dan Williams Link: http://lkml.kernel.org/r/20200508084217.9160-1-david@redhat.com Link: http://lkml.kernel.org/r/20200508084217.9160-3-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/ioport.h | 1 + include/linux/memory_hotplug.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index a9b9170b5dd2..cc9a5b4593ca 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -103,6 +103,7 @@ struct resource { #define IORESOURCE_MEM_32BIT (3<<3) #define IORESOURCE_MEM_SHADOWABLE (1<<5) /* dup: IORESOURCE_SHADOWABLE */ #define IORESOURCE_MEM_EXPANSIONROM (1<<6) +#define IORESOURCE_MEM_DRIVER_MANAGED (1<<7) /* PnP I/O specific bits (IORESOURCE_BITS) */ #define IORESOURCE_IO_16BIT_ADDR (1<<0) diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7dca9cd6076b..fee7fab5d706 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -342,6 +342,8 @@ extern void __ref free_area_init_core_hotplug(int nid); extern int __add_memory(int nid, u64 start, u64 size); extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource); +extern int add_memory_driver_managed(int nid, u64 start, u64 size, + const char *resource_name); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); extern void remove_pfn_range_from_zone(struct zone *zone, -- cgit v1.2.3 From 57e86fa16a707db9e05dec77eb88a398f05a022b Mon Sep 17 00:00:00 2001 From: chenqiwu Date: Thu, 4 Jun 2020 16:48:55 -0700 Subject: mm: replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") [akpm@linux-foundation.org: fix build] Signed-off-by: chenqiwu Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Reviewed-by: Wei Yang Cc: Matthew Wilcox Cc: David Hildenbrand Cc: Michal Hocko Cc: Pankaj Gupta Cc: Yang Shi Cc: Qian Cai Cc: Baoquan He Link: http://lkml.kernel.org/r/1586599916-15456-1-git-send-email-qiwuchen55@gmail.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5bfc36320e3c..1744081a34d4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1726,7 +1726,7 @@ struct frame_vector { unsigned int nr_frames; /* Number of frames stored in ptrs array */ bool got_ref; /* Did we pin pages by getting page ref? */ bool is_pfns; /* Does array contain pages or pfns? */ - void *ptrs[0]; /* Array of pinned pfns / pages. Use + void *ptrs[]; /* Array of pinned pfns / pages. Use * pfns_vector_pages() or pfns_vector_pfns() * for access */ }; -- cgit v1.2.3 From 2b7874490243e014112100925405c4a17a8c40aa Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Thu, 4 Jun 2020 16:49:49 -0700 Subject: include/linux/mm.h: return true in cpupid_pid_unset() Fix the following coccicheck warning: include/linux/mm.h:1371:8-9: WARNING: return of 0/1 in function 'cpupid_pid_unset' with return type bool Signed-off-by: Jason Yan Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Link: http://lkml.kernel.org/r/20200422071816.48879-1-yanaijie@huawei.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1744081a34d4..86adc71a972f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1373,7 +1373,7 @@ static inline int cpu_pid_to_cpupid(int nid, int pid) static inline bool cpupid_pid_unset(int cpupid) { - return 1; + return true; } static inline void page_cpupid_reset_last(struct page *page) -- cgit v1.2.3 From bd93f003b7462ae39a43c531abca37fe7073b866 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 4 Jun 2020 16:50:30 -0700 Subject: include/linux/bitops.h: avoid clang shift-count-overflow warnings Clang normally does not warn about certain issues in inline functions when it only happens in an eliminated code path. However if something else goes wrong, it does tend to complain about the definition of hweight_long() on 32-bit targets: include/linux/bitops.h:75:41: error: shift count >= width of type [-Werror,-Wshift-count-overflow] return sizeof(w) == 4 ? hweight32(w) : hweight64(w); ^~~~~~~~~~~~ include/asm-generic/bitops/const_hweight.h:29:49: note: expanded from macro 'hweight64' define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w)) ^~~~~~~~~~~~~~~~~~~~ include/asm-generic/bitops/const_hweight.h:21:76: note: expanded from macro '__const_hweight64' define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32)) ^ ~~ include/asm-generic/bitops/const_hweight.h:20:49: note: expanded from macro '__const_hweight32' define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16)) ^ include/asm-generic/bitops/const_hweight.h:19:72: note: expanded from macro '__const_hweight16' define __const_hweight16(w) (__const_hweight8(w) + __const_hweight8((w) >> 8 )) ^ include/asm-generic/bitops/const_hweight.h:12:9: note: expanded from macro '__const_hweight8' (!!((w) & (1ULL << 2))) + \ Adding an explicit cast to __u64 avoids that warning and makes it easier to read other output. Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Acked-by: Christian Brauner Cc: Andy Shevchenko Cc: Rasmus Villemoes Cc: Josh Poimboeuf Cc: Nick Desaulniers Link: http://lkml.kernel.org/r/20200505135513.65265-1-arnd@arndb.de Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 9acf654f0b19..99f2ac30b1d9 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -72,7 +72,7 @@ static inline int get_bitmask_order(unsigned int count) static __always_inline unsigned long hweight_long(unsigned long w) { - return sizeof(w) == 4 ? hweight32(w) : hweight64(w); + return sizeof(w) == 4 ? hweight32(w) : hweight64((__u64)w); } /** -- cgit v1.2.3 From 51da9dfb7f20911ae4e79e9b412a9c2d4c373d4b Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Thu, 4 Jun 2020 16:50:49 -0700 Subject: elfnote: mark all .note sections SHF_ALLOC ELFNOTE_START allows callers to specify flags for .pushsection assembler directives. All callsites but ELF_NOTE use "a" for SHF_ALLOC. For vdso's that explicitly use ELF_NOTE_START and BUILD_SALT, the same section is specified twice after preprocessing, once with "a" flag, once without. Example: .pushsection .note.Linux, "a", @note ; .pushsection .note.Linux, "", @note ; While GNU as allows this ordering, it warns for the opposite ordering, making these directives position dependent. We'd prefer not to precisely match this behavior in Clang's integrated assembler. Instead, the non __ASSEMBLY__ definition of ELF_NOTE uses __attribute__((section(".note.Linux"))) which is created with SHF_ALLOC, so let's make the __ASSEMBLY__ definition of ELF_NOTE consistent with C and just always use "a" flag. This allows Clang to assemble a working mainline (5.6) kernel via: $ make CC=clang AS=clang Signed-off-by: Nick Desaulniers Signed-off-by: Andrew Morton Reviewed-by: Nathan Chancellor Reviewed-by: Fangrui Song Cc: Jeremy Fitzhardinge Cc: Thomas Gleixner Cc: Vincenzo Frascino Link: https://github.com/ClangBuiltLinux/linux/issues/913 Link: http://lkml.kernel.org/r/20200325231250.99205-1-ndesaulniers@google.com Debugged-by: Ilie Halip Signed-off-by: Linus Torvalds --- include/linux/elfnote.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elfnote.h b/include/linux/elfnote.h index 594d4e78654f..69b136e4dd2b 100644 --- a/include/linux/elfnote.h +++ b/include/linux/elfnote.h @@ -54,7 +54,7 @@ .popsection ; #define ELFNOTE(name, type, desc) \ - ELFNOTE_START(name, type, "") \ + ELFNOTE_START(name, type, "a") \ desc ; \ ELFNOTE_END -- cgit v1.2.3 From d2c0e6e91c7990c67921005f44f9b2b326ff2906 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 4 Jun 2020 16:51:05 -0700 Subject: include/linux/seq_file.h: introduce DEFINE_SEQ_ATTRIBUTE() helper macro Patch series "seq_file: Introduce DEFINE_SEQ_ATTRIBUTE() helper macro". As discussed in https://lore.kernel.org/lkml/20191129222310.GA3712618@kroah.com/, we could introduce a new helper macro to reduce losts of boilerplate code, vmstat and kprobes is the example which covert to use it, if this is accepted, I will send out more cleanups. This patch (of 3): Introduce DEFINE_SEQ_ATTRIBUTE() helper macro to decrease code duplication. [akpm@linux-foundation.org: coding style fixes] Signed-off-by: Kefeng Wang Signed-off-by: Andrew Morton Cc: Greg KH Cc: Ingo Molnar Cc: Kefeng Wang Cc: Anil S Keshavamurthy Cc: "David S. Miller" Cc: Masami Hiramatsu Cc: Al Viro Link: http://lkml.kernel.org/r/20200509064031.181091-1-wangkefeng.wang@huawei.com Link: http://lkml.kernel.org/r/20200509064031.181091-2-wangkefeng.wang@huawei.com Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 1672cf6f7614..813614d4b71f 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -145,6 +145,25 @@ void *__seq_open_private(struct file *, const struct seq_operations *, int); int seq_open_private(struct file *, const struct seq_operations *, int); int seq_release_private(struct inode *, struct file *); +#define DEFINE_SEQ_ATTRIBUTE(__name) \ +static int __name ## _open(struct inode *inode, struct file *file) \ +{ \ + int ret = seq_open(file, &__name ## _sops); \ + if (!ret && inode->i_private) { \ + struct seq_file *seq_f = file->private_data; \ + seq_f->private = inode->i_private; \ + } \ + return ret; \ +} \ + \ +static const struct file_operations __name ## _fops = { \ + .owner = THIS_MODULE, \ + .open = __name ## _open, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = seq_release, \ +} + #define DEFINE_SHOW_ATTRIBUTE(__name) \ static int __name ## _open(struct inode *inode, struct file *file) \ { \ -- cgit v1.2.3 From 986db2d14a6dca6456b63b4f5c410ae2aab4ec9d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 4 Jun 2020 16:51:14 -0700 Subject: exec: simplify the copy_strings_kernel calling convention copy_strings_kernel is always used with a single argument, adjust the calling convention to that. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexander Viro Link: http://lkml.kernel.org/r/20200501104105.2621149-2-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index a345d9fed3d8..3d3afe094c97 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -144,8 +144,7 @@ extern int setup_arg_pages(struct linux_binprm * bprm, extern int transfer_args_to_stack(struct linux_binprm *bprm, unsigned long *sp_location); extern int bprm_change_interp(const char *interp, struct linux_binprm *bprm); -extern int copy_strings_kernel(int argc, const char *const *argv, - struct linux_binprm *bprm); +int copy_string_kernel(const char *arg, struct linux_binprm *bprm); extern void install_exec_creds(struct linux_binprm *bprm); extern void set_binfmt(struct linux_binfmt *new); extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t); -- cgit v1.2.3 From 5872f1a2e5c783783d51e96468f0ff6aede61182 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 11 May 2020 21:59:51 +0100 Subject: READ_ONCE: Fix comment describing 2x32-bit atomicity READ_ONCE() permits 64-bit accesses on 32-bit architectures, since this crops up in a few places and is generally harmless because either the upper bits are always zero (e.g. for a virtual address or 32-bit time_t) or the architecture provides 64-bit atomicity anyway. Update the corresponding comment above compiletime_assert_rwonce_type(), which incorrectly states that 32-bit x86 provides 64-bit atomicity, and instead reference 32-bit Armv7 with LPAE. Cc: Thomas Gleixner Cc: Peter Zijlstra Reported-by: Jann Horn Signed-off-by: Will Deacon --- include/linux/compiler.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c363d8debc43..657e4fd38a77 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -332,9 +332,9 @@ static inline void *offset_to_ptr(const int *off) /* * Yes, this permits 64-bit accesses on 32-bit architectures. These will - * actually be atomic in many cases (namely x86), but for others we rely on - * the access being split into 2x32-bit accesses for a 32-bit quantity (e.g. - * a virtual address) and a strong prevailing wind. + * actually be atomic in some cases (namely Armv7 + LPAE), but for others we + * rely on the access being split into 2x32-bit accesses for a 32-bit quantity + * (e.g. a virtual address) and a strong prevailing wind. */ #define compiletime_assert_rwonce_type(t) \ compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ -- cgit v1.2.3 From 8d4beed7bbc71666de2630b79899c8852c3bf5cd Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 5 Jun 2020 11:05:51 +0100 Subject: compiler-types.h: Include naked type in __pick_integer_type() match __pick_integer_type() checks whether the type of its first argument is compatible with an explicitly signed or unsigned integer type, returning the compatible type if it exists. Unfortunately, 'char' is neither compatible with 'signed char' nor 'unsigned char', so add a check against the naked type to allow the __unqual_scalar_typeof() macro to strip qualifiers from char types without an explicit signedness. Reported-by: Rasmus Villemoes Signed-off-by: Will Deacon --- include/linux/compiler_types.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 233066c92f6f..6ed0612bc143 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -220,9 +220,14 @@ struct ftrace_likely_data { #define __pick_scalar_type(x, type, otherwise) \ __builtin_choose_expr(__same_type(x, type), (type)0, otherwise) +/* + * 'char' is not type-compatible with either 'signed char' or 'unsigned char', + * so we include the naked type here as well as the signed/unsigned variants. + */ #define __pick_integer_type(x, type, otherwise) \ - __pick_scalar_type(x, unsigned type, \ - __pick_scalar_type(x, signed type, otherwise)) + __pick_scalar_type(x, type, \ + __pick_scalar_type(x, unsigned type, \ + __pick_scalar_type(x, signed type, otherwise))) #define __unqual_scalar_typeof(x) typeof( \ __pick_integer_type(x, char, \ -- cgit v1.2.3 From b16d8ecf4fa17e16fff20638364f9bd2205615e7 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 5 Jun 2020 11:19:46 +0100 Subject: compiler.h: Enforce that READ_ONCE_NOCHECK() access size is sizeof(long) READ_ONCE_NOCHECK() unconditionally performs a sizeof(long)-sized access, so enforce that the size of the pointed-to object that we are loading from is the same size as 'long'. Reported-by: Marco Elver Signed-off-by: Will Deacon --- include/linux/compiler.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 657e4fd38a77..a0aa56e6b782 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -254,9 +254,12 @@ unsigned long __read_once_word_nocheck(const void *addr) */ #define READ_ONCE_NOCHECK(x) \ ({ \ - unsigned long __x = __read_once_word_nocheck(&(x)); \ + unsigned long __x; \ + compiletime_assert(sizeof(x) == sizeof(__x), \ + "Unsupported access size for READ_ONCE_NOCHECK()."); \ + __x = __read_once_word_nocheck(&(x)); \ smp_read_barrier_depends(); \ - __x; \ + (typeof(x))__x; \ }) static __no_kasan_or_inline -- cgit v1.2.3 From 1fd76043ecb04b8567a76b106db09ac778e1e2b8 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 27 May 2020 12:32:36 +0200 Subject: compiler_types.h: Optimize __unqual_scalar_typeof compilation time If the compiler supports C11's _Generic, use it to speed up compilation times of __unqual_scalar_typeof(). GCC version 4.9 or later and all supported versions of Clang support the feature (the oldest supported compiler that doesn't support _Generic is GCC 4.8, for which we use the slower alternative). The non-_Generic variant relies on multiple expansions of __pick_integer_type -> __pick_scalar_type -> __builtin_choose_expr, which increases pre-processed code size, and can cause compile times to increase in files with numerous expansions of READ_ONCE(), or other users of __unqual_scalar_typeof(). Summary of compile-time benchmarking done by Arnd Bergmann: clang-11 gcc-9 this patch 0.78 0.91 ideal 0.76 0.86 See https://lkml.kernel.org/r/CAK8P3a3UYQeXhiufUevz=rwe09WM_vSTCd9W+KvJHJcOeQyWVA@mail.gmail.com Further compile-testing done with: gcc 4.8, 4.9, 5.5, 6.4, 7.5, 8.4; clang 9, 10. Reported-by: Arnd Bergmann Signed-off-by: Marco Elver Signed-off-by: Borislav Petkov Acked-by: Peter Zijlstra Tested-by: Arnd Bergmann Link: https://lkml.kernel.org/r/20200527103236.148700-1-elver@google.com Link: https://lkml.kernel.org/r/CAK8P3a0RJtbVi1JMsfik=jkHCNFv+DJn_FeDg-YLW+ueQW3tNg@mail.gmail.com [will: tweak new macros to make them a bit more readable] Signed-off-by: Will Deacon --- include/linux/compiler_types.h | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 6ed0612bc143..31416b60eabf 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -213,7 +213,9 @@ struct ftrace_likely_data { /* * __unqual_scalar_typeof(x) - Declare an unqualified scalar type, leaving * non-scalar types unchanged. - * + */ +#if defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 40900 +/* * We build this out of a couple of helper macros in a vain attempt to * help you keep your lunch down while reading it. */ @@ -235,6 +237,25 @@ struct ftrace_likely_data { __pick_integer_type(x, int, \ __pick_integer_type(x, long, \ __pick_integer_type(x, long long, x)))))) +#else +/* + * If supported, prefer C11 _Generic for better compile-times. As above, 'char' + * is not type-compatible with 'signed char', and we define a separate case. + */ +#define __scalar_type_to_expr_cases(type) \ + unsigned type: (unsigned type)0, \ + signed type: (signed type)0 + +#define __unqual_scalar_typeof(x) typeof( \ + _Generic((x), \ + char: (char)0, \ + __scalar_type_to_expr_cases(char), \ + __scalar_type_to_expr_cases(short), \ + __scalar_type_to_expr_cases(int), \ + __scalar_type_to_expr_cases(long), \ + __scalar_type_to_expr_cases(long long), \ + default: (x))) +#endif /* Is this type a native word size -- useful for atomic operations */ #define __native_word(t) \ -- cgit v1.2.3 From b398ace5d2ea0b7f00d9f1ce23c647e289c206ca Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 28 May 2020 09:43:13 +0200 Subject: compiler_types.h: Use unoptimized __unqual_scalar_typeof for sparse If the file is being checked with sparse, use the unoptimized version of __unqual_scalar_typeof(), since sparse does not support _Generic. Reported-by: kbuild test robot Signed-off-by: Marco Elver Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/202005280727.lXn1VnTw%lkp@intel.com Signed-off-by: Will Deacon --- include/linux/compiler_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 31416b60eabf..cd73e3857a87 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -214,7 +214,7 @@ struct ftrace_likely_data { * __unqual_scalar_typeof(x) - Declare an unqualified scalar type, leaving * non-scalar types unchanged. */ -#if defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 40900 +#if (defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 40900) || defined(__CHECKER__) /* * We build this out of a couple of helper macros in a vain attempt to * help you keep your lunch down while reading it. -- cgit v1.2.3 From cf6fada71543ceea0f6228ffdc0b85778f3f5a6e Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Sat, 30 May 2020 10:08:30 +0800 Subject: cpufreq: change '.set_boost' to act on one policy Macro 'for_each_active_policy()' is defined internally. To avoid some cpufreq driver needing this macro to iterate over all the policies in '.set_boost' callback, we redefine '.set_boost' to act on only one policy and pass the policy as an argument. 'cpufreq_boost_trigger_state()' iterates over all the policies to set boost for the system. This is preparation for adding SW BOOST support for CPPC. To protect Boost enable/disable by sysfs from CPU online/offline, add 'cpu_hotplug_lock' before calling '.set_boost' for each CPU. Also move the lock from 'set_boost()' to 'store_cpb()' in acpi_cpufreq. Signed-off-by: Xiongfeng Wang Suggested-by: Viresh Kumar Acked-by: Viresh Kumar [ rjw: Subject & changelog ] Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 67d5950bd878..3494f6763597 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -367,7 +367,7 @@ struct cpufreq_driver { /* platform specific boost support code */ bool boost_enabled; - int (*set_boost)(int state); + int (*set_boost)(struct cpufreq_policy *policy, int state); }; /* flags */ -- cgit v1.2.3 From 33a180623b6c35f2727daecb63763955af3af1df Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 2 Jun 2020 15:34:40 +0200 Subject: dm bufio: introduce forget_buffer_locked Introduce a function forget_buffer_locked that forgets a range of buffers. It is more efficient than calling forget_buffer in a loop. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- include/linux/dm-bufio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 5ec6bfbde9ae..29d255fdd5d6 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -136,6 +136,13 @@ void dm_bufio_release_move(struct dm_buffer *b, sector_t new_block); */ void dm_bufio_forget(struct dm_bufio_client *c, sector_t block); +/* + * Free the given range of buffers. + * This is just a hint, if the buffer is in use or dirty, this function + * does nothing. + */ +void dm_bufio_forget_buffers(struct dm_bufio_client *c, sector_t block, sector_t n_blocks); + /* * Set the minimum number of buffers before cleanup happens. */ -- cgit v1.2.3 From 90c56b3877995d948dc382fe833a1c5eeaaee2ad Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Jun 2020 07:21:22 -0700 Subject: net: ethtool: Fix comment mentioning typo in IS_ENABLED() This has no code changes, but it's a typo noticed in other clean-ups, so we might as well fix it. IS_ENABLED() takes full names, and should have the "CONFIG_" prefix. Reported-by: Joe Perches Link: https://lore.kernel.org/lkml/b08611018fdb6d88757c6008a5c02fa0e07b32fb.camel@perches.com Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 8fbe4f97ffad..1e7bf78cb382 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -67,5 +67,5 @@ static inline int ethnl_cable_test_step(struct phy_device *phydev, u32 first, { return -EOPNOTSUPP; } -#endif /* IS_ENABLED(ETHTOOL_NETLINK) */ +#endif /* IS_ENABLED(CONFIG_ETHTOOL_NETLINK) */ #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ -- cgit v1.2.3 From 46f21af862656c477387f2256adc1005503db67d Mon Sep 17 00:00:00 2001 From: Wesley Sheng Date: Tue, 26 May 2020 15:59:43 +0800 Subject: NTB: correct ntb_peer_spad_addr and ntb_peer_spad_read comment typos The comment for ntb_peer_spad_addr and ntb_peer_spad_read incorrectly referred to peer doorbell register and local scratchpad register. Signed-off-by: Wesley Sheng Signed-off-by: Jon Mason --- include/linux/ntb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index a07252f78770..191b524e5c0d 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -1351,7 +1351,7 @@ static inline int ntb_spad_write(struct ntb_dev *ntb, int sidx, u32 val) * @sidx: Scratchpad index. * @spad_addr: OUT - The address of the peer scratchpad register. * - * Return the address of the peer doorbell register. This may be used, for + * Return the address of the peer scratchpad register. This may be used, for * example, by drivers that offload memory copy operations to a dma engine. * * Return: Zero on success, otherwise an error number. @@ -1373,7 +1373,7 @@ static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int pidx, int sidx, * * Read the peer scratchpad register, and return the value. * - * Return: The value of the local scratchpad register. + * Return: The value of the peer scratchpad register. */ static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx) { -- cgit v1.2.3 From f5152f4ded3ce6d332d5e4f9d7e325c3b81cae1b Mon Sep 17 00:00:00 2001 From: Erwan Velu Date: Sat, 6 Jun 2020 11:35:50 +0200 Subject: firmware/dmi: Report DMI Bios & EC firmware release Some vendors like HPe or Dell, encode the release version of their BIOS in the "System BIOS {Major|Minor} Release" fields of Type 0. This information is used to know which bios release actually runs. It could be used for some quirks, debugging sessions or inventory tasks. A typical output for a Dell system running the 65.27 bios is : [root@t1700 ~]# cat /sys/devices/virtual/dmi/id/bios_release 65.27 [root@t1700 ~]# Servers that have a BMC encode the release version of their firmware in the "Embedded Controller Firmware {Major|Minor} Release" fields of Type 0. This information is used to know which BMC release actually runs. It could be used for some quirks, debugging sessions or inventory tasks. A typical output for a Dell system running the 3.75 bmc release is : [root@t1700 ~]# cat /sys/devices/virtual/dmi/id/ec_firmware_release 3.75 [root@t1700 ~]# Signed-off-by: Erwan Velu Signed-off-by: Jean Delvare --- include/linux/mod_devicetable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 4c2ddd0941a7..4b3d0a4945df 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -532,6 +532,8 @@ enum dmi_field { DMI_BIOS_VENDOR, DMI_BIOS_VERSION, DMI_BIOS_DATE, + DMI_BIOS_RELEASE, + DMI_EC_FIRMWARE_RELEASE, DMI_SYS_VENDOR, DMI_PRODUCT_NAME, DMI_PRODUCT_VERSION, -- cgit v1.2.3 From e649b3f0188f8fd34dd0dde8d43fd3312b902fb2 Mon Sep 17 00:00:00 2001 From: Eiichi Tsukata Date: Sat, 6 Jun 2020 13:26:27 +0900 Subject: KVM: x86: Fix APIC page invalidation race Commit b1394e745b94 ("KVM: x86: fix APIC page invalidation") tried to fix inappropriate APIC page invalidation by re-introducing arch specific kvm_arch_mmu_notifier_invalidate_range() and calling it from kvm_mmu_notifier_invalidate_range_start. However, the patch left a possible race where the VMCS APIC address cache is updated *before* it is unmapped: (Invalidator) kvm_mmu_notifier_invalidate_range_start() (Invalidator) kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD) (KVM VCPU) vcpu_enter_guest() (KVM VCPU) kvm_vcpu_reload_apic_access_page() (Invalidator) actually unmap page Because of the above race, there can be a mismatch between the host physical address stored in the APIC_ACCESS_PAGE VMCS field and the host physical address stored in the EPT entry for the APIC GPA (0xfee0000). When this happens, the processor will not trap APIC accesses, and will instead show the raw contents of the APIC-access page. Because Windows OS periodically checks for unexpected modifications to the LAPIC register, this will show up as a BSOD crash with BugCheck CRITICAL_STRUCTURE_CORRUPTION (109) we are currently seeing in https://bugzilla.redhat.com/show_bug.cgi?id=1751017. The root cause of the issue is that kvm_arch_mmu_notifier_invalidate_range() cannot guarantee that no additional references are taken to the pages in the range before kvm_mmu_notifier_invalidate_range_end(). Fortunately, this case is supported by the MMU notifier API, as documented in include/linux/mmu_notifier.h: * If the subsystem * can't guarantee that no additional references are taken to * the pages in the range, it has to implement the * invalidate_range() notifier to remove any references taken * after invalidate_range_start(). The fix therefore is to reload the APIC-access page field in the VMCS from kvm_mmu_notifier_invalidate_range() instead of ..._range_start(). Cc: stable@vger.kernel.org Fixes: b1394e745b94 ("KVM: x86: fix APIC page invalidation") Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=197951 Signed-off-by: Eiichi Tsukata Message-Id: <20200606042627.61070-1-eiichi.tsukata@nutanix.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d38d6b9c24be..e2f82131bb3e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1420,8 +1420,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, } #endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */ -int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end, bool blockable); +void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end); #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); -- cgit v1.2.3 From 7ff0d4490ebadae8037a079a70c5cac13385a808 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 3 Jun 2020 07:52:37 +0200 Subject: trace: fix an incorrect __user annotation on stack_trace_sysctl No user pointers for sysctls anymore. Fixes: 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") Reported-by: build test robot Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/ftrace.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ddfc377de0d2..fce81238f304 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -319,9 +319,8 @@ static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, extern int stack_tracer_enabled; -int stack_trace_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); +int stack_trace_sysctl(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */ DECLARE_PER_CPU(int, disable_stack_tracer); -- cgit v1.2.3 From e1eb26fa62d04ec0955432be1aa8722a97cb52e7 Mon Sep 17 00:00:00 2001 From: Giuseppe Scrivano Date: Sun, 7 Jun 2020 21:40:10 -0700 Subject: ipc/namespace.c: use a work queue to free_ipc the reason is to avoid a delay caused by the synchronize_rcu() call in kern_umount() when the mqueue mount is freed. the code: #define _GNU_SOURCE #include #include #include #include int main() { int i; for (i = 0; i < 1000; i++) if (unshare(CLONE_NEWIPC) < 0) error(EXIT_FAILURE, errno, "unshare"); } goes from Command being timed: "./ipc-namespace" User time (seconds): 0.00 System time (seconds): 0.06 Percent of CPU this job got: 0% Elapsed (wall clock) time (h:mm:ss or m:ss): 0:08.05 to Command being timed: "./ipc-namespace" User time (seconds): 0.00 System time (seconds): 0.02 Percent of CPU this job got: 96% Elapsed (wall clock) time (h:mm:ss or m:ss): 0:00.03 Signed-off-by: Giuseppe Scrivano Signed-off-by: Andrew Morton Reviewed-by: Paul E. McKenney Reviewed-by: Waiman Long Cc: Davidlohr Bueso Cc: Manfred Spraul Link: http://lkml.kernel.org/r/20200225145419.527994-1-gscrivan@redhat.com Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index c309f43bde45..a06a78c67f19 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -68,6 +68,8 @@ struct ipc_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; + struct llist_node mnt_llist; + struct ns_common ns; } __randomize_layout; -- cgit v1.2.3 From ceabef7dd71720aef58bd182943352c9c307a3de Mon Sep 17 00:00:00 2001 From: Orson Zhai Date: Sun, 7 Jun 2020 21:40:14 -0700 Subject: dynamic_debug: add an option to enable dynamic debug for modules only Instead of enabling dynamic debug globally with CONFIG_DYNAMIC_DEBUG, CONFIG_DYNAMIC_DEBUG_CORE will only enable core function of dynamic debug. With the DYNAMIC_DEBUG_MODULE defined for any modules, dynamic debug will be tied to them. This is useful for people who only want to enable dynamic debug for kernel modules without worrying about kernel image size and memory consumption is increasing too much. [orson.zhai@unisoc.com: v2] Link: http://lkml.kernel.org/r/1587408228-10861-1-git-send-email-orson.unisoc@gmail.com Signed-off-by: Orson Zhai Signed-off-by: Andrew Morton Acked-by: Greg Kroah-Hartman Acked-by: Petr Mladek Cc: Jonathan Corbet Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Jason Baron Cc: Randy Dunlap Link: http://lkml.kernel.org/r/1586521984-5890-1-git-send-email-orson.unisoc@gmail.com Signed-off-by: Linus Torvalds --- include/linux/dev_printk.h | 6 ++++-- include/linux/dynamic_debug.h | 2 +- include/linux/net.h | 3 ++- include/linux/netdevice.h | 6 ++++-- include/linux/printk.h | 9 ++++++--- 5 files changed, 17 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 5aad06b4ca7b..3028b644b4fb 100644 --- a/include/linux/dev_printk.h +++ b/include/linux/dev_printk.h @@ -109,7 +109,8 @@ void _dev_info(const struct device *dev, const char *fmt, ...) #define dev_info(dev, fmt, ...) \ _dev_info(dev, dev_fmt(fmt), ##__VA_ARGS__) -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define dev_dbg(dev, fmt, ...) \ dynamic_dev_dbg(dev, dev_fmt(fmt), ##__VA_ARGS__) #elif defined(DEBUG) @@ -181,7 +182,8 @@ do { \ dev_level_ratelimited(dev_notice, dev, fmt, ##__VA_ARGS__) #define dev_info_ratelimited(dev, fmt, ...) \ dev_level_ratelimited(dev_info, dev, fmt, ##__VA_ARGS__) -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define dev_dbg_ratelimited(dev, fmt, ...) \ do { \ diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 4cf02ecd67de..abcd5fde30eb 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -48,7 +48,7 @@ struct _ddebug { -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG_CORE) int ddebug_add_module(struct _ddebug *tab, unsigned int n, const char *modname); extern int ddebug_remove_module(const char *mod_name); diff --git a/include/linux/net.h b/include/linux/net.h index e10f378194a5..016a9c5faa34 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -264,7 +264,8 @@ do { \ net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__) #define net_info_ratelimited(fmt, ...) \ net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__) -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define net_dbg_ratelimited(fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1a96e9c4ec36..5b364a2e0006 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4942,7 +4942,8 @@ do { \ #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define netdev_dbg(__dev, format, args...) \ do { \ dynamic_netdev_dbg(__dev, format, ##args); \ @@ -5012,7 +5013,8 @@ do { \ #define netif_info(priv, type, dev, fmt, args...) \ netif_level(info, priv, type, dev, fmt, ##args) -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define netif_dbg(priv, type, netdev, format, args...) \ do { \ if (netif_msg_##type(priv)) \ diff --git a/include/linux/printk.h b/include/linux/printk.h index 3cc2f178bf06..fc8f03c54543 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -399,7 +399,8 @@ extern int kptr_restrict; /* If you are writing a driver, please use dev_dbg instead */ -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #include /** @@ -535,7 +536,8 @@ extern int kptr_restrict; #endif /* If you are writing a driver, please use dev_dbg instead */ -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define pr_debug_ratelimited(fmt, ...) \ do { \ @@ -582,7 +584,8 @@ static inline void print_hex_dump_bytes(const char *prefix_str, int prefix_type, #endif -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ -- cgit v1.2.3 From db38d5c106dfdd7cb7207c83267d82fdf4950b61 Mon Sep 17 00:00:00 2001 From: Rafael Aquini Date: Sun, 7 Jun 2020 21:40:17 -0700 Subject: kernel: add panic_on_taint Analogously to the introduction of panic_on_warn, this patch introduces a kernel option named panic_on_taint in order to provide a simple and generic way to stop execution and catch a coredump when the kernel gets tainted by any given flag. This is useful for debugging sessions as it avoids having to rebuild the kernel to explicitly add calls to panic() into the code sites that introduce the taint flags of interest. For instance, if one is interested in proceeding with a post-mortem analysis at the point a given code path is hitting a bad page (i.e. unaccount_page_cache_page(), or slab_bug()), a coredump can be collected by rebooting the kernel with 'panic_on_taint=0x20' amended to the command line. Another, perhaps less frequent, use for this option would be as a means for assuring a security policy case where only a subset of taints, or no single taint (in paranoid mode), is allowed for the running system. The optional switch 'nousertaint' is handy in this particular scenario, as it will avoid userspace induced crashes by writes to sysctl interface /proc/sys/kernel/tainted causing false positive hits for such policies. [akpm@linux-foundation.org: tweak kernel-parameters.txt wording] Suggested-by: Qian Cai Signed-off-by: Rafael Aquini Signed-off-by: Andrew Morton Reviewed-by: Luis Chamberlain Cc: Dave Young Cc: Baoquan He Cc: Jonathan Corbet Cc: Kees Cook Cc: Randy Dunlap Cc: "Theodore Ts'o" Cc: Adrian Bunk Cc: Greg Kroah-Hartman Cc: Laura Abbott Cc: Jeff Mahoney Cc: Jiri Kosina Cc: Takashi Iwai Link: http://lkml.kernel.org/r/20200515175502.146720-1-aquini@redhat.com Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 9b7a8d74a9d6..f7835db7102e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -528,6 +528,8 @@ extern int panic_on_oops; extern int panic_on_unrecovered_nmi; extern int panic_on_io_nmi; extern int panic_on_warn; +extern unsigned long panic_on_taint; +extern bool panic_on_taint_nousertaint; extern int sysctl_panic_on_rcu_stall; extern int sysctl_panic_on_stackoverflow; @@ -596,6 +598,7 @@ extern enum system_states { #define TAINT_AUX 16 #define TAINT_RANDSTRUCT 17 #define TAINT_FLAGS_COUNT 18 +#define TAINT_FLAGS_MAX ((1UL << TAINT_FLAGS_COUNT) - 1) struct taint_flag { char c_true; /* character printed when tainted */ -- cgit v1.2.3 From 01f39c1c11ee5bf44a1df49e47eb53a86515b9dc Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Sun, 7 Jun 2020 21:40:20 -0700 Subject: xarray.h: correct return code documentation for xa_store_{bh,irq}() __xa_store() and xa_store() document that the functions can fail, and that the return code can be an xa_err() encoded error code. xa_store_bh() and xa_store_irq() do not document that the functions can fail and that they can also return xa_err() encoded error codes. Thus: Update the documentation. Signed-off-by: Manfred Spraul Signed-off-by: Andrew Morton Cc: Matthew Wilcox Link: http://lkml.kernel.org/r/20200430111424.16634-1-manfred@colorfullife.com Signed-off-by: Linus Torvalds --- include/linux/xarray.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 14c893433139..b4d70e7568b2 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -576,7 +576,7 @@ void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. - * Return: The entry which used to be at this index. + * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) @@ -602,7 +602,7 @@ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. - * Return: The entry which used to be at this index. + * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) -- cgit v1.2.3 From 3db978d480e2843979a2b56f2f7da726f2b295b2 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Sun, 7 Jun 2020 21:40:24 -0700 Subject: kernel/sysctl: support setting sysctl parameters from kernel command line Patch series "support setting sysctl parameters from kernel command line", v3. This series adds support for something that seems like many people always wanted but nobody added it yet, so here's the ability to set sysctl parameters via kernel command line options in the form of sysctl.vm.something=1 The important part is Patch 1. The second, not so important part is an attempt to clean up legacy one-off parameters that do the same thing as a sysctl. I don't want to remove them completely for compatibility reasons, but with generic sysctl support the idea is to remove the one-off param handlers and treat the parameters as aliases for the sysctl variants. I have identified several parameters that mention sysctl counterparts in Documentation/admin-guide/kernel-parameters.txt but there might be more. The conversion also has varying level of success: - numa_zonelist_order is converted in Patch 2 together with adding the necessary infrastructure. It's easy as it doesn't really do anything but warn on deprecated value these days. - hung_task_panic is converted in Patch 3, but there's a downside that now it only accepts 0 and 1, while previously it was any integer value - nmi_watchdog maps to two sysctls nmi_watchdog and hardlockup_panic, so there's no straighforward conversion possible - traceoff_on_warning is a flag without value and it would be required to handle that somehow in the conversion infractructure, which seems pointless for a single flag This patch (of 5): A recently proposed patch to add vm_swappiness command line parameter in addition to existing sysctl [1] made me wonder why we don't have a general support for passing sysctl parameters via command line. Googling found only somebody else wondering the same [2], but I haven't found any prior discussion with reasons why not to do this. Settings the vm_swappiness issue aside (the underlying issue might be solved in a different way), quick search of kernel-parameters.txt shows there are already some that exist as both sysctl and kernel parameter - hung_task_panic, nmi_watchdog, numa_zonelist_order, traceoff_on_warning. A general mechanism would remove the need to add more of those one-offs and might be handy in situations where configuration by e.g. /etc/sysctl.d/ is impractical. Hence, this patch adds a new parse_args() pass that looks for parameters prefixed by 'sysctl.' and tries to interpret them as writes to the corresponding sys/ files using an temporary in-kernel procfs mount. This mechanism was suggested by Eric W. Biederman [3], as it handles all dynamically registered sysctl tables, even though we don't handle modular sysctls. Errors due to e.g. invalid parameter name or value are reported in the kernel log. The processing is hooked right before the init process is loaded, as some handlers might be more complicated than simple setters and might need some subsystems to be initialized. At the moment the init process can be started and eventually execute a process writing to /proc/sys/ then it should be also fine to do that from the kernel. Sysctls registered later on module load time are not set by this mechanism - it's expected that in such scenarios, setting sysctl values from userspace is practical enough. [1] https://lore.kernel.org/r/BL0PR02MB560167492CA4094C91589930E9FC0@BL0PR02MB5601.namprd02.prod.outlook.com/ [2] https://unix.stackexchange.com/questions/558802/how-to-set-sysctl-using-kernel-command-line-parameter [3] https://lore.kernel.org/r/87bloj2skm.fsf@x220.int.ebiederm.org/ Signed-off-by: Vlastimil Babka Signed-off-by: Andrew Morton Reviewed-by: Luis Chamberlain Reviewed-by: Masami Hiramatsu Acked-by: Kees Cook Acked-by: Michal Hocko Cc: Iurii Zaikin Cc: Ivan Teterevkov Cc: Michal Hocko Cc: David Rientjes Cc: Matthew Wilcox Cc: "Eric W . Biederman" Cc: "Guilherme G . Piccoli" Cc: Alexey Dobriyan Cc: Thomas Gleixner Cc: Greg Kroah-Hartman Cc: Christian Brauner Link: http://lkml.kernel.org/r/20200427180433.7029-1-vbabka@suse.cz Link: http://lkml.kernel.org/r/20200427180433.7029-2-vbabka@suse.cz Signed-off-by: Linus Torvalds --- include/linux/sysctl.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index f2401e45a3c2..50bb7f383a1b 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -197,6 +197,7 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init(void); +void do_sysctl_args(void); extern int pwrsw_enabled; extern int unaligned_enabled; @@ -235,6 +236,9 @@ static inline void setup_sysctl_set(struct ctl_table_set *p, { } +static inline void do_sysctl_args(void) +{ +} #endif /* CONFIG_SYSCTL */ int sysctl_max_threads(struct ctl_table *table, int write, void *buffer, -- cgit v1.2.3 From 0ec9dc9bcba0a62b0844e54c1caf6b8b0bf6b5b4 Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Sun, 7 Jun 2020 21:40:45 -0700 Subject: kernel/hung_task.c: introduce sysctl to print all traces when a hung task is detected Commit 401c636a0eeb ("kernel/hung_task.c: show all hung tasks before panic") introduced a change in that we started to show all CPUs backtraces when a hung task is detected _and_ the sysctl/kernel parameter "hung_task_panic" is set. The idea is good, because usually when observing deadlocks (that may lead to hung tasks), the culprit is another task holding a lock and not necessarily the task detected as hung. The problem with this approach is that dumping backtraces is a slightly expensive task, specially printing that on console (and specially in many CPU machines, as servers commonly found nowadays). So, users that plan to collect a kdump to investigate the hung tasks and narrow down the deadlock definitely don't need the CPUs backtrace on dmesg/console, which will delay the panic and pollute the log (crash tool would easily grab all CPUs traces with 'bt -a' command). Also, there's the reciprocal scenario: some users may be interested in seeing the CPUs backtraces but not have the system panic when a hung task is detected. The current approach hence is almost as embedding a policy in the kernel, by forcing the CPUs backtraces' dump (only) on hung_task_panic. This patch decouples the panic event on hung task from the CPUs backtraces dump, by creating (and documenting) a new sysctl called "hung_task_all_cpu_backtrace", analog to the approach taken on soft/hard lockups, that have both a panic and an "all_cpu_backtrace" sysctl to allow individual control. The new mechanism for dumping the CPUs backtraces on hung task detection respects "hung_task_warnings" by not dumping the traces in case there's no warnings left. Signed-off-by: Guilherme G. Piccoli Signed-off-by: Andrew Morton Reviewed-by: Kees Cook Cc: Tetsuo Handa Link: http://lkml.kernel.org/r/20200327223646.20779-1-gpiccoli@canonical.com Signed-off-by: Linus Torvalds --- include/linux/sched/sysctl.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 7b4d3a49b6c5..660ac49f2b53 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -7,6 +7,13 @@ struct ctl_table; #ifdef CONFIG_DETECT_HUNG_TASK + +#ifdef CONFIG_SMP +extern unsigned int sysctl_hung_task_all_cpu_backtrace; +#else +#define sysctl_hung_task_all_cpu_backtrace 0 +#endif /* CONFIG_SMP */ + extern int sysctl_hung_task_check_count; extern unsigned int sysctl_hung_task_panic; extern unsigned long sysctl_hung_task_timeout_secs; -- cgit v1.2.3 From 60c958d8df9cfc40b745d6cd583cfbfa7525ead6 Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Sun, 7 Jun 2020 21:40:48 -0700 Subject: panic: add sysctl to dump all CPUs backtraces on oops event Usually when the kernel reaches an oops condition, it's a point of no return; in case not enough debug information is available in the kernel splat, one of the last resorts would be to collect a kernel crash dump and analyze it. The problem with this approach is that in order to collect the dump, a panic is required (to kexec-load the crash kernel). When in an environment of multiple virtual machines, users may prefer to try living with the oops, at least until being able to properly shutdown their VMs / finish their important tasks. This patch implements a way to collect a bit more debug details when an oops event is reached, by printing all the CPUs backtraces through the usage of NMIs (on architectures that support that). The sysctl added (and documented) here was called "oops_all_cpu_backtrace", and when set will (as the name suggests) dump all CPUs backtraces. Far from ideal, this may be the last option though for users that for some reason cannot panic on oops. Most of times oopses are clear enough to indicate the kernel portion that must be investigated, but in virtual environments it's possible to observe hypervisor/KVM issues that could lead to oopses shown in other guests CPUs (like virtual APIC crashes). This patch hence aims to help debug such complex issues without resorting to kdump. Signed-off-by: Guilherme G. Piccoli Signed-off-by: Andrew Morton Reviewed-by: Kees Cook Cc: Luis Chamberlain Cc: Iurii Zaikin Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Randy Dunlap Cc: Matthew Wilcox Link: http://lkml.kernel.org/r/20200327224116.21030-1-gpiccoli@canonical.com Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f7835db7102e..82d91547d122 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -520,6 +520,12 @@ static inline u32 int_sqrt64(u64 x) } #endif +#ifdef CONFIG_SMP +extern unsigned int sysctl_oops_all_cpu_backtrace; +#else +#define sysctl_oops_all_cpu_backtrace 0 +#endif /* CONFIG_SMP */ + extern void bust_spinlocks(int yes); extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ extern int panic_timeout; -- cgit v1.2.3 From dadbb612f6e50bbf9101c2f5d82690ce9ea4d66b Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Sun, 7 Jun 2020 21:40:55 -0700 Subject: mm/gup.c: convert to use get_user_{page|pages}_fast_only() API __get_user_pages_fast() renamed to get_user_pages_fast_only() to align with pin_user_pages_fast_only(). As part of this we will get rid of write parameter. Instead caller will pass FOLL_WRITE to get_user_pages_fast_only(). This will not change any existing functionality of the API. All the callers are changed to pass FOLL_WRITE. Also introduce get_user_page_fast_only(), and use it in a few places that hard-code nr_pages to 1. Updated the documentation of the API. Signed-off-by: Souptick Joarder Signed-off-by: Andrew Morton Reviewed-by: John Hubbard Reviewed-by: Paul Mackerras [arch/powerpc/kvm] Cc: Matthew Wilcox Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Mark Rutland Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paolo Bonzini Cc: Stephen Rothwell Cc: Mike Rapoport Cc: Aneesh Kumar K.V Cc: Michal Suchanek Link: http://lkml.kernel.org/r/1590396812-31277-1-git-send-email-jrdr.linux@gmail.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 86adc71a972f..22010c4175f2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1824,10 +1824,16 @@ extern int mprotect_fixup(struct vm_area_struct *vma, /* * doesn't attempt to fault and will return short. */ -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages); +int get_user_pages_fast_only(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); int pin_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); + +static inline bool get_user_page_fast_only(unsigned long addr, + unsigned int gup_flags, struct page **pagep) +{ + return get_user_pages_fast_only(addr, 1, gup_flags, pagep) == 1; +} /* * per-process(per-mm_struct) statistics. */ -- cgit v1.2.3 From 420c2091b65a95b1daea4c36d27df4ac5f38033d Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Sun, 7 Jun 2020 21:41:02 -0700 Subject: mm/gup: introduce pin_user_pages_locked() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "mm/gup: introduce pin_user_pages_locked(), use it in frame_vector.c", v2. This adds yet one more pin_user_pages*() variant, and uses that to convert mm/frame_vector.c. With this, along with maybe 20 or 30 other recent patches in various trees, we are close to having the relevant gup call sites converted--with the notable exception of the bio/block layer. This patch (of 2): Introduce pin_user_pages_locked(), which is nearly identical to get_user_pages_locked() except that it sets FOLL_PIN and rejects FOLL_GET. As with other pairs of get_user_pages*() and pin_user_pages() API calls, it's prudent to assert that FOLL_PIN is *not* set in the get_user_pages*() call, so add that as part of this. [jhubbard@nvidia.com: v2] Link: http://lkml.kernel.org/r/20200531234131.770697-2-jhubbard@nvidia.com Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Acked-by: Pankaj Gupta Cc: Daniel Vetter Cc: Jérôme Glisse Cc: Vlastimil Babka Cc: Jan Kara Cc: Dave Chinner Cc: Souptick Joarder Link: http://lkml.kernel.org/r/20200531234131.770697-1-jhubbard@nvidia.com Link: http://lkml.kernel.org/r/20200527223243.884385-1-jhubbard@nvidia.com Link: http://lkml.kernel.org/r/20200527223243.884385-2-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 22010c4175f2..9d6042178ca7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1706,6 +1706,8 @@ long pin_user_pages(unsigned long start, unsigned long nr_pages, struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); +long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, -- cgit v1.2.3 From 2062a4e8ae9f486847652927aaf88e21ab8d195d Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 8 Jun 2020 21:29:56 -0700 Subject: kallsyms/printk: add loglvl to print_ip_sym() Patch series "Add log level to show_stack()", v3. Add log level argument to show_stack(). Done in three stages: 1. Introducing show_stack_loglvl() for every architecture 2. Migrating old users with an explicit log level 3. Renaming show_stack_loglvl() into show_stack() Justification: - It's a design mistake to move a business-logic decision into platform realization detail. - I have currently two patches sets that would benefit from this work: Removing console_loglevel jumps in sysrq driver [1] Hung task warning before panic [2] - suggested by Tetsuo (but he probably didn't realise what it would involve). - While doing (1), (2) the backtraces were adjusted to headers and other messages for each situation - so there won't be a situation when the backtrace is printed, but the headers are missing because they have lesser log level (or the reverse). - As the result in (2) plays with console_loglevel for kdb are removed. The least important for upstream, but maybe still worth to note that every company I've worked in so far had an off-list patch to print backtrace with the needed log level (but only for the architecture they cared about). If you have other ideas how you will benefit from show_stack() with a log level - please, reply to this cover letter. See also discussion on v1: https://lore.kernel.org/linux-riscv/20191106083538.z5nlpuf64cigxigh@pathway.suse.cz/ This patch (of 50): print_ip_sym() needs to have a log level parameter to comply with other parts being printed. Otherwise, half of the expected backtrace would be printed and other may be missing with some logging level. The following callee(s) are using now the adjusted log level: - microblaze/unwind: the same level as headers & userspace unwind. Note that pr_debug()'s there are for debugging the unwinder itself. - nds32/traps: symbol addresses are printed with the same log level as backtrace headers. - lockdep: ip for locking issues is printed with the same log level as other part of the warning. - sched: ip where preemption was disabled is printed as error like the rest part of the message. - ftrace: bug reports are now consistent in the log level being used. Signed-off-by: Dmitry Safonov Signed-off-by: Andrew Morton Acked-by: Steven Rostedt (VMware) Cc: Albert Ou Cc: Ben Segall Cc: Dietmar Eggemann Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: James Hogan Cc: Juri Lelli Cc: Mel Gorman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Thomas Gleixner Cc: Vincent Chen Cc: Vincent Guittot Cc: Will Deacon Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Dmitry Safonov Cc: Jiri Slaby Cc: Petr Mladek Cc: Sergey Senozhatsky Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Richard Henderson Cc: Vineet Gupta Cc: Russell King Cc: Catalin Marinas Cc: Aurelien Jacquiot Cc: Mark Salter Cc: Guo Ren Cc: Yoshinori Sato Cc: Brian Cain Cc: Fenghua Yu Cc: Tony Luck Cc: Geert Uytterhoeven Cc: Ley Foon Tan Cc: Jonas Bonn Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Benjamin Herrenschmidt Cc: Michael Ellerman Cc: Paul Mackerras Cc: Christian Borntraeger Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Rich Felker Cc: "David S. Miller" Cc: Anton Ivanov Cc: Jeff Dike Cc: Richard Weinberger Cc: Guan Xuetao Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Chris Zankel Cc: Max Filippov Cc: Len Brown Cc: Pavel Machek Cc: "Rafael J. Wysocki" Cc: "Rafael J. Wysocki" Cc: Daniel Thompson Cc: Douglas Anderson Cc: Jason Wessel Link: http://lkml.kernel.org/r/20200418201944.482088-2-dima@arista.com Signed-off-by: Linus Torvalds --- include/linux/kallsyms.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 657a83b943f0..98338dc6b5d2 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -165,9 +165,9 @@ static inline int kallsyms_show_value(void) #endif /*CONFIG_KALLSYMS*/ -static inline void print_ip_sym(unsigned long ip) +static inline void print_ip_sym(const char *loglvl, unsigned long ip) { - printk("[<%px>] %pS\n", (void *) ip, (void *) ip); + printk("%s[<%px>] %pS\n", loglvl, (void *) ip, (void *) ip); } #endif /*_LINUX_KALLSYMS_H*/ -- cgit v1.2.3 From ab34b46d1a74e98996e67a7da7e5d683ecfd9f57 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 8 Jun 2020 21:32:10 -0700 Subject: sysrq: use show_stack_loglvl() Show the stack trace on a CPU with the same log level as "CPU%d" header. Signed-off-by: Dmitry Safonov Signed-off-by: Andrew Morton Cc: Greg Kroah-Hartman Cc: Jiri Slaby Link: http://lkml.kernel.org/r/20200418201944.482088-45-dima@arista.com Signed-off-by: Linus Torvalds --- include/linux/sched/debug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h index 95fb9e025247..373e4e3faf2a 100644 --- a/include/linux/sched/debug.h +++ b/include/linux/sched/debug.h @@ -31,6 +31,8 @@ extern void show_regs(struct pt_regs *); * trace (or NULL if the entire call-chain of the task should be shown). */ extern void show_stack(struct task_struct *task, unsigned long *sp); +extern void show_stack_loglvl(struct task_struct *task, unsigned long *sp, + const char *loglvl); extern void sched_show_task(struct task_struct *p); -- cgit v1.2.3 From 9cb8f069deeed708bf19486d5893e297dc467ae0 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 8 Jun 2020 21:32:29 -0700 Subject: kernel: rename show_stack_loglvl() => show_stack() Now the last users of show_stack() got converted to use an explicit log level, show_stack_loglvl() can drop it's redundant suffix and become once again well known show_stack(). Signed-off-by: Dmitry Safonov Signed-off-by: Andrew Morton Link: http://lkml.kernel.org/r/20200418201944.482088-51-dima@arista.com Signed-off-by: Linus Torvalds --- include/linux/sched/debug.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h index 373e4e3faf2a..00c45a0e6abe 100644 --- a/include/linux/sched/debug.h +++ b/include/linux/sched/debug.h @@ -30,9 +30,8 @@ extern void show_regs(struct pt_regs *); * task), SP is the stack pointer of the first frame that should be shown in the back * trace (or NULL if the entire call-chain of the task should be shown). */ -extern void show_stack(struct task_struct *task, unsigned long *sp); -extern void show_stack_loglvl(struct task_struct *task, unsigned long *sp, - const char *loglvl); +extern void show_stack(struct task_struct *task, unsigned long *sp, + const char *loglvl); extern void sched_show_task(struct task_struct *p); -- cgit v1.2.3 From e31cf2f4ca422ac9b14ecc4a1295b8977a20f812 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 8 Jun 2020 21:32:33 -0700 Subject: mm: don't include asm/pgtable.h if linux/mm.h is already included Patch series "mm: consolidate definitions of page table accessors", v2. The low level page table accessors (pXY_index(), pXY_offset()) are duplicated across all architectures and sometimes more than once. For instance, we have 31 definition of pgd_offset() for 25 supported architectures. Most of these definitions are actually identical and typically it boils down to, e.g. static inline unsigned long pmd_index(unsigned long address) { return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); } static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address); } These definitions can be shared among 90% of the arches provided XYZ_SHIFT, PTRS_PER_XYZ and xyz_page_vaddr() are defined. For architectures that really need a custom version there is always possibility to override the generic version with the usual ifdefs magic. These patches introduce include/linux/pgtable.h that replaces include/asm-generic/pgtable.h and add the definitions of the page table accessors to the new header. This patch (of 12): The linux/mm.h header includes to allow inlining of the functions involving page table manipulations, e.g. pte_alloc() and pmd_alloc(). So, there is no point to explicitly include in the files that include . The include statements in such cases are remove with a simple loop: for f in $(git grep -l "include ") ; do sed -i -e '/include / d' $f done Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brian Cain Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ley Foon Tan Cc: Mark Salter Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Mike Rapoport Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Tony Luck Cc: Vincent Chen Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200514170327.31389-1-rppt@kernel.org Link: http://lkml.kernel.org/r/20200514170327.31389-2-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/dax.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index d7af5d243f24..6904d4e0b2e0 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -5,7 +5,6 @@ #include #include #include -#include /* Flag for synchronous flush */ #define DAXDEV_F_SYNC (1UL << 0) -- cgit v1.2.3 From ca5999fde0a1761665a38e4c9a72dbcd7d190a81 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 8 Jun 2020 21:32:38 -0700 Subject: mm: introduce include/linux/pgtable.h The include/linux/pgtable.h is going to be the home of generic page table manipulation functions. Start with moving asm-generic/pgtable.h to include/linux/pgtable.h and make the latter include asm/pgtable.h. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brian Cain Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ley Foon Tan Cc: Mark Salter Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Tony Luck Cc: Vincent Chen Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200514170327.31389-3-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 2 +- include/linux/dma-noncoherent.h | 2 +- include/linux/hmm.h | 2 +- include/linux/hugetlb.h | 2 +- include/linux/io-mapping.h | 2 +- include/linux/kasan.h | 2 +- include/linux/mm.h | 2 +- include/linux/pgtable.h | 1323 +++++++++++++++++++++++++++++++++++++++ 8 files changed, 1330 insertions(+), 7 deletions(-) create mode 100644 include/linux/pgtable.h (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index bc156285d097..be79a45d7aa3 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -7,7 +7,7 @@ #include #include -#include /* for pgprot_t */ +#include /* for pgprot_t */ #ifdef CONFIG_CRASH_DUMP #define ELFCORE_ADDR_MAX (-1ULL) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index b59f1b6be3e9..ca09a4e07d2d 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -3,7 +3,7 @@ #define _LINUX_DMA_NONCOHERENT_H 1 #include -#include +#include #ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H #include diff --git a/include/linux/hmm.h b/include/linux/hmm.h index e912b9dc4633..f4a09ed223ac 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -10,7 +10,7 @@ #define LINUX_HMM_H #include -#include +#include #include #include diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0cced410e0bd..50650d0d01b9 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -9,7 +9,7 @@ #include #include #include -#include +#include struct ctl_table; struct user_struct; diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index b336622612f3..94e24e58966d 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -99,7 +99,7 @@ io_mapping_unmap(void __iomem *vaddr) #else #include -#include +#include /* Create the io_mapping object*/ static inline struct io_mapping * diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 31314ca7c635..17d8915eaebb 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -12,7 +12,7 @@ struct task_struct; #ifdef CONFIG_KASAN #include -#include +#include extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE]; diff --git a/include/linux/mm.h b/include/linux/mm.h index 9d6042178ca7..af0a09b89837 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -92,7 +92,7 @@ extern int mmap_rnd_compat_bits __read_mostly; #endif #include -#include +#include #include /* diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h new file mode 100644 index 000000000000..6e274da637fd --- /dev/null +++ b/include/linux/pgtable.h @@ -0,0 +1,1323 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PGTABLE_H +#define _LINUX_PGTABLE_H + +#include +#include + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_MMU + +#include +#include +#include +#include + +#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ + defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS +#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED +#endif + +/* + * On almost all architectures and configurations, 0 can be used as the + * upper ceiling to free_pgtables(): on many architectures it has the same + * effect as using TASK_SIZE. However, there is one configuration which + * must impose a more careful limit, to avoid freeing kernel pgtables. + */ +#ifndef USER_PGTABLES_CEILING +#define USER_PGTABLES_CEILING 0UL +#endif + +#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +extern int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty); +#endif + +#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty); +extern int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty); +#else +static inline int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty) +{ + BUILD_BUG(); + return 0; +} +static inline int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty) +{ + BUILD_BUG(); + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep) +{ + pte_t pte = *ptep; + int r = 1; + if (!pte_young(pte)) + r = 0; + else + set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte)); + return r; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + int r = 1; + if (!pmd_young(pmd)) + r = 0; + else + set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd)); + return r; +} +#else +static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + BUILD_BUG(); + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep); +#endif + +#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#else +/* + * Despite relevant to THP only, this API is called from generic rmap code + * under PageTransHuge(), hence needs a dummy implementation for !THP + */ +static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + BUILD_BUG(); + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, + unsigned long address, + pte_t *ptep) +{ + pte_t pte = *ptep; + pte_clear(mm, address, ptep); + return pte; +} +#endif + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + pmd_clear(pmdp); + return pmd; +} +#endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */ +#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR +static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long address, + pud_t *pudp) +{ + pud_t pud = *pudp; + + pud_clear(pudp); + return pud; +} +#endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL +static inline pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + int full) +{ + return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); +} +#endif + +#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL +static inline pud_t pudp_huge_get_and_clear_full(struct mm_struct *mm, + unsigned long address, pud_t *pudp, + int full) +{ + return pudp_huge_get_and_clear(mm, address, pudp); +} +#endif +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL +static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, + unsigned long address, pte_t *ptep, + int full) +{ + pte_t pte; + pte = ptep_get_and_clear(mm, address, ptep); + return pte; +} +#endif + + +/* + * If two threads concurrently fault at the same page, the thread that + * won the race updates the PTE and its local TLB/Cache. The other thread + * gives up, simply does nothing, and continues; on architectures where + * software can update TLB, local TLB can be updated here to avoid next page + * fault. This function updates TLB only, do nothing with cache or others. + * It is the difference with function update_mmu_cache. + */ +#ifndef __HAVE_ARCH_UPDATE_MMU_TLB +static inline void update_mmu_tlb(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ +} +#define __HAVE_ARCH_UPDATE_MMU_TLB +#endif + +/* + * Some architectures may be able to avoid expensive synchronization + * primitives when modifications are made to PTE's which are already + * not present, or in the process of an address space destruction. + */ +#ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL +static inline void pte_clear_not_present_full(struct mm_struct *mm, + unsigned long address, + pte_t *ptep, + int full) +{ + pte_clear(mm, address, ptep); +} +#endif + +#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH +extern pte_t ptep_clear_flush(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep); +#endif + +#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH +extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp); +extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, + unsigned long address, + pud_t *pudp); +#endif + +#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT +struct mm_struct; +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) +{ + pte_t old_pte = *ptep; + set_pte_at(mm, address, ptep, pte_wrprotect(old_pte)); +} +#endif + +/* + * On some architectures hardware does not set page access bit when accessing + * memory page, it is responsibilty of software setting this bit. It brings + * out extra page fault penalty to track page access bit. For optimization page + * access bit can be set during all page fault flow on these arches. + * To be differentiate with macro pte_mkyoung, this macro is used on platforms + * where software maintains page access bit. + */ +#ifndef pte_sw_mkyoung +static inline pte_t pte_sw_mkyoung(pte_t pte) +{ + return pte; +} +#define pte_sw_mkyoung pte_sw_mkyoung +#endif + +#ifndef pte_savedwrite +#define pte_savedwrite pte_write +#endif + +#ifndef pte_mk_savedwrite +#define pte_mk_savedwrite pte_mkwrite +#endif + +#ifndef pte_clear_savedwrite +#define pte_clear_savedwrite pte_wrprotect +#endif + +#ifndef pmd_savedwrite +#define pmd_savedwrite pmd_write +#endif + +#ifndef pmd_mk_savedwrite +#define pmd_mk_savedwrite pmd_mkwrite +#endif + +#ifndef pmd_clear_savedwrite +#define pmd_clear_savedwrite pmd_wrprotect +#endif + +#ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + pmd_t old_pmd = *pmdp; + set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd)); +} +#else +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + BUILD_BUG(); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif +#ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static inline void pudp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pud_t *pudp) +{ + pud_t old_pud = *pudp; + + set_pud_at(mm, address, pudp, pud_wrprotect(old_pud)); +} +#else +static inline void pudp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pud_t *pudp) +{ + BUILD_BUG(); +} +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +#endif + +#ifndef pmdp_collapse_flush +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#else +static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + BUILD_BUG(); + return *pmdp; +} +#define pmdp_collapse_flush pmdp_collapse_flush +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT +extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); +#endif + +#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW +extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); +#endif + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * This is an implementation of pmdp_establish() that is only suitable for an + * architecture that doesn't have hardware dirty/accessed bits. In this case we + * can't race with CPU which sets these bits and non-atomic aproach is fine. + */ +static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, pmd_t pmd) +{ + pmd_t old_pmd = *pmdp; + set_pmd_at(vma->vm_mm, address, pmdp, pmd); + return old_pmd; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_INVALIDATE +extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp); +#endif + +#ifndef __HAVE_ARCH_PTE_SAME +static inline int pte_same(pte_t pte_a, pte_t pte_b) +{ + return pte_val(pte_a) == pte_val(pte_b); +} +#endif + +#ifndef __HAVE_ARCH_PTE_UNUSED +/* + * Some architectures provide facilities to virtualization guests + * so that they can flag allocated pages as unused. This allows the + * host to transparently reclaim unused pages. This function returns + * whether the pte's page is unused. + */ +static inline int pte_unused(pte_t pte) +{ + return 0; +} +#endif + +#ifndef pte_access_permitted +#define pte_access_permitted(pte, write) \ + (pte_present(pte) && (!(write) || pte_write(pte))) +#endif + +#ifndef pmd_access_permitted +#define pmd_access_permitted(pmd, write) \ + (pmd_present(pmd) && (!(write) || pmd_write(pmd))) +#endif + +#ifndef pud_access_permitted +#define pud_access_permitted(pud, write) \ + (pud_present(pud) && (!(write) || pud_write(pud))) +#endif + +#ifndef p4d_access_permitted +#define p4d_access_permitted(p4d, write) \ + (p4d_present(p4d) && (!(write) || p4d_write(p4d))) +#endif + +#ifndef pgd_access_permitted +#define pgd_access_permitted(pgd, write) \ + (pgd_present(pgd) && (!(write) || pgd_write(pgd))) +#endif + +#ifndef __HAVE_ARCH_PMD_SAME +static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + return pmd_val(pmd_a) == pmd_val(pmd_b); +} + +static inline int pud_same(pud_t pud_a, pud_t pud_b) +{ + return pud_val(pud_a) == pud_val(pud_b); +} +#endif + +#ifndef __HAVE_ARCH_P4D_SAME +static inline int p4d_same(p4d_t p4d_a, p4d_t p4d_b) +{ + return p4d_val(p4d_a) == p4d_val(p4d_b); +} +#endif + +#ifndef __HAVE_ARCH_PGD_SAME +static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) +{ + return pgd_val(pgd_a) == pgd_val(pgd_b); +} +#endif + +/* + * Use set_p*_safe(), and elide TLB flushing, when confident that *no* + * TLB flush will be required as a result of the "set". For example, use + * in scenarios where it is known ahead of time that the routine is + * setting non-present entries, or re-setting an existing entry to the + * same value. Otherwise, use the typical "set" helpers and flush the + * TLB. + */ +#define set_pte_safe(ptep, pte) \ +({ \ + WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ + set_pte(ptep, pte); \ +}) + +#define set_pmd_safe(pmdp, pmd) \ +({ \ + WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ + set_pmd(pmdp, pmd); \ +}) + +#define set_pud_safe(pudp, pud) \ +({ \ + WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ + set_pud(pudp, pud); \ +}) + +#define set_p4d_safe(p4dp, p4d) \ +({ \ + WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ + set_p4d(p4dp, p4d); \ +}) + +#define set_pgd_safe(pgdp, pgd) \ +({ \ + WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ + set_pgd(pgdp, pgd); \ +}) + +#ifndef __HAVE_ARCH_DO_SWAP_PAGE +/* + * Some architectures support metadata associated with a page. When a + * page is being swapped out, this metadata must be saved so it can be + * restored when the page is swapped back in. SPARC M7 and newer + * processors support an ADI (Application Data Integrity) tag for the + * page as metadata for the page. arch_do_swap_page() can restore this + * metadata when a page is swapped back in. + */ +static inline void arch_do_swap_page(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + pte_t pte, pte_t oldpte) +{ + +} +#endif + +#ifndef __HAVE_ARCH_UNMAP_ONE +/* + * Some architectures support metadata associated with a page. When a + * page is being swapped out, this metadata must be saved so it can be + * restored when the page is swapped back in. SPARC M7 and newer + * processors support an ADI (Application Data Integrity) tag for the + * page as metadata for the page. arch_unmap_one() can save this + * metadata on a swap-out of a page. + */ +static inline int arch_unmap_one(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + pte_t orig_pte) +{ + return 0; +} +#endif + +#ifndef __HAVE_ARCH_PGD_OFFSET_GATE +#define pgd_offset_gate(mm, addr) pgd_offset(mm, addr) +#endif + +#ifndef __HAVE_ARCH_MOVE_PTE +#define move_pte(pte, prot, old_addr, new_addr) (pte) +#endif + +#ifndef pte_accessible +# define pte_accessible(mm, pte) ((void)(pte), 1) +#endif + +#ifndef flush_tlb_fix_spurious_fault +#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) +#endif + +#ifndef pgprot_nx +#define pgprot_nx(prot) (prot) +#endif + +#ifndef pgprot_noncached +#define pgprot_noncached(prot) (prot) +#endif + +#ifndef pgprot_writecombine +#define pgprot_writecombine pgprot_noncached +#endif + +#ifndef pgprot_writethrough +#define pgprot_writethrough pgprot_noncached +#endif + +#ifndef pgprot_device +#define pgprot_device pgprot_noncached +#endif + +#ifndef pgprot_modify +#define pgprot_modify pgprot_modify +static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) +{ + if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot))) + newprot = pgprot_noncached(newprot); + if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot))) + newprot = pgprot_writecombine(newprot); + if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot))) + newprot = pgprot_device(newprot); + return newprot; +} +#endif + +/* + * When walking page tables, get the address of the next boundary, + * or the end address of the range if that comes earlier. Although no + * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout. + */ + +#define pgd_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) + +#ifndef p4d_addr_end +#define p4d_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) +#endif + +#ifndef pud_addr_end +#define pud_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) +#endif + +#ifndef pmd_addr_end +#define pmd_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) +#endif + +/* + * When walking page tables, we usually want to skip any p?d_none entries; + * and any p?d_bad entries - reporting the error before resetting to none. + * Do the tests inline, but report and clear the bad entry in mm/memory.c. + */ +void pgd_clear_bad(pgd_t *); + +#ifndef __PAGETABLE_P4D_FOLDED +void p4d_clear_bad(p4d_t *); +#else +#define p4d_clear_bad(p4d) do { } while (0) +#endif + +#ifndef __PAGETABLE_PUD_FOLDED +void pud_clear_bad(pud_t *); +#else +#define pud_clear_bad(p4d) do { } while (0) +#endif + +void pmd_clear_bad(pmd_t *); + +static inline int pgd_none_or_clear_bad(pgd_t *pgd) +{ + if (pgd_none(*pgd)) + return 1; + if (unlikely(pgd_bad(*pgd))) { + pgd_clear_bad(pgd); + return 1; + } + return 0; +} + +static inline int p4d_none_or_clear_bad(p4d_t *p4d) +{ + if (p4d_none(*p4d)) + return 1; + if (unlikely(p4d_bad(*p4d))) { + p4d_clear_bad(p4d); + return 1; + } + return 0; +} + +static inline int pud_none_or_clear_bad(pud_t *pud) +{ + if (pud_none(*pud)) + return 1; + if (unlikely(pud_bad(*pud))) { + pud_clear_bad(pud); + return 1; + } + return 0; +} + +static inline int pmd_none_or_clear_bad(pmd_t *pmd) +{ + if (pmd_none(*pmd)) + return 1; + if (unlikely(pmd_bad(*pmd))) { + pmd_clear_bad(pmd); + return 1; + } + return 0; +} + +static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep) +{ + /* + * Get the current pte state, but zero it out to make it + * non-present, preventing the hardware from asynchronously + * updating it. + */ + return ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep, pte_t pte) +{ + /* + * The pte is non-present, so there's no hardware state to + * preserve. + */ + set_pte_at(vma->vm_mm, addr, ptep, pte); +} + +#ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION +/* + * Start a pte protection read-modify-write transaction, which + * protects against asynchronous hardware modifications to the pte. + * The intention is not to prevent the hardware from making pte + * updates, but to prevent any updates it may make from being lost. + * + * This does not protect against other software modifications of the + * pte; the appropriate pte lock must be held over the transation. + * + * Note that this interface is intended to be batchable, meaning that + * ptep_modify_prot_commit may not actually update the pte, but merely + * queue the update to be done at some later time. The update must be + * actually committed before the pte lock is released, however. + */ +static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep) +{ + return __ptep_modify_prot_start(vma, addr, ptep); +} + +/* + * Commit an update to a pte, leaving any hardware-controlled bits in + * the PTE unmodified. + */ +static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep, pte_t old_pte, pte_t pte) +{ + __ptep_modify_prot_commit(vma, addr, ptep, pte); +} +#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */ +#endif /* CONFIG_MMU */ + +/* + * No-op macros that just return the current protection value. Defined here + * because these macros can be used used even if CONFIG_MMU is not defined. + */ +#ifndef pgprot_encrypted +#define pgprot_encrypted(prot) (prot) +#endif + +#ifndef pgprot_decrypted +#define pgprot_decrypted(prot) (prot) +#endif + +/* + * A facility to provide lazy MMU batching. This allows PTE updates and + * page invalidations to be delayed until a call to leave lazy MMU mode + * is issued. Some architectures may benefit from doing this, and it is + * beneficial for both shadow and direct mode hypervisors, which may batch + * the PTE updates which happen during this window. Note that using this + * interface requires that read hazards be removed from the code. A read + * hazard could result in the direct mode hypervisor case, since the actual + * write to the page tables may not yet have taken place, so reads though + * a raw PTE pointer after it has been modified are not guaranteed to be + * up to date. This mode can only be entered and left under the protection of + * the page table locks for all page tables which may be modified. In the UP + * case, this is required so that preemption is disabled, and in the SMP case, + * it must synchronize the delayed page table writes properly on other CPUs. + */ +#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE +#define arch_enter_lazy_mmu_mode() do {} while (0) +#define arch_leave_lazy_mmu_mode() do {} while (0) +#define arch_flush_lazy_mmu_mode() do {} while (0) +#endif + +/* + * A facility to provide batching of the reload of page tables and + * other process state with the actual context switch code for + * paravirtualized guests. By convention, only one of the batched + * update (lazy) modes (CPU, MMU) should be active at any given time, + * entry should never be nested, and entry and exits should always be + * paired. This is for sanity of maintaining and reasoning about the + * kernel code. In this case, the exit (end of the context switch) is + * in architecture-specific code, and so doesn't need a generic + * definition. + */ +#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH +#define arch_start_context_switch(prev) do {} while (0) +#endif + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +#ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION +static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) +{ + return pmd; +} + +static inline int pmd_swp_soft_dirty(pmd_t pmd) +{ + return 0; +} + +static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) +{ + return pmd; +} +#endif +#else /* !CONFIG_HAVE_ARCH_SOFT_DIRTY */ +static inline int pte_soft_dirty(pte_t pte) +{ + return 0; +} + +static inline int pmd_soft_dirty(pmd_t pmd) +{ + return 0; +} + +static inline pte_t pte_mksoft_dirty(pte_t pte) +{ + return pte; +} + +static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) +{ + return pmd; +} + +static inline pte_t pte_clear_soft_dirty(pte_t pte) +{ + return pte; +} + +static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) +{ + return pmd; +} + +static inline pte_t pte_swp_mksoft_dirty(pte_t pte) +{ + return pte; +} + +static inline int pte_swp_soft_dirty(pte_t pte) +{ + return 0; +} + +static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) +{ + return pte; +} + +static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) +{ + return pmd; +} + +static inline int pmd_swp_soft_dirty(pmd_t pmd) +{ + return 0; +} + +static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) +{ + return pmd; +} +#endif + +#ifndef __HAVE_PFNMAP_TRACKING +/* + * Interfaces that can be used by architecture code to keep track of + * memory type of pfn mappings specified by the remap_pfn_range, + * vmf_insert_pfn. + */ + +/* + * track_pfn_remap is called when a _new_ pfn mapping is being established + * by remap_pfn_range() for physical range indicated by pfn and size. + */ +static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, + unsigned long pfn, unsigned long addr, + unsigned long size) +{ + return 0; +} + +/* + * track_pfn_insert is called when a _new_ single pfn is established + * by vmf_insert_pfn(). + */ +static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, + pfn_t pfn) +{ +} + +/* + * track_pfn_copy is called when vma that is covering the pfnmap gets + * copied through copy_page_range(). + */ +static inline int track_pfn_copy(struct vm_area_struct *vma) +{ + return 0; +} + +/* + * untrack_pfn is called while unmapping a pfnmap for a region. + * untrack can be called for a specific region indicated by pfn and size or + * can be for the entire vma (in which case pfn, size are zero). + */ +static inline void untrack_pfn(struct vm_area_struct *vma, + unsigned long pfn, unsigned long size) +{ +} + +/* + * untrack_pfn_moved is called while mremapping a pfnmap for a new region. + */ +static inline void untrack_pfn_moved(struct vm_area_struct *vma) +{ +} +#else +extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, + unsigned long pfn, unsigned long addr, + unsigned long size); +extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, + pfn_t pfn); +extern int track_pfn_copy(struct vm_area_struct *vma); +extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, + unsigned long size); +extern void untrack_pfn_moved(struct vm_area_struct *vma); +#endif + +#ifdef __HAVE_COLOR_ZERO_PAGE +static inline int is_zero_pfn(unsigned long pfn) +{ + extern unsigned long zero_pfn; + unsigned long offset_from_zero_pfn = pfn - zero_pfn; + return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT); +} + +#define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) + +#else +static inline int is_zero_pfn(unsigned long pfn) +{ + extern unsigned long zero_pfn; + return pfn == zero_pfn; +} + +static inline unsigned long my_zero_pfn(unsigned long addr) +{ + extern unsigned long zero_pfn; + return zero_pfn; +} +#endif + +#ifdef CONFIG_MMU + +#ifndef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmd_trans_huge(pmd_t pmd) +{ + return 0; +} +#ifndef pmd_write +static inline int pmd_write(pmd_t pmd) +{ + BUG(); + return 0; +} +#endif /* pmd_write */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#ifndef pud_write +static inline int pud_write(pud_t pud) +{ + BUG(); + return 0; +} +#endif /* pud_write */ + +#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) +static inline int pmd_devmap(pmd_t pmd) +{ + return 0; +} +static inline int pud_devmap(pud_t pud) +{ + return 0; +} +static inline int pgd_devmap(pgd_t pgd) +{ + return 0; +} +#endif + +#if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \ + (defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)) +static inline int pud_trans_huge(pud_t pud) +{ + return 0; +} +#endif + +/* See pmd_none_or_trans_huge_or_clear_bad for discussion. */ +static inline int pud_none_or_trans_huge_or_dev_or_clear_bad(pud_t *pud) +{ + pud_t pudval = READ_ONCE(*pud); + + if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval)) + return 1; + if (unlikely(pud_bad(pudval))) { + pud_clear_bad(pud); + return 1; + } + return 0; +} + +/* See pmd_trans_unstable for discussion. */ +static inline int pud_trans_unstable(pud_t *pud) +{ +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) + return pud_none_or_trans_huge_or_dev_or_clear_bad(pud); +#else + return 0; +#endif +} + +#ifndef pmd_read_atomic +static inline pmd_t pmd_read_atomic(pmd_t *pmdp) +{ + /* + * Depend on compiler for an atomic pmd read. NOTE: this is + * only going to work, if the pmdval_t isn't larger than + * an unsigned long. + */ + return *pmdp; +} +#endif + +#ifndef arch_needs_pgtable_deposit +#define arch_needs_pgtable_deposit() (false) +#endif +/* + * This function is meant to be used by sites walking pagetables with + * the mmap_sem hold in read mode to protect against MADV_DONTNEED and + * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd + * into a null pmd and the transhuge page fault can convert a null pmd + * into an hugepmd or into a regular pmd (if the hugepage allocation + * fails). While holding the mmap_sem in read mode the pmd becomes + * stable and stops changing under us only if it's not null and not a + * transhuge pmd. When those races occurs and this function makes a + * difference vs the standard pmd_none_or_clear_bad, the result is + * undefined so behaving like if the pmd was none is safe (because it + * can return none anyway). The compiler level barrier() is critically + * important to compute the two checks atomically on the same pmdval. + * + * For 32bit kernels with a 64bit large pmd_t this automatically takes + * care of reading the pmd atomically to avoid SMP race conditions + * against pmd_populate() when the mmap_sem is hold for reading by the + * caller (a special atomic read not done by "gcc" as in the generic + * version above, is also needed when THP is disabled because the page + * fault can populate the pmd from under us). + */ +static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd) +{ + pmd_t pmdval = pmd_read_atomic(pmd); + /* + * The barrier will stabilize the pmdval in a register or on + * the stack so that it will stop changing under the code. + * + * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE, + * pmd_read_atomic is allowed to return a not atomic pmdval + * (for example pointing to an hugepage that has never been + * mapped in the pmd). The below checks will only care about + * the low part of the pmd with 32bit PAE x86 anyway, with the + * exception of pmd_none(). So the important thing is that if + * the low part of the pmd is found null, the high part will + * be also null or the pmd_none() check below would be + * confused. + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + barrier(); +#endif + /* + * !pmd_present() checks for pmd migration entries + * + * The complete check uses is_pmd_migration_entry() in linux/swapops.h + * But using that requires moving current function and pmd_trans_unstable() + * to linux/swapops.h to resovle dependency, which is too much code move. + * + * !pmd_present() is equivalent to is_pmd_migration_entry() currently, + * because !pmd_present() pages can only be under migration not swapped + * out. + * + * pmd_none() is preseved for future condition checks on pmd migration + * entries and not confusing with this function name, although it is + * redundant with !pmd_present(). + */ + if (pmd_none(pmdval) || pmd_trans_huge(pmdval) || + (IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION) && !pmd_present(pmdval))) + return 1; + if (unlikely(pmd_bad(pmdval))) { + pmd_clear_bad(pmd); + return 1; + } + return 0; +} + +/* + * This is a noop if Transparent Hugepage Support is not built into + * the kernel. Otherwise it is equivalent to + * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in + * places that already verified the pmd is not none and they want to + * walk ptes while holding the mmap sem in read mode (write mode don't + * need this). If THP is not enabled, the pmd can't go away under the + * code even if MADV_DONTNEED runs, but if THP is enabled we need to + * run a pmd_trans_unstable before walking the ptes after + * split_huge_pmd returns (because it may have run when the pmd become + * null, but then a page fault can map in a THP and not a regular page). + */ +static inline int pmd_trans_unstable(pmd_t *pmd) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + return pmd_none_or_trans_huge_or_clear_bad(pmd); +#else + return 0; +#endif +} + +#ifndef CONFIG_NUMA_BALANCING +/* + * Technically a PTE can be PROTNONE even when not doing NUMA balancing but + * the only case the kernel cares is for NUMA balancing and is only ever set + * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked + * _PAGE_PROTNONE so by by default, implement the helper as "always no". It + * is the responsibility of the caller to distinguish between PROT_NONE + * protections and NUMA hinting fault protections. + */ +static inline int pte_protnone(pte_t pte) +{ + return 0; +} + +static inline int pmd_protnone(pmd_t pmd) +{ + return 0; +} +#endif /* CONFIG_NUMA_BALANCING */ + +#endif /* CONFIG_MMU */ + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP + +#ifndef __PAGETABLE_P4D_FOLDED +int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); +int p4d_clear_huge(p4d_t *p4d); +#else +static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int p4d_clear_huge(p4d_t *p4d) +{ + return 0; +} +#endif /* !__PAGETABLE_P4D_FOLDED */ + +int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); +int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); +int pud_clear_huge(pud_t *pud); +int pmd_clear_huge(pmd_t *pmd); +int p4d_free_pud_page(p4d_t *p4d, unsigned long addr); +int pud_free_pmd_page(pud_t *pud, unsigned long addr); +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); +#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ +static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int p4d_clear_huge(p4d_t *p4d) +{ + return 0; +} +static inline int pud_clear_huge(pud_t *pud) +{ + return 0; +} +static inline int pmd_clear_huge(pmd_t *pmd) +{ + return 0; +} +static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) +{ + return 0; +} +static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr) +{ + return 0; +} +static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) +{ + return 0; +} +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ + +#ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * ARCHes with special requirements for evicting THP backing TLB entries can + * implement this. Otherwise also, it can help optimize normal TLB flush in + * THP regime. stock flush_tlb_range() typically has optimization to nuke the + * entire TLB TLB if flush span is greater than a threshold, which will + * likely be true for a single huge page. Thus a single thp flush will + * invalidate the entire TLB which is not desitable. + * e.g. see arch/arc: flush_pmd_tlb_range + */ +#define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) +#define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) +#else +#define flush_pmd_tlb_range(vma, addr, end) BUILD_BUG() +#define flush_pud_tlb_range(vma, addr, end) BUILD_BUG() +#endif +#endif + +struct file; +int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t *vma_prot); + +#ifndef CONFIG_X86_ESPFIX64 +static inline void init_espfix_bsp(void) { } +#endif + +extern void __init pgtable_cache_init(void); + +#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED +static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) +{ + return true; +} + +static inline bool arch_has_pfn_modify_check(void) +{ + return false; +} +#endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */ + +/* + * Architecture PAGE_KERNEL_* fallbacks + * + * Some architectures don't define certain PAGE_KERNEL_* flags. This is either + * because they really don't support them, or the port needs to be updated to + * reflect the required functionality. Below are a set of relatively safe + * fallbacks, as best effort, which we can count on in lieu of the architectures + * not defining them on their own yet. + */ + +#ifndef PAGE_KERNEL_RO +# define PAGE_KERNEL_RO PAGE_KERNEL +#endif + +#ifndef PAGE_KERNEL_EXEC +# define PAGE_KERNEL_EXEC PAGE_KERNEL +#endif + +/* + * Page Table Modification bits for pgtbl_mod_mask. + * + * These are used by the p?d_alloc_track*() set of functions an in the generic + * vmalloc/ioremap code to track at which page-table levels entries have been + * modified. Based on that the code can better decide when vmalloc and ioremap + * mapping changes need to be synchronized to other page-tables in the system. + */ +#define __PGTBL_PGD_MODIFIED 0 +#define __PGTBL_P4D_MODIFIED 1 +#define __PGTBL_PUD_MODIFIED 2 +#define __PGTBL_PMD_MODIFIED 3 +#define __PGTBL_PTE_MODIFIED 4 + +#define PGTBL_PGD_MODIFIED BIT(__PGTBL_PGD_MODIFIED) +#define PGTBL_P4D_MODIFIED BIT(__PGTBL_P4D_MODIFIED) +#define PGTBL_PUD_MODIFIED BIT(__PGTBL_PUD_MODIFIED) +#define PGTBL_PMD_MODIFIED BIT(__PGTBL_PMD_MODIFIED) +#define PGTBL_PTE_MODIFIED BIT(__PGTBL_PTE_MODIFIED) + +/* Page-Table Modification Mask */ +typedef unsigned int pgtbl_mod_mask; + +#endif /* !__ASSEMBLY__ */ + +#ifndef io_remap_pfn_range +#define io_remap_pfn_range remap_pfn_range +#endif + +#ifndef has_transparent_hugepage +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define has_transparent_hugepage() 1 +#else +#define has_transparent_hugepage() 0 +#endif +#endif + +/* + * On some architectures it depends on the mm if the p4d/pud or pmd + * layer of the page table hierarchy is folded or not. + */ +#ifndef mm_p4d_folded +#define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED) +#endif + +#ifndef mm_pud_folded +#define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED) +#endif + +#ifndef mm_pmd_folded +#define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) +#endif + +/* + * p?d_leaf() - true if this entry is a final mapping to a physical address. + * This differs from p?d_huge() by the fact that they are always available (if + * the architecture supports large pages at the appropriate level) even + * if CONFIG_HUGETLB_PAGE is not defined. + * Only meaningful when called on a valid entry. + */ +#ifndef pgd_leaf +#define pgd_leaf(x) 0 +#endif +#ifndef p4d_leaf +#define p4d_leaf(x) 0 +#endif +#ifndef pud_leaf +#define pud_leaf(x) 0 +#endif +#ifndef pmd_leaf +#define pmd_leaf(x) 0 +#endif + +#endif /* _LINUX_PGTABLE_H */ -- cgit v1.2.3 From 65fddcfca8ad14778f71a57672fd01e8112d30fa Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 8 Jun 2020 21:32:42 -0700 Subject: mm: reorder includes after introduction of linux/pgtable.h The replacement of with made the include of the latter in the middle of asm includes. Fix this up with the aid of the below script and manual adjustments here and there. import sys import re if len(sys.argv) is not 3: print "USAGE: %s
" % (sys.argv[0]) sys.exit(1) hdr_to_move="#include " % sys.argv[2] moved = False in_hdrs = False with open(sys.argv[1], "r") as f: lines = f.readlines() for _line in lines: line = _line.rstrip(' ') if line == hdr_to_move: continue if line.startswith("#include Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brian Cain Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ley Foon Tan Cc: Mark Salter Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Tony Luck Cc: Vincent Chen Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200514170327.31389-4-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 1 + include/linux/io-mapping.h | 2 +- include/linux/kasan.h | 2 +- include/linux/mm.h | 2 +- 4 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index be79a45d7aa3..a5192b718dbe 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include /* for pgprot_t */ diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 94e24e58966d..0beaa3eba155 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -10,6 +10,7 @@ #include #include #include +#include #include /* @@ -99,7 +100,6 @@ io_mapping_unmap(void __iomem *vaddr) #else #include -#include /* Create the io_mapping object*/ static inline struct io_mapping * diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 17d8915eaebb..82522e996c76 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -11,8 +11,8 @@ struct task_struct; #ifdef CONFIG_KASAN -#include #include +#include extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE]; diff --git a/include/linux/mm.h b/include/linux/mm.h index af0a09b89837..1844c522d0de 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -28,6 +28,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -92,7 +93,6 @@ extern int mmap_rnd_compat_bits __read_mostly; #endif #include -#include #include /* -- cgit v1.2.3 From e05c7b1f2bc4b7b28199b9a7572f73436d97317e Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 8 Jun 2020 21:33:05 -0700 Subject: mm: pgtable: add shortcuts for accessing kernel PMD and PTE The powerpc 32-bit implementation of pgtable has nice shortcuts for accessing kernel PMD and PTE for a given virtual address. Make these helpers available for all architectures. [rppt@linux.ibm.com: microblaze: fix page table traversal in setup_rt_frame()] Link: http://lkml.kernel.org/r/20200518191511.GD1118872@kernel.org [akpm@linux-foundation.org: s/pmd_ptr_k/pmd_off_k/ in various powerpc places] Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brian Cain Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ley Foon Tan Cc: Mark Salter Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Tony Luck Cc: Vincent Chen Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200514170327.31389-9-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 6e274da637fd..ee85b222d098 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -28,6 +28,30 @@ #define USER_PGTABLES_CEILING 0UL #endif +/* + * In many cases it is known that a virtual address is mapped at PMD or PTE + * level, so instead of traversing all the page table levels, we can get a + * pointer to the PMD entry in user or kernel page table or translate a virtual + * address to the pointer in the PTE in the kernel page tables with simple + * helpers. + */ +static inline pmd_t *pmd_off(struct mm_struct *mm, unsigned long va) +{ + return pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, va), va), va), va); +} + +static inline pmd_t *pmd_off_k(unsigned long va) +{ + return pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va); +} + +static inline pte_t *virt_to_kpte(unsigned long vaddr) +{ + pmd_t *pmd = pmd_off_k(vaddr); + + return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr); +} + #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, -- cgit v1.2.3 From 974b9b2c68f3d35a65e80af9657fe378d2439b60 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 8 Jun 2020 21:33:10 -0700 Subject: mm: consolidate pte_index() and pte_offset_*() definitions All architectures define pte_index() as (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1) and all architectures define pte_offset_kernel() as an entry in the array of PTEs indexed by the pte_index(). For the most architectures the pte_offset_kernel() implementation relies on the availability of pmd_page_vaddr() that converts a PMD entry value to the virtual address of the page containing PTEs array. Let's move x86 definitions of the PTE accessors to the generic place in and then simply drop the respective definitions from the other architectures. The architectures that didn't provide pmd_page_vaddr() are updated to have that defined. The generic implementation of pte_offset_kernel() can be overridden by an architecture and alpha makes use of this because it has special ordering requirements for its version of pte_offset_kernel(). [rppt@linux.ibm.com: v2] Link: http://lkml.kernel.org/r/20200514170327.31389-11-rppt@kernel.org [rppt@linux.ibm.com: update] Link: http://lkml.kernel.org/r/20200514170327.31389-12-rppt@kernel.org [rppt@linux.ibm.com: update] Link: http://lkml.kernel.org/r/20200514170327.31389-13-rppt@kernel.org [akpm@linux-foundation.org: fix x86 warning] [sfr@canb.auug.org.au: fix powerpc build] Link: http://lkml.kernel.org/r/20200607153443.GB738695@linux.ibm.com Signed-off-by: Mike Rapoport Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brian Cain Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ley Foon Tan Cc: Mark Salter Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Tony Luck Cc: Vincent Chen Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200514170327.31389-10-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 91 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 91 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index ee85b222d098..90a5d0c78fca 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -28,6 +28,97 @@ #define USER_PGTABLES_CEILING 0UL #endif +/* + * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] + * + * The pXx_index() functions return the index of the entry in the page + * table page which would control the given virtual address + * + * As these functions may be used by the same code for different levels of + * the page table folding, they are always available, regardless of + * CONFIG_PGTABLE_LEVELS value. For the folded levels they simply return 0 + * because in such cases PTRS_PER_PxD equals 1. + */ + +static inline unsigned long pte_index(unsigned long address) +{ + return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); +} + +#ifndef pmd_index +static inline unsigned long pmd_index(unsigned long address) +{ + return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); +} +#define pmd_index pmd_index +#endif + +#ifndef pud_index +static inline unsigned long pud_index(unsigned long address) +{ + return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); +} +#define pud_index pud_index +#endif + +#ifndef pgd_index +/* Must be a compile-time constant, so implement it as a macro */ +#define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) +#endif + +#ifndef pte_offset_kernel +static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) +{ + return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address); +} +#define pte_offset_kernel pte_offset_kernel +#endif + +#if defined(CONFIG_HIGHPTE) +#define pte_offset_map(dir, address) \ + ((pte_t *)kmap_atomic(pmd_page(*(dir))) + \ + pte_index((address))) +#define pte_unmap(pte) kunmap_atomic((pte)) +#else +#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address)) +#define pte_unmap(pte) ((void)(pte)) /* NOP */ +#endif + +/* Find an entry in the second-level page table.. */ +#ifndef pmd_offset +static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) +{ + return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address); +} +#define pmd_offset pmd_offset +#endif + +#ifndef pud_offset +static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) +{ + return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address); +} +#define pud_offset pud_offset +#endif + +static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) +{ + return (pgd + pgd_index(address)); +}; + +/* + * a shortcut to get a pgd_t in a given mm + */ +#ifndef pgd_offset +#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address)) +#endif + +/* + * a shortcut which implies the use of the kernel's pgd, instead + * of a process's + */ +#define pgd_offset_k(address) pgd_offset(&init_mm, (address)) + /* * In many cases it is known that a virtual address is mapped at PMD or PTE * level, so instead of traversing all the page table levels, we can get a -- cgit v1.2.3 From 9740ca4e95b43b91a4a848694a20d01ba6818f7b Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:14 -0700 Subject: mmap locking API: initial implementation as rwsem wrappers This patch series adds a new mmap locking API replacing the existing mmap_sem lock and unlocks. Initially the API is just implemente in terms of inlined rwsem calls, so it doesn't provide any new functionality. There are two justifications for the new API: - At first, it provides an easy hooking point to instrument mmap_sem locking latencies independently of any other rwsems. - In the future, it may be a starting point for replacing the rwsem implementation with a different one, such as range locks. This is something that is being explored, even though there is no wide concensus about this possible direction yet. (see https://patchwork.kernel.org/cover/11401483/) This patch (of 12): This change wraps the existing mmap_sem related rwsem calls into a new mmap locking API. There are two justifications for the new API: - At first, it provides an easy hooking point to instrument mmap_sem locking latencies independently of any other rwsems. - In the future, it may be a starting point for replacing the rwsem implementation with a different one, such as range locks. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Reviewed-by: Davidlohr Bueso Reviewed-by: Laurent Dufour Reviewed-by: Vlastimil Babka Cc: Peter Zijlstra Cc: Matthew Wilcox Cc: Liam Howlett Cc: Jerome Glisse Cc: David Rientjes Cc: Hugh Dickins Cc: Ying Han Cc: Jason Gunthorpe Cc: John Hubbard Cc: Michel Lespinasse Link: http://lkml.kernel.org/r/20200520052908.204642-1-walken@google.com Link: http://lkml.kernel.org/r/20200520052908.204642-2-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + include/linux/mmap_lock.h | 54 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+) create mode 100644 include/linux/mmap_lock.h (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1844c522d0de..256c4b5b3b11 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h new file mode 100644 index 000000000000..97ac53b66052 --- /dev/null +++ b/include/linux/mmap_lock.h @@ -0,0 +1,54 @@ +#ifndef _LINUX_MMAP_LOCK_H +#define _LINUX_MMAP_LOCK_H + +static inline void mmap_init_lock(struct mm_struct *mm) +{ + init_rwsem(&mm->mmap_sem); +} + +static inline void mmap_write_lock(struct mm_struct *mm) +{ + down_write(&mm->mmap_sem); +} + +static inline int mmap_write_lock_killable(struct mm_struct *mm) +{ + return down_write_killable(&mm->mmap_sem); +} + +static inline bool mmap_write_trylock(struct mm_struct *mm) +{ + return down_write_trylock(&mm->mmap_sem) != 0; +} + +static inline void mmap_write_unlock(struct mm_struct *mm) +{ + up_write(&mm->mmap_sem); +} + +static inline void mmap_write_downgrade(struct mm_struct *mm) +{ + downgrade_write(&mm->mmap_sem); +} + +static inline void mmap_read_lock(struct mm_struct *mm) +{ + down_read(&mm->mmap_sem); +} + +static inline int mmap_read_lock_killable(struct mm_struct *mm) +{ + return down_read_killable(&mm->mmap_sem); +} + +static inline bool mmap_read_trylock(struct mm_struct *mm) +{ + return down_read_trylock(&mm->mmap_sem) != 0; +} + +static inline void mmap_read_unlock(struct mm_struct *mm) +{ + up_read(&mm->mmap_sem); +} + +#endif /* _LINUX_MMAP_LOCK_H */ -- cgit v1.2.3 From b72327fc8dfc1babce18526239b08724b95ef5f0 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:18 -0700 Subject: MMU notifier: use the new mmap locking API This use is converted manually ahead of the next patch in the series, as it requires including a new header which the automated conversion would miss. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Reviewed-by: Davidlohr Bueso Reviewed-by: Laurent Dufour Reviewed-by: Vlastimil Babka Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-3-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 736f6918335e..2f462710a1a4 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -277,9 +278,9 @@ mmu_notifier_get(const struct mmu_notifier_ops *ops, struct mm_struct *mm) { struct mmu_notifier *ret; - down_write(&mm->mmap_sem); + mmap_write_lock(mm); ret = mmu_notifier_get_locked(ops, mm); - up_write(&mm->mmap_sem); + mmap_write_unlock(mm); return ret; } void mmu_notifier_put(struct mmu_notifier *subscription); -- cgit v1.2.3 From aaa2cc56c1cd757efec88a4978ffce4cbf884352 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:33 -0700 Subject: mmap locking API: convert nested write lock sites Add API for nested write locks and convert the few call sites doing that. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Reviewed-by: Laurent Dufour Reviewed-by: Vlastimil Babka Cc: Davidlohr Bueso Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-7-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mmap_lock.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 97ac53b66052..a757cb30ae77 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -11,6 +11,11 @@ static inline void mmap_write_lock(struct mm_struct *mm) down_write(&mm->mmap_sem); } +static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) +{ + down_write_nested(&mm->mmap_sem, subclass); +} + static inline int mmap_write_lock_killable(struct mm_struct *mm) { return down_write_killable(&mm->mmap_sem); -- cgit v1.2.3 From 0cc55a0213a02b760ade1d4755fdccfbf7d3157e Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:37 -0700 Subject: mmap locking API: add mmap_read_trylock_non_owner() Add a couple APIs used by kernel/bpf/stackmap.c only: - mmap_read_trylock_non_owner() - mmap_read_unlock_non_owner() (may be called from a work queue). It's still not ideal that bpf/stackmap subverts the lock ownership in this way. Thanks to Peter Zijlstra for suggesting this API as the least-ugly way of addressing this in the short term. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Reviewed-by: Vlastimil Babka Reviewed-by: Davidlohr Bueso Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Laurent Dufour Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-8-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mmap_lock.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index a757cb30ae77..d1826ce42f00 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -56,4 +56,18 @@ static inline void mmap_read_unlock(struct mm_struct *mm) up_read(&mm->mmap_sem); } +static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) +{ + if (down_read_trylock(&mm->mmap_sem)) { + rwsem_release(&mm->mmap_sem.dep_map, _RET_IP_); + return true; + } + return false; +} + +static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) +{ + up_read_non_owner(&mm->mmap_sem); +} + #endif /* _LINUX_MMAP_LOCK_H */ -- cgit v1.2.3 From 14c3656b7284a8649496584869e8c6642ec1abbb Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:40 -0700 Subject: mmap locking API: add MMAP_LOCK_INITIALIZER Define a new initializer for the mmap locking api. Initially this just evaluates to __RWSEM_INITIALIZER as the API is defined as wrappers around rwsem. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Laurent Dufour Reviewed-by: Vlastimil Babka Reviewed-by: Daniel Jordan Cc: Davidlohr Bueso Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-9-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mmap_lock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index d1826ce42f00..acac1bf5ecd2 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -1,6 +1,9 @@ #ifndef _LINUX_MMAP_LOCK_H #define _LINUX_MMAP_LOCK_H +#define MMAP_LOCK_INITIALIZER(name) \ + .mmap_sem = __RWSEM_INITIALIZER((name).mmap_sem), + static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_sem); -- cgit v1.2.3 From 42fc541404f249778e752ab39c8bc25fcb2dbe1e Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:44 -0700 Subject: mmap locking API: add mmap_assert_locked() and mmap_assert_write_locked() Add new APIs to assert that mmap_sem is held. Using this instead of rwsem_is_locked and lockdep_assert_held[_write] makes the assertions more tolerant of future changes to the lock type. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Daniel Jordan Cc: Davidlohr Bueso Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Laurent Dufour Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-10-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mmap_lock.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index acac1bf5ecd2..43ef914e6468 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -1,6 +1,8 @@ #ifndef _LINUX_MMAP_LOCK_H #define _LINUX_MMAP_LOCK_H +#include + #define MMAP_LOCK_INITIALIZER(name) \ .mmap_sem = __RWSEM_INITIALIZER((name).mmap_sem), @@ -73,4 +75,16 @@ static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) up_read_non_owner(&mm->mmap_sem); } +static inline void mmap_assert_locked(struct mm_struct *mm) +{ + lockdep_assert_held(&mm->mmap_sem); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); +} + +static inline void mmap_assert_write_locked(struct mm_struct *mm) +{ + lockdep_assert_held_write(&mm->mmap_sem); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); +} + #endif /* _LINUX_MMAP_LOCK_H */ -- cgit v1.2.3 From da1c55f1b272f4bd54671d459b39ea7b54944ef9 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:47 -0700 Subject: mmap locking API: rename mmap_sem to mmap_lock Rename the mmap_sem field to mmap_lock. Any new uses of this lock should now go through the new mmap locking api. The mmap_lock is still implemented as a rwsem, though this could change in the future. [akpm@linux-foundation.org: fix it for mm-gup-might_lock_readmmap_sem-in-get_user_pages_fast.patch] Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Davidlohr Bueso Reviewed-by: Daniel Jordan Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Laurent Dufour Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-11-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- include/linux/mmap_lock.h | 38 +++++++++++++++++++------------------- 2 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ef6d3aface8a..b6639b30a83b 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -440,7 +440,7 @@ struct mm_struct { spinlock_t page_table_lock; /* Protects page tables and some * counters */ - struct rw_semaphore mmap_sem; + struct rw_semaphore mmap_lock; struct list_head mmlist; /* List of maybe swapped mm's. These * are globally strung together off diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 43ef914e6468..0707671851a8 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -4,67 +4,67 @@ #include #define MMAP_LOCK_INITIALIZER(name) \ - .mmap_sem = __RWSEM_INITIALIZER((name).mmap_sem), + .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), static inline void mmap_init_lock(struct mm_struct *mm) { - init_rwsem(&mm->mmap_sem); + init_rwsem(&mm->mmap_lock); } static inline void mmap_write_lock(struct mm_struct *mm) { - down_write(&mm->mmap_sem); + down_write(&mm->mmap_lock); } static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) { - down_write_nested(&mm->mmap_sem, subclass); + down_write_nested(&mm->mmap_lock, subclass); } static inline int mmap_write_lock_killable(struct mm_struct *mm) { - return down_write_killable(&mm->mmap_sem); + return down_write_killable(&mm->mmap_lock); } static inline bool mmap_write_trylock(struct mm_struct *mm) { - return down_write_trylock(&mm->mmap_sem) != 0; + return down_write_trylock(&mm->mmap_lock) != 0; } static inline void mmap_write_unlock(struct mm_struct *mm) { - up_write(&mm->mmap_sem); + up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { - downgrade_write(&mm->mmap_sem); + downgrade_write(&mm->mmap_lock); } static inline void mmap_read_lock(struct mm_struct *mm) { - down_read(&mm->mmap_sem); + down_read(&mm->mmap_lock); } static inline int mmap_read_lock_killable(struct mm_struct *mm) { - return down_read_killable(&mm->mmap_sem); + return down_read_killable(&mm->mmap_lock); } static inline bool mmap_read_trylock(struct mm_struct *mm) { - return down_read_trylock(&mm->mmap_sem) != 0; + return down_read_trylock(&mm->mmap_lock) != 0; } static inline void mmap_read_unlock(struct mm_struct *mm) { - up_read(&mm->mmap_sem); + up_read(&mm->mmap_lock); } static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) { - if (down_read_trylock(&mm->mmap_sem)) { - rwsem_release(&mm->mmap_sem.dep_map, _RET_IP_); + if (down_read_trylock(&mm->mmap_lock)) { + rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); return true; } return false; @@ -72,19 +72,19 @@ static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { - up_read_non_owner(&mm->mmap_sem); + up_read_non_owner(&mm->mmap_lock); } static inline void mmap_assert_locked(struct mm_struct *mm) { - lockdep_assert_held(&mm->mmap_sem); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); + lockdep_assert_held(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } static inline void mmap_assert_write_locked(struct mm_struct *mm) { - lockdep_assert_held_write(&mm->mmap_sem); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); + lockdep_assert_held_write(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } #endif /* _LINUX_MMAP_LOCK_H */ -- cgit v1.2.3 From c1e8d7c6a7a682e1405e3e242d32fc377fd196ff Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jun 2020 21:33:54 -0700 Subject: mmap locking API: convert mmap_sem comments Convert comments that reference mmap_sem to reference mmap_lock instead. [akpm@linux-foundation.org: fix up linux-next leftovers] [akpm@linux-foundation.org: s/lockaphore/lock/, per Vlastimil] [akpm@linux-foundation.org: more linux-next fixups, per Michel] Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Daniel Jordan Cc: Davidlohr Bueso Cc: David Rientjes Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Laurent Dufour Cc: Liam Howlett Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Ying Han Link: http://lkml.kernel.org/r/20200520052908.204642-13-walken@google.com Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 ++-- include/linux/huge_mm.h | 2 +- include/linux/mempolicy.h | 2 +- include/linux/mm.h | 10 +++++----- include/linux/mm_types.h | 2 +- include/linux/mmu_notifier.h | 8 ++++---- include/linux/pagemap.h | 2 +- include/linux/pgtable.h | 6 +++--- include/linux/rmap.h | 2 +- include/linux/sched/mm.h | 10 +++++----- 10 files changed, 24 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 01f5d296f9bb..0b026329dbed 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1679,10 +1679,10 @@ static inline int sb_start_write_trylock(struct super_block *sb) * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to - * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault + * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * - * mmap_sem + * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index cfbb0a87c5f0..71f20776b06c 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -248,7 +248,7 @@ static inline int is_swap_pmd(pmd_t pmd) return !pmd_none(pmd) && !pmd_present(pmd); } -/* mmap_sem must be held on entry */ +/* mmap_lock must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 8165278c348a..ea9c15b60a96 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -31,7 +31,7 @@ struct mm_struct; * Locking policy for interlave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on - * mmap_sem. + * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when diff --git a/include/linux/mm.h b/include/linux/mm.h index 256c4b5b3b11..dc7b87310c10 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -402,7 +402,7 @@ extern pgprot_t protection_map[16]; * @FAULT_FLAG_WRITE: Fault was a write fault. * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. - * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_sem and wait when retrying. + * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. * @FAULT_FLAG_TRIED: The fault has been tried once. * @FAULT_FLAG_USER: The fault originated in userspace. @@ -452,10 +452,10 @@ extern pgprot_t protection_map[16]; * fault_flag_allow_retry_first - check ALLOW_RETRY the first time * * This is mostly used for places where we want to try to avoid taking - * the mmap_sem for too long a time when waiting for another condition + * the mmap_lock for too long a time when waiting for another condition * to change, in which case we can try to be polite to release the - * mmap_sem in the first round to avoid potential starvation of other - * processes that would also want the mmap_sem. + * mmap_lock in the first round to avoid potential starvation of other + * processes that would also want the mmap_lock. * * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. @@ -582,7 +582,7 @@ struct vm_operations_struct { * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not - * marked as MPOL_SHARED. vma policies are protected by the mmap_sem. + * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index b6639b30a83b..64ede5f150dc 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -344,7 +344,7 @@ struct vm_area_struct { * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack * or brk vma (with NULL file) can only be in an anon_vma list. */ - struct list_head anon_vma_chain; /* Serialized by mmap_sem & + struct list_head anon_vma_chain; /* Serialized by mmap_lock & * page_table_lock */ struct anon_vma *anon_vma; /* Serialized by page_table_lock */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 2f462710a1a4..fc68f3570e19 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -122,7 +122,7 @@ struct mmu_notifier_ops { /* * invalidate_range_start() and invalidate_range_end() must be - * paired and are called only when the mmap_sem and/or the + * paired and are called only when the mmap_lock and/or the * locks protecting the reverse maps are held. If the subsystem * can't guarantee that no additional references are taken to * the pages in the range, it has to implement the @@ -213,13 +213,13 @@ struct mmu_notifier_ops { }; /* - * The notifier chains are protected by mmap_sem and/or the reverse map + * The notifier chains are protected by mmap_lock and/or the reverse map * semaphores. Notifier chains are only changed when all reverse maps and - * the mmap_sem locks are taken. + * the mmap_lock locks are taken. * * Therefore notifier chains can only be traversed when either * - * 1. mmap_sem is held. + * 1. mmap_lock is held. * 2. One of the reverse map locks is held (i_mmap_rwsem or anon_vma->rwsem). * 3. No other concurrent thread can access the list (release) */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8e085713150c..cf2468da68e9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -538,7 +538,7 @@ static inline int lock_page_killable(struct page *page) * lock_page_or_retry - Lock the page, unless this would block and the * caller indicated that it can handle a retry. * - * Return value and mmap_sem implications depend on flags; see + * Return value and mmap_lock implications depend on flags; see * __lock_page_or_retry(). */ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 90a5d0c78fca..32b6c52d41b9 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1134,11 +1134,11 @@ static inline pmd_t pmd_read_atomic(pmd_t *pmdp) #endif /* * This function is meant to be used by sites walking pagetables with - * the mmap_sem hold in read mode to protect against MADV_DONTNEED and + * the mmap_lock held in read mode to protect against MADV_DONTNEED and * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd * into a null pmd and the transhuge page fault can convert a null pmd * into an hugepmd or into a regular pmd (if the hugepage allocation - * fails). While holding the mmap_sem in read mode the pmd becomes + * fails). While holding the mmap_lock in read mode the pmd becomes * stable and stops changing under us only if it's not null and not a * transhuge pmd. When those races occurs and this function makes a * difference vs the standard pmd_none_or_clear_bad, the result is @@ -1148,7 +1148,7 @@ static inline pmd_t pmd_read_atomic(pmd_t *pmdp) * * For 32bit kernels with a 64bit large pmd_t this automatically takes * care of reading the pmd atomically to avoid SMP race conditions - * against pmd_populate() when the mmap_sem is hold for reading by the + * against pmd_populate() when the mmap_lock is hold for reading by the * caller (a special atomic read not done by "gcc" as in the generic * version above, is also needed when THP is disabled because the page * fault can populate the pmd from under us). diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 988d176472df..3a6adfa70fb0 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -77,7 +77,7 @@ struct anon_vma { struct anon_vma_chain { struct vm_area_struct *vma; struct anon_vma *anon_vma; - struct list_head same_vma; /* locked by mmap_sem & page_table_lock */ + struct list_head same_vma; /* locked by mmap_lock & page_table_lock */ struct rb_node rb; /* locked by anon_vma->rwsem */ unsigned long rb_subtree_last; #ifdef CONFIG_DEBUG_VM_RB diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index a132d875d351..480a4d1b7dd8 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -53,7 +53,7 @@ void mmdrop(struct mm_struct *mm); /* * This has to be called after a get_task_mm()/mmget_not_zero() - * followed by taking the mmap_sem for writing before modifying the + * followed by taking the mmap_lock for writing before modifying the * vmas or anything the coredump pretends not to change from under it. * * It also has to be called when mmgrab() is used in the context of @@ -61,14 +61,14 @@ void mmdrop(struct mm_struct *mm); * the context of the process to run down_write() on that pinned mm. * * NOTE: find_extend_vma() called from GUP context is the only place - * that can modify the "mm" (notably the vm_start/end) under mmap_sem + * that can modify the "mm" (notably the vm_start/end) under mmap_lock * for reading and outside the context of the process, so it is also - * the only case that holds the mmap_sem for reading that must call - * this function. Generally if the mmap_sem is hold for reading + * the only case that holds the mmap_lock for reading that must call + * this function. Generally if the mmap_lock is hold for reading * there's no need of this check after get_task_mm()/mmget_not_zero(). * * This function can be obsoleted and the check can be removed, after - * the coredump code will hold the mmap_sem for writing before + * the coredump code will hold the mmap_lock for writing before * invoking the ->core_dump methods. */ static inline bool mmget_still_valid(struct mm_struct *mm) -- cgit v1.2.3 From 48c49c0e5f318e7c329d9a0ee6facce30bbb28e6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:01 -0700 Subject: maccess: remove various unused weak aliases maccess tends to define lots of underscore prefixed symbols that then have other weak aliases. But except for two cases they are never actually used, so remove them. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-3-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 9861c89f93be..88d9ef56d07b 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -324,7 +324,6 @@ extern long __probe_kernel_read(void *dst, const void *src, size_t size); * happens, handle that and return -EFAULT. */ extern long probe_user_read(void *dst, const void __user *src, size_t size); -extern long __probe_user_read(void *dst, const void __user *src, size_t size); /* * probe_kernel_write(): safely attempt to write to a location @@ -336,7 +335,6 @@ extern long __probe_user_read(void *dst, const void __user *src, size_t size); * happens, handle that and return -EFAULT. */ extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); -extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size); /* * probe_user_write(): safely attempt to write to a location in user space @@ -348,7 +346,6 @@ extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size * happens, handle that and return -EFAULT. */ extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); -extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size); extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, -- cgit v1.2.3 From 3ed740841bf94a8028ec44164d84f9af9bd552fd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:04 -0700 Subject: maccess: remove duplicate kerneldoc comments Many of the maccess routines have a copy of the kerneldoc comment in the header. Remove it as it is not useful and will get out of sync sooner or later. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-4-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 38 -------------------------------------- 1 file changed, 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 88d9ef56d07b..4f4622b01a50 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -301,50 +301,12 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, return 0; } -/* - * probe_kernel_read(): safely attempt to read from a location - * @dst: pointer to the buffer that shall take the data - * @src: address to read from - * @size: size of the data chunk - * - * Safely read from address @src to the buffer at @dst. If a kernel fault - * happens, handle that and return -EFAULT. - */ extern long probe_kernel_read(void *dst, const void *src, size_t size); extern long probe_kernel_read_strict(void *dst, const void *src, size_t size); extern long __probe_kernel_read(void *dst, const void *src, size_t size); - -/* - * probe_user_read(): safely attempt to read from a location in user space - * @dst: pointer to the buffer that shall take the data - * @src: address to read from - * @size: size of the data chunk - * - * Safely read from address @src to the buffer at @dst. If a kernel fault - * happens, handle that and return -EFAULT. - */ extern long probe_user_read(void *dst, const void __user *src, size_t size); -/* - * probe_kernel_write(): safely attempt to write to a location - * @dst: address to write to - * @src: pointer to the data that shall be written - * @size: size of the data chunk - * - * Safely write to address @dst from the buffer at @src. If a kernel fault - * happens, handle that and return -EFAULT. - */ extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); - -/* - * probe_user_write(): safely attempt to write to a location in user space - * @dst: address to write to - * @src: pointer to the data that shall be written - * @size: size of the data chunk - * - * Safely write to address @dst from the buffer at @src. If a kernel fault - * happens, handle that and return -EFAULT. - */ extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); -- cgit v1.2.3 From bd88bb5d4007949be7154deae7cef7173c751a95 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:14 -0700 Subject: maccess: rename strncpy_from_unsafe_user to strncpy_from_user_nofault This matches the naming of strncpy_from_user, and also makes it more clear what the function is supposed to do. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-7-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 4f4622b01a50..d1a4fa66067c 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -313,8 +313,8 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, long count); extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); -extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, - long count); +long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, + long count); extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); /** -- cgit v1.2.3 From c4cb164426aebd635baa53685b0ebf1a127e9803 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:17 -0700 Subject: maccess: rename strncpy_from_unsafe_strict to strncpy_from_kernel_nofault This matches the naming of strncpy_from_user_nofault, and also makes it more clear what the function is supposed to do. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-8-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index d1a4fa66067c..d9ae3c69802d 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -310,8 +310,8 @@ extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); -extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, - long count); +long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, + long count); extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); -- cgit v1.2.3 From 02dddb160ec1dccb51e75f3113654a090bc3963a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:20 -0700 Subject: maccess: rename strnlen_unsafe_user to strnlen_user_nofault This matches the naming of strnlen_user, and also makes it more clear what the function is supposed to do. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-9-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index d9ae3c69802d..575cc308d98b 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -315,7 +315,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); -extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); +long strnlen_user_nofault(const void __user *unsafe_addr, long count); /** * probe_kernel_address(): safely attempt to read from a location -- cgit v1.2.3 From eab0c6089b68974ebc6a9a7eab68456eeb6a99c7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:27 -0700 Subject: maccess: unify the probe kernel arch hooks Currently architectures have to override every routine that probes kernel memory, which includes a pure read and strcpy, both in strict and not strict variants. Just provide a single arch hooks instead to make sure all architectures cover all the cases. [akpm@linux-foundation.org: fix !CONFIG_X86_64 build] Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-11-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 575cc308d98b..bb3ab8227850 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -301,9 +301,11 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, return 0; } +bool probe_kernel_read_allowed(const void *unsafe_src, size_t size, + bool strict); + extern long probe_kernel_read(void *dst, const void *src, size_t size); extern long probe_kernel_read_strict(void *dst, const void *src, size_t size); -extern long __probe_kernel_read(void *dst, const void *src, size_t size); extern long probe_user_read(void *dst, const void __user *src, size_t size); extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); @@ -312,7 +314,7 @@ extern long notrace probe_user_write(void __user *dst, const void *src, size_t s extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); -extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); + long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); -- cgit v1.2.3 From 7676fbf21b5fa04341c8046c2cbcd1949293e7ec Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:47 -0700 Subject: maccess: remove strncpy_from_unsafe All users are gone now. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-16-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index bb3ab8227850..4183e585dee6 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -311,7 +311,6 @@ extern long probe_user_read(void *dst, const void __user *src, size_t size); extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); -extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); -- cgit v1.2.3 From 98a23609b10364a51a1bb3688f8dd1cd1aa94a9a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2020 21:34:50 -0700 Subject: maccess: always use strict semantics for probe_kernel_read Except for historical confusion in the kprobes/uprobes and bpf tracers, which has been fixed now, there is no good reason to ever allow user memory accesses from probe_kernel_read. Switch probe_kernel_read to only read from kernel memory. [akpm@linux-foundation.org: update it for "mm, dump_page(): do not crash with invalid mapping pointer"] Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200521152301.2587579-17-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 4183e585dee6..dac1db05bf7e 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -301,11 +301,9 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, return 0; } -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size, - bool strict); +bool probe_kernel_read_allowed(const void *unsafe_src, size_t size); extern long probe_kernel_read(void *dst, const void *src, size_t size); -extern long probe_kernel_read_strict(void *dst, const void *src, size_t size); extern long probe_user_read(void *dst, const void __user *src, size_t size); extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); -- cgit v1.2.3 From 4fa7252338a56fbc90220e6330f136a379175a7a Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Mon, 8 Jun 2020 21:35:07 -0700 Subject: include/linux/cache.h: expand documentation over __read_mostly __read_mostly can easily be misused by folks, its not meant for just read-only data. There are performance reasons for using it, but we also don't provide any guidance about its use. Provide a bit more guidance over its use. Signed-off-by: Luis Chamberlain Signed-off-by: Andrew Morton Reviewed-by: Kees Cook Acked-by: Christoph Lameter Acked-by: Rafael Aquini Cc: Arnd Bergmann Cc: Matthew Wilcox Link: http://lkml.kernel.org/r/20200507161424.2584-1-mcgrof@kernel.org Signed-off-by: Linus Torvalds --- include/linux/cache.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cache.h b/include/linux/cache.h index 750621e41d1c..1aa8009f6d06 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -15,8 +15,14 @@ /* * __read_mostly is used to keep rarely changing variables out of frequently - * updated cachelines. If an architecture doesn't support it, ignore the - * hint. + * updated cachelines. Its use should be reserved for data that is used + * frequently in hot paths. Performance traces can help decide when to use + * this. You want __read_mostly data to be tightly packed, so that in the + * best case multiple frequently read variables for a hot path will be next + * to each other in order to reduce the number of cachelines needed to + * execute a critical path. We should be mindful and selective of its use. + * ie: if you're going to use it please supply a *good* justification in your + * commit log */ #ifndef __read_mostly #define __read_mostly -- cgit v1.2.3 From f1084bc60a1ec592011a805a0f925f2f1205897d Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 9 Jun 2020 19:22:47 +0200 Subject: Revert "fs: remove dio_end_io()" This reverts commit b75b7ca7c27dfd61dba368f390b7d4dc20b3a8cb. The patch restores a helper that was not necessary after direct IO port to iomap infrastructure, which gets reverted. Signed-off-by: David Sterba --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e84623d5e173..366c533d30cd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3187,6 +3187,8 @@ enum { DIO_SKIP_HOLES = 0x02, }; +void dio_end_io(struct bio *bio); + ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, -- cgit v1.2.3 From 845e0ebb4408d4473cf60d21224a897037e9a77a Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 8 Jun 2020 14:53:01 -0700 Subject: net: change addr_list_lock back to static key The dynamic key update for addr_list_lock still causes troubles, for example the following race condition still exists: CPU 0: CPU 1: (RCU read lock) (RTNL lock) dev_mc_seq_show() netdev_update_lockdep_key() -> lockdep_unregister_key() -> netif_addr_lock_bh() because lockdep doesn't provide an API to update it atomically. Therefore, we have to move it back to static keys and use subclass for nest locking like before. In commit 1a33e10e4a95 ("net: partially revert dynamic lockdep key changes"), I already reverted most parts of commit ab92d68fc22f ("net: core: add generic lockdep keys"). This patch reverts the rest and also part of commit f3b0a18bb6cb ("net: remove unnecessary variables and callback"). After this patch, addr_list_lock changes back to using static keys and subclasses to satisfy lockdep. Thanks to dev->lower_level, we do not have to change back to ->ndo_get_lock_subclass(). And hopefully this reduces some syzbot lockdep noises too. Reported-by: syzbot+f3a0e80c34b3fc28ac5e@syzkaller.appspotmail.com Cc: Taehee Yoo Cc: Dmitry Vyukov Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1a96e9c4ec36..e2825e27ef89 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1821,8 +1821,6 @@ enum netdev_priv_flags { * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. * - * @addr_list_lock_key: lockdep class annotating - * net_device->addr_list_lock spinlock * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount * @@ -2125,7 +2123,6 @@ struct net_device { #endif struct phy_device *phydev; struct sfp_bus *sfp_bus; - struct lock_class_key addr_list_lock_key; struct lock_class_key *qdisc_tx_busylock; struct lock_class_key *qdisc_running_key; bool proto_down; @@ -2217,10 +2214,13 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, static struct lock_class_key qdisc_tx_busylock_key; \ static struct lock_class_key qdisc_running_key; \ static struct lock_class_key qdisc_xmit_lock_key; \ + static struct lock_class_key dev_addr_list_lock_key; \ unsigned int i; \ \ (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ (dev)->qdisc_running_key = &qdisc_running_key; \ + lockdep_set_class(&(dev)->addr_list_lock, \ + &dev_addr_list_lock_key); \ for (i = 0; i < (dev)->num_tx_queues; i++) \ lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ &qdisc_xmit_lock_key); \ @@ -3253,7 +3253,6 @@ static inline void netif_stop_queue(struct net_device *dev) } void netif_tx_stop_all_queues(struct net_device *dev); -void netdev_update_lockdep_key(struct net_device *dev); static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue) { @@ -4239,6 +4238,11 @@ static inline void netif_addr_lock(struct net_device *dev) spin_lock(&dev->addr_list_lock); } +static inline void netif_addr_lock_nested(struct net_device *dev) +{ + spin_lock_nested(&dev->addr_list_lock, dev->lower_level); +} + static inline void netif_addr_lock_bh(struct net_device *dev) { spin_lock_bh(&dev->addr_list_lock); -- cgit v1.2.3 From 6b7ce8927b5a4d739670d4dc0de301f2abfd9a5c Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Mon, 1 Jun 2020 14:45:40 +0530 Subject: irqchip: RISC-V per-HART local interrupt controller driver The RISC-V per-HART local interrupt controller manages software interrupts, timer interrupts, external interrupts (which are routed via the platform level interrupt controller) and other per-HART local interrupts. We add a driver for the RISC-V local interrupt controller, which eventually replaces the RISC-V architecture code, allowing for a better split between arch code and drivers. The driver is compliant with RISC-V Hart-Level Interrupt Controller DT bindings located at: Documentation/devicetree/bindings/interrupt-controller/riscv,cpu-intc.txt Co-developed-by: Palmer Dabbelt Signed-off-by: Anup Patel [Palmer: Cleaned up warnings] Signed-off-by: Palmer Dabbelt --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 24b3a77810b6..0a13f8f23a64 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -102,6 +102,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_ARMADA_XP_STARTING, CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_IRQ_MIPS_GIC_STARTING, + CPUHP_AP_IRQ_RISCV_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_MICROCODE_LOADER, -- cgit v1.2.3 From 496df3d3ab8a407f83330fb8d7160a5f91898c55 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Wed, 10 Jun 2020 18:41:50 -0700 Subject: mm: add comments on pglist_data zones While making other modifications it was easy to confuse the two struct members node_zones and node_zonelists. For those already familiar with the code, this might seem to be a silly patch, but it's quite helpful to disambiguate the similar-sounding fields While here, add a small comment on why nr_zones isn't simply MAX_NR_ZONES Signed-off-by: Ben Widawsky Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Link: http://lkml.kernel.org/r/20200520205443.2757414-1-ben.widawsky@intel.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index df1f08486d81..c4c37fd12104 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -660,9 +660,21 @@ struct deferred_split { * per-zone basis. */ typedef struct pglist_data { + /* + * node_zones contains just the zones for THIS node. Not all of the + * zones may be populated, but it is the full list. It is referenced by + * this node's node_zonelists as well as other node's node_zonelists. + */ struct zone node_zones[MAX_NR_ZONES]; + + /* + * node_zonelists contains references to all zones in all nodes. + * Generally the first zones will be references to this node's + * node_zones. + */ struct zonelist node_zonelists[MAX_ZONELISTS]; - int nr_zones; + + int nr_zones; /* number of populated zones in this node */ #ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION -- cgit v1.2.3 From 2c34f6f738d2509cf9b710abd35a605acfd6ada6 Mon Sep 17 00:00:00 2001 From: Walter Wu Date: Wed, 10 Jun 2020 18:41:56 -0700 Subject: stacktrace: cleanup inconsistent variable type Modify the variable type of 'skip' member of struct stack_trace. In theory, the 'skip' variable type should be unsigned int. There are two reasons: - The 'skip' only has two situation, 1)Positive value, 2)Zero - The 'skip' of struct stack_trace has inconsistent type with struct stack_trace_data, it makes a bit confusion in the relationship between struct stack_trace and stack_trace_data. Signed-off-by: Walter Wu Signed-off-by: Andrew Morton Reviewed-by: Bart Van Assche Cc: Matthias Brugger Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Josh Poimboeuf Link: http://lkml.kernel.org/r/20200421013511.5960-1-walter-zh.wu@mediatek.com Signed-off-by: Linus Torvalds --- include/linux/stacktrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 83bd8cb475d7..b7af8cc13eda 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -64,7 +64,7 @@ void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, struct stack_trace { unsigned int nr_entries, max_entries; unsigned long *entries; - int skip; /* input argument: How many entries to skip */ + unsigned int skip; /* input argument: How many entries to skip */ }; extern void save_stack_trace(struct stack_trace *trace); -- cgit v1.2.3 From 9bf5b9eb232b34738800868e30bea3bad4a6a1ba Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Jun 2020 18:41:59 -0700 Subject: kernel: move use_mm/unuse_mm to kthread.c Patch series "improve use_mm / unuse_mm", v2. This series improves the use_mm / unuse_mm interface by better documenting the assumptions, and my taking the set_fs manipulations spread over the callers into the core API. This patch (of 3): Use the proper API instead. Link: http://lkml.kernel.org/r/20200404094101.672954-1-hch@lst.de These helpers are only for use with kernel threads, and I will tie them more into the kthread infrastructure going forward. Also move the prototypes to kthread.h - mmu_context.h was a little weird to start with as it otherwise contains very low-level MM bits. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Tested-by: Jens Axboe Reviewed-by: Jens Axboe Acked-by: Felix Kuehling Cc: Alex Deucher Cc: Al Viro Cc: Felipe Balbi Cc: Jason Wang Cc: "Michael S. Tsirkin" Cc: Zhenyu Wang Cc: Zhi Wang Cc: Greg Kroah-Hartman Link: http://lkml.kernel.org/r/20200404094101.672954-1-hch@lst.de Link: http://lkml.kernel.org/r/20200416053158.586887-1-hch@lst.de Link: http://lkml.kernel.org/r/20200404094101.672954-5-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/kthread.h | 5 +++++ include/linux/mmu_context.h | 5 ----- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 8bbcaad7ef0f..c2d40c9672d6 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -5,6 +5,8 @@ #include #include +struct mm_struct; + __printf(4, 5) struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, @@ -198,6 +200,9 @@ bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *work); void kthread_destroy_worker(struct kthread_worker *worker); +void use_mm(struct mm_struct *mm); +void unuse_mm(struct mm_struct *mm); + struct cgroup_subsys_state; #ifdef CONFIG_BLK_CGROUP diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index d9a543a9e1cc..c51a84132d7c 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -4,11 +4,6 @@ #include -struct mm_struct; - -void use_mm(struct mm_struct *mm); -void unuse_mm(struct mm_struct *mm); - /* Architectures that care about IRQ state in switch_mm can override this. */ #ifndef switch_mm_irqs_off # define switch_mm_irqs_off switch_mm -- cgit v1.2.3 From f5678e7f2ac31c270334b936352f0ef2fe7dd2b3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Jun 2020 18:42:06 -0700 Subject: kernel: better document the use_mm/unuse_mm API contract Switch the function documentation to kerneldoc comments, and add WARN_ON_ONCE asserts that the calling thread is a kernel thread and does not have ->mm set (or has ->mm set in the case of unuse_mm). Also give the functions a kthread_ prefix to better document the use case. [hch@lst.de: fix a comment typo, cover the newly merged use_mm/unuse_mm caller in vfio] Link: http://lkml.kernel.org/r/20200416053158.586887-3-hch@lst.de [sfr@canb.auug.org.au: powerpc/vas: fix up for {un}use_mm() rename] Link: http://lkml.kernel.org/r/20200422163935.5aa93ba5@canb.auug.org.au Signed-off-by: Christoph Hellwig Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Tested-by: Jens Axboe Reviewed-by: Jens Axboe Acked-by: Felix Kuehling Acked-by: Greg Kroah-Hartman [usb] Acked-by: Haren Myneni Cc: Alex Deucher Cc: Al Viro Cc: Felipe Balbi Cc: Jason Wang Cc: "Michael S. Tsirkin" Cc: Zhenyu Wang Cc: Zhi Wang Link: http://lkml.kernel.org/r/20200404094101.672954-6-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/kthread.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index c2d40c9672d6..12258ea077cf 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -200,8 +200,8 @@ bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *work); void kthread_destroy_worker(struct kthread_worker *worker); -void use_mm(struct mm_struct *mm); -void unuse_mm(struct mm_struct *mm); +void kthread_use_mm(struct mm_struct *mm); +void kthread_unuse_mm(struct mm_struct *mm); struct cgroup_subsys_state; -- cgit v1.2.3 From 765dcd209947e7b3666c08fb109ab8b879f7a471 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 26 Nov 2019 15:04:05 +0100 Subject: asm-generic/atomic: Use __always_inline for fallback wrappers Use __always_inline for atomic fallback wrappers. When building for size (CC_OPTIMIZE_FOR_SIZE), some compilers appear to be less inclined to inline even relatively small static inline functions that are assumed to be inlinable such as atomic ops. This can cause problems, for example in UACCESS regions. While the fallback wrappers aren't pure wrappers, they are trivial nonetheless, and the function they wrap should determine the final inlining policy. For x86 tinyconfig we observe: - vmlinux baseline: 1315988 - vmlinux with patch: 1315928 (-60 bytes) [ tglx: Cherry-picked from KCSAN ] Suggested-by: Mark Rutland Signed-off-by: Marco Elver Acked-by: Mark Rutland Signed-off-by: Paul E. McKenney Signed-off-by: Thomas Gleixner --- include/linux/atomic-fallback.h | 340 ++++++++++++++++++++-------------------- 1 file changed, 171 insertions(+), 169 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic-fallback.h b/include/linux/atomic-fallback.h index a7d240e465c0..656b5489b673 100644 --- a/include/linux/atomic-fallback.h +++ b/include/linux/atomic-fallback.h @@ -6,6 +6,8 @@ #ifndef _LINUX_ATOMIC_FALLBACK_H #define _LINUX_ATOMIC_FALLBACK_H +#include + #ifndef xchg_relaxed #define xchg_relaxed xchg #define xchg_acquire xchg @@ -76,7 +78,7 @@ #endif /* cmpxchg64_relaxed */ #ifndef atomic_read_acquire -static inline int +static __always_inline int atomic_read_acquire(const atomic_t *v) { return smp_load_acquire(&(v)->counter); @@ -85,7 +87,7 @@ atomic_read_acquire(const atomic_t *v) #endif #ifndef atomic_set_release -static inline void +static __always_inline void atomic_set_release(atomic_t *v, int i) { smp_store_release(&(v)->counter, i); @@ -100,7 +102,7 @@ atomic_set_release(atomic_t *v, int i) #else /* atomic_add_return_relaxed */ #ifndef atomic_add_return_acquire -static inline int +static __always_inline int atomic_add_return_acquire(int i, atomic_t *v) { int ret = atomic_add_return_relaxed(i, v); @@ -111,7 +113,7 @@ atomic_add_return_acquire(int i, atomic_t *v) #endif #ifndef atomic_add_return_release -static inline int +static __always_inline int atomic_add_return_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -121,7 +123,7 @@ atomic_add_return_release(int i, atomic_t *v) #endif #ifndef atomic_add_return -static inline int +static __always_inline int atomic_add_return(int i, atomic_t *v) { int ret; @@ -142,7 +144,7 @@ atomic_add_return(int i, atomic_t *v) #else /* atomic_fetch_add_relaxed */ #ifndef atomic_fetch_add_acquire -static inline int +static __always_inline int atomic_fetch_add_acquire(int i, atomic_t *v) { int ret = atomic_fetch_add_relaxed(i, v); @@ -153,7 +155,7 @@ atomic_fetch_add_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_add_release -static inline int +static __always_inline int atomic_fetch_add_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -163,7 +165,7 @@ atomic_fetch_add_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_add -static inline int +static __always_inline int atomic_fetch_add(int i, atomic_t *v) { int ret; @@ -184,7 +186,7 @@ atomic_fetch_add(int i, atomic_t *v) #else /* atomic_sub_return_relaxed */ #ifndef atomic_sub_return_acquire -static inline int +static __always_inline int atomic_sub_return_acquire(int i, atomic_t *v) { int ret = atomic_sub_return_relaxed(i, v); @@ -195,7 +197,7 @@ atomic_sub_return_acquire(int i, atomic_t *v) #endif #ifndef atomic_sub_return_release -static inline int +static __always_inline int atomic_sub_return_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -205,7 +207,7 @@ atomic_sub_return_release(int i, atomic_t *v) #endif #ifndef atomic_sub_return -static inline int +static __always_inline int atomic_sub_return(int i, atomic_t *v) { int ret; @@ -226,7 +228,7 @@ atomic_sub_return(int i, atomic_t *v) #else /* atomic_fetch_sub_relaxed */ #ifndef atomic_fetch_sub_acquire -static inline int +static __always_inline int atomic_fetch_sub_acquire(int i, atomic_t *v) { int ret = atomic_fetch_sub_relaxed(i, v); @@ -237,7 +239,7 @@ atomic_fetch_sub_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_sub_release -static inline int +static __always_inline int atomic_fetch_sub_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -247,7 +249,7 @@ atomic_fetch_sub_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_sub -static inline int +static __always_inline int atomic_fetch_sub(int i, atomic_t *v) { int ret; @@ -262,7 +264,7 @@ atomic_fetch_sub(int i, atomic_t *v) #endif /* atomic_fetch_sub_relaxed */ #ifndef atomic_inc -static inline void +static __always_inline void atomic_inc(atomic_t *v) { atomic_add(1, v); @@ -278,7 +280,7 @@ atomic_inc(atomic_t *v) #endif /* atomic_inc_return */ #ifndef atomic_inc_return -static inline int +static __always_inline int atomic_inc_return(atomic_t *v) { return atomic_add_return(1, v); @@ -287,7 +289,7 @@ atomic_inc_return(atomic_t *v) #endif #ifndef atomic_inc_return_acquire -static inline int +static __always_inline int atomic_inc_return_acquire(atomic_t *v) { return atomic_add_return_acquire(1, v); @@ -296,7 +298,7 @@ atomic_inc_return_acquire(atomic_t *v) #endif #ifndef atomic_inc_return_release -static inline int +static __always_inline int atomic_inc_return_release(atomic_t *v) { return atomic_add_return_release(1, v); @@ -305,7 +307,7 @@ atomic_inc_return_release(atomic_t *v) #endif #ifndef atomic_inc_return_relaxed -static inline int +static __always_inline int atomic_inc_return_relaxed(atomic_t *v) { return atomic_add_return_relaxed(1, v); @@ -316,7 +318,7 @@ atomic_inc_return_relaxed(atomic_t *v) #else /* atomic_inc_return_relaxed */ #ifndef atomic_inc_return_acquire -static inline int +static __always_inline int atomic_inc_return_acquire(atomic_t *v) { int ret = atomic_inc_return_relaxed(v); @@ -327,7 +329,7 @@ atomic_inc_return_acquire(atomic_t *v) #endif #ifndef atomic_inc_return_release -static inline int +static __always_inline int atomic_inc_return_release(atomic_t *v) { __atomic_release_fence(); @@ -337,7 +339,7 @@ atomic_inc_return_release(atomic_t *v) #endif #ifndef atomic_inc_return -static inline int +static __always_inline int atomic_inc_return(atomic_t *v) { int ret; @@ -359,7 +361,7 @@ atomic_inc_return(atomic_t *v) #endif /* atomic_fetch_inc */ #ifndef atomic_fetch_inc -static inline int +static __always_inline int atomic_fetch_inc(atomic_t *v) { return atomic_fetch_add(1, v); @@ -368,7 +370,7 @@ atomic_fetch_inc(atomic_t *v) #endif #ifndef atomic_fetch_inc_acquire -static inline int +static __always_inline int atomic_fetch_inc_acquire(atomic_t *v) { return atomic_fetch_add_acquire(1, v); @@ -377,7 +379,7 @@ atomic_fetch_inc_acquire(atomic_t *v) #endif #ifndef atomic_fetch_inc_release -static inline int +static __always_inline int atomic_fetch_inc_release(atomic_t *v) { return atomic_fetch_add_release(1, v); @@ -386,7 +388,7 @@ atomic_fetch_inc_release(atomic_t *v) #endif #ifndef atomic_fetch_inc_relaxed -static inline int +static __always_inline int atomic_fetch_inc_relaxed(atomic_t *v) { return atomic_fetch_add_relaxed(1, v); @@ -397,7 +399,7 @@ atomic_fetch_inc_relaxed(atomic_t *v) #else /* atomic_fetch_inc_relaxed */ #ifndef atomic_fetch_inc_acquire -static inline int +static __always_inline int atomic_fetch_inc_acquire(atomic_t *v) { int ret = atomic_fetch_inc_relaxed(v); @@ -408,7 +410,7 @@ atomic_fetch_inc_acquire(atomic_t *v) #endif #ifndef atomic_fetch_inc_release -static inline int +static __always_inline int atomic_fetch_inc_release(atomic_t *v) { __atomic_release_fence(); @@ -418,7 +420,7 @@ atomic_fetch_inc_release(atomic_t *v) #endif #ifndef atomic_fetch_inc -static inline int +static __always_inline int atomic_fetch_inc(atomic_t *v) { int ret; @@ -433,7 +435,7 @@ atomic_fetch_inc(atomic_t *v) #endif /* atomic_fetch_inc_relaxed */ #ifndef atomic_dec -static inline void +static __always_inline void atomic_dec(atomic_t *v) { atomic_sub(1, v); @@ -449,7 +451,7 @@ atomic_dec(atomic_t *v) #endif /* atomic_dec_return */ #ifndef atomic_dec_return -static inline int +static __always_inline int atomic_dec_return(atomic_t *v) { return atomic_sub_return(1, v); @@ -458,7 +460,7 @@ atomic_dec_return(atomic_t *v) #endif #ifndef atomic_dec_return_acquire -static inline int +static __always_inline int atomic_dec_return_acquire(atomic_t *v) { return atomic_sub_return_acquire(1, v); @@ -467,7 +469,7 @@ atomic_dec_return_acquire(atomic_t *v) #endif #ifndef atomic_dec_return_release -static inline int +static __always_inline int atomic_dec_return_release(atomic_t *v) { return atomic_sub_return_release(1, v); @@ -476,7 +478,7 @@ atomic_dec_return_release(atomic_t *v) #endif #ifndef atomic_dec_return_relaxed -static inline int +static __always_inline int atomic_dec_return_relaxed(atomic_t *v) { return atomic_sub_return_relaxed(1, v); @@ -487,7 +489,7 @@ atomic_dec_return_relaxed(atomic_t *v) #else /* atomic_dec_return_relaxed */ #ifndef atomic_dec_return_acquire -static inline int +static __always_inline int atomic_dec_return_acquire(atomic_t *v) { int ret = atomic_dec_return_relaxed(v); @@ -498,7 +500,7 @@ atomic_dec_return_acquire(atomic_t *v) #endif #ifndef atomic_dec_return_release -static inline int +static __always_inline int atomic_dec_return_release(atomic_t *v) { __atomic_release_fence(); @@ -508,7 +510,7 @@ atomic_dec_return_release(atomic_t *v) #endif #ifndef atomic_dec_return -static inline int +static __always_inline int atomic_dec_return(atomic_t *v) { int ret; @@ -530,7 +532,7 @@ atomic_dec_return(atomic_t *v) #endif /* atomic_fetch_dec */ #ifndef atomic_fetch_dec -static inline int +static __always_inline int atomic_fetch_dec(atomic_t *v) { return atomic_fetch_sub(1, v); @@ -539,7 +541,7 @@ atomic_fetch_dec(atomic_t *v) #endif #ifndef atomic_fetch_dec_acquire -static inline int +static __always_inline int atomic_fetch_dec_acquire(atomic_t *v) { return atomic_fetch_sub_acquire(1, v); @@ -548,7 +550,7 @@ atomic_fetch_dec_acquire(atomic_t *v) #endif #ifndef atomic_fetch_dec_release -static inline int +static __always_inline int atomic_fetch_dec_release(atomic_t *v) { return atomic_fetch_sub_release(1, v); @@ -557,7 +559,7 @@ atomic_fetch_dec_release(atomic_t *v) #endif #ifndef atomic_fetch_dec_relaxed -static inline int +static __always_inline int atomic_fetch_dec_relaxed(atomic_t *v) { return atomic_fetch_sub_relaxed(1, v); @@ -568,7 +570,7 @@ atomic_fetch_dec_relaxed(atomic_t *v) #else /* atomic_fetch_dec_relaxed */ #ifndef atomic_fetch_dec_acquire -static inline int +static __always_inline int atomic_fetch_dec_acquire(atomic_t *v) { int ret = atomic_fetch_dec_relaxed(v); @@ -579,7 +581,7 @@ atomic_fetch_dec_acquire(atomic_t *v) #endif #ifndef atomic_fetch_dec_release -static inline int +static __always_inline int atomic_fetch_dec_release(atomic_t *v) { __atomic_release_fence(); @@ -589,7 +591,7 @@ atomic_fetch_dec_release(atomic_t *v) #endif #ifndef atomic_fetch_dec -static inline int +static __always_inline int atomic_fetch_dec(atomic_t *v) { int ret; @@ -610,7 +612,7 @@ atomic_fetch_dec(atomic_t *v) #else /* atomic_fetch_and_relaxed */ #ifndef atomic_fetch_and_acquire -static inline int +static __always_inline int atomic_fetch_and_acquire(int i, atomic_t *v) { int ret = atomic_fetch_and_relaxed(i, v); @@ -621,7 +623,7 @@ atomic_fetch_and_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_and_release -static inline int +static __always_inline int atomic_fetch_and_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -631,7 +633,7 @@ atomic_fetch_and_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_and -static inline int +static __always_inline int atomic_fetch_and(int i, atomic_t *v) { int ret; @@ -646,7 +648,7 @@ atomic_fetch_and(int i, atomic_t *v) #endif /* atomic_fetch_and_relaxed */ #ifndef atomic_andnot -static inline void +static __always_inline void atomic_andnot(int i, atomic_t *v) { atomic_and(~i, v); @@ -662,7 +664,7 @@ atomic_andnot(int i, atomic_t *v) #endif /* atomic_fetch_andnot */ #ifndef atomic_fetch_andnot -static inline int +static __always_inline int atomic_fetch_andnot(int i, atomic_t *v) { return atomic_fetch_and(~i, v); @@ -671,7 +673,7 @@ atomic_fetch_andnot(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot_acquire -static inline int +static __always_inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) { return atomic_fetch_and_acquire(~i, v); @@ -680,7 +682,7 @@ atomic_fetch_andnot_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot_release -static inline int +static __always_inline int atomic_fetch_andnot_release(int i, atomic_t *v) { return atomic_fetch_and_release(~i, v); @@ -689,7 +691,7 @@ atomic_fetch_andnot_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot_relaxed -static inline int +static __always_inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v) { return atomic_fetch_and_relaxed(~i, v); @@ -700,7 +702,7 @@ atomic_fetch_andnot_relaxed(int i, atomic_t *v) #else /* atomic_fetch_andnot_relaxed */ #ifndef atomic_fetch_andnot_acquire -static inline int +static __always_inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) { int ret = atomic_fetch_andnot_relaxed(i, v); @@ -711,7 +713,7 @@ atomic_fetch_andnot_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot_release -static inline int +static __always_inline int atomic_fetch_andnot_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -721,7 +723,7 @@ atomic_fetch_andnot_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_andnot -static inline int +static __always_inline int atomic_fetch_andnot(int i, atomic_t *v) { int ret; @@ -742,7 +744,7 @@ atomic_fetch_andnot(int i, atomic_t *v) #else /* atomic_fetch_or_relaxed */ #ifndef atomic_fetch_or_acquire -static inline int +static __always_inline int atomic_fetch_or_acquire(int i, atomic_t *v) { int ret = atomic_fetch_or_relaxed(i, v); @@ -753,7 +755,7 @@ atomic_fetch_or_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_or_release -static inline int +static __always_inline int atomic_fetch_or_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -763,7 +765,7 @@ atomic_fetch_or_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_or -static inline int +static __always_inline int atomic_fetch_or(int i, atomic_t *v) { int ret; @@ -784,7 +786,7 @@ atomic_fetch_or(int i, atomic_t *v) #else /* atomic_fetch_xor_relaxed */ #ifndef atomic_fetch_xor_acquire -static inline int +static __always_inline int atomic_fetch_xor_acquire(int i, atomic_t *v) { int ret = atomic_fetch_xor_relaxed(i, v); @@ -795,7 +797,7 @@ atomic_fetch_xor_acquire(int i, atomic_t *v) #endif #ifndef atomic_fetch_xor_release -static inline int +static __always_inline int atomic_fetch_xor_release(int i, atomic_t *v) { __atomic_release_fence(); @@ -805,7 +807,7 @@ atomic_fetch_xor_release(int i, atomic_t *v) #endif #ifndef atomic_fetch_xor -static inline int +static __always_inline int atomic_fetch_xor(int i, atomic_t *v) { int ret; @@ -826,7 +828,7 @@ atomic_fetch_xor(int i, atomic_t *v) #else /* atomic_xchg_relaxed */ #ifndef atomic_xchg_acquire -static inline int +static __always_inline int atomic_xchg_acquire(atomic_t *v, int i) { int ret = atomic_xchg_relaxed(v, i); @@ -837,7 +839,7 @@ atomic_xchg_acquire(atomic_t *v, int i) #endif #ifndef atomic_xchg_release -static inline int +static __always_inline int atomic_xchg_release(atomic_t *v, int i) { __atomic_release_fence(); @@ -847,7 +849,7 @@ atomic_xchg_release(atomic_t *v, int i) #endif #ifndef atomic_xchg -static inline int +static __always_inline int atomic_xchg(atomic_t *v, int i) { int ret; @@ -868,7 +870,7 @@ atomic_xchg(atomic_t *v, int i) #else /* atomic_cmpxchg_relaxed */ #ifndef atomic_cmpxchg_acquire -static inline int +static __always_inline int atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { int ret = atomic_cmpxchg_relaxed(v, old, new); @@ -879,7 +881,7 @@ atomic_cmpxchg_acquire(atomic_t *v, int old, int new) #endif #ifndef atomic_cmpxchg_release -static inline int +static __always_inline int atomic_cmpxchg_release(atomic_t *v, int old, int new) { __atomic_release_fence(); @@ -889,7 +891,7 @@ atomic_cmpxchg_release(atomic_t *v, int old, int new) #endif #ifndef atomic_cmpxchg -static inline int +static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; @@ -911,7 +913,7 @@ atomic_cmpxchg(atomic_t *v, int old, int new) #endif /* atomic_try_cmpxchg */ #ifndef atomic_try_cmpxchg -static inline bool +static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) { int r, o = *old; @@ -924,7 +926,7 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg_acquire -static inline bool +static __always_inline bool atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { int r, o = *old; @@ -937,7 +939,7 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg_release -static inline bool +static __always_inline bool atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { int r, o = *old; @@ -950,7 +952,7 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg_relaxed -static inline bool +static __always_inline bool atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { int r, o = *old; @@ -965,7 +967,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) #else /* atomic_try_cmpxchg_relaxed */ #ifndef atomic_try_cmpxchg_acquire -static inline bool +static __always_inline bool atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { bool ret = atomic_try_cmpxchg_relaxed(v, old, new); @@ -976,7 +978,7 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg_release -static inline bool +static __always_inline bool atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { __atomic_release_fence(); @@ -986,7 +988,7 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) #endif #ifndef atomic_try_cmpxchg -static inline bool +static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) { bool ret; @@ -1010,7 +1012,7 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) * true if the result is zero, or false for all * other cases. */ -static inline bool +static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { return atomic_sub_return(i, v) == 0; @@ -1027,7 +1029,7 @@ atomic_sub_and_test(int i, atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ -static inline bool +static __always_inline bool atomic_dec_and_test(atomic_t *v) { return atomic_dec_return(v) == 0; @@ -1044,7 +1046,7 @@ atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ -static inline bool +static __always_inline bool atomic_inc_and_test(atomic_t *v) { return atomic_inc_return(v) == 0; @@ -1062,7 +1064,7 @@ atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline bool +static __always_inline bool atomic_add_negative(int i, atomic_t *v) { return atomic_add_return(i, v) < 0; @@ -1080,7 +1082,7 @@ atomic_add_negative(int i, atomic_t *v) * Atomically adds @a to @v, so long as @v was not already @u. * Returns original value of @v */ -static inline int +static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c = atomic_read(v); @@ -1105,7 +1107,7 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u) * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ -static inline bool +static __always_inline bool atomic_add_unless(atomic_t *v, int a, int u) { return atomic_fetch_add_unless(v, a, u) != u; @@ -1121,7 +1123,7 @@ atomic_add_unless(atomic_t *v, int a, int u) * Atomically increments @v by 1, if @v is non-zero. * Returns true if the increment was done. */ -static inline bool +static __always_inline bool atomic_inc_not_zero(atomic_t *v) { return atomic_add_unless(v, 1, 0); @@ -1130,7 +1132,7 @@ atomic_inc_not_zero(atomic_t *v) #endif #ifndef atomic_inc_unless_negative -static inline bool +static __always_inline bool atomic_inc_unless_negative(atomic_t *v) { int c = atomic_read(v); @@ -1146,7 +1148,7 @@ atomic_inc_unless_negative(atomic_t *v) #endif #ifndef atomic_dec_unless_positive -static inline bool +static __always_inline bool atomic_dec_unless_positive(atomic_t *v) { int c = atomic_read(v); @@ -1162,7 +1164,7 @@ atomic_dec_unless_positive(atomic_t *v) #endif #ifndef atomic_dec_if_positive -static inline int +static __always_inline int atomic_dec_if_positive(atomic_t *v) { int dec, c = atomic_read(v); @@ -1186,7 +1188,7 @@ atomic_dec_if_positive(atomic_t *v) #endif #ifndef atomic64_read_acquire -static inline s64 +static __always_inline s64 atomic64_read_acquire(const atomic64_t *v) { return smp_load_acquire(&(v)->counter); @@ -1195,7 +1197,7 @@ atomic64_read_acquire(const atomic64_t *v) #endif #ifndef atomic64_set_release -static inline void +static __always_inline void atomic64_set_release(atomic64_t *v, s64 i) { smp_store_release(&(v)->counter, i); @@ -1210,7 +1212,7 @@ atomic64_set_release(atomic64_t *v, s64 i) #else /* atomic64_add_return_relaxed */ #ifndef atomic64_add_return_acquire -static inline s64 +static __always_inline s64 atomic64_add_return_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_add_return_relaxed(i, v); @@ -1221,7 +1223,7 @@ atomic64_add_return_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_add_return_release -static inline s64 +static __always_inline s64 atomic64_add_return_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1231,7 +1233,7 @@ atomic64_add_return_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_add_return -static inline s64 +static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v) { s64 ret; @@ -1252,7 +1254,7 @@ atomic64_add_return(s64 i, atomic64_t *v) #else /* atomic64_fetch_add_relaxed */ #ifndef atomic64_fetch_add_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_add_relaxed(i, v); @@ -1263,7 +1265,7 @@ atomic64_fetch_add_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_add_release -static inline s64 +static __always_inline s64 atomic64_fetch_add_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1273,7 +1275,7 @@ atomic64_fetch_add_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_add -static inline s64 +static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v) { s64 ret; @@ -1294,7 +1296,7 @@ atomic64_fetch_add(s64 i, atomic64_t *v) #else /* atomic64_sub_return_relaxed */ #ifndef atomic64_sub_return_acquire -static inline s64 +static __always_inline s64 atomic64_sub_return_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_sub_return_relaxed(i, v); @@ -1305,7 +1307,7 @@ atomic64_sub_return_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_sub_return_release -static inline s64 +static __always_inline s64 atomic64_sub_return_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1315,7 +1317,7 @@ atomic64_sub_return_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_sub_return -static inline s64 +static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v) { s64 ret; @@ -1336,7 +1338,7 @@ atomic64_sub_return(s64 i, atomic64_t *v) #else /* atomic64_fetch_sub_relaxed */ #ifndef atomic64_fetch_sub_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_sub_relaxed(i, v); @@ -1347,7 +1349,7 @@ atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_sub_release -static inline s64 +static __always_inline s64 atomic64_fetch_sub_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1357,7 +1359,7 @@ atomic64_fetch_sub_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_sub -static inline s64 +static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v) { s64 ret; @@ -1372,7 +1374,7 @@ atomic64_fetch_sub(s64 i, atomic64_t *v) #endif /* atomic64_fetch_sub_relaxed */ #ifndef atomic64_inc -static inline void +static __always_inline void atomic64_inc(atomic64_t *v) { atomic64_add(1, v); @@ -1388,7 +1390,7 @@ atomic64_inc(atomic64_t *v) #endif /* atomic64_inc_return */ #ifndef atomic64_inc_return -static inline s64 +static __always_inline s64 atomic64_inc_return(atomic64_t *v) { return atomic64_add_return(1, v); @@ -1397,7 +1399,7 @@ atomic64_inc_return(atomic64_t *v) #endif #ifndef atomic64_inc_return_acquire -static inline s64 +static __always_inline s64 atomic64_inc_return_acquire(atomic64_t *v) { return atomic64_add_return_acquire(1, v); @@ -1406,7 +1408,7 @@ atomic64_inc_return_acquire(atomic64_t *v) #endif #ifndef atomic64_inc_return_release -static inline s64 +static __always_inline s64 atomic64_inc_return_release(atomic64_t *v) { return atomic64_add_return_release(1, v); @@ -1415,7 +1417,7 @@ atomic64_inc_return_release(atomic64_t *v) #endif #ifndef atomic64_inc_return_relaxed -static inline s64 +static __always_inline s64 atomic64_inc_return_relaxed(atomic64_t *v) { return atomic64_add_return_relaxed(1, v); @@ -1426,7 +1428,7 @@ atomic64_inc_return_relaxed(atomic64_t *v) #else /* atomic64_inc_return_relaxed */ #ifndef atomic64_inc_return_acquire -static inline s64 +static __always_inline s64 atomic64_inc_return_acquire(atomic64_t *v) { s64 ret = atomic64_inc_return_relaxed(v); @@ -1437,7 +1439,7 @@ atomic64_inc_return_acquire(atomic64_t *v) #endif #ifndef atomic64_inc_return_release -static inline s64 +static __always_inline s64 atomic64_inc_return_release(atomic64_t *v) { __atomic_release_fence(); @@ -1447,7 +1449,7 @@ atomic64_inc_return_release(atomic64_t *v) #endif #ifndef atomic64_inc_return -static inline s64 +static __always_inline s64 atomic64_inc_return(atomic64_t *v) { s64 ret; @@ -1469,7 +1471,7 @@ atomic64_inc_return(atomic64_t *v) #endif /* atomic64_fetch_inc */ #ifndef atomic64_fetch_inc -static inline s64 +static __always_inline s64 atomic64_fetch_inc(atomic64_t *v) { return atomic64_fetch_add(1, v); @@ -1478,7 +1480,7 @@ atomic64_fetch_inc(atomic64_t *v) #endif #ifndef atomic64_fetch_inc_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_inc_acquire(atomic64_t *v) { return atomic64_fetch_add_acquire(1, v); @@ -1487,7 +1489,7 @@ atomic64_fetch_inc_acquire(atomic64_t *v) #endif #ifndef atomic64_fetch_inc_release -static inline s64 +static __always_inline s64 atomic64_fetch_inc_release(atomic64_t *v) { return atomic64_fetch_add_release(1, v); @@ -1496,7 +1498,7 @@ atomic64_fetch_inc_release(atomic64_t *v) #endif #ifndef atomic64_fetch_inc_relaxed -static inline s64 +static __always_inline s64 atomic64_fetch_inc_relaxed(atomic64_t *v) { return atomic64_fetch_add_relaxed(1, v); @@ -1507,7 +1509,7 @@ atomic64_fetch_inc_relaxed(atomic64_t *v) #else /* atomic64_fetch_inc_relaxed */ #ifndef atomic64_fetch_inc_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_inc_acquire(atomic64_t *v) { s64 ret = atomic64_fetch_inc_relaxed(v); @@ -1518,7 +1520,7 @@ atomic64_fetch_inc_acquire(atomic64_t *v) #endif #ifndef atomic64_fetch_inc_release -static inline s64 +static __always_inline s64 atomic64_fetch_inc_release(atomic64_t *v) { __atomic_release_fence(); @@ -1528,7 +1530,7 @@ atomic64_fetch_inc_release(atomic64_t *v) #endif #ifndef atomic64_fetch_inc -static inline s64 +static __always_inline s64 atomic64_fetch_inc(atomic64_t *v) { s64 ret; @@ -1543,7 +1545,7 @@ atomic64_fetch_inc(atomic64_t *v) #endif /* atomic64_fetch_inc_relaxed */ #ifndef atomic64_dec -static inline void +static __always_inline void atomic64_dec(atomic64_t *v) { atomic64_sub(1, v); @@ -1559,7 +1561,7 @@ atomic64_dec(atomic64_t *v) #endif /* atomic64_dec_return */ #ifndef atomic64_dec_return -static inline s64 +static __always_inline s64 atomic64_dec_return(atomic64_t *v) { return atomic64_sub_return(1, v); @@ -1568,7 +1570,7 @@ atomic64_dec_return(atomic64_t *v) #endif #ifndef atomic64_dec_return_acquire -static inline s64 +static __always_inline s64 atomic64_dec_return_acquire(atomic64_t *v) { return atomic64_sub_return_acquire(1, v); @@ -1577,7 +1579,7 @@ atomic64_dec_return_acquire(atomic64_t *v) #endif #ifndef atomic64_dec_return_release -static inline s64 +static __always_inline s64 atomic64_dec_return_release(atomic64_t *v) { return atomic64_sub_return_release(1, v); @@ -1586,7 +1588,7 @@ atomic64_dec_return_release(atomic64_t *v) #endif #ifndef atomic64_dec_return_relaxed -static inline s64 +static __always_inline s64 atomic64_dec_return_relaxed(atomic64_t *v) { return atomic64_sub_return_relaxed(1, v); @@ -1597,7 +1599,7 @@ atomic64_dec_return_relaxed(atomic64_t *v) #else /* atomic64_dec_return_relaxed */ #ifndef atomic64_dec_return_acquire -static inline s64 +static __always_inline s64 atomic64_dec_return_acquire(atomic64_t *v) { s64 ret = atomic64_dec_return_relaxed(v); @@ -1608,7 +1610,7 @@ atomic64_dec_return_acquire(atomic64_t *v) #endif #ifndef atomic64_dec_return_release -static inline s64 +static __always_inline s64 atomic64_dec_return_release(atomic64_t *v) { __atomic_release_fence(); @@ -1618,7 +1620,7 @@ atomic64_dec_return_release(atomic64_t *v) #endif #ifndef atomic64_dec_return -static inline s64 +static __always_inline s64 atomic64_dec_return(atomic64_t *v) { s64 ret; @@ -1640,7 +1642,7 @@ atomic64_dec_return(atomic64_t *v) #endif /* atomic64_fetch_dec */ #ifndef atomic64_fetch_dec -static inline s64 +static __always_inline s64 atomic64_fetch_dec(atomic64_t *v) { return atomic64_fetch_sub(1, v); @@ -1649,7 +1651,7 @@ atomic64_fetch_dec(atomic64_t *v) #endif #ifndef atomic64_fetch_dec_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_dec_acquire(atomic64_t *v) { return atomic64_fetch_sub_acquire(1, v); @@ -1658,7 +1660,7 @@ atomic64_fetch_dec_acquire(atomic64_t *v) #endif #ifndef atomic64_fetch_dec_release -static inline s64 +static __always_inline s64 atomic64_fetch_dec_release(atomic64_t *v) { return atomic64_fetch_sub_release(1, v); @@ -1667,7 +1669,7 @@ atomic64_fetch_dec_release(atomic64_t *v) #endif #ifndef atomic64_fetch_dec_relaxed -static inline s64 +static __always_inline s64 atomic64_fetch_dec_relaxed(atomic64_t *v) { return atomic64_fetch_sub_relaxed(1, v); @@ -1678,7 +1680,7 @@ atomic64_fetch_dec_relaxed(atomic64_t *v) #else /* atomic64_fetch_dec_relaxed */ #ifndef atomic64_fetch_dec_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_dec_acquire(atomic64_t *v) { s64 ret = atomic64_fetch_dec_relaxed(v); @@ -1689,7 +1691,7 @@ atomic64_fetch_dec_acquire(atomic64_t *v) #endif #ifndef atomic64_fetch_dec_release -static inline s64 +static __always_inline s64 atomic64_fetch_dec_release(atomic64_t *v) { __atomic_release_fence(); @@ -1699,7 +1701,7 @@ atomic64_fetch_dec_release(atomic64_t *v) #endif #ifndef atomic64_fetch_dec -static inline s64 +static __always_inline s64 atomic64_fetch_dec(atomic64_t *v) { s64 ret; @@ -1720,7 +1722,7 @@ atomic64_fetch_dec(atomic64_t *v) #else /* atomic64_fetch_and_relaxed */ #ifndef atomic64_fetch_and_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_and_relaxed(i, v); @@ -1731,7 +1733,7 @@ atomic64_fetch_and_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_and_release -static inline s64 +static __always_inline s64 atomic64_fetch_and_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1741,7 +1743,7 @@ atomic64_fetch_and_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_and -static inline s64 +static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v) { s64 ret; @@ -1756,7 +1758,7 @@ atomic64_fetch_and(s64 i, atomic64_t *v) #endif /* atomic64_fetch_and_relaxed */ #ifndef atomic64_andnot -static inline void +static __always_inline void atomic64_andnot(s64 i, atomic64_t *v) { atomic64_and(~i, v); @@ -1772,7 +1774,7 @@ atomic64_andnot(s64 i, atomic64_t *v) #endif /* atomic64_fetch_andnot */ #ifndef atomic64_fetch_andnot -static inline s64 +static __always_inline s64 atomic64_fetch_andnot(s64 i, atomic64_t *v) { return atomic64_fetch_and(~i, v); @@ -1781,7 +1783,7 @@ atomic64_fetch_andnot(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { return atomic64_fetch_and_acquire(~i, v); @@ -1790,7 +1792,7 @@ atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot_release -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { return atomic64_fetch_and_release(~i, v); @@ -1799,7 +1801,7 @@ atomic64_fetch_andnot_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot_relaxed -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { return atomic64_fetch_and_relaxed(~i, v); @@ -1810,7 +1812,7 @@ atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) #else /* atomic64_fetch_andnot_relaxed */ #ifndef atomic64_fetch_andnot_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_andnot_relaxed(i, v); @@ -1821,7 +1823,7 @@ atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot_release -static inline s64 +static __always_inline s64 atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1831,7 +1833,7 @@ atomic64_fetch_andnot_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_andnot -static inline s64 +static __always_inline s64 atomic64_fetch_andnot(s64 i, atomic64_t *v) { s64 ret; @@ -1852,7 +1854,7 @@ atomic64_fetch_andnot(s64 i, atomic64_t *v) #else /* atomic64_fetch_or_relaxed */ #ifndef atomic64_fetch_or_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_or_relaxed(i, v); @@ -1863,7 +1865,7 @@ atomic64_fetch_or_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_or_release -static inline s64 +static __always_inline s64 atomic64_fetch_or_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1873,7 +1875,7 @@ atomic64_fetch_or_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_or -static inline s64 +static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v) { s64 ret; @@ -1894,7 +1896,7 @@ atomic64_fetch_or(s64 i, atomic64_t *v) #else /* atomic64_fetch_xor_relaxed */ #ifndef atomic64_fetch_xor_acquire -static inline s64 +static __always_inline s64 atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { s64 ret = atomic64_fetch_xor_relaxed(i, v); @@ -1905,7 +1907,7 @@ atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_xor_release -static inline s64 +static __always_inline s64 atomic64_fetch_xor_release(s64 i, atomic64_t *v) { __atomic_release_fence(); @@ -1915,7 +1917,7 @@ atomic64_fetch_xor_release(s64 i, atomic64_t *v) #endif #ifndef atomic64_fetch_xor -static inline s64 +static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) { s64 ret; @@ -1936,7 +1938,7 @@ atomic64_fetch_xor(s64 i, atomic64_t *v) #else /* atomic64_xchg_relaxed */ #ifndef atomic64_xchg_acquire -static inline s64 +static __always_inline s64 atomic64_xchg_acquire(atomic64_t *v, s64 i) { s64 ret = atomic64_xchg_relaxed(v, i); @@ -1947,7 +1949,7 @@ atomic64_xchg_acquire(atomic64_t *v, s64 i) #endif #ifndef atomic64_xchg_release -static inline s64 +static __always_inline s64 atomic64_xchg_release(atomic64_t *v, s64 i) { __atomic_release_fence(); @@ -1957,7 +1959,7 @@ atomic64_xchg_release(atomic64_t *v, s64 i) #endif #ifndef atomic64_xchg -static inline s64 +static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 i) { s64 ret; @@ -1978,7 +1980,7 @@ atomic64_xchg(atomic64_t *v, s64 i) #else /* atomic64_cmpxchg_relaxed */ #ifndef atomic64_cmpxchg_acquire -static inline s64 +static __always_inline s64 atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { s64 ret = atomic64_cmpxchg_relaxed(v, old, new); @@ -1989,7 +1991,7 @@ atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) #endif #ifndef atomic64_cmpxchg_release -static inline s64 +static __always_inline s64 atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { __atomic_release_fence(); @@ -1999,7 +2001,7 @@ atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) #endif #ifndef atomic64_cmpxchg -static inline s64 +static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { s64 ret; @@ -2021,7 +2023,7 @@ atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) #endif /* atomic64_try_cmpxchg */ #ifndef atomic64_try_cmpxchg -static inline bool +static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; @@ -2034,7 +2036,7 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg_acquire -static inline bool +static __always_inline bool atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; @@ -2047,7 +2049,7 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg_release -static inline bool +static __always_inline bool atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; @@ -2060,7 +2062,7 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg_relaxed -static inline bool +static __always_inline bool atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; @@ -2075,7 +2077,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) #else /* atomic64_try_cmpxchg_relaxed */ #ifndef atomic64_try_cmpxchg_acquire -static inline bool +static __always_inline bool atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { bool ret = atomic64_try_cmpxchg_relaxed(v, old, new); @@ -2086,7 +2088,7 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg_release -static inline bool +static __always_inline bool atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { __atomic_release_fence(); @@ -2096,7 +2098,7 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) #endif #ifndef atomic64_try_cmpxchg -static inline bool +static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { bool ret; @@ -2120,7 +2122,7 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) * true if the result is zero, or false for all * other cases. */ -static inline bool +static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) { return atomic64_sub_return(i, v) == 0; @@ -2137,7 +2139,7 @@ atomic64_sub_and_test(s64 i, atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ -static inline bool +static __always_inline bool atomic64_dec_and_test(atomic64_t *v) { return atomic64_dec_return(v) == 0; @@ -2154,7 +2156,7 @@ atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ -static inline bool +static __always_inline bool atomic64_inc_and_test(atomic64_t *v) { return atomic64_inc_return(v) == 0; @@ -2172,7 +2174,7 @@ atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline bool +static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) { return atomic64_add_return(i, v) < 0; @@ -2190,7 +2192,7 @@ atomic64_add_negative(s64 i, atomic64_t *v) * Atomically adds @a to @v, so long as @v was not already @u. * Returns original value of @v */ -static inline s64 +static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { s64 c = atomic64_read(v); @@ -2215,7 +2217,7 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ -static inline bool +static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { return atomic64_fetch_add_unless(v, a, u) != u; @@ -2231,7 +2233,7 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u) * Atomically increments @v by 1, if @v is non-zero. * Returns true if the increment was done. */ -static inline bool +static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { return atomic64_add_unless(v, 1, 0); @@ -2240,7 +2242,7 @@ atomic64_inc_not_zero(atomic64_t *v) #endif #ifndef atomic64_inc_unless_negative -static inline bool +static __always_inline bool atomic64_inc_unless_negative(atomic64_t *v) { s64 c = atomic64_read(v); @@ -2256,7 +2258,7 @@ atomic64_inc_unless_negative(atomic64_t *v) #endif #ifndef atomic64_dec_unless_positive -static inline bool +static __always_inline bool atomic64_dec_unless_positive(atomic64_t *v) { s64 c = atomic64_read(v); @@ -2272,7 +2274,7 @@ atomic64_dec_unless_positive(atomic64_t *v) #endif #ifndef atomic64_dec_if_positive -static inline s64 +static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { s64 dec, c = atomic64_read(v); @@ -2292,4 +2294,4 @@ atomic64_dec_if_positive(atomic64_t *v) #define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 25de4a2804d70f57e994fe3b419148658bb5378a +// baaf45f4c24ed88ceae58baca39d7fd80bb8101b -- cgit v1.2.3 From 37f8173dd84936ea78000ed1cad24f8b18d48ebb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 24 Jan 2020 22:13:03 +0100 Subject: locking/atomics: Flip fallbacks and instrumentation Currently instrumentation of atomic primitives is done at the architecture level, while composites or fallbacks are provided at the generic level. The result is that there are no uninstrumented variants of the fallbacks. Since there is now need of such variants to isolate text poke from any form of instrumentation invert this ordering. Doing this means moving the instrumentation into the generic code as well as having (for now) two variants of the fallbacks. Notes: - the various *cond_read* primitives are not proper fallbacks and got moved into linux/atomic.c. No arch_ variants are generated because the base primitives smp_cond_load*() are instrumented. - once all architectures are moved over to arch_atomic_ one of the fallback variants can be removed and some 2300 lines reclaimed. - atomic_{read,set}*() are no longer double-instrumented Reported-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Acked-by: Mark Rutland Link: https://lkml.kernel.org/r/20200505134058.769149955@linutronix.de --- include/linux/atomic-arch-fallback.h | 2291 ++++++++++++++++++++++++++++++++++ include/linux/atomic-fallback.h | 8 +- include/linux/atomic.h | 11 + 3 files changed, 2303 insertions(+), 7 deletions(-) create mode 100644 include/linux/atomic-arch-fallback.h (limited to 'include/linux') diff --git a/include/linux/atomic-arch-fallback.h b/include/linux/atomic-arch-fallback.h new file mode 100644 index 000000000000..bcb6aa27cfa6 --- /dev/null +++ b/include/linux/atomic-arch-fallback.h @@ -0,0 +1,2291 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Generated by scripts/atomic/gen-atomic-fallback.sh +// DO NOT MODIFY THIS FILE DIRECTLY + +#ifndef _LINUX_ATOMIC_FALLBACK_H +#define _LINUX_ATOMIC_FALLBACK_H + +#include + +#ifndef arch_xchg_relaxed +#define arch_xchg_relaxed arch_xchg +#define arch_xchg_acquire arch_xchg +#define arch_xchg_release arch_xchg +#else /* arch_xchg_relaxed */ + +#ifndef arch_xchg_acquire +#define arch_xchg_acquire(...) \ + __atomic_op_acquire(arch_xchg, __VA_ARGS__) +#endif + +#ifndef arch_xchg_release +#define arch_xchg_release(...) \ + __atomic_op_release(arch_xchg, __VA_ARGS__) +#endif + +#ifndef arch_xchg +#define arch_xchg(...) \ + __atomic_op_fence(arch_xchg, __VA_ARGS__) +#endif + +#endif /* arch_xchg_relaxed */ + +#ifndef arch_cmpxchg_relaxed +#define arch_cmpxchg_relaxed arch_cmpxchg +#define arch_cmpxchg_acquire arch_cmpxchg +#define arch_cmpxchg_release arch_cmpxchg +#else /* arch_cmpxchg_relaxed */ + +#ifndef arch_cmpxchg_acquire +#define arch_cmpxchg_acquire(...) \ + __atomic_op_acquire(arch_cmpxchg, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg_release +#define arch_cmpxchg_release(...) \ + __atomic_op_release(arch_cmpxchg, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg +#define arch_cmpxchg(...) \ + __atomic_op_fence(arch_cmpxchg, __VA_ARGS__) +#endif + +#endif /* arch_cmpxchg_relaxed */ + +#ifndef arch_cmpxchg64_relaxed +#define arch_cmpxchg64_relaxed arch_cmpxchg64 +#define arch_cmpxchg64_acquire arch_cmpxchg64 +#define arch_cmpxchg64_release arch_cmpxchg64 +#else /* arch_cmpxchg64_relaxed */ + +#ifndef arch_cmpxchg64_acquire +#define arch_cmpxchg64_acquire(...) \ + __atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg64_release +#define arch_cmpxchg64_release(...) \ + __atomic_op_release(arch_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg64 +#define arch_cmpxchg64(...) \ + __atomic_op_fence(arch_cmpxchg64, __VA_ARGS__) +#endif + +#endif /* arch_cmpxchg64_relaxed */ + +#ifndef arch_atomic_read_acquire +static __always_inline int +arch_atomic_read_acquire(const atomic_t *v) +{ + return smp_load_acquire(&(v)->counter); +} +#define arch_atomic_read_acquire arch_atomic_read_acquire +#endif + +#ifndef arch_atomic_set_release +static __always_inline void +arch_atomic_set_release(atomic_t *v, int i) +{ + smp_store_release(&(v)->counter, i); +} +#define arch_atomic_set_release arch_atomic_set_release +#endif + +#ifndef arch_atomic_add_return_relaxed +#define arch_atomic_add_return_acquire arch_atomic_add_return +#define arch_atomic_add_return_release arch_atomic_add_return +#define arch_atomic_add_return_relaxed arch_atomic_add_return +#else /* arch_atomic_add_return_relaxed */ + +#ifndef arch_atomic_add_return_acquire +static __always_inline int +arch_atomic_add_return_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_add_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_add_return_acquire arch_atomic_add_return_acquire +#endif + +#ifndef arch_atomic_add_return_release +static __always_inline int +arch_atomic_add_return_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_add_return_relaxed(i, v); +} +#define arch_atomic_add_return_release arch_atomic_add_return_release +#endif + +#ifndef arch_atomic_add_return +static __always_inline int +arch_atomic_add_return(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_add_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_add_return arch_atomic_add_return +#endif + +#endif /* arch_atomic_add_return_relaxed */ + +#ifndef arch_atomic_fetch_add_relaxed +#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add +#define arch_atomic_fetch_add_release arch_atomic_fetch_add +#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add +#else /* arch_atomic_fetch_add_relaxed */ + +#ifndef arch_atomic_fetch_add_acquire +static __always_inline int +arch_atomic_fetch_add_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_add_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add_acquire +#endif + +#ifndef arch_atomic_fetch_add_release +static __always_inline int +arch_atomic_fetch_add_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_add_relaxed(i, v); +} +#define arch_atomic_fetch_add_release arch_atomic_fetch_add_release +#endif + +#ifndef arch_atomic_fetch_add +static __always_inline int +arch_atomic_fetch_add(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_add_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_add arch_atomic_fetch_add +#endif + +#endif /* arch_atomic_fetch_add_relaxed */ + +#ifndef arch_atomic_sub_return_relaxed +#define arch_atomic_sub_return_acquire arch_atomic_sub_return +#define arch_atomic_sub_return_release arch_atomic_sub_return +#define arch_atomic_sub_return_relaxed arch_atomic_sub_return +#else /* arch_atomic_sub_return_relaxed */ + +#ifndef arch_atomic_sub_return_acquire +static __always_inline int +arch_atomic_sub_return_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_sub_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_sub_return_acquire arch_atomic_sub_return_acquire +#endif + +#ifndef arch_atomic_sub_return_release +static __always_inline int +arch_atomic_sub_return_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_sub_return_relaxed(i, v); +} +#define arch_atomic_sub_return_release arch_atomic_sub_return_release +#endif + +#ifndef arch_atomic_sub_return +static __always_inline int +arch_atomic_sub_return(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_sub_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_sub_return arch_atomic_sub_return +#endif + +#endif /* arch_atomic_sub_return_relaxed */ + +#ifndef arch_atomic_fetch_sub_relaxed +#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub +#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub +#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub +#else /* arch_atomic_fetch_sub_relaxed */ + +#ifndef arch_atomic_fetch_sub_acquire +static __always_inline int +arch_atomic_fetch_sub_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_sub_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub_acquire +#endif + +#ifndef arch_atomic_fetch_sub_release +static __always_inline int +arch_atomic_fetch_sub_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_sub_relaxed(i, v); +} +#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub_release +#endif + +#ifndef arch_atomic_fetch_sub +static __always_inline int +arch_atomic_fetch_sub(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_sub_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_sub arch_atomic_fetch_sub +#endif + +#endif /* arch_atomic_fetch_sub_relaxed */ + +#ifndef arch_atomic_inc +static __always_inline void +arch_atomic_inc(atomic_t *v) +{ + arch_atomic_add(1, v); +} +#define arch_atomic_inc arch_atomic_inc +#endif + +#ifndef arch_atomic_inc_return_relaxed +#ifdef arch_atomic_inc_return +#define arch_atomic_inc_return_acquire arch_atomic_inc_return +#define arch_atomic_inc_return_release arch_atomic_inc_return +#define arch_atomic_inc_return_relaxed arch_atomic_inc_return +#endif /* arch_atomic_inc_return */ + +#ifndef arch_atomic_inc_return +static __always_inline int +arch_atomic_inc_return(atomic_t *v) +{ + return arch_atomic_add_return(1, v); +} +#define arch_atomic_inc_return arch_atomic_inc_return +#endif + +#ifndef arch_atomic_inc_return_acquire +static __always_inline int +arch_atomic_inc_return_acquire(atomic_t *v) +{ + return arch_atomic_add_return_acquire(1, v); +} +#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire +#endif + +#ifndef arch_atomic_inc_return_release +static __always_inline int +arch_atomic_inc_return_release(atomic_t *v) +{ + return arch_atomic_add_return_release(1, v); +} +#define arch_atomic_inc_return_release arch_atomic_inc_return_release +#endif + +#ifndef arch_atomic_inc_return_relaxed +static __always_inline int +arch_atomic_inc_return_relaxed(atomic_t *v) +{ + return arch_atomic_add_return_relaxed(1, v); +} +#define arch_atomic_inc_return_relaxed arch_atomic_inc_return_relaxed +#endif + +#else /* arch_atomic_inc_return_relaxed */ + +#ifndef arch_atomic_inc_return_acquire +static __always_inline int +arch_atomic_inc_return_acquire(atomic_t *v) +{ + int ret = arch_atomic_inc_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire +#endif + +#ifndef arch_atomic_inc_return_release +static __always_inline int +arch_atomic_inc_return_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_inc_return_relaxed(v); +} +#define arch_atomic_inc_return_release arch_atomic_inc_return_release +#endif + +#ifndef arch_atomic_inc_return +static __always_inline int +arch_atomic_inc_return(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_inc_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_inc_return arch_atomic_inc_return +#endif + +#endif /* arch_atomic_inc_return_relaxed */ + +#ifndef arch_atomic_fetch_inc_relaxed +#ifdef arch_atomic_fetch_inc +#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc +#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc +#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc +#endif /* arch_atomic_fetch_inc */ + +#ifndef arch_atomic_fetch_inc +static __always_inline int +arch_atomic_fetch_inc(atomic_t *v) +{ + return arch_atomic_fetch_add(1, v); +} +#define arch_atomic_fetch_inc arch_atomic_fetch_inc +#endif + +#ifndef arch_atomic_fetch_inc_acquire +static __always_inline int +arch_atomic_fetch_inc_acquire(atomic_t *v) +{ + return arch_atomic_fetch_add_acquire(1, v); +} +#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire +#endif + +#ifndef arch_atomic_fetch_inc_release +static __always_inline int +arch_atomic_fetch_inc_release(atomic_t *v) +{ + return arch_atomic_fetch_add_release(1, v); +} +#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release +#endif + +#ifndef arch_atomic_fetch_inc_relaxed +static __always_inline int +arch_atomic_fetch_inc_relaxed(atomic_t *v) +{ + return arch_atomic_fetch_add_relaxed(1, v); +} +#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc_relaxed +#endif + +#else /* arch_atomic_fetch_inc_relaxed */ + +#ifndef arch_atomic_fetch_inc_acquire +static __always_inline int +arch_atomic_fetch_inc_acquire(atomic_t *v) +{ + int ret = arch_atomic_fetch_inc_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire +#endif + +#ifndef arch_atomic_fetch_inc_release +static __always_inline int +arch_atomic_fetch_inc_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_inc_relaxed(v); +} +#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release +#endif + +#ifndef arch_atomic_fetch_inc +static __always_inline int +arch_atomic_fetch_inc(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_inc_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_inc arch_atomic_fetch_inc +#endif + +#endif /* arch_atomic_fetch_inc_relaxed */ + +#ifndef arch_atomic_dec +static __always_inline void +arch_atomic_dec(atomic_t *v) +{ + arch_atomic_sub(1, v); +} +#define arch_atomic_dec arch_atomic_dec +#endif + +#ifndef arch_atomic_dec_return_relaxed +#ifdef arch_atomic_dec_return +#define arch_atomic_dec_return_acquire arch_atomic_dec_return +#define arch_atomic_dec_return_release arch_atomic_dec_return +#define arch_atomic_dec_return_relaxed arch_atomic_dec_return +#endif /* arch_atomic_dec_return */ + +#ifndef arch_atomic_dec_return +static __always_inline int +arch_atomic_dec_return(atomic_t *v) +{ + return arch_atomic_sub_return(1, v); +} +#define arch_atomic_dec_return arch_atomic_dec_return +#endif + +#ifndef arch_atomic_dec_return_acquire +static __always_inline int +arch_atomic_dec_return_acquire(atomic_t *v) +{ + return arch_atomic_sub_return_acquire(1, v); +} +#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire +#endif + +#ifndef arch_atomic_dec_return_release +static __always_inline int +arch_atomic_dec_return_release(atomic_t *v) +{ + return arch_atomic_sub_return_release(1, v); +} +#define arch_atomic_dec_return_release arch_atomic_dec_return_release +#endif + +#ifndef arch_atomic_dec_return_relaxed +static __always_inline int +arch_atomic_dec_return_relaxed(atomic_t *v) +{ + return arch_atomic_sub_return_relaxed(1, v); +} +#define arch_atomic_dec_return_relaxed arch_atomic_dec_return_relaxed +#endif + +#else /* arch_atomic_dec_return_relaxed */ + +#ifndef arch_atomic_dec_return_acquire +static __always_inline int +arch_atomic_dec_return_acquire(atomic_t *v) +{ + int ret = arch_atomic_dec_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire +#endif + +#ifndef arch_atomic_dec_return_release +static __always_inline int +arch_atomic_dec_return_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_dec_return_relaxed(v); +} +#define arch_atomic_dec_return_release arch_atomic_dec_return_release +#endif + +#ifndef arch_atomic_dec_return +static __always_inline int +arch_atomic_dec_return(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_dec_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_dec_return arch_atomic_dec_return +#endif + +#endif /* arch_atomic_dec_return_relaxed */ + +#ifndef arch_atomic_fetch_dec_relaxed +#ifdef arch_atomic_fetch_dec +#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec +#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec +#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec +#endif /* arch_atomic_fetch_dec */ + +#ifndef arch_atomic_fetch_dec +static __always_inline int +arch_atomic_fetch_dec(atomic_t *v) +{ + return arch_atomic_fetch_sub(1, v); +} +#define arch_atomic_fetch_dec arch_atomic_fetch_dec +#endif + +#ifndef arch_atomic_fetch_dec_acquire +static __always_inline int +arch_atomic_fetch_dec_acquire(atomic_t *v) +{ + return arch_atomic_fetch_sub_acquire(1, v); +} +#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire +#endif + +#ifndef arch_atomic_fetch_dec_release +static __always_inline int +arch_atomic_fetch_dec_release(atomic_t *v) +{ + return arch_atomic_fetch_sub_release(1, v); +} +#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release +#endif + +#ifndef arch_atomic_fetch_dec_relaxed +static __always_inline int +arch_atomic_fetch_dec_relaxed(atomic_t *v) +{ + return arch_atomic_fetch_sub_relaxed(1, v); +} +#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec_relaxed +#endif + +#else /* arch_atomic_fetch_dec_relaxed */ + +#ifndef arch_atomic_fetch_dec_acquire +static __always_inline int +arch_atomic_fetch_dec_acquire(atomic_t *v) +{ + int ret = arch_atomic_fetch_dec_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire +#endif + +#ifndef arch_atomic_fetch_dec_release +static __always_inline int +arch_atomic_fetch_dec_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_dec_relaxed(v); +} +#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release +#endif + +#ifndef arch_atomic_fetch_dec +static __always_inline int +arch_atomic_fetch_dec(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_dec_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_dec arch_atomic_fetch_dec +#endif + +#endif /* arch_atomic_fetch_dec_relaxed */ + +#ifndef arch_atomic_fetch_and_relaxed +#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and +#define arch_atomic_fetch_and_release arch_atomic_fetch_and +#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and +#else /* arch_atomic_fetch_and_relaxed */ + +#ifndef arch_atomic_fetch_and_acquire +static __always_inline int +arch_atomic_fetch_and_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_and_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and_acquire +#endif + +#ifndef arch_atomic_fetch_and_release +static __always_inline int +arch_atomic_fetch_and_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_and_relaxed(i, v); +} +#define arch_atomic_fetch_and_release arch_atomic_fetch_and_release +#endif + +#ifndef arch_atomic_fetch_and +static __always_inline int +arch_atomic_fetch_and(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_and_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_and arch_atomic_fetch_and +#endif + +#endif /* arch_atomic_fetch_and_relaxed */ + +#ifndef arch_atomic_andnot +static __always_inline void +arch_atomic_andnot(int i, atomic_t *v) +{ + arch_atomic_and(~i, v); +} +#define arch_atomic_andnot arch_atomic_andnot +#endif + +#ifndef arch_atomic_fetch_andnot_relaxed +#ifdef arch_atomic_fetch_andnot +#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot +#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot +#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot +#endif /* arch_atomic_fetch_andnot */ + +#ifndef arch_atomic_fetch_andnot +static __always_inline int +arch_atomic_fetch_andnot(int i, atomic_t *v) +{ + return arch_atomic_fetch_and(~i, v); +} +#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot +#endif + +#ifndef arch_atomic_fetch_andnot_acquire +static __always_inline int +arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + return arch_atomic_fetch_and_acquire(~i, v); +} +#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire +#endif + +#ifndef arch_atomic_fetch_andnot_release +static __always_inline int +arch_atomic_fetch_andnot_release(int i, atomic_t *v) +{ + return arch_atomic_fetch_and_release(~i, v); +} +#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release +#endif + +#ifndef arch_atomic_fetch_andnot_relaxed +static __always_inline int +arch_atomic_fetch_andnot_relaxed(int i, atomic_t *v) +{ + return arch_atomic_fetch_and_relaxed(~i, v); +} +#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed +#endif + +#else /* arch_atomic_fetch_andnot_relaxed */ + +#ifndef arch_atomic_fetch_andnot_acquire +static __always_inline int +arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_andnot_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire +#endif + +#ifndef arch_atomic_fetch_andnot_release +static __always_inline int +arch_atomic_fetch_andnot_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_andnot_relaxed(i, v); +} +#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release +#endif + +#ifndef arch_atomic_fetch_andnot +static __always_inline int +arch_atomic_fetch_andnot(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_andnot_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot +#endif + +#endif /* arch_atomic_fetch_andnot_relaxed */ + +#ifndef arch_atomic_fetch_or_relaxed +#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or +#define arch_atomic_fetch_or_release arch_atomic_fetch_or +#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or +#else /* arch_atomic_fetch_or_relaxed */ + +#ifndef arch_atomic_fetch_or_acquire +static __always_inline int +arch_atomic_fetch_or_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_or_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or_acquire +#endif + +#ifndef arch_atomic_fetch_or_release +static __always_inline int +arch_atomic_fetch_or_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_or_relaxed(i, v); +} +#define arch_atomic_fetch_or_release arch_atomic_fetch_or_release +#endif + +#ifndef arch_atomic_fetch_or +static __always_inline int +arch_atomic_fetch_or(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_or_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_or arch_atomic_fetch_or +#endif + +#endif /* arch_atomic_fetch_or_relaxed */ + +#ifndef arch_atomic_fetch_xor_relaxed +#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor +#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor +#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor +#else /* arch_atomic_fetch_xor_relaxed */ + +#ifndef arch_atomic_fetch_xor_acquire +static __always_inline int +arch_atomic_fetch_xor_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_xor_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor_acquire +#endif + +#ifndef arch_atomic_fetch_xor_release +static __always_inline int +arch_atomic_fetch_xor_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_xor_relaxed(i, v); +} +#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor_release +#endif + +#ifndef arch_atomic_fetch_xor +static __always_inline int +arch_atomic_fetch_xor(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_xor_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_xor arch_atomic_fetch_xor +#endif + +#endif /* arch_atomic_fetch_xor_relaxed */ + +#ifndef arch_atomic_xchg_relaxed +#define arch_atomic_xchg_acquire arch_atomic_xchg +#define arch_atomic_xchg_release arch_atomic_xchg +#define arch_atomic_xchg_relaxed arch_atomic_xchg +#else /* arch_atomic_xchg_relaxed */ + +#ifndef arch_atomic_xchg_acquire +static __always_inline int +arch_atomic_xchg_acquire(atomic_t *v, int i) +{ + int ret = arch_atomic_xchg_relaxed(v, i); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_xchg_acquire arch_atomic_xchg_acquire +#endif + +#ifndef arch_atomic_xchg_release +static __always_inline int +arch_atomic_xchg_release(atomic_t *v, int i) +{ + __atomic_release_fence(); + return arch_atomic_xchg_relaxed(v, i); +} +#define arch_atomic_xchg_release arch_atomic_xchg_release +#endif + +#ifndef arch_atomic_xchg +static __always_inline int +arch_atomic_xchg(atomic_t *v, int i) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_xchg_relaxed(v, i); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_xchg arch_atomic_xchg +#endif + +#endif /* arch_atomic_xchg_relaxed */ + +#ifndef arch_atomic_cmpxchg_relaxed +#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg +#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg +#define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg +#else /* arch_atomic_cmpxchg_relaxed */ + +#ifndef arch_atomic_cmpxchg_acquire +static __always_inline int +arch_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) +{ + int ret = arch_atomic_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire +#endif + +#ifndef arch_atomic_cmpxchg_release +static __always_inline int +arch_atomic_cmpxchg_release(atomic_t *v, int old, int new) +{ + __atomic_release_fence(); + return arch_atomic_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg_release +#endif + +#ifndef arch_atomic_cmpxchg +static __always_inline int +arch_atomic_cmpxchg(atomic_t *v, int old, int new) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_cmpxchg arch_atomic_cmpxchg +#endif + +#endif /* arch_atomic_cmpxchg_relaxed */ + +#ifndef arch_atomic_try_cmpxchg_relaxed +#ifdef arch_atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg +#endif /* arch_atomic_try_cmpxchg */ + +#ifndef arch_atomic_try_cmpxchg +static __always_inline bool +arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg +#endif + +#ifndef arch_atomic_try_cmpxchg_acquire +static __always_inline bool +arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg_acquire(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic_try_cmpxchg_release +static __always_inline bool +arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg_release(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release +#endif + +#ifndef arch_atomic_try_cmpxchg_relaxed +static __always_inline bool +arch_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg_relaxed(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg_relaxed +#endif + +#else /* arch_atomic_try_cmpxchg_relaxed */ + +#ifndef arch_atomic_try_cmpxchg_acquire +static __always_inline bool +arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic_try_cmpxchg_release +static __always_inline bool +arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + __atomic_release_fence(); + return arch_atomic_try_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release +#endif + +#ifndef arch_atomic_try_cmpxchg +static __always_inline bool +arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + bool ret; + __atomic_pre_full_fence(); + ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg +#endif + +#endif /* arch_atomic_try_cmpxchg_relaxed */ + +#ifndef arch_atomic_sub_and_test +/** + * arch_atomic_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic_sub_and_test(int i, atomic_t *v) +{ + return arch_atomic_sub_return(i, v) == 0; +} +#define arch_atomic_sub_and_test arch_atomic_sub_and_test +#endif + +#ifndef arch_atomic_dec_and_test +/** + * arch_atomic_dec_and_test - decrement and test + * @v: pointer of type atomic_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static __always_inline bool +arch_atomic_dec_and_test(atomic_t *v) +{ + return arch_atomic_dec_return(v) == 0; +} +#define arch_atomic_dec_and_test arch_atomic_dec_and_test +#endif + +#ifndef arch_atomic_inc_and_test +/** + * arch_atomic_inc_and_test - increment and test + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic_inc_and_test(atomic_t *v) +{ + return arch_atomic_inc_return(v) == 0; +} +#define arch_atomic_inc_and_test arch_atomic_inc_and_test +#endif + +#ifndef arch_atomic_add_negative +/** + * arch_atomic_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic_add_negative(int i, atomic_t *v) +{ + return arch_atomic_add_return(i, v) < 0; +} +#define arch_atomic_add_negative arch_atomic_add_negative +#endif + +#ifndef arch_atomic_fetch_add_unless +/** + * arch_atomic_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as @v was not already @u. + * Returns original value of @v + */ +static __always_inline int +arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + int c = arch_atomic_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); + + return c; +} +#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless +#endif + +#ifndef arch_atomic_add_unless +/** + * arch_atomic_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +static __always_inline bool +arch_atomic_add_unless(atomic_t *v, int a, int u) +{ + return arch_atomic_fetch_add_unless(v, a, u) != u; +} +#define arch_atomic_add_unless arch_atomic_add_unless +#endif + +#ifndef arch_atomic_inc_not_zero +/** + * arch_atomic_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +static __always_inline bool +arch_atomic_inc_not_zero(atomic_t *v) +{ + return arch_atomic_add_unless(v, 1, 0); +} +#define arch_atomic_inc_not_zero arch_atomic_inc_not_zero +#endif + +#ifndef arch_atomic_inc_unless_negative +static __always_inline bool +arch_atomic_inc_unless_negative(atomic_t *v) +{ + int c = arch_atomic_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!arch_atomic_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative +#endif + +#ifndef arch_atomic_dec_unless_positive +static __always_inline bool +arch_atomic_dec_unless_positive(atomic_t *v) +{ + int c = arch_atomic_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!arch_atomic_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive +#endif + +#ifndef arch_atomic_dec_if_positive +static __always_inline int +arch_atomic_dec_if_positive(atomic_t *v) +{ + int dec, c = arch_atomic_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!arch_atomic_try_cmpxchg(v, &c, dec)); + + return dec; +} +#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive +#endif + +#ifdef CONFIG_GENERIC_ATOMIC64 +#include +#endif + +#ifndef arch_atomic64_read_acquire +static __always_inline s64 +arch_atomic64_read_acquire(const atomic64_t *v) +{ + return smp_load_acquire(&(v)->counter); +} +#define arch_atomic64_read_acquire arch_atomic64_read_acquire +#endif + +#ifndef arch_atomic64_set_release +static __always_inline void +arch_atomic64_set_release(atomic64_t *v, s64 i) +{ + smp_store_release(&(v)->counter, i); +} +#define arch_atomic64_set_release arch_atomic64_set_release +#endif + +#ifndef arch_atomic64_add_return_relaxed +#define arch_atomic64_add_return_acquire arch_atomic64_add_return +#define arch_atomic64_add_return_release arch_atomic64_add_return +#define arch_atomic64_add_return_relaxed arch_atomic64_add_return +#else /* arch_atomic64_add_return_relaxed */ + +#ifndef arch_atomic64_add_return_acquire +static __always_inline s64 +arch_atomic64_add_return_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_add_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_add_return_acquire arch_atomic64_add_return_acquire +#endif + +#ifndef arch_atomic64_add_return_release +static __always_inline s64 +arch_atomic64_add_return_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_add_return_relaxed(i, v); +} +#define arch_atomic64_add_return_release arch_atomic64_add_return_release +#endif + +#ifndef arch_atomic64_add_return +static __always_inline s64 +arch_atomic64_add_return(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_add_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_add_return arch_atomic64_add_return +#endif + +#endif /* arch_atomic64_add_return_relaxed */ + +#ifndef arch_atomic64_fetch_add_relaxed +#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add +#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add +#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add +#else /* arch_atomic64_fetch_add_relaxed */ + +#ifndef arch_atomic64_fetch_add_acquire +static __always_inline s64 +arch_atomic64_fetch_add_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_add_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add_acquire +#endif + +#ifndef arch_atomic64_fetch_add_release +static __always_inline s64 +arch_atomic64_fetch_add_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_add_relaxed(i, v); +} +#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add_release +#endif + +#ifndef arch_atomic64_fetch_add +static __always_inline s64 +arch_atomic64_fetch_add(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_add_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_add arch_atomic64_fetch_add +#endif + +#endif /* arch_atomic64_fetch_add_relaxed */ + +#ifndef arch_atomic64_sub_return_relaxed +#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return +#define arch_atomic64_sub_return_release arch_atomic64_sub_return +#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return +#else /* arch_atomic64_sub_return_relaxed */ + +#ifndef arch_atomic64_sub_return_acquire +static __always_inline s64 +arch_atomic64_sub_return_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_sub_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return_acquire +#endif + +#ifndef arch_atomic64_sub_return_release +static __always_inline s64 +arch_atomic64_sub_return_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_sub_return_relaxed(i, v); +} +#define arch_atomic64_sub_return_release arch_atomic64_sub_return_release +#endif + +#ifndef arch_atomic64_sub_return +static __always_inline s64 +arch_atomic64_sub_return(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_sub_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_sub_return arch_atomic64_sub_return +#endif + +#endif /* arch_atomic64_sub_return_relaxed */ + +#ifndef arch_atomic64_fetch_sub_relaxed +#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub +#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub +#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub +#else /* arch_atomic64_fetch_sub_relaxed */ + +#ifndef arch_atomic64_fetch_sub_acquire +static __always_inline s64 +arch_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_sub_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub_acquire +#endif + +#ifndef arch_atomic64_fetch_sub_release +static __always_inline s64 +arch_atomic64_fetch_sub_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_sub_relaxed(i, v); +} +#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub_release +#endif + +#ifndef arch_atomic64_fetch_sub +static __always_inline s64 +arch_atomic64_fetch_sub(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_sub_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub +#endif + +#endif /* arch_atomic64_fetch_sub_relaxed */ + +#ifndef arch_atomic64_inc +static __always_inline void +arch_atomic64_inc(atomic64_t *v) +{ + arch_atomic64_add(1, v); +} +#define arch_atomic64_inc arch_atomic64_inc +#endif + +#ifndef arch_atomic64_inc_return_relaxed +#ifdef arch_atomic64_inc_return +#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return +#define arch_atomic64_inc_return_release arch_atomic64_inc_return +#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return +#endif /* arch_atomic64_inc_return */ + +#ifndef arch_atomic64_inc_return +static __always_inline s64 +arch_atomic64_inc_return(atomic64_t *v) +{ + return arch_atomic64_add_return(1, v); +} +#define arch_atomic64_inc_return arch_atomic64_inc_return +#endif + +#ifndef arch_atomic64_inc_return_acquire +static __always_inline s64 +arch_atomic64_inc_return_acquire(atomic64_t *v) +{ + return arch_atomic64_add_return_acquire(1, v); +} +#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire +#endif + +#ifndef arch_atomic64_inc_return_release +static __always_inline s64 +arch_atomic64_inc_return_release(atomic64_t *v) +{ + return arch_atomic64_add_return_release(1, v); +} +#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release +#endif + +#ifndef arch_atomic64_inc_return_relaxed +static __always_inline s64 +arch_atomic64_inc_return_relaxed(atomic64_t *v) +{ + return arch_atomic64_add_return_relaxed(1, v); +} +#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed +#endif + +#else /* arch_atomic64_inc_return_relaxed */ + +#ifndef arch_atomic64_inc_return_acquire +static __always_inline s64 +arch_atomic64_inc_return_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_inc_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire +#endif + +#ifndef arch_atomic64_inc_return_release +static __always_inline s64 +arch_atomic64_inc_return_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_inc_return_relaxed(v); +} +#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release +#endif + +#ifndef arch_atomic64_inc_return +static __always_inline s64 +arch_atomic64_inc_return(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_inc_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_inc_return arch_atomic64_inc_return +#endif + +#endif /* arch_atomic64_inc_return_relaxed */ + +#ifndef arch_atomic64_fetch_inc_relaxed +#ifdef arch_atomic64_fetch_inc +#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc +#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc +#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc +#endif /* arch_atomic64_fetch_inc */ + +#ifndef arch_atomic64_fetch_inc +static __always_inline s64 +arch_atomic64_fetch_inc(atomic64_t *v) +{ + return arch_atomic64_fetch_add(1, v); +} +#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc +#endif + +#ifndef arch_atomic64_fetch_inc_acquire +static __always_inline s64 +arch_atomic64_fetch_inc_acquire(atomic64_t *v) +{ + return arch_atomic64_fetch_add_acquire(1, v); +} +#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire +#endif + +#ifndef arch_atomic64_fetch_inc_release +static __always_inline s64 +arch_atomic64_fetch_inc_release(atomic64_t *v) +{ + return arch_atomic64_fetch_add_release(1, v); +} +#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release +#endif + +#ifndef arch_atomic64_fetch_inc_relaxed +static __always_inline s64 +arch_atomic64_fetch_inc_relaxed(atomic64_t *v) +{ + return arch_atomic64_fetch_add_relaxed(1, v); +} +#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc_relaxed +#endif + +#else /* arch_atomic64_fetch_inc_relaxed */ + +#ifndef arch_atomic64_fetch_inc_acquire +static __always_inline s64 +arch_atomic64_fetch_inc_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_inc_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire +#endif + +#ifndef arch_atomic64_fetch_inc_release +static __always_inline s64 +arch_atomic64_fetch_inc_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_inc_relaxed(v); +} +#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release +#endif + +#ifndef arch_atomic64_fetch_inc +static __always_inline s64 +arch_atomic64_fetch_inc(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_inc_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc +#endif + +#endif /* arch_atomic64_fetch_inc_relaxed */ + +#ifndef arch_atomic64_dec +static __always_inline void +arch_atomic64_dec(atomic64_t *v) +{ + arch_atomic64_sub(1, v); +} +#define arch_atomic64_dec arch_atomic64_dec +#endif + +#ifndef arch_atomic64_dec_return_relaxed +#ifdef arch_atomic64_dec_return +#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return +#define arch_atomic64_dec_return_release arch_atomic64_dec_return +#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return +#endif /* arch_atomic64_dec_return */ + +#ifndef arch_atomic64_dec_return +static __always_inline s64 +arch_atomic64_dec_return(atomic64_t *v) +{ + return arch_atomic64_sub_return(1, v); +} +#define arch_atomic64_dec_return arch_atomic64_dec_return +#endif + +#ifndef arch_atomic64_dec_return_acquire +static __always_inline s64 +arch_atomic64_dec_return_acquire(atomic64_t *v) +{ + return arch_atomic64_sub_return_acquire(1, v); +} +#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire +#endif + +#ifndef arch_atomic64_dec_return_release +static __always_inline s64 +arch_atomic64_dec_return_release(atomic64_t *v) +{ + return arch_atomic64_sub_return_release(1, v); +} +#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release +#endif + +#ifndef arch_atomic64_dec_return_relaxed +static __always_inline s64 +arch_atomic64_dec_return_relaxed(atomic64_t *v) +{ + return arch_atomic64_sub_return_relaxed(1, v); +} +#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed +#endif + +#else /* arch_atomic64_dec_return_relaxed */ + +#ifndef arch_atomic64_dec_return_acquire +static __always_inline s64 +arch_atomic64_dec_return_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_dec_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire +#endif + +#ifndef arch_atomic64_dec_return_release +static __always_inline s64 +arch_atomic64_dec_return_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_dec_return_relaxed(v); +} +#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release +#endif + +#ifndef arch_atomic64_dec_return +static __always_inline s64 +arch_atomic64_dec_return(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_dec_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_dec_return arch_atomic64_dec_return +#endif + +#endif /* arch_atomic64_dec_return_relaxed */ + +#ifndef arch_atomic64_fetch_dec_relaxed +#ifdef arch_atomic64_fetch_dec +#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec +#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec +#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec +#endif /* arch_atomic64_fetch_dec */ + +#ifndef arch_atomic64_fetch_dec +static __always_inline s64 +arch_atomic64_fetch_dec(atomic64_t *v) +{ + return arch_atomic64_fetch_sub(1, v); +} +#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec +#endif + +#ifndef arch_atomic64_fetch_dec_acquire +static __always_inline s64 +arch_atomic64_fetch_dec_acquire(atomic64_t *v) +{ + return arch_atomic64_fetch_sub_acquire(1, v); +} +#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire +#endif + +#ifndef arch_atomic64_fetch_dec_release +static __always_inline s64 +arch_atomic64_fetch_dec_release(atomic64_t *v) +{ + return arch_atomic64_fetch_sub_release(1, v); +} +#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release +#endif + +#ifndef arch_atomic64_fetch_dec_relaxed +static __always_inline s64 +arch_atomic64_fetch_dec_relaxed(atomic64_t *v) +{ + return arch_atomic64_fetch_sub_relaxed(1, v); +} +#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec_relaxed +#endif + +#else /* arch_atomic64_fetch_dec_relaxed */ + +#ifndef arch_atomic64_fetch_dec_acquire +static __always_inline s64 +arch_atomic64_fetch_dec_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_dec_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire +#endif + +#ifndef arch_atomic64_fetch_dec_release +static __always_inline s64 +arch_atomic64_fetch_dec_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_dec_relaxed(v); +} +#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release +#endif + +#ifndef arch_atomic64_fetch_dec +static __always_inline s64 +arch_atomic64_fetch_dec(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_dec_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec +#endif + +#endif /* arch_atomic64_fetch_dec_relaxed */ + +#ifndef arch_atomic64_fetch_and_relaxed +#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and +#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and +#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and +#else /* arch_atomic64_fetch_and_relaxed */ + +#ifndef arch_atomic64_fetch_and_acquire +static __always_inline s64 +arch_atomic64_fetch_and_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_and_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and_acquire +#endif + +#ifndef arch_atomic64_fetch_and_release +static __always_inline s64 +arch_atomic64_fetch_and_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_and_relaxed(i, v); +} +#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and_release +#endif + +#ifndef arch_atomic64_fetch_and +static __always_inline s64 +arch_atomic64_fetch_and(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_and_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_and arch_atomic64_fetch_and +#endif + +#endif /* arch_atomic64_fetch_and_relaxed */ + +#ifndef arch_atomic64_andnot +static __always_inline void +arch_atomic64_andnot(s64 i, atomic64_t *v) +{ + arch_atomic64_and(~i, v); +} +#define arch_atomic64_andnot arch_atomic64_andnot +#endif + +#ifndef arch_atomic64_fetch_andnot_relaxed +#ifdef arch_atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot +#endif /* arch_atomic64_fetch_andnot */ + +#ifndef arch_atomic64_fetch_andnot +static __always_inline s64 +arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and(~i, v); +} +#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot +#endif + +#ifndef arch_atomic64_fetch_andnot_acquire +static __always_inline s64 +arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and_acquire(~i, v); +} +#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire +#endif + +#ifndef arch_atomic64_fetch_andnot_release +static __always_inline s64 +arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and_release(~i, v); +} +#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release +#endif + +#ifndef arch_atomic64_fetch_andnot_relaxed +static __always_inline s64 +arch_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and_relaxed(~i, v); +} +#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed +#endif + +#else /* arch_atomic64_fetch_andnot_relaxed */ + +#ifndef arch_atomic64_fetch_andnot_acquire +static __always_inline s64 +arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire +#endif + +#ifndef arch_atomic64_fetch_andnot_release +static __always_inline s64 +arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_andnot_relaxed(i, v); +} +#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release +#endif + +#ifndef arch_atomic64_fetch_andnot +static __always_inline s64 +arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_andnot_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot +#endif + +#endif /* arch_atomic64_fetch_andnot_relaxed */ + +#ifndef arch_atomic64_fetch_or_relaxed +#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or +#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or +#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or +#else /* arch_atomic64_fetch_or_relaxed */ + +#ifndef arch_atomic64_fetch_or_acquire +static __always_inline s64 +arch_atomic64_fetch_or_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_or_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or_acquire +#endif + +#ifndef arch_atomic64_fetch_or_release +static __always_inline s64 +arch_atomic64_fetch_or_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_or_relaxed(i, v); +} +#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or_release +#endif + +#ifndef arch_atomic64_fetch_or +static __always_inline s64 +arch_atomic64_fetch_or(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_or_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_or arch_atomic64_fetch_or +#endif + +#endif /* arch_atomic64_fetch_or_relaxed */ + +#ifndef arch_atomic64_fetch_xor_relaxed +#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor +#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor +#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor +#else /* arch_atomic64_fetch_xor_relaxed */ + +#ifndef arch_atomic64_fetch_xor_acquire +static __always_inline s64 +arch_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_xor_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor_acquire +#endif + +#ifndef arch_atomic64_fetch_xor_release +static __always_inline s64 +arch_atomic64_fetch_xor_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_xor_relaxed(i, v); +} +#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor_release +#endif + +#ifndef arch_atomic64_fetch_xor +static __always_inline s64 +arch_atomic64_fetch_xor(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_xor_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor +#endif + +#endif /* arch_atomic64_fetch_xor_relaxed */ + +#ifndef arch_atomic64_xchg_relaxed +#define arch_atomic64_xchg_acquire arch_atomic64_xchg +#define arch_atomic64_xchg_release arch_atomic64_xchg +#define arch_atomic64_xchg_relaxed arch_atomic64_xchg +#else /* arch_atomic64_xchg_relaxed */ + +#ifndef arch_atomic64_xchg_acquire +static __always_inline s64 +arch_atomic64_xchg_acquire(atomic64_t *v, s64 i) +{ + s64 ret = arch_atomic64_xchg_relaxed(v, i); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_xchg_acquire arch_atomic64_xchg_acquire +#endif + +#ifndef arch_atomic64_xchg_release +static __always_inline s64 +arch_atomic64_xchg_release(atomic64_t *v, s64 i) +{ + __atomic_release_fence(); + return arch_atomic64_xchg_relaxed(v, i); +} +#define arch_atomic64_xchg_release arch_atomic64_xchg_release +#endif + +#ifndef arch_atomic64_xchg +static __always_inline s64 +arch_atomic64_xchg(atomic64_t *v, s64 i) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_xchg_relaxed(v, i); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_xchg arch_atomic64_xchg +#endif + +#endif /* arch_atomic64_xchg_relaxed */ + +#ifndef arch_atomic64_cmpxchg_relaxed +#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg +#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg +#define arch_atomic64_cmpxchg_relaxed arch_atomic64_cmpxchg +#else /* arch_atomic64_cmpxchg_relaxed */ + +#ifndef arch_atomic64_cmpxchg_acquire +static __always_inline s64 +arch_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) +{ + s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg_acquire +#endif + +#ifndef arch_atomic64_cmpxchg_release +static __always_inline s64 +arch_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) +{ + __atomic_release_fence(); + return arch_atomic64_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg_release +#endif + +#ifndef arch_atomic64_cmpxchg +static __always_inline s64 +arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg +#endif + +#endif /* arch_atomic64_cmpxchg_relaxed */ + +#ifndef arch_atomic64_try_cmpxchg_relaxed +#ifdef arch_atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg +#endif /* arch_atomic64_try_cmpxchg */ + +#ifndef arch_atomic64_try_cmpxchg +static __always_inline bool +arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg +#endif + +#ifndef arch_atomic64_try_cmpxchg_acquire +static __always_inline bool +arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg_acquire(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic64_try_cmpxchg_release +static __always_inline bool +arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg_release(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release +#endif + +#ifndef arch_atomic64_try_cmpxchg_relaxed +static __always_inline bool +arch_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg_relaxed(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg_relaxed +#endif + +#else /* arch_atomic64_try_cmpxchg_relaxed */ + +#ifndef arch_atomic64_try_cmpxchg_acquire +static __always_inline bool +arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) +{ + bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic64_try_cmpxchg_release +static __always_inline bool +arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) +{ + __atomic_release_fence(); + return arch_atomic64_try_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release +#endif + +#ifndef arch_atomic64_try_cmpxchg +static __always_inline bool +arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + bool ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg +#endif + +#endif /* arch_atomic64_try_cmpxchg_relaxed */ + +#ifndef arch_atomic64_sub_and_test +/** + * arch_atomic64_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic64_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic64_sub_and_test(s64 i, atomic64_t *v) +{ + return arch_atomic64_sub_return(i, v) == 0; +} +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test +#endif + +#ifndef arch_atomic64_dec_and_test +/** + * arch_atomic64_dec_and_test - decrement and test + * @v: pointer of type atomic64_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static __always_inline bool +arch_atomic64_dec_and_test(atomic64_t *v) +{ + return arch_atomic64_dec_return(v) == 0; +} +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test +#endif + +#ifndef arch_atomic64_inc_and_test +/** + * arch_atomic64_inc_and_test - increment and test + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic64_inc_and_test(atomic64_t *v) +{ + return arch_atomic64_inc_return(v) == 0; +} +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test +#endif + +#ifndef arch_atomic64_add_negative +/** + * arch_atomic64_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic64_add_negative(s64 i, atomic64_t *v) +{ + return arch_atomic64_add_return(i, v) < 0; +} +#define arch_atomic64_add_negative arch_atomic64_add_negative +#endif + +#ifndef arch_atomic64_fetch_add_unless +/** + * arch_atomic64_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as @v was not already @u. + * Returns original value of @v + */ +static __always_inline s64 +arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +{ + s64 c = arch_atomic64_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); + + return c; +} +#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless +#endif + +#ifndef arch_atomic64_add_unless +/** + * arch_atomic64_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +static __always_inline bool +arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) +{ + return arch_atomic64_fetch_add_unless(v, a, u) != u; +} +#define arch_atomic64_add_unless arch_atomic64_add_unless +#endif + +#ifndef arch_atomic64_inc_not_zero +/** + * arch_atomic64_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +static __always_inline bool +arch_atomic64_inc_not_zero(atomic64_t *v) +{ + return arch_atomic64_add_unless(v, 1, 0); +} +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero +#endif + +#ifndef arch_atomic64_inc_unless_negative +static __always_inline bool +arch_atomic64_inc_unless_negative(atomic64_t *v) +{ + s64 c = arch_atomic64_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!arch_atomic64_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative +#endif + +#ifndef arch_atomic64_dec_unless_positive +static __always_inline bool +arch_atomic64_dec_unless_positive(atomic64_t *v) +{ + s64 c = arch_atomic64_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!arch_atomic64_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive +#endif + +#ifndef arch_atomic64_dec_if_positive +static __always_inline s64 +arch_atomic64_dec_if_positive(atomic64_t *v) +{ + s64 dec, c = arch_atomic64_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); + + return dec; +} +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive +#endif + +#endif /* _LINUX_ATOMIC_FALLBACK_H */ +// 90cd26cfd69d2250303d654955a0cc12620fb91b diff --git a/include/linux/atomic-fallback.h b/include/linux/atomic-fallback.h index 656b5489b673..2c4927bf7b8d 100644 --- a/include/linux/atomic-fallback.h +++ b/include/linux/atomic-fallback.h @@ -1180,9 +1180,6 @@ atomic_dec_if_positive(atomic_t *v) #define atomic_dec_if_positive atomic_dec_if_positive #endif -#define atomic_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) -#define atomic_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) - #ifdef CONFIG_GENERIC_ATOMIC64 #include #endif @@ -2290,8 +2287,5 @@ atomic64_dec_if_positive(atomic64_t *v) #define atomic64_dec_if_positive atomic64_dec_if_positive #endif -#define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) -#define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) - #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// baaf45f4c24ed88ceae58baca39d7fd80bb8101b +// 1fac0941c79bf0ae100723cc2ac9b94061f0b67a diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 4c0d009a46f0..571a11008ab5 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -25,6 +25,12 @@ * See Documentation/memory-barriers.txt for ACQUIRE/RELEASE definitions. */ +#define atomic_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) +#define atomic_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) + +#define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c)) +#define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c)) + /* * The idea here is to build acquire/release variants by adding explicit * barriers on top of the relaxed variant. In the case where the relaxed @@ -71,7 +77,12 @@ __ret; \ }) +#ifdef ARCH_ATOMIC +#include +#include +#else #include +#endif #include -- cgit v1.2.3 From 0372007f5a79d61d3cb48a507717b9afb5d6addd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 4 Mar 2020 11:05:22 +0100 Subject: context_tracking: Ensure that the critical path cannot be instrumented context tracking lacks a few protection mechanisms against instrumentation: - While the core functions are marked NOKPROBE they lack protection against function tracing which is required as the function entry/exit points can be utilized by BPF. - static functions invoked from the protected functions need to be marked as well as they can be instrumented otherwise. - using plain inline allows the compiler to emit traceable and probable functions. Fix this by marking the functions noinstr and converting the plain inlines to __always_inline. The NOKPROBE_SYMBOL() annotations are removed as the .noinstr.text section is already excluded from being probed. Cures the following objtool warnings: vmlinux.o: warning: objtool: enter_from_user_mode()+0x34: call to __context_tracking_exit() leaves .noinstr.text section vmlinux.o: warning: objtool: prepare_exit_to_usermode()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_return_slowpath()+0x29: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_syscall_64()+0x7f: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_int80_syscall_32()+0x3d: call to __context_tracking_enter() leaves .noinstr.text section vmlinux.o: warning: objtool: do_fast_syscall_32()+0x9c: call to __context_tracking_enter() leaves .noinstr.text section and generates new ones... Signed-off-by: Thomas Gleixner Reviewed-by: Masami Hiramatsu Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Link: https://lkml.kernel.org/r/20200505134340.811520478@linutronix.de --- include/linux/context_tracking.h | 6 +++--- include/linux/context_tracking_state.h | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 8cac62ee6add..981b880d5b60 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -33,13 +33,13 @@ static inline void user_exit(void) } /* Called with interrupts disabled. */ -static inline void user_enter_irqoff(void) +static __always_inline void user_enter_irqoff(void) { if (context_tracking_enabled()) __context_tracking_enter(CONTEXT_USER); } -static inline void user_exit_irqoff(void) +static __always_inline void user_exit_irqoff(void) { if (context_tracking_enabled()) __context_tracking_exit(CONTEXT_USER); @@ -75,7 +75,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) * is enabled. If context tracking is disabled, returns * CONTEXT_DISABLED. This should be used primarily for debugging. */ -static inline enum ctx_state ct_state(void) +static __always_inline enum ctx_state ct_state(void) { return context_tracking_enabled() ? this_cpu_read(context_tracking.state) : CONTEXT_DISABLED; diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index e7fe6678b7ad..65a60d3313b0 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -26,12 +26,12 @@ struct context_tracking { extern struct static_key_false context_tracking_key; DECLARE_PER_CPU(struct context_tracking, context_tracking); -static inline bool context_tracking_enabled(void) +static __always_inline bool context_tracking_enabled(void) { return static_branch_unlikely(&context_tracking_key); } -static inline bool context_tracking_enabled_cpu(int cpu) +static __always_inline bool context_tracking_enabled_cpu(int cpu) { return context_tracking_enabled() && per_cpu(context_tracking.active, cpu); } @@ -41,7 +41,7 @@ static inline bool context_tracking_enabled_this_cpu(void) return context_tracking_enabled() && __this_cpu_read(context_tracking.active); } -static inline bool context_tracking_in_user(void) +static __always_inline bool context_tracking_in_user(void) { return __this_cpu_read(context_tracking.state) == CONTEXT_USER; } -- cgit v1.2.3 From df65bba1dcd8ffadd922a71196b78c6d7630c33b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 Feb 2020 18:25:09 +0100 Subject: lib/bsearch: Provide __always_inline variant For code that needs the ultimate performance (it can inline the @cmp function too) or simply needs to avoid calling external functions for whatever reason, provide an __always_inline variant of bsearch(). [ tglx: Renamed to __inline_bsearch() as suggested by Andy ] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Andy Lutomirski Link: https://lkml.kernel.org/r/20200505135313.624443814@linutronix.de --- include/linux/bsearch.h | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bsearch.h b/include/linux/bsearch.h index 8ed53d7524ea..e66b711d091e 100644 --- a/include/linux/bsearch.h +++ b/include/linux/bsearch.h @@ -4,7 +4,29 @@ #include -void *bsearch(const void *key, const void *base, size_t num, size_t size, - cmp_func_t cmp); +static __always_inline +void *__inline_bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) +{ + const char *pivot; + int result; + + while (num > 0) { + pivot = base + (num >> 1) * size; + result = cmp(key, pivot); + + if (result == 0) + return (void *)pivot; + + if (result > 0) { + base = pivot + size; + num--; + } + num >>= 1; + } + + return NULL; +} + +extern void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp); #endif /* _LINUX_BSEARCH_H */ -- cgit v1.2.3 From 2ab70319bc1f79228da4dce7b9d604740c9beeef Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 May 2020 22:05:14 +0200 Subject: nmi, tracing: Make hardware latency tracing noinstr safe The hardware latency tracer calls into instrumentable functions. Move the calls into the RCU watching sections and annotate them. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Acked-by: Andy Lutomirski Cc: Paul E. McKenney Link: https://lore.kernel.org/r/20200521202116.904176298@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/hardirq.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index e07cf853aa16..29b862aba740 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -87,20 +87,24 @@ extern void rcu_nmi_exit(void); arch_nmi_enter(); \ printk_nmi_enter(); \ lockdep_off(); \ - ftrace_nmi_enter(); \ BUG_ON(in_nmi() == NMI_MASK); \ __preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ rcu_nmi_enter(); \ lockdep_hardirq_enter(); \ + instrumentation_begin(); \ + ftrace_nmi_enter(); \ + instrumentation_end(); \ } while (0) #define nmi_exit() \ do { \ + instrumentation_begin(); \ + ftrace_nmi_exit(); \ + instrumentation_end(); \ lockdep_hardirq_exit(); \ rcu_nmi_exit(); \ BUG_ON(!in_nmi()); \ __preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ - ftrace_nmi_exit(); \ lockdep_on(); \ printk_nmi_exit(); \ arch_nmi_exit(); \ -- cgit v1.2.3 From 8a6bc4787f05d087fda8e11ead225c8830250703 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 May 2020 22:05:21 +0200 Subject: genirq: Provide irq_enter/exit_rcu() irq_enter()/exit() currently include RCU handling. To properly separate the RCU handling code, provide variants which contain only the non-RCU related functionality. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Reviewed-by: Andy Lutomirski Link: https://lore.kernel.org/r/20200521202117.567023613@linutronix.de --- include/linux/hardirq.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 29b862aba740..3dc9102d16cf 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -40,7 +40,11 @@ static __always_inline void rcu_irq_enter_check_tick(void) /* * Enter irq context (on NO_HZ, update jiffies): */ -extern void irq_enter(void); +void irq_enter(void); +/* + * Like irq_enter(), but RCU is already watching. + */ +void irq_enter_rcu(void); /* * Exit irq context without processing softirqs: @@ -55,7 +59,12 @@ extern void irq_enter(void); /* * Exit irq context and process softirqs if needed: */ -extern void irq_exit(void); +void irq_exit(void); + +/* + * Like irq_exit(), but return with RCU watching. + */ +void irq_exit_rcu(void); #ifndef arch_nmi_enter #define arch_nmi_enter() do { } while (0) -- cgit v1.2.3 From 98a3bf195e1a14755da3d2b83e1dbb4a3158866d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 May 2020 22:05:22 +0200 Subject: genirq: Provide __irq_enter/exit_raw() Like __irq_enter/exit() but without time accounting. To be used for "empty" system vectors like the scheduler IPI to avoid the overhead. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Reviewed-by: Andy Lutomirski Link: https://lore.kernel.org/r/20200521202117.671682341@linutronix.de --- include/linux/hardirq.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 3dc9102d16cf..03c9fece7d43 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -37,6 +37,17 @@ static __always_inline void rcu_irq_enter_check_tick(void) lockdep_hardirq_enter(); \ } while (0) +/* + * Like __irq_enter() without time accounting for fast + * interrupts, e.g. reschedule IPI where time accounting + * is more expensive than the actual interrupt. + */ +#define __irq_enter_raw() \ + do { \ + preempt_count_add(HARDIRQ_OFFSET); \ + lockdep_hardirq_enter(); \ + } while (0) + /* * Enter irq context (on NO_HZ, update jiffies): */ @@ -56,6 +67,15 @@ void irq_enter_rcu(void); preempt_count_sub(HARDIRQ_OFFSET); \ } while (0) +/* + * Like __irq_exit() without time accounting + */ +#define __irq_exit_raw() \ + do { \ + lockdep_hardirq_exit(); \ + preempt_count_sub(HARDIRQ_OFFSET); \ + } while (0) + /* * Exit irq context and process softirqs if needed: */ -- cgit v1.2.3 From bf2b3008440072068580c609d79a079656af0588 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 29 May 2020 23:27:40 +0200 Subject: x86/entry: Rename trace_hardirqs_off_prepare() The typical pattern for trace_hardirqs_off_prepare() is: ENTRY lockdep_hardirqs_off(); // because hardware ... do entry magic instrumentation_begin(); trace_hardirqs_off_prepare(); ... do actual work trace_hardirqs_on_prepare(); lockdep_hardirqs_on_prepare(); instrumentation_end(); ... do exit magic lockdep_hardirqs_on(); which shows that it's named wrong, rename it to trace_hardirqs_off_finish(), as it concludes the hardirq_off transition. Also, given that the above is the only correct order, make the traditional all-in-one trace_hardirqs_off() follow suit. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20200529213321.415774872@infradead.org --- include/linux/irqflags.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index d7f7e436c3af..6384d2813ded 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -32,7 +32,7 @@ #ifdef CONFIG_TRACE_IRQFLAGS extern void trace_hardirqs_on_prepare(void); - extern void trace_hardirqs_off_prepare(void); + extern void trace_hardirqs_off_finish(void); extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); # define lockdep_hardirq_context(p) ((p)->hardirq_context) @@ -101,7 +101,7 @@ do { \ #else # define trace_hardirqs_on_prepare() do { } while (0) -# define trace_hardirqs_off_prepare() do { } while (0) +# define trace_hardirqs_off_finish() do { } while (0) # define trace_hardirqs_on() do { } while (0) # define trace_hardirqs_off() do { } while (0) # define lockdep_hardirq_context(p) 0 -- cgit v1.2.3 From 6eebad1ad303db360ebe3e51c2b9656c3d407157 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 3 Jun 2020 13:40:21 +0200 Subject: lockdep: __always_inline more for noinstr vmlinux.o: warning: objtool: debug_locks_off()+0xd: call to __debug_locks_off() leaves .noinstr.text section vmlinux.o: warning: objtool: match_held_lock()+0x6a: call to look_up_lock_class.isra.0() leaves .noinstr.text section vmlinux.o: warning: objtool: lock_is_held_type()+0x90: call to lockdep_recursion_finish() leaves .noinstr.text section Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20200603114052.185201076@infradead.org --- include/linux/debug_locks.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 257ab3c92cb8..e7e45f0cc7da 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -12,7 +12,7 @@ extern int debug_locks __read_mostly; extern int debug_locks_silent __read_mostly; -static inline int __debug_locks_off(void) +static __always_inline int __debug_locks_off(void) { return xchg(&debug_locks, 0); } -- cgit v1.2.3 From f0178fc01fe46bab6a95415f5647d1a74efcad1b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 10 Jun 2020 08:37:01 +0200 Subject: x86/entry: Unbreak __irqentry_text_start/end magic The entry rework moved interrupt entry code from the irqentry to the noinstr section which made the irqentry section empty. This breaks boundary checks which rely on the __irqentry_text_start/end markers to find out whether a function in a stack trace is interrupt/exception entry code. This affects the function graph tracer and filter_irq_stacks(). As the IDT entry points are all sequentialy emitted this is rather simple to unbreak by injecting __irqentry_text_start/end as global labels. To make this work correctly: - Remove the IRQENTRY_TEXT section from the x86 linker script - Define __irqentry so it breaks the build if it's used - Adjust the entry mirroring in PTI - Remove the redundant kprobes and unwinder bound checks Reported-by: Qian Cai Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 80f637c3a6f3..5db970b6615a 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -760,8 +760,10 @@ extern int arch_early_irq_init(void); /* * We want to know which function is an entrypoint of a hardirq or a softirq. */ -#define __irq_entry __attribute__((__section__(".irqentry.text"))) -#define __softirq_entry \ - __attribute__((__section__(".softirqentry.text"))) +#ifndef __irq_entry +# define __irq_entry __attribute__((__section__(".irqentry.text"))) +#endif + +#define __softirq_entry __attribute__((__section__(".softirqentry.text"))) #endif -- cgit v1.2.3 From 17fae1294ad9d711b2c3dd0edef479d40c76a5e8 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Wed, 20 May 2020 09:35:46 -0700 Subject: x86/{mce,mm}: Unmap the entire page if the whole page is affected and poisoned An interesting thing happened when a guest Linux instance took a machine check. The VMM unmapped the bad page from guest physical space and passed the machine check to the guest. Linux took all the normal actions to offline the page from the process that was using it. But then guest Linux crashed because it said there was a second machine check inside the kernel with this stack trace: do_memory_failure set_mce_nospec set_memory_uc _set_memory_uc change_page_attr_set_clr cpa_flush clflush_cache_range_opt This was odd, because a CLFLUSH instruction shouldn't raise a machine check (it isn't consuming the data). Further investigation showed that the VMM had passed in another machine check because is appeared that the guest was accessing the bad page. Fix is to check the scope of the poison by checking the MCi_MISC register. If the entire page is affected, then unmap the page. If only part of the page is affected, then mark the page as uncacheable. This assumes that VMMs will do the logical thing and pass in the "whole page scope" via the MCi_MISC register (since they unmapped the entire page). [ bp: Adjust to x86/entry changes. ] Fixes: 284ce4011ba6 ("x86/memory_failure: Introduce {set, clear}_mce_nospec()") Reported-by: Jue Wang Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Tested-by: Jue Wang Cc: Link: https://lkml.kernel.org/r/20200520163546.GA7977@agluck-desk2.amr.corp.intel.com --- include/linux/sched.h | 4 +++- include/linux/set_memory.h | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c5d96e3e7fff..62c1de522fc5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1304,7 +1304,9 @@ struct task_struct { #ifdef CONFIG_X86_MCE u64 mce_addr; - u64 mce_status; + __u64 mce_ripv : 1, + mce_whole_page : 1, + __mce_reserved : 62; struct callback_head mce_kill_me; #endif diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index 86281ac7c305..860e0f843c12 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -26,7 +26,7 @@ static inline int set_direct_map_default_noflush(struct page *page) #endif #ifndef set_mce_nospec -static inline int set_mce_nospec(unsigned long pfn) +static inline int set_mce_nospec(unsigned long pfn, bool unmap) { return 0; } -- cgit v1.2.3 From 2a18b7e7cd8882f626316c340c6f2fca49b5fa12 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 10 Jun 2020 19:55:32 +0200 Subject: KVM: async_pf: Inject 'page ready' event only if 'page not present' was previously injected 'Page not present' event may or may not get injected depending on guest's state. If the event wasn't injected, there is no need to inject the corresponding 'page ready' event as the guest may get confused. E.g. Linux thinks that the corresponding 'page not present' event wasn't delivered *yet* and allocates a 'dummy entry' for it. This entry is never freed. Note, 'wakeup all' events have no corresponding 'page not present' event and always get injected. s390 seems to always be able to inject 'page not present', the change is effectively a nop. Suggested-by: Vivek Goyal Signed-off-by: Vitaly Kuznetsov Message-Id: <20200610175532.779793-2-vkuznets@redhat.com> Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=208081 Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e2f82131bb3e..62ec926c78a0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -206,6 +206,7 @@ struct kvm_async_pf { unsigned long addr; struct kvm_arch_async_pf arch; bool wakeup_all; + bool notpresent_injected; }; void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); -- cgit v1.2.3 From 53bc19f17f21738735706fabcae3070f16c833db Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 12 May 2020 17:13:01 -0400 Subject: SUNRPC: receive buffer size estimation values almost never change Avoid unnecessary cache sloshing by placing the buffer size estimation update logic behind an atomic bit flag. The size of GSS information included in each wrapped Reply does not change during the lifetime of a GSS context. Therefore, the au_rslack and au_ralign fields need to be updated only once after establishing a fresh GSS credential. Thus a slack size update must occur after a cred is created, duplicated, renewed, or expires. I'm not sure I have this exactly right. A trace point is introduced to track updates to these variables to enable troubleshooting the problem if I missed a spot. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/sunrpc/auth.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 4f6b28487f28..98da816b5fc2 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -76,7 +76,7 @@ struct rpc_auth { unsigned int au_verfsize; /* size of reply verifier */ unsigned int au_ralign; /* words before UL header */ - unsigned int au_flags; + unsigned long au_flags; const struct rpc_authops *au_ops; rpc_authflavor_t au_flavor; /* pseudoflavor (note may * differ from the flavor in @@ -89,7 +89,8 @@ struct rpc_auth { }; /* rpc_auth au_flags */ -#define RPCAUTH_AUTH_DATATOUCH 0x00000002 +#define RPCAUTH_AUTH_DATATOUCH (1) +#define RPCAUTH_AUTH_UPDATE_SLACK (2) struct rpc_auth_create_args { rpc_authflavor_t pseudoflavor; -- cgit v1.2.3 From 3a39e778690500066b31fe982d18e2e394d3bce2 Mon Sep 17 00:00:00 2001 From: Zheng Bin Date: Thu, 21 May 2020 17:17:21 +0800 Subject: nfs: set invalid blocks after NFSv4 writes Use the following command to test nfsv4(size of file1M is 1MB): mount -t nfs -o vers=4.0,actimeo=60 127.0.0.1/dir1 /mnt cp file1M /mnt du -h /mnt/file1M -->0 within 60s, then 1M When write is done(cp file1M /mnt), will call this: nfs_writeback_done nfs4_write_done nfs4_write_done_cb nfs_writeback_update_inode nfs_post_op_update_inode_force_wcc_locked(change, ctime, mtime nfs_post_op_update_inode_force_wcc_locked nfs_set_cache_invalid nfs_refresh_inode_locked nfs_update_inode nfsd write response contains change, ctime, mtime, the flag will be clear after nfs_update_inode. Howerver, write response does not contain space_used, previous open response contains space_used whose value is 0, so inode->i_blocks is still 0. nfs_getattr -->called by "du -h" do_update |= force_sync || nfs_attribute_cache_expired -->false in 60s cache_validity = READ_ONCE(NFS_I(inode)->cache_validity) do_update |= cache_validity & (NFS_INO_INVALID_ATTR -->false if (do_update) { __nfs_revalidate_inode } Within 60s, does not send getattr request to nfsd, thus "du -h /mnt/file1M" is 0. Add a NFS_INO_INVALID_BLOCKS flag, set it when nfsv4 write is done. Fixes: 16e143751727 ("NFS: More fine grained attribute tracking") Signed-off-by: Zheng Bin Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 73eda45f1cfd..6ee9119acc5d 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -230,6 +230,7 @@ struct nfs4_copy_state { #define NFS_INO_INVALID_OTHER BIT(12) /* other attrs are invalid */ #define NFS_INO_DATA_INVAL_DEFER \ BIT(13) /* Deferred cache invalidation */ +#define NFS_INO_INVALID_BLOCKS BIT(14) /* cached blocks are invalid */ #define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \ | NFS_INO_INVALID_CTIME \ -- cgit v1.2.3 From e3b779d9ebe82b4be0121f25f27632844bb86d96 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 21 May 2020 16:20:41 +0200 Subject: kcsan: Remove 'noinline' from __no_kcsan_or_inline Some compilers incorrectly inline small __no_kcsan functions, which then results in instrumenting the accesses. For this reason, the 'noinline' attribute was added to __no_kcsan_or_inline. All known versions of GCC are affected by this. Supported versions of Clang are unaffected, and never inline a no_sanitize function. However, the attribute 'noinline' in __no_kcsan_or_inline causes unexpected code generation in functions that are __no_kcsan and call a __no_kcsan_or_inline function. In certain situations it is expected that the __no_kcsan_or_inline function is actually inlined by the __no_kcsan function, and *no* calls are emitted. By removing the 'noinline' attribute, give the compiler the ability to inline and generate the expected code in __no_kcsan functions. Signed-off-by: Marco Elver Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Link: https://lkml.kernel.org/r/CANpmjNNOpJk0tprXKB_deiNAv_UmmORf1-2uajLhnLWQQ1hvoA@mail.gmail.com Link: https://lkml.kernel.org/r/20200521142047.169334-6-elver@google.com --- include/linux/compiler.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index f09ebbf16562..6d307c0aa4b4 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -329,11 +329,9 @@ do { \ #ifdef __SANITIZE_THREAD__ /* * Rely on __SANITIZE_THREAD__ instead of CONFIG_KCSAN, to avoid not inlining in - * compilation units where instrumentation is disabled. The attribute 'noinline' - * is required for older compilers, where implicit inlining of very small - * functions renders __no_sanitize_thread ineffective. + * compilation units where instrumentation is disabled. */ -# define __no_kcsan_or_inline __no_kcsan noinline notrace __maybe_unused +# define __no_kcsan_or_inline __no_kcsan notrace __maybe_unused # define __no_sanitize_or_inline __no_kcsan_or_inline #else # define __no_kcsan_or_inline __always_inline -- cgit v1.2.3 From 44b97dccb2291a56454549827adc5e99d94811f3 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 21 May 2020 16:20:44 +0200 Subject: compiler.h: Remove data_race() and unnecessary checks from {READ,WRITE}_ONCE() The volatile accesses no longer need to be wrapped in data_race() because compilers that emit instrumentation distinguishing volatile accesses are required for KCSAN. Consequently, the explicit kcsan_check_atomic*() are no longer required either since the compiler emits instrumentation distinguishing the volatile accesses. Finally, simplify __READ_ONCE_SCALAR() and remove __WRITE_ONCE_SCALAR(). [ bp: Convert commit message to passive voice. ] Signed-off-by: Marco Elver Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Link: https://lkml.kernel.org/r/20200521142047.169334-9-elver@google.com --- include/linux/compiler.h | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 6d307c0aa4b4..7b090d263fec 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -281,9 +281,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define __READ_ONCE_SCALAR(x) \ ({ \ - typeof(x) *__xp = &(x); \ - __unqual_scalar_typeof(x) __x = data_race(__READ_ONCE(*__xp)); \ - kcsan_check_atomic_read(__xp, sizeof(*__xp)); \ + __unqual_scalar_typeof(x) __x = __READ_ONCE(x); \ smp_read_barrier_depends(); \ (typeof(x))__x; \ }) @@ -299,17 +297,10 @@ do { \ *(volatile typeof(x) *)&(x) = (val); \ } while (0) -#define __WRITE_ONCE_SCALAR(x, val) \ -do { \ - typeof(x) *__xp = &(x); \ - kcsan_check_atomic_write(__xp, sizeof(*__xp)); \ - data_race(({ __WRITE_ONCE(*__xp, val); 0; })); \ -} while (0) - #define WRITE_ONCE(x, val) \ do { \ compiletime_assert_rwonce_type(x); \ - __WRITE_ONCE_SCALAR(x, val); \ + __WRITE_ONCE(x, val); \ } while (0) #ifdef CONFIG_KASAN -- cgit v1.2.3 From 95c094fccb85422eff3c12930ebebbda9278f76b Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 21 May 2020 16:20:45 +0200 Subject: compiler.h: Avoid nested statement expression in data_race() It appears that compilers have trouble with nested statement expressions. Therefore, remove one level of statement expression nesting from the data_race() macro. This will help avoiding potential problems in the future as its usage increases. Reported-by: Borislav Petkov Reported-by: Nathan Chancellor Signed-off-by: Marco Elver Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Tested-by: Nick Desaulniers Link: https://lkml.kernel.org/r/20200520221712.GA21166@zn.tnic Link: https://lkml.kernel.org/r/20200521142047.169334-10-elver@google.com --- include/linux/compiler.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 7b090d263fec..f0bfbe82f0fe 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -264,12 +264,12 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, */ #define data_race(expr) \ ({ \ - __kcsan_disable_current(); \ - ({ \ - __unqual_scalar_typeof(({ expr; })) __v = ({ expr; }); \ - __kcsan_enable_current(); \ - __v; \ + __unqual_scalar_typeof(({ expr; })) __v = ({ \ + __kcsan_disable_current(); \ + expr; \ }); \ + __kcsan_enable_current(); \ + __v; \ }) /* -- cgit v1.2.3 From eb73876c74313231c35cee6310f8ad62c56fa2b3 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 21 May 2020 16:20:46 +0200 Subject: compiler.h: Move function attributes to compiler_types.h Cleanup and move the KASAN and KCSAN related function attributes to compiler_types.h, where the rest of the same kind live. No functional change intended. Signed-off-by: Marco Elver Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Link: https://lkml.kernel.org/r/20200521142047.169334-11-elver@google.com --- include/linux/compiler.h | 29 ----------------------------- include/linux/compiler_types.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index f0bfbe82f0fe..30827f82ad62 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -303,35 +303,6 @@ do { \ __WRITE_ONCE(x, val); \ } while (0) -#ifdef CONFIG_KASAN -/* - * We can't declare function 'inline' because __no_sanitize_address conflicts - * with inlining. Attempt to inline it may cause a build failure. - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - * '__maybe_unused' allows us to avoid defined-but-not-used warnings. - */ -# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused -# define __no_sanitize_or_inline __no_kasan_or_inline -#else -# define __no_kasan_or_inline __always_inline -#endif - -#define __no_kcsan __no_sanitize_thread -#ifdef __SANITIZE_THREAD__ -/* - * Rely on __SANITIZE_THREAD__ instead of CONFIG_KCSAN, to avoid not inlining in - * compilation units where instrumentation is disabled. - */ -# define __no_kcsan_or_inline __no_kcsan notrace __maybe_unused -# define __no_sanitize_or_inline __no_kcsan_or_inline -#else -# define __no_kcsan_or_inline __always_inline -#endif - -#ifndef __no_sanitize_or_inline -#define __no_sanitize_or_inline __always_inline -#endif - static __no_sanitize_or_inline unsigned long __read_once_word_nocheck(const void *addr) { diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index d4e1956f903f..725cec6f56ea 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -171,6 +171,35 @@ struct ftrace_likely_data { */ #define noinline_for_stack noinline +#ifdef CONFIG_KASAN +/* + * We can't declare function 'inline' because __no_sanitize_address conflicts + * with inlining. Attempt to inline it may cause a build failure. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + * '__maybe_unused' allows us to avoid defined-but-not-used warnings. + */ +# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused +# define __no_sanitize_or_inline __no_kasan_or_inline +#else +# define __no_kasan_or_inline __always_inline +#endif + +#define __no_kcsan __no_sanitize_thread +#ifdef __SANITIZE_THREAD__ +/* + * Rely on __SANITIZE_THREAD__ instead of CONFIG_KCSAN, to avoid not inlining in + * compilation units where instrumentation is disabled. + */ +# define __no_kcsan_or_inline __no_kcsan notrace __maybe_unused +# define __no_sanitize_or_inline __no_kcsan_or_inline +#else +# define __no_kcsan_or_inline __always_inline +#endif + +#ifndef __no_sanitize_or_inline +#define __no_sanitize_or_inline __always_inline +#endif + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ -- cgit v1.2.3 From 1f44328ea24c9de368a3cfe5cc0e110b949afb2e Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 21 May 2020 16:20:47 +0200 Subject: compiler_types.h, kasan: Use __SANITIZE_ADDRESS__ instead of CONFIG_KASAN to decide inlining Use __always_inline in compilation units that have instrumentation disabled (KASAN_SANITIZE_foo.o := n) for KASAN, like it is done for KCSAN. Also, add common documentation for KASAN and KCSAN explaining the attribute. [ bp: Massage commit message. ] Signed-off-by: Marco Elver Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Link: https://lkml.kernel.org/r/20200521142047.169334-12-elver@google.com --- include/linux/compiler_types.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 725cec6f56ea..21aed0981edf 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -171,7 +171,14 @@ struct ftrace_likely_data { */ #define noinline_for_stack noinline -#ifdef CONFIG_KASAN +/* + * Sanitizer helper attributes: Because using __always_inline and + * __no_sanitize_* conflict, provide helper attributes that will either expand + * to __no_sanitize_* in compilation units where instrumentation is enabled + * (__SANITIZE_*__), or __always_inline in compilation units without + * instrumentation (__SANITIZE_*__ undefined). + */ +#ifdef __SANITIZE_ADDRESS__ /* * We can't declare function 'inline' because __no_sanitize_address conflicts * with inlining. Attempt to inline it may cause a build failure. @@ -186,10 +193,6 @@ struct ftrace_likely_data { #define __no_kcsan __no_sanitize_thread #ifdef __SANITIZE_THREAD__ -/* - * Rely on __SANITIZE_THREAD__ instead of CONFIG_KCSAN, to avoid not inlining in - * compilation units where instrumentation is disabled. - */ # define __no_kcsan_or_inline __no_kcsan notrace __maybe_unused # define __no_sanitize_or_inline __no_kcsan_or_inline #else -- cgit v1.2.3 From 7b97d868b7ab2448859668de9222b8af43f76e78 Mon Sep 17 00:00:00 2001 From: "zhangyi (F)" Date: Tue, 9 Jun 2020 15:35:40 +0800 Subject: ext4, jbd2: ensure panic by fix a race between jbd2 abort and ext4 error handlers In the ext4 filesystem with errors=panic, if one process is recording errno in the superblock when invoking jbd2_journal_abort() due to some error cases, it could be raced by another __ext4_abort() which is setting the SB_RDONLY flag but missing panic because errno has not been recorded. jbd2_journal_commit_transaction() jbd2_journal_abort() journal->j_flags |= JBD2_ABORT; jbd2_journal_update_sb_errno() | ext4_journal_check_start() | __ext4_abort() | sb->s_flags |= SB_RDONLY; | if (!JBD2_REC_ERR) | return; journal->j_flags |= JBD2_REC_ERR; Finally, it will no longer trigger panic because the filesystem has already been set read-only. Fix this by introduce j_abort_mutex to make sure journal abort is completed before panic, and remove JBD2_REC_ERR flag. Fixes: 4327ba52afd03 ("ext4, jbd2: ensure entering into panic after recording an error in superblock") Signed-off-by: zhangyi (F) Reviewed-by: Jan Kara Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200609073540.3810702-1-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index f613d8529863..d56128df2aff 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -765,6 +765,11 @@ struct journal_s */ int j_errno; + /** + * @j_abort_mutex: Lock the whole aborting procedure. + */ + struct mutex j_abort_mutex; + /** * @j_sb_buffer: The first part of the superblock buffer. */ @@ -1247,7 +1252,6 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) #define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file * data write error in ordered * mode */ -#define JBD2_REC_ERR 0x080 /* The errno in the sb has been recorded */ /* * Function declarations for the journaling transaction and buffer -- cgit v1.2.3 From e7e3b9d23f3bc6774cce585ef4fcb02462e04065 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 26 May 2020 21:35:17 -0700 Subject: iio: cros_ec: Reapply range at resume EC does not currently preserve range across sensor reinit. If sensor is powered down at suspend, it will default to the EC default range at resume, not the range set by the host. Save range if modified, and apply at resume. Signed-off-by: Gwendal Grignou Signed-off-by: Jonathan Cameron --- include/linux/iio/common/cros_ec_sensors_core.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h index 7bc961defa87..caa8bb279a34 100644 --- a/include/linux/iio/common/cros_ec_sensors_core.h +++ b/include/linux/iio/common/cros_ec_sensors_core.h @@ -42,6 +42,10 @@ typedef irqreturn_t (*cros_ec_sensors_capture_t)(int irq, void *p); * @resp: motion sensor response structure * @type: type of motion sensor * @loc: location where the motion sensor is placed + * @range_updated: True if the range of the sensor has been + * updated. + * @curr_range: If updated, the current range value. + * It will be reapplied at every resume. * @calib: calibration parameters. Note that trigger * captured data will always provide the calibrated * data @@ -65,6 +69,9 @@ struct cros_ec_sensors_core_state { enum motionsensor_type type; enum motionsensor_location loc; + bool range_updated; + int curr_range; + struct calib_data { s16 offset; u16 scale; @@ -114,7 +121,9 @@ int cros_ec_sensors_core_write(struct cros_ec_sensors_core_state *st, struct iio_chan_spec const *chan, int val, int val2, long mask); -/* List of extended channel specification for all sensors */ +extern const struct dev_pm_ops cros_ec_sensors_pm_ops; + +/* List of extended channel specification for all sensors. */ extern const struct iio_chan_spec_ext_info cros_ec_sensors_ext_info[]; extern const struct attribute *cros_ec_sensor_fifo_attributes[]; -- cgit v1.2.3 From 18d563858d97dbefc9a16c8210ef2f97dc264202 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Thu, 21 May 2020 18:53:22 +0100 Subject: iio: make iio_device_get_drvdata take a const struct iio_dev *. As this just calls dev_get_drvdata underneath which is happy with a const struct device * we should change and avoid potentially casting away a const in order to then put it back again. Signed-off-by: Jonathan Cameron Reviewed-by: Jean-Baptiste Maneyrol Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index a1be82e74c93..e846a0a7001e 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -669,7 +669,7 @@ static inline void iio_device_set_drvdata(struct iio_dev *indio_dev, void *data) * * Returns the data previously set with iio_device_set_drvdata() */ -static inline void *iio_device_get_drvdata(struct iio_dev *indio_dev) +static inline void *iio_device_get_drvdata(const struct iio_dev *indio_dev) { return dev_get_drvdata(&indio_dev->dev); } -- cgit v1.2.3 From 78289b4a58b58e9a8a76ef43ffbaf04a097e33c6 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Wed, 3 Jun 2020 14:40:18 +0300 Subject: iio: core: pass parent device as parameter during allocation The change passes the parent device to the iio_device_alloc() call. This also updates the devm_iio_device_alloc() call to consider the device object as the parent device by default. Having it passed like this, should ensure that any IIO device object already has a device object as parent, allowing for neater control, like passing the 'indio_dev' object for other stuff [like buffers/triggers/etc], and potentially creating iiom_xxx(indio_dev) functions. With this patch, only the 'drivers/platform/x86/toshiba_acpi.c' needs an update to pass the parent object as a parameter. In the next patch all devm_iio_device_alloc() calls will be handled. Acked-by: Andy Shevchenko Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index e846a0a7001e..655e34a08d94 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -676,7 +676,7 @@ static inline void *iio_device_get_drvdata(const struct iio_dev *indio_dev) /* Can we make this smaller? */ #define IIO_ALIGN L1_CACHE_BYTES -struct iio_dev *iio_device_alloc(int sizeof_priv); +struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv); static inline void *iio_priv(const struct iio_dev *indio_dev) { @@ -690,7 +690,7 @@ static inline struct iio_dev *iio_priv_to_dev(void *priv) } void iio_device_free(struct iio_dev *indio_dev); -struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); +struct iio_dev *devm_iio_device_alloc(struct device *parent, int sizeof_priv); struct iio_trigger *devm_iio_trigger_alloc(struct device *dev, const char *fmt, ...); /** -- cgit v1.2.3 From f5d017938e7a6517b85f7fd215213a28e11291fb Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Wed, 3 Jun 2020 14:40:19 +0300 Subject: iio: core: add iio_device_set_parent() helper By default, the device allocation will also assign a parent device to the IIO device object. In cases where devm_iio_device_alloc() is used, sometimes the parent device must be different than the device used to manage the allocation. In that case, this helper should be used to change the parent, hence the requirement to call this between allocation & registration. This pattern/requirement is not very common in the IIO space, and it may be cleaned up later. But until then, assigning the parent manually between allocation & registration is slightly easier. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 655e34a08d94..1c1d02107722 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -649,6 +649,26 @@ static inline struct iio_dev *iio_device_get(struct iio_dev *indio_dev) return indio_dev ? dev_to_iio_dev(get_device(&indio_dev->dev)) : NULL; } +/** + * iio_device_set_parent() - assign parent device to the IIO device object + * @indio_dev: IIO device structure + * @parent: reference to parent device object + * + * This utility must be called between IIO device allocation + * (via devm_iio_device_alloc()) & IIO device registration + * (via {devm_}iio_device_register()). + * By default, the device allocation will also assign a parent device to + * the IIO device object. In cases where devm_iio_device_alloc() is used, + * sometimes the parent device must be different than the device used to + * manage the allocation. + * In that case, this helper should be used to change the parent, hence the + * requirement to call this between allocation & registration. + **/ +static inline void iio_device_set_parent(struct iio_dev *indio_dev, + struct device *parent) +{ + indio_dev->dev.parent = parent; +} /** * iio_device_set_drvdata() - Set device driver data -- cgit v1.2.3 From 39030e1351aa1aa7443bb2da24426573077c83da Mon Sep 17 00:00:00 2001 From: Thomas Cedeno Date: Tue, 9 Jun 2020 10:22:13 -0700 Subject: security: Add LSM hooks to set*gid syscalls The SafeSetID LSM uses the security_task_fix_setuid hook to filter set*uid() syscalls according to its configured security policy. In preparation for adding analagous support in the LSM for set*gid() syscalls, we add the requisite hook here. Tested by putting print statements in the security_task_fix_setgid hook and seeing them get hit during kernel boot. Signed-off-by: Thomas Cedeno Signed-off-by: Micah Morton --- include/linux/lsm_hook_defs.h | 2 ++ include/linux/lsm_hooks.h | 9 +++++++++ include/linux/security.h | 9 +++++++++ 3 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 5616b2567aa7..2a5a53a83ecb 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -190,6 +190,8 @@ LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) LSM_HOOK(int, 0, task_fix_setuid, struct cred *new, const struct cred *old, int flags) +LSM_HOOK(int, 0, task_fix_setgid, struct cred *new, const struct cred * old, + int flags) LSM_HOOK(int, 0, task_setpgid, struct task_struct *p, pid_t pgid) LSM_HOOK(int, 0, task_getpgid, struct task_struct *p) LSM_HOOK(int, 0, task_getsid, struct task_struct *p) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 988ca0df7824..b20132bcea2d 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -651,6 +651,15 @@ * @old is the set of credentials that are being replaces * @flags contains one of the LSM_SETID_* values. * Return 0 on success. + * @task_fix_setgid: + * Update the module's state after setting one or more of the group + * identity attributes of the current process. The @flags parameter + * indicates which of the set*gid system calls invoked this hook. + * @new is the set of credentials that will be installed. Modifications + * should be made to this rather than to @current->cred. + * @old is the set of credentials that are being replaced. + * @flags contains one of the LSM_SETID_* values. + * Return 0 on success. * @task_setpgid: * Check permission before setting the process group identifier of the * process @p to @pgid. diff --git a/include/linux/security.h b/include/linux/security.h index a8d9310472df..88749bf0d1d7 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -389,6 +389,8 @@ int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id); int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags); +int security_task_fix_setgid(struct cred *new, const struct cred *old, + int flags); int security_task_setpgid(struct task_struct *p, pid_t pgid); int security_task_getpgid(struct task_struct *p); int security_task_getsid(struct task_struct *p); @@ -1027,6 +1029,13 @@ static inline int security_task_fix_setuid(struct cred *new, return cap_task_fix_setuid(new, old, flags); } +static inline int security_task_fix_setgid(struct cred *new, + const struct cred *old, + int flags) +{ + return 0; +} + static inline int security_task_setpgid(struct task_struct *p, pid_t pgid) { return 0; -- cgit v1.2.3 From 5afced3bf28100d81fb2fe7e98918632a08feaf5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 29 May 2020 15:05:22 +0200 Subject: writeback: Avoid skipping inode writeback Inode's i_io_list list head is used to attach inode to several different lists - wb->{b_dirty, b_dirty_time, b_io, b_more_io}. When flush worker prepares a list of inodes to writeback e.g. for sync(2), it moves inodes to b_io list. Thus it is critical for sync(2) data integrity guarantees that inode is not requeued to any other writeback list when inode is queued for processing by flush worker. That's the reason why writeback_single_inode() does not touch i_io_list (unless the inode is completely clean) and why __mark_inode_dirty() does not touch i_io_list if I_SYNC flag is set. However there are two flaws in the current logic: 1) When inode has only I_DIRTY_TIME set but it is already queued in b_io list due to sync(2), concurrent __mark_inode_dirty(inode, I_DIRTY_SYNC) can still move inode back to b_dirty list resulting in skipping writeback of inode time stamps during sync(2). 2) When inode is on b_dirty_time list and writeback_single_inode() races with __mark_inode_dirty() like: writeback_single_inode() __mark_inode_dirty(inode, I_DIRTY_PAGES) inode->i_state |= I_SYNC __writeback_single_inode() inode->i_state |= I_DIRTY_PAGES; if (inode->i_state & I_SYNC) bail if (!(inode->i_state & I_DIRTY_ALL)) - not true so nothing done We end up with I_DIRTY_PAGES inode on b_dirty_time list and thus standard background writeback will not writeback this inode leading to possible dirty throttling stalls etc. (thanks to Martijn Coenen for this analysis). Fix these problems by tracking whether inode is queued in b_io or b_more_io lists in a new I_SYNC_QUEUED flag. When this flag is set, we know flush worker has queued inode and we should not touch i_io_list. On the other hand we also know that once flush worker is done with the inode it will requeue the inode to appropriate dirty list. When I_SYNC_QUEUED is not set, __mark_inode_dirty() can (and must) move inode to appropriate dirty list. Reported-by: Martijn Coenen Reviewed-by: Martijn Coenen Tested-by: Martijn Coenen Reviewed-by: Christoph Hellwig Fixes: 0ae45f63d4ef ("vfs: add support for a lazytime mount option") CC: stable@vger.kernel.org Signed-off-by: Jan Kara --- include/linux/fs.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 19ef6c88c152..48556efcdcf0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2157,6 +2157,10 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_DONTCACHE Evict inode as soon as it is not used anymore. * + * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. + * Used to detect that mark_inode_dirty() should not move + * inode between dirty lists. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2174,12 +2178,12 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) -#define __I_DIRTY_TIME_EXPIRED 12 -#define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) +#define I_DIRTY_TIME_EXPIRED (1 << 12) #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) +#define I_SYNC_QUEUED (1 << 17) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) -- cgit v1.2.3 From 5fcd57505c002efc5823a7355e21f48dd02d5a51 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 29 May 2020 16:24:43 +0200 Subject: writeback: Drop I_DIRTY_TIME_EXPIRE The only use of I_DIRTY_TIME_EXPIRE is to detect in __writeback_single_inode() that inode got there because flush worker decided it's time to writeback the dirty inode time stamps (either because we are syncing or because of age). However we can detect this directly in __writeback_single_inode() and there's no need for the strange propagation with I_DIRTY_TIME_EXPIRE flag. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 48556efcdcf0..45eadf5bea5d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2178,7 +2178,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) -#define I_DIRTY_TIME_EXPIRED (1 << 12) #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) #define I_CREATING (1 << 15) -- cgit v1.2.3 From 376bd28d03c97b4d53f5797d5f9b3522c8bd4d3d Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 4 Jun 2020 18:09:41 +1000 Subject: crypto: ccp - Fix sparse warnings in sev-dev This patch fixes a bunch of sparse warnings in sev-dev where the __user marking is incorrectly handled. Reported-by: kbuild test robot Fixes: 7360e4b14350 ("crypto: ccp: Implement SEV_PEK_CERT_IMPORT...") Fixes: e799035609e1 ("crypto: ccp: Implement SEV_PEK_CSR ioctl...") Fixes: 76a2b524a4b1 ("crypto: ccp: Implement SEV_PDH_CERT_EXPORT...") Fixes: d6112ea0cb34 ("crypto: ccp - introduce SEV_GET_ID2 command") Signed-off-by: Herbert Xu Reviewed-by: Brijesh Singh Acked-by: Tom Lendacky Signed-off-by: Herbert Xu --- include/linux/psp-sev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 7fbc8679145c..49d155cd2dfe 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -597,7 +597,7 @@ int sev_guest_df_flush(int *error); */ int sev_guest_decommission(struct sev_data_decommission *data, int *error); -void *psp_copy_user_blob(u64 __user uaddr, u32 len); +void *psp_copy_user_blob(u64 uaddr, u32 len); #else /* !CONFIG_CRYPTO_DEV_SP_PSP */ -- cgit v1.2.3 From e012d15a238f24795081ef1e43ffe2859b6538ed Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 15 Jun 2020 08:46:47 +0200 Subject: gpio: driver.h: fix kernel-doc markup There is one parameter with a wrong name at kernel-doc macro: ./include/linux/gpio/driver.h:499: warning: Function parameter or member 'gc' not described in 'gpiochip_add_data' ./include/linux/gpio/driver.h:499: warning: Excess function parameter 'chip' description in 'gpiochip_add_data' Fix it. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index c4f272af7af5..c11261f3c724 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -481,7 +481,7 @@ extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, /** * gpiochip_add_data() - register a gpio_chip - * @chip: the chip to register, with chip->base initialized + * @gc: the chip to register, with chip->base initialized * @data: driver-private data associated with this chip * * Context: potentially before irqs will work -- cgit v1.2.3 From 8e742aa79780b13cd300a42198c1a4cea9c89905 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 10 Jun 2020 13:48:51 +0200 Subject: syscalls: Fix offset type of ksys_ftruncate() After the commit below, truncate() on x86 32bit uses ksys_ftruncate(). But ksys_ftruncate() truncates the offset to unsigned long. Switch the type of offset to loff_t which is what do_sys_ftruncate() expects. Fixes: 121b32a58a3a (x86/entry/32: Use IA32-specific wrappers for syscalls taking 64-bit arguments) Signed-off-by: Jiri Slaby Signed-off-by: Thomas Gleixner Reviewed-by: Brian Gerst Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20200610114851.28549-1-jslaby@suse.cz --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7c354c2955f5..b951a87da987 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1360,7 +1360,7 @@ static inline long ksys_lchown(const char __user *filename, uid_t user, extern long do_sys_ftruncate(unsigned int fd, loff_t length, int small); -static inline long ksys_ftruncate(unsigned int fd, unsigned long length) +static inline long ksys_ftruncate(unsigned int fd, loff_t length) { return do_sys_ftruncate(fd, length, 1); } -- cgit v1.2.3 From e17d43b93e544f5016c0251d2074c15568d5d963 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 12 May 2020 15:19:08 +0300 Subject: perf: Add perf text poke event Record (single instruction) changes to the kernel text (i.e. self-modifying code) in order to support tracers like Intel PT and ARM CoreSight. A copy of the running kernel code is needed as a reference point (e.g. from /proc/kcore). The text poke event records the old bytes and the new bytes so that the event can be processed forwards or backwards. The basic problem is recording the modified instruction in an unambiguous manner given SMP instruction cache (in)coherence. That is, when modifying an instruction concurrently any solution with one or multiple timestamps is not sufficient: CPU0 CPU1 0 1 write insn A 2 execute insn A 3 sync-I$ 4 Due to I$, CPU1 might execute either the old or new A. No matter where we record tracepoints on CPU0, one simply cannot tell what CPU1 will have observed, except that at 0 it must be the old one and at 4 it must be the new one. To solve this, take inspiration from x86 text poking, which has to solve this exact problem due to variable length instruction encoding and I-fetch windows. 1) overwrite the instruction with a breakpoint and sync I$ This guarantees that that code flow will never hit the target instruction anymore, on any CPU (or rather, it will cause an exception). 2) issue the TEXT_POKE event 3) overwrite the breakpoint with the new instruction and sync I$ Now we know that any execution after the TEXT_POKE event will either observe the breakpoint (and hit the exception) or the new instruction. So by guarding the TEXT_POKE event with an exception on either side; we can now tell, without doubt, which instruction another CPU will have observed. Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200512121922.8997-2-adrian.hunter@intel.com --- include/linux/perf_event.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b4bb32082342..46fe5cfb5163 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1232,6 +1232,9 @@ extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); +extern void perf_event_text_poke(const void *addr, + const void *old_bytes, size_t old_len, + const void *new_bytes, size_t new_len); /* Callchains */ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); @@ -1479,6 +1482,11 @@ static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } +static inline void perf_event_text_poke(const void *addr, + const void *old_bytes, + size_t old_len, + const void *new_bytes, + size_t new_len) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } static inline void perf_swevent_put_recursion_context(int rctx) { } -- cgit v1.2.3 From d002b8bc6dbc20e9043e279196cff8795dba05fe Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 28 May 2020 11:00:58 +0300 Subject: kprobes: Add symbols for kprobe insn pages Symbols are needed for tools to describe instruction addresses. Pages allocated for kprobe's purposes need symbols to be created for them. Add such symbols to be visible via /proc/kallsyms. Note: kprobe insn pages are not used if ftrace is configured. To see the effect of this patch, the kernel must be configured with: # CONFIG_FUNCTION_TRACER is not set CONFIG_KPROBES=y and for optimised kprobes: CONFIG_OPTPROBES=y Example on x86: # perf probe __schedule Added new event: probe:__schedule (on __schedule) # cat /proc/kallsyms | grep '\[__builtin__kprobes\]' ffffffffc00d4000 t kprobe_insn_page [__builtin__kprobes] ffffffffc00d6000 t kprobe_optinsn_page [__builtin__kprobes] Note: This patch adds "__builtin__kprobes" as a module name in /proc/kallsyms for symbols for pages allocated for kprobes' purposes, even though "__builtin__kprobes" is not a module. Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Acked-by: Masami Hiramatsu Link: https://lkml.kernel.org/r/20200528080058.20230-1-adrian.hunter@intel.com --- include/linux/kprobes.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 594265bfd390..13fc58a74c04 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -242,6 +242,7 @@ struct kprobe_insn_cache { struct mutex mutex; void *(*alloc)(void); /* allocate insn page */ void (*free)(void *); /* free insn page */ + const char *sym; /* symbol for insn pages */ struct list_head pages; /* list of kprobe_insn_page */ size_t insn_size; /* size of instruction slot */ int nr_garbage; @@ -272,6 +273,10 @@ static inline bool is_kprobe_##__name##_slot(unsigned long addr) \ { \ return __is_insn_slot_addr(&kprobe_##__name##_slots, addr); \ } +#define KPROBE_INSN_PAGE_SYM "kprobe_insn_page" +#define KPROBE_OPTINSN_PAGE_SYM "kprobe_optinsn_page" +int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum, + unsigned long *value, char *type, char *sym); #else /* __ARCH_WANT_KPROBES_INSN_SLOT */ #define DEFINE_INSN_CACHE_OPS(__name) \ static inline bool is_kprobe_##__name##_slot(unsigned long addr) \ @@ -373,6 +378,11 @@ void dump_kprobe(struct kprobe *kp); void *alloc_insn_page(void); void free_insn_page(void *page); +int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, + char *sym); + +int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value, + char *type, char *sym); #else /* !CONFIG_KPROBES: */ static inline int kprobes_built_in(void) @@ -435,6 +445,11 @@ static inline bool within_kprobe_blacklist(unsigned long addr) { return true; } +static inline int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, + char *type, char *sym) +{ + return -ERANGE; +} #endif /* CONFIG_KPROBES */ static inline int disable_kretprobe(struct kretprobe *rp) { -- cgit v1.2.3 From fc0ea795f53c8d7040fa42471f74fe51d78d0834 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 12 May 2020 15:19:13 +0300 Subject: ftrace: Add symbols for ftrace trampolines Symbols are needed for tools to describe instruction addresses. Pages allocated for ftrace's purposes need symbols to be created for them. Add such symbols to be visible via /proc/kallsyms. Example on x86 with CONFIG_DYNAMIC_FTRACE=y # echo function > /sys/kernel/debug/tracing/current_tracer # cat /proc/kallsyms | grep '\[__builtin__ftrace\]' ffffffffc0238000 t ftrace_trampoline [__builtin__ftrace] Note: This patch adds "__builtin__ftrace" as a module name in /proc/kallsyms for symbols for pages allocated for ftrace's purposes, even though "__builtin__ftrace" is not a module. Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200512121922.8997-7-adrian.hunter@intel.com --- include/linux/ftrace.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e339dac91ee6..ce2c06f72e86 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -58,9 +58,6 @@ struct ftrace_direct_func; const char * ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym); -int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value, - char *type, char *name, - char *module_name, int *exported); #else static inline const char * ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, @@ -68,6 +65,13 @@ ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, { return NULL; } +#endif + +#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE) +int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value, + char *type, char *name, + char *module_name, int *exported); +#else static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported) @@ -76,7 +80,6 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val } #endif - #ifdef CONFIG_FUNCTION_TRACER extern int ftrace_enabled; @@ -207,6 +210,7 @@ struct ftrace_ops { struct ftrace_ops_hash old_hash; unsigned long trampoline; unsigned long trampoline_size; + struct list_head list; #endif }; -- cgit v1.2.3 From 3dc167ba5729ddd2d8e3fa1841653792c295d3f1 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 19 May 2020 19:25:06 +0200 Subject: sched/cputime: Improve cputime_adjust() People report that utime and stime from /proc//stat become very wrong when the numbers are big enough, especially if you watch these counters incrementally. Specifically, the current implementation of: stime*rtime/total, results in a saw-tooth function on top of the desired line, where the teeth grow in size the larger the values become. IOW, it has a relative error. The result is that, when watching incrementally as time progresses (for large values), we'll see periods of pure stime or utime increase, irrespective of the actual ratio we're striving for. Replace scale_stime() with a math64.h helper: mul_u64_u64_div_u64() that is far more accurate. This also allows architectures to override the implementation -- for instance they can opt for the old algorithm if this new one turns out to be too expensive for them. Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200519172506.GA317395@hirez.programming.kicks-ass.net --- include/linux/math64.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index 11a267413e8e..d097119419e6 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -263,6 +263,8 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) } #endif /* mul_u64_u32_div */ +u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div); + #define DIV64_U64_ROUND_UP(ll, d) \ ({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); }) -- cgit v1.2.3 From 461daba06bdcb9c7a3f92b9bbd110e1f7d093ffc Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 28 May 2020 12:54:42 -0700 Subject: psi: eliminate kthread_worker from psi trigger scheduling mechanism Each psi group requires a dedicated kthread_delayed_work and kthread_worker. Since no other work can be performed using psi_group's kthread_worker, the same result can be obtained using a task_struct and a timer directly. This makes psi triggering simpler by removing lists and locks involved with kthread_worker usage and eliminates the need for poll_scheduled atomic use in the hot path. Signed-off-by: Suren Baghdasaryan Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200528195442.190116-1-surenb@google.com --- include/linux/psi_types.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 4b7258495a04..b95f3211566a 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -153,9 +153,10 @@ struct psi_group { unsigned long avg[NR_PSI_STATES - 1][3]; /* Monitor work control */ - atomic_t poll_scheduled; - struct kthread_worker __rcu *poll_kworker; - struct kthread_delayed_work poll_work; + struct task_struct __rcu *poll_task; + struct timer_list poll_timer; + wait_queue_head_t poll_wait; + atomic_t poll_wakeup; /* Protects data used by the monitor */ struct mutex trigger_lock; -- cgit v1.2.3 From 9cc5b8656892a72438ee7deb5e80f5be47643b8b Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 27 May 2020 16:29:09 +0200 Subject: isolcpus: Affine unbound kernel threads to housekeeping cpus This is a kernel enhancement that configures the cpu affinity of kernel threads via kernel boot option nohz_full=. When this option is specified, the cpumask is immediately applied upon kthread launch. This does not affect kernel threads that specify cpu and node. This allows CPU isolation (that is not allowing certain threads to execute on certain CPUs) without using the isolcpus=domain parameter, making it possible to enable load balancing on such CPUs during runtime (see kernel-parameters.txt). Note-1: this is based off on Wind River's patch at https://github.com/starlingx-staging/stx-integ/blob/master/kernel/kernel-std/centos/patches/affine-compute-kernel-threads.patch Difference being that this patch is limited to modifying kernel thread cpumask. Behaviour of other threads can be controlled via cgroups or sched_setaffinity. Note-2: Wind River's patch was based off Christoph Lameter's patch at https://lwn.net/Articles/565932/ with the only difference being the kernel parameter changed from kthread to kthread_cpus. Signed-off-by: Frederic Weisbecker Signed-off-by: Marcelo Tosatti Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200527142909.23372-3-frederic@kernel.org --- include/linux/sched/isolation.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 0fbcbacd1b29..cc9f393e2a70 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -14,6 +14,7 @@ enum hk_flags { HK_FLAG_DOMAIN = (1 << 5), HK_FLAG_WQ = (1 << 6), HK_FLAG_MANAGED_IRQ = (1 << 7), + HK_FLAG_KTHREAD = (1 << 8), }; #ifdef CONFIG_CPU_ISOLATION -- cgit v1.2.3 From b4098bfc5efb1fd7ecf40165132a1283aeea3500 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 26 Jul 2019 16:54:10 +0200 Subject: sched/deadline: Impose global limits on sched_attr::sched_period Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20190726161357.397880775@infradead.org --- include/linux/sched/sysctl.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 660ac49f2b53..24be30a40814 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -61,6 +61,9 @@ int sched_proc_update_handler(struct ctl_table *table, int write, extern unsigned int sysctl_sched_rt_period; extern int sysctl_sched_rt_runtime; +extern unsigned int sysctl_sched_dl_period_max; +extern unsigned int sysctl_sched_dl_period_min; + #ifdef CONFIG_UCLAMP_TASK extern unsigned int sysctl_sched_uclamp_util_min; extern unsigned int sysctl_sched_uclamp_util_max; -- cgit v1.2.3 From e79302ae8c8cceb51cf642d5ace9da02668cb7b4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 2 Jun 2020 17:04:03 +0200 Subject: kcsan: Remove __no_kcsan_or_inline There are no more user of this function attribute, also, with us now actively supporting '__no_kcsan inline' it doesn't make sense to have in any case. Signed-off-by: Peter Zijlstra (Intel) --- include/linux/compiler_types.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 21aed0981edf..938249809511 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -193,10 +193,7 @@ struct ftrace_likely_data { #define __no_kcsan __no_sanitize_thread #ifdef __SANITIZE_THREAD__ -# define __no_kcsan_or_inline __no_kcsan notrace __maybe_unused -# define __no_sanitize_or_inline __no_kcsan_or_inline -#else -# define __no_kcsan_or_inline __always_inline +# define __no_sanitize_or_inline __no_kcsan notrace __maybe_unused #endif #ifndef __no_sanitize_or_inline -- cgit v1.2.3 From 5ddbc4082e1072eeeae52ff561a88620a05be08f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 2 Jun 2020 18:47:11 +0200 Subject: x86, kcsan: Add __no_kcsan to noinstr The 'noinstr' function attribute means no-instrumentation, this should very much include *SAN. Because lots of that is broken at present, only include KCSAN for now, as that is limited to clang11, which has sane function attribute behaviour. Signed-off-by: Peter Zijlstra (Intel) --- include/linux/compiler_types.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 938249809511..a8b4266084a1 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -118,10 +118,6 @@ struct ftrace_likely_data { #define notrace __attribute__((__no_instrument_function__)) #endif -/* Section for code which can't be instrumented at all */ -#define noinstr \ - noinline notrace __attribute((__section__(".noinstr.text"))) - /* * it doesn't make sense on ARM (currently the only user of __naked) * to trace naked functions because then mcount is called without @@ -200,6 +196,10 @@ struct ftrace_likely_data { #define __no_sanitize_or_inline __always_inline #endif +/* Section for code which can't be instrumented at all */ +#define noinstr \ + noinline notrace __attribute((__section__(".noinstr.text"))) __no_kcsan + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ -- cgit v1.2.3 From 5144f8a8dfd7b3681f0a2b5bf599a210b2315018 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 4 Jun 2020 07:58:11 +0200 Subject: compiler_types.h: Add __no_sanitize_{address,undefined} to noinstr Adds the portable definitions for __no_sanitize_address, and __no_sanitize_undefined, and subsequently changes noinstr to use the attributes to disable instrumentation via KASAN or UBSAN. Reported-by: syzbot+dc1fa714cb070b184db5@syzkaller.appspotmail.com Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Acked-by: Miguel Ojeda Link: https://lore.kernel.org/lkml/000000000000d2474c05a6c938fe@google.com/ --- include/linux/compiler-clang.h | 8 ++++++++ include/linux/compiler-gcc.h | 6 ++++++ include/linux/compiler_types.h | 3 ++- 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index ee37256ec8bd..5e55302e3bf6 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -33,6 +33,14 @@ #define __no_sanitize_thread #endif +#if __has_feature(undefined_behavior_sanitizer) +/* GCC does not have __SANITIZE_UNDEFINED__ */ +#define __no_sanitize_undefined \ + __attribute__((no_sanitize("undefined"))) +#else +#define __no_sanitize_undefined +#endif + /* * Not all versions of clang implement the the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 7dd4e0349ef3..1c74464c80c6 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -150,6 +150,12 @@ #define __no_sanitize_thread #endif +#if __has_attribute(__no_sanitize_undefined__) +#define __no_sanitize_undefined __attribute__((no_sanitize_undefined)) +#else +#define __no_sanitize_undefined +#endif + #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index a8b4266084a1..85b8d2370c24 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -198,7 +198,8 @@ struct ftrace_likely_data { /* Section for code which can't be instrumented at all */ #define noinstr \ - noinline notrace __attribute((__section__(".noinstr.text"))) __no_kcsan + noinline notrace __attribute((__section__(".noinstr.text"))) \ + __no_kcsan __no_sanitize_address __no_sanitize_undefined #endif /* __KERNEL__ */ -- cgit v1.2.3 From 6b643a07a7e41f9e11cfbb9bba4c5c9791ac2997 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 3 Jun 2020 20:09:06 +0200 Subject: x86/entry, ubsan, objtool: Whitelist __ubsan_handle_*() The UBSAN instrumentation only inserts external CALLs when things go 'BAD', much like WARN(). So treat them similar to WARN()s for noinstr, that is: allow them, at the risk of taking the machine down, to get their message out. Suggested-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Acked-by: Marco Elver --- include/linux/compiler_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 85b8d2370c24..14513e88b7e0 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -199,7 +199,7 @@ struct ftrace_likely_data { /* Section for code which can't be instrumented at all */ #define noinstr \ noinline notrace __attribute((__section__(".noinstr.text"))) \ - __no_kcsan __no_sanitize_address __no_sanitize_undefined + __no_kcsan __no_sanitize_address #endif /* __KERNEL__ */ -- cgit v1.2.3 From 7318d4cc14c8c8a5dde2b0b72ea50fd2545f0b7a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 21 Apr 2020 12:09:13 +0200 Subject: sched: Provide sched_set_fifo() SCHED_FIFO (or any static priority scheduler) is a broken scheduler model; it is fundamentally incapable of resource management, the one thing an OS is actually supposed to do. It is impossible to compose static priority workloads. One cannot take two well designed and functional static priority workloads and mash them together and still expect them to work. Therefore it doesn't make sense to expose the priority field; the kernel is fundamentally incapable of setting a sensible value, it needs systems knowledge that it doesn't have. Take away sched_setschedule() / sched_setattr() from modules and replace them with: - sched_set_fifo(p); create a FIFO task (at prio 50) - sched_set_fifo_low(p); create a task higher than NORMAL, which ends up being a FIFO task at prio 1. - sched_set_normal(p, nice); (re)set the task to normal This stops the proliferation of randomly chosen, and irrelevant, FIFO priorities that dont't really mean anything anyway. The system administrator/integrator, whoever has insight into the actual system design and requirements (userspace) can set-up appropriate priorities if and when needed. Cc: airlied@redhat.com Cc: alexander.deucher@amd.com Cc: awalls@md.metrocast.net Cc: axboe@kernel.dk Cc: broonie@kernel.org Cc: daniel.lezcano@linaro.org Cc: gregkh@linuxfoundation.org Cc: hannes@cmpxchg.org Cc: herbert@gondor.apana.org.au Cc: hverkuil@xs4all.nl Cc: john.stultz@linaro.org Cc: nico@fluxnic.net Cc: paulmck@kernel.org Cc: rafael.j.wysocki@intel.com Cc: rmk+kernel@arm.linux.org.uk Cc: sudeep.holla@arm.com Cc: tglx@linutronix.de Cc: ulf.hansson@linaro.org Cc: wim@linux-watchdog.org Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ingo Molnar Tested-by: Paul E. McKenney --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b62e6aaf28f0..b792b8f0f4cf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1653,6 +1653,9 @@ extern int idle_cpu(int cpu); extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); +extern int sched_set_fifo(struct task_struct *p); +extern int sched_set_fifo_low(struct task_struct *p); +extern int sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); -- cgit v1.2.3 From 8b700983de82f79e05b2c1136d6513ea4c9b22c4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 22 Apr 2020 13:10:04 +0200 Subject: sched: Remove sched_set_*() return value Ingo suggested that since the new sched_set_*() functions are implemented using the 'nocheck' variants, they really shouldn't ever fail, so remove the return value. Cc: axboe@kernel.dk Cc: daniel.lezcano@linaro.org Cc: sudeep.holla@arm.com Cc: airlied@redhat.com Cc: broonie@kernel.org Cc: paulmck@kernel.org Suggested-by: Ingo Molnar Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ingo Molnar --- include/linux/sched.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b792b8f0f4cf..ae7664492af2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1653,9 +1653,9 @@ extern int idle_cpu(int cpu); extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); -extern int sched_set_fifo(struct task_struct *p); -extern int sched_set_fifo_low(struct task_struct *p); -extern int sched_set_normal(struct task_struct *p, int nice); +extern void sched_set_fifo(struct task_struct *p); +extern void sched_set_fifo_low(struct task_struct *p); +extern void sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); -- cgit v1.2.3 From 7dfc06a0f25b593a9f51992f540c0f80a57f3629 Mon Sep 17 00:00:00 2001 From: Fabian Vogt Date: Mon, 15 Jun 2020 09:16:36 +0200 Subject: efi/tpm: Verify event log header before parsing It is possible that the first event in the event log is not actually a log header at all, but rather a normal event. This leads to the cast in __calc_tpm2_event_size being an invalid conversion, which means that the values read are effectively garbage. Depending on the first event's contents, this leads either to apparently normal behaviour, a crash or a freeze. While this behaviour of the firmware is not in accordance with the TCG Client EFI Specification, this happens on a Dell Precision 5510 with the TPM enabled but hidden from the OS ("TPM On" disabled, state otherwise untouched). The EFI firmware claims that the TPM is present and active and that it supports the TCG 2.0 event log format. Fortunately, this can be worked around by simply checking the header of the first event and the event log header signature itself. Commit b4f1874c6216 ("tpm: check event log version before reading final events") addressed a similar issue also found on Dell models. Fixes: 6b0326190205 ("efi: Attempt to get the TCG2 event log in the boot stub") Signed-off-by: Fabian Vogt Link: https://lore.kernel.org/r/1927248.evlx2EsYKh@linux-e202.suse.de Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1165773 Signed-off-by: Ard Biesheuvel --- include/linux/tpm_eventlog.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 4f8c90c93c29..64356b199e94 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -81,6 +81,8 @@ struct tcg_efi_specid_event_algs { u16 digest_size; } __packed; +#define TCG_SPECID_SIG "Spec ID Event03" + struct tcg_efi_specid_event_head { u8 signature[16]; u32 platform_class; @@ -171,6 +173,7 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, int i; int j; u32 count, event_type; + const u8 zero_digest[sizeof(event_header->digest)] = {0}; marker = event; marker_start = marker; @@ -198,10 +201,19 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, count = READ_ONCE(event->count); event_type = READ_ONCE(event->event_type); + /* Verify that it's the log header */ + if (event_header->pcr_idx != 0 || + event_header->event_type != NO_ACTION || + memcmp(event_header->digest, zero_digest, sizeof(zero_digest))) { + size = 0; + goto out; + } + efispecid = (struct tcg_efi_specid_event_head *)event_header->event; /* Check if event is malformed. */ - if (count > efispecid->num_algs) { + if (memcmp(efispecid->signature, TCG_SPECID_SIG, + sizeof(TCG_SPECID_SIG)) || count > efispecid->num_algs) { size = 0; goto out; } -- cgit v1.2.3 From 2963795122f50b36ed16e3ba880c3ed2de1bda6e Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 27 May 2020 12:14:25 -0500 Subject: efi: Replace zero-length array and use struct_size() helper The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. Lastly, make use of the sizeof_field() helper instead of an open-coded version. This issue was found with the help of Coccinelle and audited _manually_. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20200527171425.GA4053@embeddedor Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 2c6495f72f79..c3449c9699d0 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1236,14 +1236,11 @@ struct linux_efi_memreserve { struct { phys_addr_t base; phys_addr_t size; - } entry[0]; + } entry[]; }; -#define EFI_MEMRESERVE_SIZE(count) (sizeof(struct linux_efi_memreserve) + \ - (count) * sizeof(((struct linux_efi_memreserve *)0)->entry[0])) - #define EFI_MEMRESERVE_COUNT(size) (((size) - sizeof(struct linux_efi_memreserve)) \ - / sizeof(((struct linux_efi_memreserve *)0)->entry[0])) + / sizeof_field(struct linux_efi_memreserve, entry[0])) void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size); -- cgit v1.2.3 From 4b9e7edb5afc4e3c27d6623f5008bf53ae96cf1a Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 15 Jun 2020 09:23:13 +0200 Subject: regmap: convert all regmap_update_bits() and co. macros to static inlines There's no reason to have these as macros. Let's convert them all to static inlines for better readability and stronger typing. Suggested-by: Mark Brown Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20200615072313.11106-1-brgl@bgdev.pl Signed-off-by: Mark Brown --- include/linux/regmap.h | 222 ++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 192 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index cb666b9c6b6a..f4917efed5c3 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -80,36 +80,6 @@ struct reg_sequence { } #define REG_SEQ0(_reg, _def) REG_SEQ(_reg, _def, 0) -#define regmap_update_bits(map, reg, mask, val) \ - regmap_update_bits_base(map, reg, mask, val, NULL, false, false) -#define regmap_update_bits_async(map, reg, mask, val)\ - regmap_update_bits_base(map, reg, mask, val, NULL, true, false) -#define regmap_update_bits_check(map, reg, mask, val, change)\ - regmap_update_bits_base(map, reg, mask, val, change, false, false) -#define regmap_update_bits_check_async(map, reg, mask, val, change)\ - regmap_update_bits_base(map, reg, mask, val, change, true, false) - -#define regmap_write_bits(map, reg, mask, val) \ - regmap_update_bits_base(map, reg, mask, val, NULL, false, true) - -#define regmap_field_write(field, val) \ - regmap_field_update_bits_base(field, ~0, val, NULL, false, false) -#define regmap_field_force_write(field, val) \ - regmap_field_update_bits_base(field, ~0, val, NULL, false, true) -#define regmap_field_update_bits(field, mask, val)\ - regmap_field_update_bits_base(field, mask, val, NULL, false, false) -#define regmap_field_force_update_bits(field, mask, val) \ - regmap_field_update_bits_base(field, mask, val, NULL, false, true) - -#define regmap_fields_write(field, id, val) \ - regmap_fields_update_bits_base(field, id, ~0, val, NULL, false, false) -#define regmap_fields_force_write(field, id, val) \ - regmap_fields_update_bits_base(field, id, ~0, val, NULL, false, true) -#define regmap_fields_update_bits(field, id, mask, val)\ - regmap_fields_update_bits_base(field, id, mask, val, NULL, false, false) -#define regmap_fields_force_update_bits(field, id, mask, val) \ - regmap_fields_update_bits_base(field, id, mask, val, NULL, false, true) - /** * regmap_read_poll_timeout - Poll until a condition is met or a timeout occurs * @@ -1054,6 +1024,42 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, int regmap_update_bits_base(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change, bool async, bool force); + +static inline int regmap_update_bits(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val) +{ + return regmap_update_bits_base(map, reg, mask, val, NULL, false, false); +} + +static inline int regmap_update_bits_async(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val) +{ + return regmap_update_bits_base(map, reg, mask, val, NULL, true, false); +} + +static inline int regmap_update_bits_check(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val, + bool *change) +{ + return regmap_update_bits_base(map, reg, mask, val, + change, false, false); +} + +static inline int +regmap_update_bits_check_async(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val, + bool *change) +{ + return regmap_update_bits_base(map, reg, mask, val, + change, true, false); +} + +static inline int regmap_write_bits(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val) +{ + return regmap_update_bits_base(map, reg, mask, val, NULL, false, true); +} + int regmap_get_val_bytes(struct regmap *map); int regmap_get_max_register(struct regmap *map); int regmap_get_reg_stride(struct regmap *map); @@ -1152,6 +1158,65 @@ int regmap_fields_read(struct regmap_field *field, unsigned int id, int regmap_fields_update_bits_base(struct regmap_field *field, unsigned int id, unsigned int mask, unsigned int val, bool *change, bool async, bool force); + +static inline int regmap_field_write(struct regmap_field *field, + unsigned int val) +{ + return regmap_field_update_bits_base(field, ~0, val, + NULL, false, false); +} + +static inline int regmap_field_force_write(struct regmap_field *field, + unsigned int val) +{ + return regmap_field_update_bits_base(field, ~0, val, NULL, false, true); +} + +static inline int regmap_field_update_bits(struct regmap_field *field, + unsigned int mask, unsigned int val) +{ + return regmap_field_update_bits_base(field, mask, val, + NULL, false, false); +} + +static inline int +regmap_field_force_update_bits(struct regmap_field *field, + unsigned int mask, unsigned int val) +{ + return regmap_field_update_bits_base(field, mask, val, + NULL, false, true); +} + +static inline int regmap_fields_write(struct regmap_field *field, + unsigned int id, unsigned int val) +{ + return regmap_fields_update_bits_base(field, id, ~0, val, + NULL, false, false); +} + +static inline int regmap_fields_force_write(struct regmap_field *field, + unsigned int id, unsigned int val) +{ + return regmap_fields_update_bits_base(field, id, ~0, val, + NULL, false, true); +} + +static inline int +regmap_fields_update_bits(struct regmap_field *field, unsigned int id, + unsigned int mask, unsigned int val) +{ + return regmap_fields_update_bits_base(field, id, mask, val, + NULL, false, false); +} + +static inline int +regmap_fields_force_update_bits(struct regmap_field *field, unsigned int id, + unsigned int mask, unsigned int val) +{ + return regmap_fields_update_bits_base(field, id, mask, val, + NULL, false, true); +} + /** * struct regmap_irq_type - IRQ type definitions. * @@ -1458,6 +1523,103 @@ static inline int regmap_fields_update_bits_base(struct regmap_field *field, return -EINVAL; } +static inline int regmap_update_bits(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_update_bits_async(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_update_bits_check(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val, + bool *change) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int +regmap_update_bits_check_async(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val, + bool *change) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_write_bits(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_field_write(struct regmap_field *field, + unsigned int val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_field_force_write(struct regmap_field *field, + unsigned int val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_field_update_bits(struct regmap_field *field, + unsigned int mask, unsigned int val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int +regmap_field_force_update_bits(struct regmap_field *field, + unsigned int mask, unsigned int val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_fields_write(struct regmap_field *field, + unsigned int id, unsigned int val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int regmap_fields_force_write(struct regmap_field *field, + unsigned int id, unsigned int val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int +regmap_fields_update_bits(struct regmap_field *field, unsigned int id, + unsigned int mask, unsigned int val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + +static inline int +regmap_fields_force_update_bits(struct regmap_field *field, unsigned int id, + unsigned int mask, unsigned int val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_get_val_bytes(struct regmap *map) { WARN_ONCE(1, "regmap API is disabled"); -- cgit v1.2.3 From dff08caf35ecef4f7647f8b1e40877a254852a2b Mon Sep 17 00:00:00 2001 From: Pi-Hsun Shih Date: Fri, 12 Jun 2020 12:05:19 +0800 Subject: platform/chrome: cros_ec: Add command for regulator control. Add host commands for voltage regulator control through ChromeOS EC. Signed-off-by: Pi-Hsun Shih Reviewed-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20200612040526.192878-3-pihsun@chromium.org Signed-off-by: Mark Brown --- include/linux/platform_data/cros_ec_commands.h | 82 ++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 69210881ebac..a417b51b5764 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -5430,6 +5430,88 @@ struct ec_response_rollback_info { /* Issue AP reset */ #define EC_CMD_AP_RESET 0x0125 +/*****************************************************************************/ +/* Voltage regulator controls */ + +/* + * Get basic info of voltage regulator for given index. + * + * Returns the regulator name and supported voltage list in mV. + */ +#define EC_CMD_REGULATOR_GET_INFO 0x012B + +/* Maximum length of regulator name */ +#define EC_REGULATOR_NAME_MAX_LEN 16 + +/* Maximum length of the supported voltage list. */ +#define EC_REGULATOR_VOLTAGE_MAX_COUNT 16 + +struct ec_params_regulator_get_info { + uint32_t index; +} __ec_align4; + +struct ec_response_regulator_get_info { + char name[EC_REGULATOR_NAME_MAX_LEN]; + uint16_t num_voltages; + uint16_t voltages_mv[EC_REGULATOR_VOLTAGE_MAX_COUNT]; +} __ec_align1; + +/* + * Configure the regulator as enabled / disabled. + */ +#define EC_CMD_REGULATOR_ENABLE 0x012C + +struct ec_params_regulator_enable { + uint32_t index; + uint8_t enable; +} __ec_align4; + +/* + * Query if the regulator is enabled. + * + * Returns 1 if the regulator is enabled, 0 if not. + */ +#define EC_CMD_REGULATOR_IS_ENABLED 0x012D + +struct ec_params_regulator_is_enabled { + uint32_t index; +} __ec_align4; + +struct ec_response_regulator_is_enabled { + uint8_t enabled; +} __ec_align1; + +/* + * Set voltage for the voltage regulator within the range specified. + * + * The driver should select the voltage in range closest to min_mv. + * + * Also note that this might be called before the regulator is enabled, and the + * setting should be in effect after the regulator is enabled. + */ +#define EC_CMD_REGULATOR_SET_VOLTAGE 0x012E + +struct ec_params_regulator_set_voltage { + uint32_t index; + uint32_t min_mv; + uint32_t max_mv; +} __ec_align4; + +/* + * Get the currently configured voltage for the voltage regulator. + * + * Note that this might be called before the regulator is enabled. + */ +#define EC_CMD_REGULATOR_GET_VOLTAGE 0x012F + +struct ec_params_regulator_get_voltage { + uint32_t index; +} __ec_align4; + +struct ec_response_regulator_get_voltage { + uint32_t voltage_mv; +} __ec_align4; + /*****************************************************************************/ /* The command range 0x200-0x2FF is reserved for Rotor. */ -- cgit v1.2.3 From 8e04187c1bc7953f6dfad3400c58b1b0b0ad767b Mon Sep 17 00:00:00 2001 From: Xu Yilun Date: Thu, 11 Jun 2020 11:25:07 +0800 Subject: spi: altera: add SPI core parameters support via platform data. This patch introduced SPI core parameters in platform data, it allows passing these SPI core parameters via platform data. Signed-off-by: Wu Hao Signed-off-by: Xu Yilun Signed-off-by: Matthew Gerlach Signed-off-by: Russ Weight Reviewed-by: Tom Rix Link: https://lore.kernel.org/r/1591845911-10197-3-git-send-email-yilun.xu@intel.com Signed-off-by: Mark Brown --- include/linux/spi/altera.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100644 include/linux/spi/altera.h (limited to 'include/linux') diff --git a/include/linux/spi/altera.h b/include/linux/spi/altera.h new file mode 100644 index 000000000000..344a3fce56a4 --- /dev/null +++ b/include/linux/spi/altera.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Header File for Altera SPI Driver. + */ +#ifndef __LINUX_SPI_ALTERA_H +#define __LINUX_SPI_ALTERA_H + +#include +#include +#include + +/** + * struct altera_spi_platform_data - Platform data of the Altera SPI driver + * @mode_bits: Mode bits of SPI master. + * @num_chipselect: Number of chipselects. + * @bits_per_word_mask: bitmask of supported bits_per_word for transfers. + */ +struct altera_spi_platform_data { + u16 mode_bits; + u16 num_chipselect; + u32 bits_per_word_mask; +}; + +#endif /* __LINUX_SPI_ALTERA_H */ -- cgit v1.2.3 From 1fccd182a4694a848f2d6f3b1820d6fc71d9c99d Mon Sep 17 00:00:00 2001 From: Xu Yilun Date: Thu, 11 Jun 2020 11:25:08 +0800 Subject: spi: altera: add platform data for slave information. This patch introduces platform data for slave information, it allows spi-altera to add new spi devices once master registration is done. Signed-off-by: Wu Hao Signed-off-by: Xu Yilun Signed-off-by: Matthew Gerlach Signed-off-by: Russ Weight Reviewed-by: Tom Rix Link: https://lore.kernel.org/r/1591845911-10197-4-git-send-email-yilun.xu@intel.com Signed-off-by: Mark Brown --- include/linux/spi/altera.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/altera.h b/include/linux/spi/altera.h index 344a3fce56a4..2d42641499a6 100644 --- a/include/linux/spi/altera.h +++ b/include/linux/spi/altera.h @@ -14,11 +14,16 @@ * @mode_bits: Mode bits of SPI master. * @num_chipselect: Number of chipselects. * @bits_per_word_mask: bitmask of supported bits_per_word for transfers. + * @num_devices: Number of devices that shall be added when the driver + * is probed. + * @devices: The devices to add. */ struct altera_spi_platform_data { u16 mode_bits; u16 num_chipselect; u32 bits_per_word_mask; + u16 num_devices; + struct spi_board_info *devices; }; #endif /* __LINUX_SPI_ALTERA_H */ -- cgit v1.2.3 From 7bb7ee8704fea9fec9eea53322b8464c3ed70a3d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 15 Jun 2020 08:46:23 +0200 Subject: scsi: libata: Provide an ata_scsi_dma_need_drain stub for !CONFIG_ATA SAS drivers can be compiled with ata support disabled. Provide a stub so that the drivers don't have to ifdef around wiring up ata_scsi_dma_need_drain. Link: https://lore.kernel.org/r/20200615064624.37317-2-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/linux/libata.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index af832852e620..042e584daca7 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1092,7 +1092,11 @@ extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd, #define ATA_SCSI_COMPAT_IOCTL /* empty */ #endif extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd); +#if IS_ENABLED(CONFIG_ATA) bool ata_scsi_dma_need_drain(struct request *rq); +#else +#define ata_scsi_dma_need_drain NULL +#endif extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev, unsigned int cmd, void __user *arg); extern bool ata_link_online(struct ata_link *link); -- cgit v1.2.3 From 466f966b1f4545acad150331911784d3f49ab1c3 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 28 May 2020 09:35:11 -0500 Subject: dmaengine: Replace zero-length array with flexible-array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://github.com/KSPP/linux/issues/21 Signed-off-by: Gustavo A. R. Silva --- include/linux/dmaengine.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index e1c03339918f..6283917edd90 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -153,7 +153,7 @@ struct dma_interleaved_template { bool dst_sgl; size_t numf; size_t frame_size; - struct data_chunk sgl[0]; + struct data_chunk sgl[]; }; /** @@ -535,7 +535,7 @@ struct dmaengine_unmap_data { struct device *dev; struct kref kref; size_t len; - dma_addr_t addr[0]; + dma_addr_t addr[]; }; struct dma_async_tx_descriptor; -- cgit v1.2.3 From d6562f1ca877e0c2b020be0a66d59592e9f37f24 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 28 May 2020 09:35:11 -0500 Subject: can: Replace zero-length array with flexible-array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://github.com/KSPP/linux/issues/21 Signed-off-by: Gustavo A. R. Silva --- include/linux/can/skb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index a954def26c0d..900b9f4e0605 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -34,7 +34,7 @@ struct can_skb_priv { int ifindex; int skbcnt; - struct can_frame cf[0]; + struct can_frame cf[]; }; static inline struct can_skb_priv *can_skb_prv(struct sk_buff *skb) -- cgit v1.2.3 From 6b5679d2378324d0ed1c02c8e828b3b8687d3b08 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 28 May 2020 09:35:11 -0500 Subject: cb710: Replace zero-length array with flexible-array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://github.com/KSPP/linux/issues/21 Signed-off-by: Gustavo A. R. Silva --- include/linux/cb710.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cb710.h b/include/linux/cb710.h index 60de3fedd3a7..405657a9a0d5 100644 --- a/include/linux/cb710.h +++ b/include/linux/cb710.h @@ -36,7 +36,7 @@ struct cb710_chip { unsigned slot_mask; unsigned slots; spinlock_t irq_lock; - struct cb710_slot slot[0]; + struct cb710_slot slot[]; }; /* NOTE: cb710_chip.slots is modified only during device init/exit and -- cgit v1.2.3 From 67cd46244611ca7b0d5447dac9a0cbd76b875210 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 28 May 2020 09:35:11 -0500 Subject: FS-Cache: Replace zero-length array with flexible-array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://github.com/KSPP/linux/issues/21 Signed-off-by: Gustavo A. R. Silva --- include/linux/fscache-cache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index ce0b5fbf239d..3f0b19dcfae7 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -46,7 +46,7 @@ struct fscache_cache_tag { unsigned long flags; #define FSCACHE_TAG_RESERVED 0 /* T if tag is reserved for a cache */ atomic_t usage; - char name[0]; /* tag name */ + char name[]; /* tag name */ }; /* -- cgit v1.2.3 From 764e515f41c82220b20099962f47ec952c9ca6de Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 28 May 2020 09:35:11 -0500 Subject: KVM: Replace zero-length array with flexible-array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://github.com/KSPP/linux/issues/21 Signed-off-by: Gustavo A. R. Silva --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 62ec926c78a0..d564855243d8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -409,7 +409,7 @@ struct kvm_irq_routing_table { * Array indexed by gsi. Each entry contains list of irq chips * the gsi is connected to. */ - struct hlist_head map[0]; + struct hlist_head map[]; }; #endif -- cgit v1.2.3 From 50b6951feb621ac6a246a6f773edc0a3b9b7f3b4 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 28 May 2020 09:35:11 -0500 Subject: kexec: Replace zero-length array with flexible-array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://github.com/KSPP/linux/issues/21 Signed-off-by: Gustavo A. R. Silva --- include/linux/kexec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 1776eb2e43a4..ea67910ae6b7 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -208,7 +208,7 @@ struct crash_mem_range { struct crash_mem { unsigned int max_nr_ranges; unsigned int nr_ranges; - struct crash_mem_range ranges[0]; + struct crash_mem_range ranges[]; }; extern int crash_exclude_mem_range(struct crash_mem *mem, -- cgit v1.2.3 From 67a862a94d5d55fbfde6942c81f9e51f943f452c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 28 May 2020 09:35:11 -0500 Subject: kprobes: Replace zero-length array with flexible-array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://github.com/KSPP/linux/issues/21 Signed-off-by: Gustavo A. R. Silva --- include/linux/kprobes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 594265bfd390..e210af75ee38 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -161,7 +161,7 @@ struct kretprobe_instance { kprobe_opcode_t *ret_addr; struct task_struct *task; void *fp; - char data[0]; + char data[]; }; struct kretprobe_blackpoint { -- cgit v1.2.3 From 9c5fbf05cb00cc9e6f1baf42751c6bfe1e6859ba Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 28 May 2020 09:35:11 -0500 Subject: libata: Replace zero-length array with flexible-array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://github.com/KSPP/linux/issues/21 Signed-off-by: Gustavo A. R. Silva --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index af832852e620..8bf5e59a7859 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -609,7 +609,7 @@ struct ata_host { struct task_struct *eh_owner; struct ata_port *simplex_claimed; /* channel owning the DMA */ - struct ata_port *ports[0]; + struct ata_port *ports[]; }; struct ata_queued_cmd { -- cgit v1.2.3 From af6bb61cc0a25fba4411f4348f01011c9a769047 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 28 May 2020 09:35:11 -0500 Subject: sctp: Replace zero-length array with flexible-array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://github.com/KSPP/linux/issues/21 Signed-off-by: Gustavo A. R. Silva --- include/linux/sctp.h | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 8ccd82105de8..76731230bbc5 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -221,7 +221,7 @@ struct sctp_datahdr { __be16 stream; __be16 ssn; __u32 ppid; - __u8 payload[0]; + __u8 payload[]; }; struct sctp_data_chunk { @@ -269,7 +269,7 @@ struct sctp_inithdr { __be16 num_outbound_streams; __be16 num_inbound_streams; __be32 initial_tsn; - __u8 params[0]; + __u8 params[]; }; struct sctp_init_chunk { @@ -299,13 +299,13 @@ struct sctp_cookie_preserve_param { /* Section 3.3.2.1 Host Name Address (11) */ struct sctp_hostname_param { struct sctp_paramhdr param_hdr; - uint8_t hostname[0]; + uint8_t hostname[]; }; /* Section 3.3.2.1 Supported Address Types (12) */ struct sctp_supported_addrs_param { struct sctp_paramhdr param_hdr; - __be16 types[0]; + __be16 types[]; }; /* ADDIP Section 3.2.6 Adaptation Layer Indication */ @@ -317,25 +317,25 @@ struct sctp_adaptation_ind_param { /* ADDIP Section 4.2.7 Supported Extensions Parameter */ struct sctp_supported_ext_param { struct sctp_paramhdr param_hdr; - __u8 chunks[0]; + __u8 chunks[]; }; /* AUTH Section 3.1 Random */ struct sctp_random_param { struct sctp_paramhdr param_hdr; - __u8 random_val[0]; + __u8 random_val[]; }; /* AUTH Section 3.2 Chunk List */ struct sctp_chunks_param { struct sctp_paramhdr param_hdr; - __u8 chunks[0]; + __u8 chunks[]; }; /* AUTH Section 3.3 HMAC Algorithm */ struct sctp_hmac_algo_param { struct sctp_paramhdr param_hdr; - __be16 hmac_ids[0]; + __be16 hmac_ids[]; }; /* RFC 2960. Section 3.3.3 Initiation Acknowledgement (INIT ACK) (2): @@ -350,7 +350,7 @@ struct sctp_initack_chunk { /* Section 3.3.3.1 State Cookie (7) */ struct sctp_cookie_param { struct sctp_paramhdr p; - __u8 body[0]; + __u8 body[]; }; /* Section 3.3.3.1 Unrecognized Parameters (8) */ @@ -384,7 +384,7 @@ struct sctp_sackhdr { __be32 a_rwnd; __be16 num_gap_ack_blocks; __be16 num_dup_tsns; - union sctp_sack_variable variable[0]; + union sctp_sack_variable variable[]; }; struct sctp_sack_chunk { @@ -436,7 +436,7 @@ struct sctp_shutdown_chunk { struct sctp_errhdr { __be16 cause; __be16 length; - __u8 variable[0]; + __u8 variable[]; }; struct sctp_operr_chunk { @@ -594,7 +594,7 @@ struct sctp_fwdtsn_skip { struct sctp_fwdtsn_hdr { __be32 new_cum_tsn; - struct sctp_fwdtsn_skip skip[0]; + struct sctp_fwdtsn_skip skip[]; }; struct sctp_fwdtsn_chunk { @@ -611,7 +611,7 @@ struct sctp_ifwdtsn_skip { struct sctp_ifwdtsn_hdr { __be32 new_cum_tsn; - struct sctp_ifwdtsn_skip skip[0]; + struct sctp_ifwdtsn_skip skip[]; }; struct sctp_ifwdtsn_chunk { @@ -658,7 +658,7 @@ struct sctp_addip_param { struct sctp_addiphdr { __be32 serial; - __u8 params[0]; + __u8 params[]; }; struct sctp_addip_chunk { @@ -718,7 +718,7 @@ struct sctp_addip_chunk { struct sctp_authhdr { __be16 shkey_id; __be16 hmac_id; - __u8 hmac[0]; + __u8 hmac[]; }; struct sctp_auth_chunk { @@ -733,7 +733,7 @@ struct sctp_infox { struct sctp_reconf_chunk { struct sctp_chunkhdr chunk_hdr; - __u8 params[0]; + __u8 params[]; }; struct sctp_strreset_outreq { @@ -741,13 +741,13 @@ struct sctp_strreset_outreq { __be32 request_seq; __be32 response_seq; __be32 send_reset_at_tsn; - __be16 list_of_streams[0]; + __be16 list_of_streams[]; }; struct sctp_strreset_inreq { struct sctp_paramhdr param_hdr; __be32 request_seq; - __be16 list_of_streams[0]; + __be16 list_of_streams[]; }; struct sctp_strreset_tsnreq { -- cgit v1.2.3 From 5cab1634e485ce7b33839f762f3bb9b5f009dc87 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 28 May 2020 09:35:11 -0500 Subject: tifm: Replace zero-length array with flexible-array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://github.com/KSPP/linux/issues/21 Signed-off-by: Gustavo A. R. Silva --- include/linux/tifm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tifm.h b/include/linux/tifm.h index 299cbb8c63bb..44073d06710f 100644 --- a/include/linux/tifm.h +++ b/include/linux/tifm.h @@ -124,7 +124,7 @@ struct tifm_adapter { int (*has_ms_pif)(struct tifm_adapter *fm, struct tifm_dev *sock); - struct tifm_dev *sockets[0]; + struct tifm_dev *sockets[]; }; struct tifm_adapter *tifm_alloc_adapter(unsigned int num_sockets, -- cgit v1.2.3 From 9357b04624013294e4204b1a837d0a611b9048c3 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Wed, 27 May 2020 17:47:31 +0200 Subject: reset: Move reset-simple header out of drivers/reset The reset-simple code can be useful for drivers outside of drivers/reset that have a few reset controls as part of their features. Let's move it to include/linux/reset. Reviewed-by: Philipp Zabel Signed-off-by: Maxime Ripard Signed-off-by: Philipp Zabel --- include/linux/reset/reset-simple.h | 41 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/linux/reset/reset-simple.h (limited to 'include/linux') diff --git a/include/linux/reset/reset-simple.h b/include/linux/reset/reset-simple.h new file mode 100644 index 000000000000..08ccb25a55e6 --- /dev/null +++ b/include/linux/reset/reset-simple.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Simple Reset Controller ops + * + * Based on Allwinner SoCs Reset Controller driver + * + * Copyright 2013 Maxime Ripard + * + * Maxime Ripard + */ + +#ifndef __RESET_SIMPLE_H__ +#define __RESET_SIMPLE_H__ + +#include +#include +#include + +/** + * struct reset_simple_data - driver data for simple reset controllers + * @lock: spinlock to protect registers during read-modify-write cycles + * @membase: memory mapped I/O register range + * @rcdev: reset controller device base structure + * @active_low: if true, bits are cleared to assert the reset. Otherwise, bits + * are set to assert the reset. Note that this says nothing about + * the voltage level of the actual reset line. + * @status_active_low: if true, bits read back as cleared while the reset is + * asserted. Otherwise, bits read back as set while the + * reset is asserted. + */ +struct reset_simple_data { + spinlock_t lock; + void __iomem *membase; + struct reset_controller_dev rcdev; + bool active_low; + bool status_active_low; +}; + +extern const struct reset_control_ops reset_simple_ops; + +#endif /* __RESET_SIMPLE_H__ */ -- cgit v1.2.3 From a9701376ed0fb61a5be4bb438daf26bd9cfa24b5 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Wed, 27 May 2020 17:47:32 +0200 Subject: reset: simple: Add reset callback The reset-simple code lacks a reset callback that is still pretty easy to implement. The only real thing to consider is the delay needed for a device to be reset, so let's expose that as part of the reset-simple driver data. Reviewed-by: Philipp Zabel Signed-off-by: Maxime Ripard Signed-off-by: Philipp Zabel --- include/linux/reset/reset-simple.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reset/reset-simple.h b/include/linux/reset/reset-simple.h index 08ccb25a55e6..c3e44f45b0f7 100644 --- a/include/linux/reset/reset-simple.h +++ b/include/linux/reset/reset-simple.h @@ -27,6 +27,12 @@ * @status_active_low: if true, bits read back as cleared while the reset is * asserted. Otherwise, bits read back as set while the * reset is asserted. + * @reset_us: Minimum delay in microseconds needed that needs to be + * waited for between an assert and a deassert to reset the + * device. If multiple consumers with different delay + * requirements are connected to this controller, it must + * be the largest minimum delay. 0 means that such a delay is + * unknown and the reset operation is unsupported. */ struct reset_simple_data { spinlock_t lock; @@ -34,6 +40,7 @@ struct reset_simple_data { struct reset_controller_dev rcdev; bool active_low; bool status_active_low; + unsigned int reset_us; }; extern const struct reset_control_ops reset_simple_ops; -- cgit v1.2.3 From 33aea07f30c261eff7ba229f19fd1b161e0fb851 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 16 Jun 2020 01:15:29 +0200 Subject: compiler_attributes.h: Support no_sanitize_undefined check with GCC 4 UBSAN is supported since GCC 4.9, which unfortunately did not yet have __has_attribute(). To work around, the __GCC4_has_attribute workaround requires defining which compiler version supports the given attribute. In the case of no_sanitize_undefined, it is the first version that supports UBSAN, which is GCC 4.9. Reported-by: kernel test robot Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Miguel Ojeda Link: https://lkml.kernel.org/r/20200615231529.GA119644@google.com --- include/linux/compiler_attributes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index cdf016596659..c8f03d2969df 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -40,6 +40,7 @@ # define __GCC4_has_attribute___noclone__ 1 # define __GCC4_has_attribute___nonstring__ 0 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) +# define __GCC4_has_attribute___no_sanitize_undefined__ (__GNUC_MINOR__ >= 9) # define __GCC4_has_attribute___fallthrough__ 0 #endif -- cgit v1.2.3 From 8a307d3601bcca99723b1a45e785adc3c9d3a476 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Artur=20=C5=9Awigo=C5=84?= Date: Thu, 21 May 2020 14:28:39 +0200 Subject: interconnect: Export of_icc_get_from_provider() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch makes the above function public (for use in exynos-bus devfreq driver). Signed-off-by: Artur Świgoń Reviewed-by: Krzysztof Kozlowski Reviewed-by: Chanwoo Choi Signed-off-by: Sylwester Nawrocki Link: https://lore.kernel.org/r/20200521122841.8867-2-s.nawrocki@samsung.com Signed-off-by: Georgi Djakov --- include/linux/interconnect-provider.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index 0c494534b4d3..c92be2a90fa0 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -103,6 +103,7 @@ void icc_node_del(struct icc_node *node); int icc_nodes_remove(struct icc_provider *provider); int icc_provider_add(struct icc_provider *provider); int icc_provider_del(struct icc_provider *provider); +struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec); #else @@ -154,6 +155,11 @@ static inline int icc_provider_del(struct icc_provider *provider) return -ENOTSUPP; } +static inline struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec) +{ + return ERR_PTR(-ENOTSUPP); +} + #endif /* CONFIG_INTERCONNECT */ #endif /* __LINUX_INTERCONNECT_PROVIDER_H */ -- cgit v1.2.3 From 65461e26b1fe73bde4326367ee23cc1a24e6c33e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Artur=20=C5=9Awigo=C5=84?= Date: Thu, 21 May 2020 14:28:41 +0200 Subject: interconnect: Allow inter-provider pairs to be configured MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds support for a new boolean 'inter_set' field in struct icc_provider. Setting it to 'true' enables calling '->set' for inter-provider node pairs. All existing users of the interconnect framework allocate this structure with kzalloc, and are therefore unaffected by this change. This makes it easier for hierarchies like exynos-bus, where every bus is probed separately and registers a separate interconnect provider, to model constraints between buses. Signed-off-by: Artur Świgoń Signed-off-by: Sylwester Nawrocki Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20200521122841.8867-4-s.nawrocki@samsung.com Signed-off-by: Georgi Djakov --- include/linux/interconnect-provider.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index c92be2a90fa0..38701925ab91 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -41,6 +41,7 @@ struct icc_node *of_icc_xlate_onecell(struct of_phandle_args *spec, * @xlate: provider-specific callback for mapping nodes from phandle arguments * @dev: the device this interconnect provider belongs to * @users: count of active users + * @inter_set: whether inter-provider pairs will be configured with @set * @data: pointer to private data */ struct icc_provider { @@ -53,6 +54,7 @@ struct icc_provider { struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data); struct device *dev; int users; + bool inter_set; void *data; }; -- cgit v1.2.3 From 12a400b016ab955be8e4c569346fa18aaceed9d7 Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Tue, 16 Jun 2020 16:43:23 +0300 Subject: interconnect: Mark all dummy functions as static inline There are a few dummy stub functions that are not marked as static inline yet. Currently this header file is not included in any other file outside of drivers/interconnect/, but that might not be the case in the future. If this file gets included and the framework is disabled, we will be see warnings. Let's fix this in advance. Link: https://lore.kernel.org/r/20200228145945.13579-1-georgi.djakov@linaro.org Signed-off-by: Georgi Djakov --- include/linux/interconnect-provider.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index 38701925ab91..4735518de515 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -120,7 +120,7 @@ static inline struct icc_node *icc_node_create(int id) return ERR_PTR(-ENOTSUPP); } -void icc_node_destroy(int id) +static inline void icc_node_destroy(int id) { } @@ -129,16 +129,16 @@ static inline int icc_link_create(struct icc_node *node, const int dst_id) return -ENOTSUPP; } -int icc_link_destroy(struct icc_node *src, struct icc_node *dst) +static inline int icc_link_destroy(struct icc_node *src, struct icc_node *dst) { return -ENOTSUPP; } -void icc_node_add(struct icc_node *node, struct icc_provider *provider) +static inline void icc_node_add(struct icc_node *node, struct icc_provider *provider) { } -void icc_node_del(struct icc_node *node) +static inline void icc_node_del(struct icc_node *node) { } -- cgit v1.2.3 From 22d2cfdffa5bff3566e16cb7320e13ceb814674b Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 4 Jun 2020 11:12:34 +0200 Subject: libceph: move away from global osd_req_flags osd_req_flags is overly general and doesn't suit its only user (read_from_replica option) well: - applying osd_req_flags in account_request() affects all OSD requests, including linger (i.e. watch and notify). However, linger requests should always go to the primary even though some of them are reads (e.g. notify has side effects but it is a read because it doesn't result in mutation on the OSDs). - calls to class methods that are reads are allowed to go to the replica, but most such calls issued for "rbd map" and/or exclusive lock transitions are requested to be resent to the primary via EAGAIN, doubling the latency. Get rid of global osd_req_flags and set read_from_replica flag only on specific OSD requests instead. Fixes: 8ad44d5e0d1e ("libceph: read_from_replica option") Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 2247e71beb83..e5ed1c541e7f 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -52,8 +52,7 @@ struct ceph_options { unsigned long osd_idle_ttl; /* jiffies */ unsigned long osd_keepalive_timeout; /* jiffies */ unsigned long osd_request_timeout; /* jiffies */ - - u32 osd_req_flags; /* CEPH_OSD_FLAG_*, applied to each OSD request */ + u32 read_from_replica; /* CEPH_OSD_FLAG_BALANCE/LOCALIZE_READS */ /* * any type that can't be simply compared or doesn't need @@ -76,6 +75,7 @@ struct ceph_options { #define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) #define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) #define CEPH_OSD_REQUEST_TIMEOUT_DEFAULT 0 /* no timeout */ +#define CEPH_READ_FROM_REPLICA_DEFAULT 0 /* read from primary */ #define CEPH_MONC_HUNT_INTERVAL msecs_to_jiffies(3 * 1000) #define CEPH_MONC_PING_INTERVAL msecs_to_jiffies(10 * 1000) -- cgit v1.2.3 From 2fd2bc7f49324e7b439e3c5584762abd0a9a13bc Mon Sep 17 00:00:00 2001 From: Colton Lewis Date: Sun, 14 Jun 2020 04:08:04 +0000 Subject: gpu: host1x: Correct trivial kernel-doc inconsistencies Silence documentation build warnings by adding kernel-doc fields. ./include/linux/host1x.h:69: warning: Function parameter or member 'parent' not described in 'host1x_client' ./include/linux/host1x.h:69: warning: Function parameter or member 'usecount' not described in 'host1x_client' ./include/linux/host1x.h:69: warning: Function parameter or member 'lock' not described in 'host1x_client' Signed-off-by: Colton Lewis Signed-off-by: Thierry Reding --- include/linux/host1x.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index c230b4e70d75..a3a568bf9686 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -48,6 +48,9 @@ struct host1x_client_ops { * @channel: host1x channel associated with this client * @syncpts: array of syncpoints requested for this client * @num_syncpts: number of syncpoints requested for this client + * @parent: pointer to parent structure + * @usecount: reference count for this structure + * @lock: mutex for mutually exclusive concurrency */ struct host1x_client { struct list_head list; -- cgit v1.2.3 From e370f886fefc23b9ca3011760d9376f1947eb321 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 16 Jun 2020 15:39:25 +0200 Subject: EDAC: Remove edac_get_dimm_by_index() It is unused now. Signed-off-by: Borislav Petkov --- include/linux/edac.h | 29 +++++++---------------------- 1 file changed, 7 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 6eb7d55d7c3d..15e8f3d8a895 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -594,27 +594,6 @@ struct mem_ctl_info { ? (mci)->dimms[(dimm)->idx + 1] \ : NULL) -/** - * edac_get_dimm_by_index - Get DIMM info at @index from a memory - * controller - * - * @mci: MC descriptor struct mem_ctl_info - * @index: index in the memory controller's DIMM array - * - * Returns a struct dimm_info * or NULL on failure. - */ -static inline struct dimm_info * -edac_get_dimm_by_index(struct mem_ctl_info *mci, int index) -{ - if (index < 0 || index >= mci->tot_dimms) - return NULL; - - if (WARN_ON_ONCE(mci->dimms[index]->idx != index)) - return NULL; - - return mci->dimms[index]; -} - /** * edac_get_dimm - Get DIMM info from a memory controller given by * [layer0,layer1,layer2] position @@ -650,6 +629,12 @@ static inline struct dimm_info *edac_get_dimm(struct mem_ctl_info *mci, if (mci->n_layers > 2) index = index * mci->layers[2].size + layer2; - return edac_get_dimm_by_index(mci, index); + if (index < 0 || index >= mci->tot_dimms) + return NULL; + + if (WARN_ON_ONCE(mci->dimms[index]->idx != index)) + return NULL; + + return mci->dimms[index]; } #endif /* _LINUX_EDAC_H_ */ -- cgit v1.2.3 From 278a5fbaed89dacd04e9d052f4594ffd0e0585de Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 24 May 2019 11:30:34 +0200 Subject: open: add close_range() This adds the close_range() syscall. It allows to efficiently close a range of file descriptors up to all file descriptors of a calling task. I was contacted by FreeBSD as they wanted to have the same close_range() syscall as we proposed here. We've coordinated this and in the meantime, Kyle was fast enough to merge close_range() into FreeBSD already in April: https://reviews.freebsd.org/D21627 https://svnweb.freebsd.org/base?view=revision&revision=359836 and the current plan is to backport close_range() to FreeBSD 12.2 (cf. [2]) once its merged in Linux too. Python is in the process of switching to close_range() on FreeBSD and they are waiting on us to merge this to switch on Linux as well: https://bugs.python.org/issue38061 The syscall came up in a recent discussion around the new mount API and making new file descriptor types cloexec by default. During this discussion, Al suggested the close_range() syscall (cf. [1]). Note, a syscall in this manner has been requested by various people over time. First, it helps to close all file descriptors of an exec()ing task. This can be done safely via (quoting Al's example from [1] verbatim): /* that exec is sensitive */ unshare(CLONE_FILES); /* we don't want anything past stderr here */ close_range(3, ~0U); execve(....); The code snippet above is one way of working around the problem that file descriptors are not cloexec by default. This is aggravated by the fact that we can't just switch them over without massively regressing userspace. For a whole class of programs having an in-kernel method of closing all file descriptors is very helpful (e.g. demons, service managers, programming language standard libraries, container managers etc.). (Please note, unshare(CLONE_FILES) should only be needed if the calling task is multi-threaded and shares the file descriptor table with another thread in which case two threads could race with one thread allocating file descriptors and the other one closing them via close_range(). For the general case close_range() before the execve() is sufficient.) Second, it allows userspace to avoid implementing closing all file descriptors by parsing through /proc//fd/* and calling close() on each file descriptor. From looking at various large(ish) userspace code bases this or similar patterns are very common in: - service managers (cf. [4]) - libcs (cf. [6]) - container runtimes (cf. [5]) - programming language runtimes/standard libraries - Python (cf. [2]) - Rust (cf. [7], [8]) As Dmitry pointed out there's even a long-standing glibc bug about missing kernel support for this task (cf. [3]). In addition, the syscall will also work for tasks that do not have procfs mounted and on kernels that do not have procfs support compiled in. In such situations the only way to make sure that all file descriptors are closed is to call close() on each file descriptor up to UINT_MAX or RLIMIT_NOFILE, OPEN_MAX trickery (cf. comment [8] on Rust). The performance is striking. For good measure, comparing the following simple close_all_fds() userspace implementation that is essentially just glibc's version in [6]: static int close_all_fds(void) { int dir_fd; DIR *dir; struct dirent *direntp; dir = opendir("/proc/self/fd"); if (!dir) return -1; dir_fd = dirfd(dir); while ((direntp = readdir(dir))) { int fd; if (strcmp(direntp->d_name, ".") == 0) continue; if (strcmp(direntp->d_name, "..") == 0) continue; fd = atoi(direntp->d_name); if (fd == dir_fd || fd == 0 || fd == 1 || fd == 2) continue; close(fd); } closedir(dir); return 0; } to close_range() yields: 1. closing 4 open files: - close_all_fds(): ~280 us - close_range(): ~24 us 2. closing 1000 open files: - close_all_fds(): ~5000 us - close_range(): ~800 us close_range() is designed to allow for some flexibility. Specifically, it does not simply always close all open file descriptors of a task. Instead, callers can specify an upper bound. This is e.g. useful for scenarios where specific file descriptors are created with well-known numbers that are supposed to be excluded from getting closed. For extra paranoia close_range() comes with a flags argument. This can e.g. be used to implement extension. Once can imagine userspace wanting to stop at the first error instead of ignoring errors under certain circumstances. There might be other valid ideas in the future. In any case, a flag argument doesn't hurt and keeps us on the safe side. From an implementation side this is kept rather dumb. It saw some input from David and Jann but all nonsense is obviously my own! - Errors to close file descriptors are currently ignored. (Could be changed by setting a flag in the future if needed.) - __close_range() is a rather simplistic wrapper around __close_fd(). My reasoning behind this is based on the nature of how __close_fd() needs to release an fd. But maybe I misunderstood specifics: We take the files_lock and rcu-dereference the fdtable of the calling task, we find the entry in the fdtable, get the file and need to release files_lock before calling filp_close(). In the meantime the fdtable might have been altered so we can't just retake the spinlock and keep the old rcu-reference of the fdtable around. Instead we need to grab a fresh reference to the fdtable. If my reasoning is correct then there's really no point in fancyfying __close_range(): We just need to rcu-dereference the fdtable of the calling task once to cap the max_fd value correctly and then go on calling __close_fd() in a loop. /* References */ [1]: https://lore.kernel.org/lkml/20190516165021.GD17978@ZenIV.linux.org.uk/ [2]: https://github.com/python/cpython/blob/9e4f2f3a6b8ee995c365e86d976937c141d867f8/Modules/_posixsubprocess.c#L220 [3]: https://sourceware.org/bugzilla/show_bug.cgi?id=10353#c7 [4]: https://github.com/systemd/systemd/blob/5238e9575906297608ff802a27e2ff9effa3b338/src/basic/fd-util.c#L217 [5]: https://github.com/lxc/lxc/blob/ddf4b77e11a4d08f09b7b9cd13e593f8c047edc5/src/lxc/start.c#L236 [6]: https://sourceware.org/git/?p=glibc.git;a=blob;f=sysdeps/unix/sysv/linux/grantpt.c;h=2030e07fa6e652aac32c775b8c6e005844c3c4eb;hb=HEAD#l17 Note that this is an internal implementation that is not exported. Currently, libc seems to not provide an exported version of this because of missing kernel support to do this. Note, in a recent patch series Florian made grantpt() a nop thereby removing the code referenced here. [7]: https://github.com/rust-lang/rust/issues/12148 [8]: https://github.com/rust-lang/rust/blob/5f47c0613ed4eb46fca3633c1297364c09e5e451/src/libstd/sys/unix/process2.rs#L303-L308 Rust's solution is slightly different but is equally unperformant. Rust calls getdtablesize() which is a glibc library function that simply returns the current RLIMIT_NOFILE or OPEN_MAX values. Rust then goes on to call close() on each fd. That's obviously overkill for most tasks. Rarely, tasks - especially non-demons - hit RLIMIT_NOFILE or OPEN_MAX. Let's be nice and assume an unprivileged user with RLIMIT_NOFILE set to 1024. Even in this case, there's a very high chance that in the common case Rust is calling the close() syscall 1021 times pointlessly if the task just has 0, 1, and 2 open. Suggested-by: Al Viro Signed-off-by: Christian Brauner Cc: Arnd Bergmann Cc: Kyle Evans Cc: Jann Horn Cc: David Howells Cc: Dmitry V. Levin Cc: Oleg Nesterov Cc: Linus Torvalds Cc: Florian Weimer Cc: linux-api@vger.kernel.org --- include/linux/fdtable.h | 2 ++ include/linux/syscalls.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index f07c55ea0c22..fcd07181a365 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -121,6 +121,8 @@ extern void __fd_install(struct files_struct *files, unsigned int fd, struct file *file); extern int __close_fd(struct files_struct *files, unsigned int fd); +extern int __close_range(struct files_struct *files, unsigned int fd, + unsigned int max_fd); extern int __close_fd_get_file(unsigned int fd, struct file **res); extern struct kmem_cache *files_cachep; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7c354c2955f5..b22382db89cf 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -444,6 +444,8 @@ asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, asmlinkage long sys_openat2(int dfd, const char __user *filename, struct open_how *how, size_t size); asmlinkage long sys_close(unsigned int fd); +asmlinkage long sys_close_range(unsigned int fd, unsigned int max_fd, + unsigned int flags); asmlinkage long sys_vhangup(void); /* fs/pipe.c */ -- cgit v1.2.3 From 60997c3d45d9a67daf01c56d805ae4fec37e0bd8 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 3 Jun 2020 21:48:55 +0200 Subject: close_range: add CLOSE_RANGE_UNSHARE One of the use-cases of close_range() is to drop file descriptors just before execve(). This would usually be expressed in the sequence: unshare(CLONE_FILES); close_range(3, ~0U); as pointed out by Linus it might be desirable to have this be a part of close_range() itself under a new flag CLOSE_RANGE_UNSHARE. This expands {dup,unshare)_fd() to take a max_fds argument that indicates the maximum number of file descriptors to copy from the old struct files. When the user requests that all file descriptors are supposed to be closed via close_range(min, max) then we can cap via unshare_fd(min) and hence don't need to do any of the heavy fput() work for everything above min. The patch makes it so that if CLOSE_RANGE_UNSHARE is requested and we do in fact currently share our file descriptor table we create a new private copy. We then close all fds in the requested range and finally after we're done we install the new fd table. Suggested-by: Linus Torvalds Signed-off-by: Christian Brauner --- include/linux/fdtable.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index fcd07181a365..a32bf47c593e 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -22,6 +22,7 @@ * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG +#define NR_OPEN_MAX ~0U struct fdtable { unsigned int max_fds; @@ -109,7 +110,7 @@ struct files_struct *get_files_struct(struct task_struct *); void put_files_struct(struct files_struct *fs); void reset_files_struct(struct files_struct *); int unshare_files(struct files_struct **); -struct files_struct *dup_fd(struct files_struct *, int *) __latent_entropy; +struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), @@ -121,9 +122,10 @@ extern void __fd_install(struct files_struct *files, unsigned int fd, struct file *file); extern int __close_fd(struct files_struct *files, unsigned int fd); -extern int __close_range(struct files_struct *files, unsigned int fd, - unsigned int max_fd); +extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); extern int __close_fd_get_file(unsigned int fd, struct file **res); +extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, + struct files_struct **new_fdp); extern struct kmem_cache *files_cachep; -- cgit v1.2.3 From 9b38cc704e844e41d9cf74e647bff1d249512cb3 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 12 May 2020 17:03:18 +0900 Subject: kretprobe: Prevent triggering kretprobe from within kprobe_flush_task Ziqian reported lockup when adding retprobe on _raw_spin_lock_irqsave. My test was also able to trigger lockdep output: ============================================ WARNING: possible recursive locking detected 5.6.0-rc6+ #6 Not tainted -------------------------------------------- sched-messaging/2767 is trying to acquire lock: ffffffff9a492798 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_hash_lock+0x52/0xa0 but task is already holding lock: ffffffff9a491a18 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_trampoline+0x0/0x50 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(kretprobe_table_locks[i].lock)); lock(&(kretprobe_table_locks[i].lock)); *** DEADLOCK *** May be due to missing lock nesting notation 1 lock held by sched-messaging/2767: #0: ffffffff9a491a18 (&(kretprobe_table_locks[i].lock)){-.-.}, at: kretprobe_trampoline+0x0/0x50 stack backtrace: CPU: 3 PID: 2767 Comm: sched-messaging Not tainted 5.6.0-rc6+ #6 Call Trace: dump_stack+0x96/0xe0 __lock_acquire.cold.57+0x173/0x2b7 ? native_queued_spin_lock_slowpath+0x42b/0x9e0 ? lockdep_hardirqs_on+0x590/0x590 ? __lock_acquire+0xf63/0x4030 lock_acquire+0x15a/0x3d0 ? kretprobe_hash_lock+0x52/0xa0 _raw_spin_lock_irqsave+0x36/0x70 ? kretprobe_hash_lock+0x52/0xa0 kretprobe_hash_lock+0x52/0xa0 trampoline_handler+0xf8/0x940 ? kprobe_fault_handler+0x380/0x380 ? find_held_lock+0x3a/0x1c0 kretprobe_trampoline+0x25/0x50 ? lock_acquired+0x392/0xbc0 ? _raw_spin_lock_irqsave+0x50/0x70 ? __get_valid_kprobe+0x1f0/0x1f0 ? _raw_spin_unlock_irqrestore+0x3b/0x40 ? finish_task_switch+0x4b9/0x6d0 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 The code within the kretprobe handler checks for probe reentrancy, so we won't trigger any _raw_spin_lock_irqsave probe in there. The problem is in outside kprobe_flush_task, where we call: kprobe_flush_task kretprobe_table_lock raw_spin_lock_irqsave _raw_spin_lock_irqsave where _raw_spin_lock_irqsave triggers the kretprobe and installs kretprobe_trampoline handler on _raw_spin_lock_irqsave return. The kretprobe_trampoline handler is then executed with already locked kretprobe_table_locks, and first thing it does is to lock kretprobe_table_locks ;-) the whole lockup path like: kprobe_flush_task kretprobe_table_lock raw_spin_lock_irqsave _raw_spin_lock_irqsave ---> probe triggered, kretprobe_trampoline installed ---> kretprobe_table_locks locked kretprobe_trampoline trampoline_handler kretprobe_hash_lock(current, &head, &flags); <--- deadlock Adding kprobe_busy_begin/end helpers that mark code with fake probe installed to prevent triggering of another kprobe within this code. Using these helpers in kprobe_flush_task, so the probe recursion protection check is hit and the probe is never set to prevent above lockup. Link: http://lkml.kernel.org/r/158927059835.27680.7011202830041561604.stgit@devnote2 Fixes: ef53d9c5e4da ("kprobes: improve kretprobe scalability with hashed locking") Cc: Ingo Molnar Cc: "Gustavo A . R . Silva" Cc: Anders Roxell Cc: "Naveen N . Rao" Cc: Anil S Keshavamurthy Cc: David Miller Cc: Ingo Molnar Cc: Peter Zijlstra Cc: stable@vger.kernel.org Reported-by: "Ziqian SUN (Zamir)" Acked-by: Masami Hiramatsu Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 594265bfd390..05ed663e6c7b 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -350,6 +350,10 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) return this_cpu_ptr(&kprobe_ctlblk); } +extern struct kprobe kprobe_busy; +void kprobe_busy_begin(void); +void kprobe_busy_end(void); + kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset); int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); -- cgit v1.2.3 From b19d57d0f3cc6f1022edf94daf1d70506a09e3c2 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 8 Jun 2020 20:22:33 -0500 Subject: overflow.h: Add flex_array_size() helper Add flex_array_size() helper for the calculation of the size, in bytes, of a flexible array member contained within an enclosing structure. Example of usage: struct something { size_t count; struct foo items[]; }; struct something *instance; instance = kmalloc(struct_size(instance, items, count), GFP_KERNEL); instance->count = count; memcpy(instance->items, src, flex_array_size(instance, items, instance->count)); The helper returns SIZE_MAX on overflow instead of wrapping around. Additionally replaces parameter "n" with "count" in struct_size() helper for greater clarity and unification. Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20200609012233.GA3371@embeddedor Signed-off-by: Kees Cook --- include/linux/overflow.h | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 659045046468..93fcef105061 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -304,16 +304,33 @@ static inline __must_check size_t __ab_c_size(size_t a, size_t b, size_t c) * struct_size() - Calculate size of structure with trailing array. * @p: Pointer to the structure. * @member: Name of the array member. - * @n: Number of elements in the array. + * @count: Number of elements in the array. * * Calculates size of memory needed for structure @p followed by an - * array of @n @member elements. + * array of @count number of @member elements. * * Return: number of bytes needed or SIZE_MAX on overflow. */ -#define struct_size(p, member, n) \ - __ab_c_size(n, \ +#define struct_size(p, member, count) \ + __ab_c_size(count, \ sizeof(*(p)->member) + __must_be_array((p)->member),\ sizeof(*(p))) +/** + * flex_array_size() - Calculate size of a flexible array member + * within an enclosing structure. + * + * @p: Pointer to the structure. + * @member: Name of the flexible array member. + * @count: Number of elements in the array. + * + * Calculates size of a flexible array of @count number of @member + * elements, at the end of structure @p. + * + * Return: number of bytes needed or SIZE_MAX on overflow. + */ +#define flex_array_size(p, member, count) \ + array_size(count, \ + sizeof(*(p)->member) + __must_be_array((p)->member)) + #endif /* __LINUX_OVERFLOW_H */ -- cgit v1.2.3 From 26749b3201ab05e288fbf78fbc8585dfa2da3218 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 15 Jun 2020 08:52:31 +0200 Subject: dma-direct: mark __dma_direct_alloc_pages static Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 136f984df0d9..cdfa400f89b3 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -77,8 +77,6 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); -struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, - gfp_t gfp, unsigned long attrs); int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); -- cgit v1.2.3 From 2a55280a3675203496d302463b941834228b9875 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sun, 7 Jun 2020 15:41:35 +0200 Subject: efi/libstub: arm: Print CPU boot mode and MMU state at boot On 32-bit ARM, we may boot at HYP mode, or with the MMU and caches off (or both), even though the EFI spec does not actually support this. While booting at HYP mode is something we might tolerate, fiddling with the caches is a more serious issue, as disabling the caches is tricky to do safely from C code, and running without the Dcache makes it impossible to support unaligned memory accesses, which is another explicit requirement imposed by the EFI spec. So take note of the CPU mode and MMU state in the EFI stub diagnostic output so that we can easily diagnose any issues that may arise from this. E.g., EFI stub: Entering in SVC mode with MMU enabled Also, capture the CPSR and SCTLR system register values at EFI stub entry, and after ExitBootServices() returns, and check whether the MMU and Dcache were disabled at any point. If this is the case, a diagnostic message like the following will be emitted: efi: [Firmware Bug]: EFI stub was entered with MMU and Dcache disabled, please fix your firmware! efi: CPSR at EFI stub entry : 0x600001d3 efi: SCTLR at EFI stub entry : 0x00c51838 efi: CPSR after ExitBootServices() : 0x600001d3 efi: SCTLR after ExitBootServices(): 0x00c50838 Signed-off-by: Ard Biesheuvel Reviewed-by: Leif Lindholm --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index c3449c9699d0..bb35f3305e55 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -350,6 +350,7 @@ void efi_native_runtime_setup(void); * associated with ConOut */ #define LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID EFI_GUID(0xe03fc20a, 0x85dc, 0x406e, 0xb9, 0x0e, 0x4a, 0xb5, 0x02, 0x37, 0x1d, 0x95) +#define LINUX_EFI_ARM_CPU_STATE_TABLE_GUID EFI_GUID(0xef79e4aa, 0x3c3d, 0x4989, 0xb9, 0x02, 0x07, 0xa9, 0x43, 0xe5, 0x50, 0xd2) #define LINUX_EFI_LOADER_ENTRY_GUID EFI_GUID(0x4a67b082, 0x0a4c, 0x41cf, 0xb6, 0xc7, 0x44, 0x0b, 0x29, 0xbb, 0x8c, 0x4f) #define LINUX_EFI_RANDOM_SEED_TABLE_GUID EFI_GUID(0x1ce1e5bc, 0x7ceb, 0x42f2, 0x81, 0xe5, 0x8a, 0xad, 0xf1, 0x80, 0xf5, 0x7b) #define LINUX_EFI_TPM_EVENT_LOG_GUID EFI_GUID(0xb7799cb0, 0xeca2, 0x4943, 0x96, 0x67, 0x1f, 0xae, 0x07, 0xb7, 0x47, 0xfa) -- cgit v1.2.3 From 47ec7f09bc107720905c96bc37771e4ed1ff0aed Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 13 May 2020 11:47:49 -0700 Subject: dmaengine: cookie bypass for out of order completion The cookie tracking in dmaengine expects all submissions completed in order. Some DMA devices like Intel DSA can complete submissions out of order, especially if configured with a work queue sharing multiple DMA engines. Add a status DMA_OUT_OF_ORDER that tx_status can be returned for those DMA devices. The user should use callbacks to track the completion rather than the DMA cookie. This would address the issue of dmatest complaining that descriptors are "busy" when the cookie count goes backwards due to out of order completion. Add DMA_COMPLETION_NO_ORDER DMA capability to allow the driver to flag the device's ability to complete operations out of order. Reported-by: Swathi Kovvuri Signed-off-by: Dave Jiang Tested-by: Swathi Kovvuri Link: https://lore.kernel.org/r/158939557151.20335.12404113976045569870.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index e1c03339918f..9f9a13a2c01f 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -39,6 +39,7 @@ enum dma_status { DMA_IN_PROGRESS, DMA_PAUSED, DMA_ERROR, + DMA_OUT_OF_ORDER, }; /** @@ -61,6 +62,7 @@ enum dma_transaction_type { DMA_SLAVE, DMA_CYCLIC, DMA_INTERLEAVE, + DMA_COMPLETION_NO_ORDER, /* last transaction type for creation of the capabilities mask */ DMA_TX_TYPE_END, }; -- cgit v1.2.3 From 2accfa69050c2a0d6fc6106f609208b3e9622b26 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 17 Jun 2020 07:14:10 -0700 Subject: cpu/speculation: Add prototype for cpu_show_srbds() 0-day is not happy that there is no prototype for cpu_show_srbds(): drivers/base/cpu.c:565:16: error: no previous prototype for 'cpu_show_srbds' Fixes: 7e5b3c267d25 ("x86/speculation: Add Special Register Buffer Data Sampling (SRBDS) mitigation") Reported-by: kernel test robot Signed-off-by: Guenter Roeck Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200617141410.93338-1-linux@roeck-us.net --- include/linux/cpu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 52692587f7fe..8aa84c052fdf 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -64,6 +64,7 @@ extern ssize_t cpu_show_tsx_async_abort(struct device *dev, char *buf); extern ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, -- cgit v1.2.3 From c935cd62d3fe985d7f0ebea185d2759e8992e96f Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 17 Jun 2020 17:17:19 +1000 Subject: lockdep: Split header file into lockdep and lockdep_types There is a header file inclusion loop between asm-generic/bug.h and linux/kernel.h. This causes potential compile failurs depending on the which file is included first. One way of breaking this loop is to stop spinlock_types.h from including lockdep.h. This patch splits lockdep.h into two files for this purpose. Signed-off-by: Herbert Xu Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Sergey Senozhatsky Reviewed-by: Andy Shevchenko Acked-by: Petr Mladek Acked-by: Steven Rostedt (VMware) Link: https://lkml.kernel.org/r/E1jlSJz-0003hE-8g@fornost.hmeau.com --- include/linux/lockdep.h | 178 +------------------------------------ include/linux/lockdep_types.h | 196 +++++++++++++++++++++++++++++++++++++++++ include/linux/spinlock.h | 1 + include/linux/spinlock_types.h | 2 +- 4 files changed, 200 insertions(+), 177 deletions(-) create mode 100644 include/linux/lockdep_types.h (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 8fce5c98a4b0..3b73cf84f77d 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -10,181 +10,20 @@ #ifndef __LINUX_LOCKDEP_H #define __LINUX_LOCKDEP_H +#include + struct task_struct; -struct lockdep_map; /* for sysctl */ extern int prove_locking; extern int lock_stat; -#define MAX_LOCKDEP_SUBCLASSES 8UL - -#include - -enum lockdep_wait_type { - LD_WAIT_INV = 0, /* not checked, catch all */ - - LD_WAIT_FREE, /* wait free, rcu etc.. */ - LD_WAIT_SPIN, /* spin loops, raw_spinlock_t etc.. */ - -#ifdef CONFIG_PROVE_RAW_LOCK_NESTING - LD_WAIT_CONFIG, /* CONFIG_PREEMPT_LOCK, spinlock_t etc.. */ -#else - LD_WAIT_CONFIG = LD_WAIT_SPIN, -#endif - LD_WAIT_SLEEP, /* sleeping locks, mutex_t etc.. */ - - LD_WAIT_MAX, /* must be last */ -}; - #ifdef CONFIG_LOCKDEP #include -#include #include #include -/* - * We'd rather not expose kernel/lockdep_states.h this wide, but we do need - * the total number of states... :-( - */ -#define XXX_LOCK_USAGE_STATES (1+2*4) - -/* - * NR_LOCKDEP_CACHING_CLASSES ... Number of classes - * cached in the instance of lockdep_map - * - * Currently main class (subclass == 0) and signle depth subclass - * are cached in lockdep_map. This optimization is mainly targeting - * on rq->lock. double_rq_lock() acquires this highly competitive with - * single depth. - */ -#define NR_LOCKDEP_CACHING_CLASSES 2 - -/* - * A lockdep key is associated with each lock object. For static locks we use - * the lock address itself as the key. Dynamically allocated lock objects can - * have a statically or dynamically allocated key. Dynamically allocated lock - * keys must be registered before being used and must be unregistered before - * the key memory is freed. - */ -struct lockdep_subclass_key { - char __one_byte; -} __attribute__ ((__packed__)); - -/* hash_entry is used to keep track of dynamically allocated keys. */ -struct lock_class_key { - union { - struct hlist_node hash_entry; - struct lockdep_subclass_key subkeys[MAX_LOCKDEP_SUBCLASSES]; - }; -}; - -extern struct lock_class_key __lockdep_no_validate__; - -struct lock_trace; - -#define LOCKSTAT_POINTS 4 - -/* - * The lock-class itself. The order of the structure members matters. - * reinit_class() zeroes the key member and all subsequent members. - */ -struct lock_class { - /* - * class-hash: - */ - struct hlist_node hash_entry; - - /* - * Entry in all_lock_classes when in use. Entry in free_lock_classes - * when not in use. Instances that are being freed are on one of the - * zapped_classes lists. - */ - struct list_head lock_entry; - - /* - * These fields represent a directed graph of lock dependencies, - * to every node we attach a list of "forward" and a list of - * "backward" graph nodes. - */ - struct list_head locks_after, locks_before; - - const struct lockdep_subclass_key *key; - unsigned int subclass; - unsigned int dep_gen_id; - - /* - * IRQ/softirq usage tracking bits: - */ - unsigned long usage_mask; - const struct lock_trace *usage_traces[XXX_LOCK_USAGE_STATES]; - - /* - * Generation counter, when doing certain classes of graph walking, - * to ensure that we check one node only once: - */ - int name_version; - const char *name; - - short wait_type_inner; - short wait_type_outer; - -#ifdef CONFIG_LOCK_STAT - unsigned long contention_point[LOCKSTAT_POINTS]; - unsigned long contending_point[LOCKSTAT_POINTS]; -#endif -} __no_randomize_layout; - -#ifdef CONFIG_LOCK_STAT -struct lock_time { - s64 min; - s64 max; - s64 total; - unsigned long nr; -}; - -enum bounce_type { - bounce_acquired_write, - bounce_acquired_read, - bounce_contended_write, - bounce_contended_read, - nr_bounce_types, - - bounce_acquired = bounce_acquired_write, - bounce_contended = bounce_contended_write, -}; - -struct lock_class_stats { - unsigned long contention_point[LOCKSTAT_POINTS]; - unsigned long contending_point[LOCKSTAT_POINTS]; - struct lock_time read_waittime; - struct lock_time write_waittime; - struct lock_time read_holdtime; - struct lock_time write_holdtime; - unsigned long bounces[nr_bounce_types]; -}; - -struct lock_class_stats lock_stats(struct lock_class *class); -void clear_lock_stats(struct lock_class *class); -#endif - -/* - * Map the lock object (the lock instance) to the lock-class object. - * This is embedded into specific lock instances: - */ -struct lockdep_map { - struct lock_class_key *key; - struct lock_class *class_cache[NR_LOCKDEP_CACHING_CLASSES]; - const char *name; - short wait_type_outer; /* can be taken in this context */ - short wait_type_inner; /* presents this context */ -#ifdef CONFIG_LOCK_STAT - int cpu; - unsigned long ip; -#endif -}; - static inline void lockdep_copy_map(struct lockdep_map *to, struct lockdep_map *from) { @@ -440,8 +279,6 @@ static inline void lock_set_subclass(struct lockdep_map *lock, extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip); -struct pin_cookie { unsigned int val; }; - #define NIL_COOKIE (struct pin_cookie){ .val = 0U, } extern struct pin_cookie lock_pin_lock(struct lockdep_map *lock); @@ -520,10 +357,6 @@ static inline void lockdep_set_selftest_task(struct task_struct *task) # define lockdep_reset() do { debug_locks = 1; } while (0) # define lockdep_free_key_range(start, size) do { } while (0) # define lockdep_sys_exit() do { } while (0) -/* - * The class key takes no space if lockdep is disabled: - */ -struct lock_class_key { }; static inline void lockdep_register_key(struct lock_class_key *key) { @@ -533,11 +366,6 @@ static inline void lockdep_unregister_key(struct lock_class_key *key) { } -/* - * The lockdep_map takes no space if lockdep is disabled: - */ -struct lockdep_map { }; - #define lockdep_depth(tsk) (0) #define lockdep_is_held_type(l, r) (1) @@ -549,8 +377,6 @@ struct lockdep_map { }; #define lockdep_recursing(tsk) (0) -struct pin_cookie { }; - #define NIL_COOKIE (struct pin_cookie){ } #define lockdep_pin_lock(l) ({ struct pin_cookie cookie = { }; cookie; }) diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h new file mode 100644 index 000000000000..7b9350624577 --- /dev/null +++ b/include/linux/lockdep_types.h @@ -0,0 +1,196 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Runtime locking correctness validator + * + * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * + * see Documentation/locking/lockdep-design.rst for more details. + */ +#ifndef __LINUX_LOCKDEP_TYPES_H +#define __LINUX_LOCKDEP_TYPES_H + +#include + +#define MAX_LOCKDEP_SUBCLASSES 8UL + +enum lockdep_wait_type { + LD_WAIT_INV = 0, /* not checked, catch all */ + + LD_WAIT_FREE, /* wait free, rcu etc.. */ + LD_WAIT_SPIN, /* spin loops, raw_spinlock_t etc.. */ + +#ifdef CONFIG_PROVE_RAW_LOCK_NESTING + LD_WAIT_CONFIG, /* CONFIG_PREEMPT_LOCK, spinlock_t etc.. */ +#else + LD_WAIT_CONFIG = LD_WAIT_SPIN, +#endif + LD_WAIT_SLEEP, /* sleeping locks, mutex_t etc.. */ + + LD_WAIT_MAX, /* must be last */ +}; + +#ifdef CONFIG_LOCKDEP + +#include + +/* + * We'd rather not expose kernel/lockdep_states.h this wide, but we do need + * the total number of states... :-( + */ +#define XXX_LOCK_USAGE_STATES (1+2*4) + +/* + * NR_LOCKDEP_CACHING_CLASSES ... Number of classes + * cached in the instance of lockdep_map + * + * Currently main class (subclass == 0) and signle depth subclass + * are cached in lockdep_map. This optimization is mainly targeting + * on rq->lock. double_rq_lock() acquires this highly competitive with + * single depth. + */ +#define NR_LOCKDEP_CACHING_CLASSES 2 + +/* + * A lockdep key is associated with each lock object. For static locks we use + * the lock address itself as the key. Dynamically allocated lock objects can + * have a statically or dynamically allocated key. Dynamically allocated lock + * keys must be registered before being used and must be unregistered before + * the key memory is freed. + */ +struct lockdep_subclass_key { + char __one_byte; +} __attribute__ ((__packed__)); + +/* hash_entry is used to keep track of dynamically allocated keys. */ +struct lock_class_key { + union { + struct hlist_node hash_entry; + struct lockdep_subclass_key subkeys[MAX_LOCKDEP_SUBCLASSES]; + }; +}; + +extern struct lock_class_key __lockdep_no_validate__; + +struct lock_trace; + +#define LOCKSTAT_POINTS 4 + +/* + * The lock-class itself. The order of the structure members matters. + * reinit_class() zeroes the key member and all subsequent members. + */ +struct lock_class { + /* + * class-hash: + */ + struct hlist_node hash_entry; + + /* + * Entry in all_lock_classes when in use. Entry in free_lock_classes + * when not in use. Instances that are being freed are on one of the + * zapped_classes lists. + */ + struct list_head lock_entry; + + /* + * These fields represent a directed graph of lock dependencies, + * to every node we attach a list of "forward" and a list of + * "backward" graph nodes. + */ + struct list_head locks_after, locks_before; + + const struct lockdep_subclass_key *key; + unsigned int subclass; + unsigned int dep_gen_id; + + /* + * IRQ/softirq usage tracking bits: + */ + unsigned long usage_mask; + const struct lock_trace *usage_traces[XXX_LOCK_USAGE_STATES]; + + /* + * Generation counter, when doing certain classes of graph walking, + * to ensure that we check one node only once: + */ + int name_version; + const char *name; + + short wait_type_inner; + short wait_type_outer; + +#ifdef CONFIG_LOCK_STAT + unsigned long contention_point[LOCKSTAT_POINTS]; + unsigned long contending_point[LOCKSTAT_POINTS]; +#endif +} __no_randomize_layout; + +#ifdef CONFIG_LOCK_STAT +struct lock_time { + s64 min; + s64 max; + s64 total; + unsigned long nr; +}; + +enum bounce_type { + bounce_acquired_write, + bounce_acquired_read, + bounce_contended_write, + bounce_contended_read, + nr_bounce_types, + + bounce_acquired = bounce_acquired_write, + bounce_contended = bounce_contended_write, +}; + +struct lock_class_stats { + unsigned long contention_point[LOCKSTAT_POINTS]; + unsigned long contending_point[LOCKSTAT_POINTS]; + struct lock_time read_waittime; + struct lock_time write_waittime; + struct lock_time read_holdtime; + struct lock_time write_holdtime; + unsigned long bounces[nr_bounce_types]; +}; + +struct lock_class_stats lock_stats(struct lock_class *class); +void clear_lock_stats(struct lock_class *class); +#endif + +/* + * Map the lock object (the lock instance) to the lock-class object. + * This is embedded into specific lock instances: + */ +struct lockdep_map { + struct lock_class_key *key; + struct lock_class *class_cache[NR_LOCKDEP_CACHING_CLASSES]; + const char *name; + short wait_type_outer; /* can be taken in this context */ + short wait_type_inner; /* presents this context */ +#ifdef CONFIG_LOCK_STAT + int cpu; + unsigned long ip; +#endif +}; + +struct pin_cookie { unsigned int val; }; + +#else /* !CONFIG_LOCKDEP */ + +/* + * The class key takes no space if lockdep is disabled: + */ +struct lock_class_key { }; + +/* + * The lockdep_map takes no space if lockdep is disabled: + */ +struct lockdep_map { }; + +struct pin_cookie { }; + +#endif /* !LOCKDEP */ + +#endif /* __LINUX_LOCKDEP_TYPES_H */ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index d3770b3f9d9a..f2f12d746dbd 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -56,6 +56,7 @@ #include #include #include +#include #include #include diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h index 6102e6bff3ae..b981caafe8bf 100644 --- a/include/linux/spinlock_types.h +++ b/include/linux/spinlock_types.h @@ -15,7 +15,7 @@ # include #endif -#include +#include typedef struct raw_spinlock { arch_spinlock_t raw_lock; -- cgit v1.2.3 From fe557319aa06c23cffc9346000f119547e0f289a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 17 Jun 2020 09:37:53 +0200 Subject: maccess: rename probe_kernel_{read,write} to copy_{from,to}_kernel_nofault Better describe what these functions do. Suggested-by: Linus Torvalds Signed-off-by: Christoph Hellwig Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 7bcadca22100..70a3d9cd9113 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -301,13 +301,14 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, return 0; } -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size); +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); -extern long probe_kernel_read(void *dst, const void *src, size_t size); -extern long probe_user_read(void *dst, const void __user *src, size_t size); +long copy_from_kernel_nofault(void *dst, const void *src, size_t size); +long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); -extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); -extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); +extern long probe_user_read(void *dst, const void __user *src, size_t size); +extern long notrace probe_user_write(void __user *dst, const void *src, + size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); @@ -324,7 +325,7 @@ long strnlen_user_nofault(const void __user *unsafe_addr, long count); * Returns 0 on success, or -EFAULT. */ #define probe_kernel_address(addr, retval) \ - probe_kernel_read(&retval, addr, sizeof(retval)) + copy_from_kernel_nofault(&retval, addr, sizeof(retval)) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) -- cgit v1.2.3 From c0ee37e85e0e47402b8bbe35b6cec8e06937ca58 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 17 Jun 2020 09:37:54 +0200 Subject: maccess: rename probe_user_{read,write} to copy_{from,to}_user_nofault Better describe what these functions do. Suggested-by: Linus Torvalds Signed-off-by: Christoph Hellwig Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 70a3d9cd9113..bef48da242cc 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -306,8 +306,8 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); -extern long probe_user_read(void *dst, const void __user *src, size_t size); -extern long notrace probe_user_write(void __user *dst, const void *src, +long copy_from_user_nofault(void *dst, const void __user *src, size_t size); +long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, -- cgit v1.2.3 From a9d887dc1c60ed67f2271d66560cdcf864c4a578 Mon Sep 17 00:00:00 2001 From: Guru Das Srinagesh Date: Tue, 2 Jun 2020 15:31:16 -0700 Subject: pwm: Convert period and duty cycle to u64 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Because period and duty cycle are defined as ints with units of nanoseconds, the maximum time duration that can be set is limited to ~2.147 seconds. Change their definitions to u64 in the structs of the PWM framework so that higher durations may be set. Also use the right format specifiers in debug prints in both core.c, pwm-stm32-lp.c as well as video/fbdev/ssd1307fb.c. Reported-by: kbuild test robot Signed-off-by: Guru Das Srinagesh Acked-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- include/linux/pwm.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 2635b2a55090..a13ff383fa1d 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -39,7 +39,7 @@ enum pwm_polarity { * current PWM hardware state. */ struct pwm_args { - unsigned int period; + u64 period; enum pwm_polarity polarity; }; @@ -56,8 +56,8 @@ enum { * @enabled: PWM enabled status */ struct pwm_state { - unsigned int period; - unsigned int duty_cycle; + u64 period; + u64 duty_cycle; enum pwm_polarity polarity; bool enabled; }; @@ -107,13 +107,13 @@ static inline bool pwm_is_enabled(const struct pwm_device *pwm) return state.enabled; } -static inline void pwm_set_period(struct pwm_device *pwm, unsigned int period) +static inline void pwm_set_period(struct pwm_device *pwm, u64 period) { if (pwm) pwm->state.period = period; } -static inline unsigned int pwm_get_period(const struct pwm_device *pwm) +static inline u64 pwm_get_period(const struct pwm_device *pwm) { struct pwm_state state; @@ -128,7 +128,7 @@ static inline void pwm_set_duty_cycle(struct pwm_device *pwm, unsigned int duty) pwm->state.duty_cycle = duty; } -static inline unsigned int pwm_get_duty_cycle(const struct pwm_device *pwm) +static inline u64 pwm_get_duty_cycle(const struct pwm_device *pwm) { struct pwm_state state; -- cgit v1.2.3 From 7d34ca3854845398cb36866d14bbdc43dcec1ad0 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Tue, 9 Jun 2020 18:19:33 -0700 Subject: driver core: Add device_is_dependent() to linux/device.h DT implementation of fw_devlink needs this function to detect cycles. So make it available. Signed-off-by: Saravana Kannan Tested-by: John Stultz Signed-off-by: Rob Herring --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 15460a5ac024..33cece5d9a4c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -829,6 +829,7 @@ extern int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); extern const char *device_get_devnode(struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp); +extern int device_is_dependent(struct device *dev, void *target); static inline bool device_supports_offline(struct device *dev) { -- cgit v1.2.3 From f097eb38f71391ff2cf078788bad5a00eb3bd96a Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Tue, 9 Jun 2020 10:17:26 +0200 Subject: timekeeping: Fix kerneldoc system_device_crosststamp & al Make kernel doc comments actually work and fix the syncronized typo. [ tglx: Added the missing /** and fixed up formatting ] Signed-off-by: Kurt Kanzenbach Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20200609081726.5657-1-kurt@linutronix.de --- include/linux/timekeeping.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index b27e2ffa96c1..d5471d6fa778 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -222,9 +222,9 @@ extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); -/* +/** * struct system_time_snapshot - simultaneous raw/real time capture with - * counter value + * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @raw: Monotonic raw system time @@ -239,9 +239,9 @@ struct system_time_snapshot { u8 cs_was_changed_seq; }; -/* +/** * struct system_device_crosststamp - system/device cross-timestamp - * (syncronized capture) + * (synchronized capture) * @device: Device time * @sys_realtime: Realtime simultaneous with device time * @sys_monoraw: Monotonic raw simultaneous with device time @@ -252,12 +252,12 @@ struct system_device_crosststamp { ktime_t sys_monoraw; }; -/* +/** * struct system_counterval_t - system counter value with the pointer to the - * corresponding clocksource + * corresponding clocksource * @cycles: System counter value * @cs: Clocksource corresponding to system counter value. Used by - * timekeeping code to verify comparibility of two cycle values + * timekeeping code to verify comparibility of two cycle values */ struct system_counterval_t { u64 cycles; -- cgit v1.2.3 From e0bcc58d876c6ece9720310509a908b7637e37cf Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Wed, 3 Jun 2020 14:54:36 +0200 Subject: mfd: stm32: Add defines to be used for clkevent purpose Add defines to be able to enable/clear irq and configure one shot mode. Signed-off-by: Benjamin Gaignard Signed-off-by: Lee Jones --- include/linux/mfd/stm32-lptimer.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/stm32-lptimer.h b/include/linux/mfd/stm32-lptimer.h index 605f62264825..90b20550c1c8 100644 --- a/include/linux/mfd/stm32-lptimer.h +++ b/include/linux/mfd/stm32-lptimer.h @@ -27,10 +27,15 @@ #define STM32_LPTIM_CMPOK BIT(3) /* STM32_LPTIM_ICR - bit fields */ +#define STM32_LPTIM_ARRMCF BIT(1) #define STM32_LPTIM_CMPOKCF_ARROKCF GENMASK(4, 3) +/* STM32_LPTIM_IER - bit flieds */ +#define STM32_LPTIM_ARRMIE BIT(1) + /* STM32_LPTIM_CR - bit fields */ #define STM32_LPTIM_CNTSTRT BIT(2) +#define STM32_LPTIM_SNGSTRT BIT(1) #define STM32_LPTIM_ENABLE BIT(0) /* STM32_LPTIM_CFGR - bit fields */ -- cgit v1.2.3 From 7f8a137f736f7366820c485c5a0d34d65b9d0125 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 15 Jun 2020 14:53:22 +0100 Subject: mfd: madera: Remove unused forward declaration of madera_codec_pdata This forward declaration is redundant since the header including the full data structure is included. Signed-off-by: Charles Keepax Signed-off-by: Lee Jones --- include/linux/mfd/madera/pdata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/pdata.h b/include/linux/mfd/madera/pdata.h index fa9595dd42ba..601cbbc10370 100644 --- a/include/linux/mfd/madera/pdata.h +++ b/include/linux/mfd/madera/pdata.h @@ -21,7 +21,6 @@ struct gpio_desc; struct pinctrl_map; -struct madera_codec_pdata; /** * struct madera_pdata - Configuration data for Madera devices -- cgit v1.2.3 From 6c27219e34911601955b72c754adfc11c527ba7b Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Mon, 8 Jun 2020 11:17:36 +0200 Subject: mfd: Add support for the Khadas System control Microcontroller This Microcontroller is present on the Khadas VIM1, VIM2, VIM3 and Edge boards. It has multiple boot control features like password check, power-on options, power-off control and system FAN control on recent boards. This implements a very basic MFD driver with the fan control and User NVMEM cells. Signed-off-by: Neil Armstrong Signed-off-by: Lee Jones --- include/linux/mfd/khadas-mcu.h | 91 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 91 insertions(+) create mode 100644 include/linux/mfd/khadas-mcu.h (limited to 'include/linux') diff --git a/include/linux/mfd/khadas-mcu.h b/include/linux/mfd/khadas-mcu.h new file mode 100644 index 000000000000..a99ba2ed0e4e --- /dev/null +++ b/include/linux/mfd/khadas-mcu.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Khadas System control Microcontroller Register map + * + * Copyright (C) 2020 BayLibre SAS + * + * Author(s): Neil Armstrong + */ + +#ifndef MFD_KHADAS_MCU_H +#define MFD_KHADAS_MCU_H + +#define KHADAS_MCU_PASSWD_VEN_0_REG 0x00 /* RO */ +#define KHADAS_MCU_PASSWD_VEN_1_REG 0x01 /* RO */ +#define KHADAS_MCU_PASSWD_VEN_2_REG 0x02 /* RO */ +#define KHADAS_MCU_PASSWD_VEN_3_REG 0x03 /* RO */ +#define KHADAS_MCU_PASSWD_VEN_4_REG 0x04 /* RO */ +#define KHADAS_MCU_PASSWD_VEN_5_REG 0x05 /* RO */ +#define KHADAS_MCU_MAC_0_REG 0x06 /* RO */ +#define KHADAS_MCU_MAC_1_REG 0x07 /* RO */ +#define KHADAS_MCU_MAC_2_REG 0x08 /* RO */ +#define KHADAS_MCU_MAC_3_REG 0x09 /* RO */ +#define KHADAS_MCU_MAC_4_REG 0x0a /* RO */ +#define KHADAS_MCU_MAC_5_REG 0x0b /* RO */ +#define KHADAS_MCU_USID_0_REG 0x0c /* RO */ +#define KHADAS_MCU_USID_1_REG 0x0d /* RO */ +#define KHADAS_MCU_USID_2_REG 0x0e /* RO */ +#define KHADAS_MCU_USID_3_REG 0x0f /* RO */ +#define KHADAS_MCU_USID_4_REG 0x10 /* RO */ +#define KHADAS_MCU_USID_5_REG 0x11 /* RO */ +#define KHADAS_MCU_VERSION_0_REG 0x12 /* RO */ +#define KHADAS_MCU_VERSION_1_REG 0x13 /* RO */ +#define KHADAS_MCU_DEVICE_NO_0_REG 0x14 /* RO */ +#define KHADAS_MCU_DEVICE_NO_1_REG 0x15 /* RO */ +#define KHADAS_MCU_FACTORY_TEST_REG 0x16 /* R */ +#define KHADAS_MCU_BOOT_MODE_REG 0x20 /* RW */ +#define KHADAS_MCU_BOOT_EN_WOL_REG 0x21 /* RW */ +#define KHADAS_MCU_BOOT_EN_RTC_REG 0x22 /* RW */ +#define KHADAS_MCU_BOOT_EN_EXP_REG 0x23 /* RW */ +#define KHADAS_MCU_BOOT_EN_IR_REG 0x24 /* RW */ +#define KHADAS_MCU_BOOT_EN_DCIN_REG 0x25 /* RW */ +#define KHADAS_MCU_BOOT_EN_KEY_REG 0x26 /* RW */ +#define KHADAS_MCU_KEY_MODE_REG 0x27 /* RW */ +#define KHADAS_MCU_LED_MODE_ON_REG 0x28 /* RW */ +#define KHADAS_MCU_LED_MODE_OFF_REG 0x29 /* RW */ +#define KHADAS_MCU_SHUTDOWN_NORMAL_REG 0x2c /* RW */ +#define KHADAS_MCU_MAC_SWITCH_REG 0x2d /* RW */ +#define KHADAS_MCU_MCU_SLEEP_MODE_REG 0x2e /* RW */ +#define KHADAS_MCU_IR_CODE1_0_REG 0x2f /* RW */ +#define KHADAS_MCU_IR_CODE1_1_REG 0x30 /* RW */ +#define KHADAS_MCU_IR_CODE1_2_REG 0x31 /* RW */ +#define KHADAS_MCU_IR_CODE1_3_REG 0x32 /* RW */ +#define KHADAS_MCU_USB_PCIE_SWITCH_REG 0x33 /* RW */ +#define KHADAS_MCU_IR_CODE2_0_REG 0x34 /* RW */ +#define KHADAS_MCU_IR_CODE2_1_REG 0x35 /* RW */ +#define KHADAS_MCU_IR_CODE2_2_REG 0x36 /* RW */ +#define KHADAS_MCU_IR_CODE2_3_REG 0x37 /* RW */ +#define KHADAS_MCU_PASSWD_USER_0_REG 0x40 /* RW */ +#define KHADAS_MCU_PASSWD_USER_1_REG 0x41 /* RW */ +#define KHADAS_MCU_PASSWD_USER_2_REG 0x42 /* RW */ +#define KHADAS_MCU_PASSWD_USER_3_REG 0x43 /* RW */ +#define KHADAS_MCU_PASSWD_USER_4_REG 0x44 /* RW */ +#define KHADAS_MCU_PASSWD_USER_5_REG 0x45 /* RW */ +#define KHADAS_MCU_USER_DATA_0_REG 0x46 /* RW 56 bytes */ +#define KHADAS_MCU_PWR_OFF_CMD_REG 0x80 /* WO */ +#define KHADAS_MCU_PASSWD_START_REG 0x81 /* WO */ +#define KHADAS_MCU_CHECK_VEN_PASSWD_REG 0x82 /* WO */ +#define KHADAS_MCU_CHECK_USER_PASSWD_REG 0x83 /* WO */ +#define KHADAS_MCU_SHUTDOWN_NORMAL_STATUS_REG 0x86 /* RO */ +#define KHADAS_MCU_WOL_INIT_START_REG 0x87 /* WO */ +#define KHADAS_MCU_CMD_FAN_STATUS_CTRL_REG 0x88 /* WO */ + +enum { + KHADAS_BOARD_VIM1 = 0x1, + KHADAS_BOARD_VIM2, + KHADAS_BOARD_VIM3, + KHADAS_BOARD_EDGE = 0x11, + KHADAS_BOARD_EDGE_V, +}; + +/** + * struct khadas_mcu - Khadas MCU structure + * @device: device reference used for logs + * @regmap: register map + */ +struct khadas_mcu { + struct device *dev; + struct regmap *regmap; +}; + +#endif /* MFD_KHADAS_MCU_H */ -- cgit v1.2.3 From ab183d460daac6292cb0cfd989d88b37b2437844 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 16 Jun 2020 13:45:36 +0300 Subject: RDMA/mlx5: Add missed RST2INIT and INIT2INIT steps during ECE handshake Missed steps during ECE handshake left userspace application with less options for the ECE handshake. Pass ECE options in the additional transitions. Fixes: 50aec2c3135e ("RDMA/mlx5: Return ECE data after modify QP") Link: https://lore.kernel.org/r/20200616104536.2426384-1-leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/mlx5_ifc.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 116bd9bb347f..ca1887dd0423 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4283,7 +4283,8 @@ struct mlx5_ifc_rst2init_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_rst2init_qp_in_bits { @@ -4300,7 +4301,7 @@ struct mlx5_ifc_rst2init_qp_in_bits { u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; @@ -6619,7 +6620,8 @@ struct mlx5_ifc_init2init_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x20]; + u8 ece[0x20]; }; struct mlx5_ifc_init2init_qp_in_bits { @@ -6636,7 +6638,7 @@ struct mlx5_ifc_init2init_qp_in_bits { u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; -- cgit v1.2.3 From b5292111de9bb70cba3489075970889765302136 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Wed, 3 Jun 2020 15:48:19 +0800 Subject: libata: Use per port sync for detach Commit 130f4caf145c ("libata: Ensure ata_port probe has completed before detach") may cause system freeze during suspend. Using async_synchronize_full() in PM callbacks is wrong, since async callbacks that are already scheduled may wait for not-yet-scheduled callbacks, causes a circular dependency. Instead of using big hammer like async_synchronize_full(), use async cookie to make sure port probe are synced, without affecting other scheduled PM callbacks. Fixes: 130f4caf145c ("libata: Ensure ata_port probe has completed before detach") Suggested-by: John Garry Signed-off-by: Kai-Heng Feng Tested-by: John Garry BugLink: https://bugs.launchpad.net/bugs/1867983 Signed-off-by: Jens Axboe --- include/linux/libata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index af832852e620..8a4843704d28 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -22,6 +22,7 @@ #include #include #include +#include /* * Define if arch has non-standard setup. This is a _PCI_ standard @@ -872,6 +873,8 @@ struct ata_port { struct timer_list fastdrain_timer; unsigned long fastdrain_cnt; + async_cookie_t cookie; + int em_message_type; void *private_data; -- cgit v1.2.3 From 3373a3461aa15b7f9a871fa4cb2c9ef21ac20b47 Mon Sep 17 00:00:00 2001 From: Zheng Bin Date: Thu, 18 Jun 2020 12:21:38 +0800 Subject: block: make function 'kill_bdev' static kill_bdev does not have any external user, so make it static. Signed-off-by: Zheng Bin Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6c4ab4dc1cd7..3f881a892ea7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2592,7 +2592,6 @@ extern void bdput(struct block_device *); extern void invalidate_bdev(struct block_device *); extern void iterate_bdevs(void (*)(struct block_device *, void *), void *); extern int sync_blockdev(struct block_device *bdev); -extern void kill_bdev(struct block_device *); extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_all(void); extern void emergency_thaw_bdev(struct super_block *sb); @@ -2608,7 +2607,6 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb) #else static inline void bd_forget(struct inode *inode) {} static inline int sync_blockdev(struct block_device *bdev) { return 0; } -static inline void kill_bdev(struct block_device *bdev) {} static inline void invalidate_bdev(struct block_device *bdev) {} static inline struct super_block *freeze_bdev(struct block_device *sb) -- cgit v1.2.3 From 670d0a4b10704667765f7d18f7592993d02783aa Mon Sep 17 00:00:00 2001 From: Luc Van Oostenryck Date: Thu, 18 Jun 2020 00:02:26 +0200 Subject: sparse: use identifiers to define address spaces Currently, address spaces in warnings are displayed as '' with 'X' being the address space's arbitrary number. But since sparse v0.6.0-rc1 (late December 2018), sparse allows you to define the address spaces using an identifier instead of a number. This identifier is then directly used in the warnings. So, use the identifiers '__user', '__iomem', '__percpu' & '__rcu' for the corresponding address spaces. The default address space, __kernel, being not displayed in warnings, stays defined as '0'. With this change, warnings that used to be displayed as: cast removes address space '' of expression ... void [noderef] * will now be displayed as: cast removes address space '__user' of expression ... void [noderef] __iomem * This also moves the __kernel annotation to be the first one, since it is quite different from the others because it's the default one, and so: - it's never displayed - it's normally not needed, nor in type annotations, nor in cast between address spaces. The only time it's needed is when it's combined with a typeof to express "the same type as this one but without the address space" - it can't be defined with a name, '0' must be used. So, it seemed strange to me to have it in the middle of the other ones. Signed-off-by: Luc Van Oostenryck Acked-by: Miguel Ojeda Signed-off-by: Linus Torvalds --- include/linux/compiler_types.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 21aed0981edf..e368384445b6 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -5,20 +5,20 @@ #ifndef __ASSEMBLY__ #ifdef __CHECKER__ -# define __user __attribute__((noderef, address_space(1))) # define __kernel __attribute__((address_space(0))) +# define __user __attribute__((noderef, address_space(__user))) # define __safe __attribute__((safe)) # define __force __attribute__((force)) # define __nocast __attribute__((nocast)) -# define __iomem __attribute__((noderef, address_space(2))) +# define __iomem __attribute__((noderef, address_space(__iomem))) # define __must_hold(x) __attribute__((context(x,1,1))) # define __acquires(x) __attribute__((context(x,0,1))) # define __releases(x) __attribute__((context(x,1,0))) # define __acquire(x) __context__(x,1) # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) -# define __percpu __attribute__((noderef, address_space(3))) -# define __rcu __attribute__((noderef, address_space(4))) +# define __percpu __attribute__((noderef, address_space(__percpu))) +# define __rcu __attribute__((noderef, address_space(__rcu))) # define __private __attribute__((noderef)) extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); -- cgit v1.2.3 From 25f12ae45fc1931a1dce3cc59f9989a9d87834b0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 17 Jun 2020 09:37:55 +0200 Subject: maccess: rename probe_kernel_address to get_kernel_nofault Better describe what this helper does, and match the naming of copy_from_kernel_nofault. Also switch the argument order around, so that it acts and looks like get_user(). Signed-off-by: Christoph Hellwig Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index bef48da242cc..a508a3c08879 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -318,14 +318,14 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long strnlen_user_nofault(const void __user *unsafe_addr, long count); /** - * probe_kernel_address(): safely attempt to read from a location - * @addr: address to read from - * @retval: read into this variable + * get_kernel_nofault(): safely attempt to read from a location + * @val: read into this variable + * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ -#define probe_kernel_address(addr, retval) \ - copy_from_kernel_nofault(&retval, addr, sizeof(retval)) +#define get_kernel_nofault(val, ptr) \ + copy_from_kernel_nofault(&(val), (ptr), sizeof(val)) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) -- cgit v1.2.3 From 0c389d89abc28edf70ae847ee2fa55acb267b826 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 18 Jun 2020 12:10:37 -0700 Subject: maccess: make get_kernel_nofault() check for minimal type compatibility Now that we've renamed probe_kernel_address() to get_kernel_nofault() and made it look and behave more in line with get_user(), some of the subtle type behavior differences end up being more obvious and possibly dangerous. When you do get_user(val, user_ptr); the type of the access comes from the "user_ptr" part, and the above basically acts as val = *user_ptr; by design (except, of course, for the fact that the actual dereference is done with a user access). Note how in the above case, the type of the end result comes from the pointer argument, and then the value is cast to the type of 'val' as part of the assignment. So the type of the pointer is ultimately the more important type both for the access itself. But 'get_kernel_nofault()' may now _look_ similar, but it behaves very differently. When you do get_kernel_nofault(val, kernel_ptr); it behaves like val = *(typeof(val) *)kernel_ptr; except, of course, for the fact that the actual dereference is done with exception handling so that a faulting access is suppressed and returned as the error code. But note how different the casting behavior of the two superficially similar accesses are: one does the actual access in the size of the type the pointer points to, while the other does the access in the size of the target, and ignores the pointer type entirely. Actually changing get_kernel_nofault() to act like get_user() is almost certainly the right thing to do eventually, but in the meantime this patch adds logit to at least verify that the pointer type is compatible with the type of the result. In many cases, this involves just casting the pointer to 'void *' to make it obvious that the type of the pointer is not the important part. It's not how 'get_user()' acts, but at least the behavioral difference is now obvious and explicit. Cc: Christoph Hellwig Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index a508a3c08879..0a76ddc07d59 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -324,8 +324,10 @@ long strnlen_user_nofault(const void __user *unsafe_addr, long count); * * Returns 0 on success, or -EFAULT. */ -#define get_kernel_nofault(val, ptr) \ - copy_from_kernel_nofault(&(val), (ptr), sizeof(val)) +#define get_kernel_nofault(val, ptr) ({ \ + const typeof(val) *__gk_ptr = (ptr); \ + copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ +}) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) -- cgit v1.2.3 From fb7861d14c8d7edac65b2fcb6e8031cb138457b2 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Tue, 16 Jun 2020 15:52:05 +0000 Subject: net: core: reduce recursion limit value In the current code, ->ndo_start_xmit() can be executed recursively only 10 times because of stack memory. But, in the case of the vxlan, 10 recursion limit value results in a stack overflow. In the current code, the nested interface is limited by 8 depth. There is no critical reason that the recursion limitation value should be 10. So, it would be good to be the same value with the limitation value of nesting interface depth. Test commands: ip link add vxlan10 type vxlan vni 10 dstport 4789 srcport 4789 4789 ip link set vxlan10 up ip a a 192.168.10.1/24 dev vxlan10 ip n a 192.168.10.2 dev vxlan10 lladdr fc:22:33:44:55:66 nud permanent for i in {9..0} do let A=$i+1 ip link add vxlan$i type vxlan vni $i dstport 4789 srcport 4789 4789 ip link set vxlan$i up ip a a 192.168.$i.1/24 dev vxlan$i ip n a 192.168.$i.2 dev vxlan$i lladdr fc:22:33:44:55:66 nud permanent bridge fdb add fc:22:33:44:55:66 dev vxlan$A dst 192.168.$i.2 self done hping3 192.168.10.2 -2 -d 60000 Splat looks like: [ 103.814237][ T1127] ============================================================================= [ 103.871955][ T1127] BUG kmalloc-2k (Tainted: G B ): Padding overwritten. 0x00000000897a2e4f-0x000 [ 103.873187][ T1127] ----------------------------------------------------------------------------- [ 103.873187][ T1127] [ 103.874252][ T1127] INFO: Slab 0x000000005cccc724 objects=5 used=5 fp=0x0000000000000000 flags=0x10000000001020 [ 103.881323][ T1127] CPU: 3 PID: 1127 Comm: hping3 Tainted: G B 5.7.0+ #575 [ 103.882131][ T1127] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 103.883006][ T1127] Call Trace: [ 103.883324][ T1127] dump_stack+0x96/0xdb [ 103.883716][ T1127] slab_err+0xad/0xd0 [ 103.884106][ T1127] ? _raw_spin_unlock+0x1f/0x30 [ 103.884620][ T1127] ? get_partial_node.isra.78+0x140/0x360 [ 103.885214][ T1127] slab_pad_check.part.53+0xf7/0x160 [ 103.885769][ T1127] ? pskb_expand_head+0x110/0xe10 [ 103.886316][ T1127] check_slab+0x97/0xb0 [ 103.886763][ T1127] alloc_debug_processing+0x84/0x1a0 [ 103.887308][ T1127] ___slab_alloc+0x5a5/0x630 [ 103.887765][ T1127] ? pskb_expand_head+0x110/0xe10 [ 103.888265][ T1127] ? lock_downgrade+0x730/0x730 [ 103.888762][ T1127] ? pskb_expand_head+0x110/0xe10 [ 103.889244][ T1127] ? __slab_alloc+0x3e/0x80 [ 103.889675][ T1127] __slab_alloc+0x3e/0x80 [ 103.890108][ T1127] __kmalloc_node_track_caller+0xc7/0x420 [ ... ] Fixes: 11a766ce915f ("net: Increase xmit RECURSION_LIMIT to 10.") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6fc613ed8eae..39e28e11863c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3157,7 +3157,7 @@ static inline int dev_recursion_level(void) return this_cpu_read(softnet_data.xmit.recursion); } -#define XMIT_RECURSION_LIMIT 10 +#define XMIT_RECURSION_LIMIT 8 static inline bool dev_xmit_recursion(void) { return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > -- cgit v1.2.3 From 91c7eaa686c3b7ae2d5b2aed22a45a02c8baa30e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 18 Jun 2020 11:42:53 +0200 Subject: USB: rename USB quirk to USB_QUIRK_ENDPOINT_IGNORE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The USB core has a quirk flag to ignore specific endpoints, so rename it to be more obvious what this quirk does. Cc: Johan Hovold Cc: Alan Stern Cc: Richard Dodd Cc: Hans de Goede Cc: Jonathan Cox Cc: Bastien Nocera Cc: "Thiébaud Weksteen" Cc: Nishad Kamdar Link: https://lore.kernel.org/r/20200618094300.1887727-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/quirks.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 22c1f579afe3..5e4c497f54d6 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -69,7 +69,7 @@ /* Hub needs extra delay after resetting its port. */ #define USB_QUIRK_HUB_SLOW_RESET BIT(14) -/* device has blacklisted endpoints */ -#define USB_QUIRK_ENDPOINT_BLACKLIST BIT(15) +/* device has endpoints that should be ignored */ +#define USB_QUIRK_ENDPOINT_IGNORE BIT(15) #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3 From 390fd0475af565d2fc31de98fcc84f3c2922e008 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 15 Jun 2020 09:58:15 +0200 Subject: i2c: remove deprecated i2c_new_device API All in-tree users have been converted to the new i2c_new_client_device function, so remove this deprecated one. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index c10617bb980a..b8b8963f8bb9 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -408,7 +408,7 @@ static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } * that are present. This information is used to grow the driver model tree. * For mainboards this is done statically using i2c_register_board_info(); * bus numbers identify adapters that aren't yet available. For add-on boards, - * i2c_new_device() does this dynamically with the adapter already known. + * i2c_new_client_device() does this dynamically with the adapter already known. */ struct i2c_board_info { char type[I2C_NAME_SIZE]; @@ -439,13 +439,11 @@ struct i2c_board_info { #if IS_ENABLED(CONFIG_I2C) -/* Add-on boards should register/unregister their devices; e.g. a board +/* + * Add-on boards should register/unregister their devices; e.g. a board * with integrated I2C, a config eeprom, sensors, and a codec that's * used in conjunction with the primary hardware. */ -struct i2c_client * -i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info); - struct i2c_client * i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *info); -- cgit v1.2.3 From 5bf74682118b3003c8f9b0b0ec596e473fc6eb82 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Wed, 17 Jun 2020 18:46:35 +0200 Subject: Drivers: hv: vmbus: Remove the target_vp field from the vmbus_channel struct The field is read only in __vmbus_open() and it is already stored twice (after a call to hv_cpu_number_to_vp_number()) in target_cpu_store() and init_vp_index(); there is no need to "cache" its value in the channel data structure. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/20200617164642.37393-2-parri.andrea@gmail.com Reviewed-by: Michael Kelley Signed-off-by: Wei Liu --- include/linux/hyperv.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 40df3103e890..738efdb194b0 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -803,15 +803,14 @@ struct vmbus_channel { u64 sig_event; /* - * Starting with win8, this field will be used to specify - * the target virtual processor on which to deliver the interrupt for - * the host to guest communication. - * Prior to win8, incoming channel interrupts would only - * be delivered on cpu 0. Setting this value to 0 would - * preserve the earlier behavior. + * Starting with win8, this field will be used to specify the + * target CPU on which to deliver the interrupt for the host + * to guest communication. + * + * Prior to win8, incoming channel interrupts would only be + * delivered on CPU 0. Setting this value to 0 would preserve + * the earlier behavior. */ - u32 target_vp; - /* The corresponding CPUID in the guest */ u32 target_cpu; int numa_node; /* -- cgit v1.2.3 From 458d090fbad59d1f849ee15e78d0471784d428b6 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Wed, 17 Jun 2020 18:46:36 +0200 Subject: Drivers: hv: vmbus: Remove the numa_node field from the vmbus_channel struct The field is read only in numa_node_show() and it is already stored twice (after a call to cpu_to_node()) in target_cpu_store() and init_vp_index(); there is no need to "cache" its value in the channel data structure. Signed-off-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/20200617164642.37393-3-parri.andrea@gmail.com Reviewed-by: Michael Kelley Signed-off-by: Wei Liu --- include/linux/hyperv.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 738efdb194b0..690394b79d72 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -812,7 +812,6 @@ struct vmbus_channel { * the earlier behavior. */ u32 target_cpu; - int numa_node; /* * Support for sub-channels. For high performance devices, * it will be useful to have multiple sub-channels to support -- cgit v1.2.3 From e32b16c31339e37d3cdc814f2773b74c1dbf660c Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Thu, 28 May 2020 04:36:03 -0700 Subject: platform/chrome: cros_ec: Update mux state bits Sync the EC_CMD_USB_PD_MUX_INFO mux state bit fields with the Chrome EC code base. The newly added bit fields will be used for cros-ec-typec mux control. Signed-off-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra --- include/linux/platform_data/cros_ec_commands.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 69210881ebac..a7b0fc440c35 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -5207,11 +5207,15 @@ struct ec_params_usb_pd_mux_info { } __ec_align1; /* Flags representing mux state */ -#define USB_PD_MUX_USB_ENABLED BIT(0) /* USB connected */ -#define USB_PD_MUX_DP_ENABLED BIT(1) /* DP connected */ -#define USB_PD_MUX_POLARITY_INVERTED BIT(2) /* CC line Polarity inverted */ -#define USB_PD_MUX_HPD_IRQ BIT(3) /* HPD IRQ is asserted */ -#define USB_PD_MUX_HPD_LVL BIT(4) /* HPD level is asserted */ +#define USB_PD_MUX_NONE 0 /* Open switch */ +#define USB_PD_MUX_USB_ENABLED BIT(0) /* USB connected */ +#define USB_PD_MUX_DP_ENABLED BIT(1) /* DP connected */ +#define USB_PD_MUX_POLARITY_INVERTED BIT(2) /* CC line Polarity inverted */ +#define USB_PD_MUX_HPD_IRQ BIT(3) /* HPD IRQ is asserted */ +#define USB_PD_MUX_HPD_LVL BIT(4) /* HPD level is asserted */ +#define USB_PD_MUX_SAFE_MODE BIT(5) /* DP is in safe mode */ +#define USB_PD_MUX_TBT_COMPAT_ENABLED BIT(6) /* TBT compat enabled */ +#define USB_PD_MUX_USB4_ENABLED BIT(7) /* USB4 enabled */ struct ec_response_usb_pd_mux_info { uint8_t flags; /* USB_PD_MUX_*-encoded USB mux state */ -- cgit v1.2.3 From 8e2a46a40fa76570e535e5baa2d351510b6e61fa Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 15 Jun 2020 08:50:25 +0200 Subject: docs: move remaining stuff under Documentation/*.txt to Documentation/staging There are several files that I was unable to find a proper place for them, and 3 ones that are still in plain old text format. Let's place those stuff behind the carpet, as we'd like to keep the root directory clean. We can later discuss and move those into better places. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/11bd0d75e65a874f7c276a0aeab0fe13f3376f5f.1592203650.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/jump_label.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 3526c0aee954..32809624d422 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -68,7 +68,7 @@ * Lacking toolchain and or architecture support, static keys fall back to a * simple conditional branch. * - * Additional babbling in: Documentation/static-keys.txt + * Additional babbling in: Documentation/staging/static-keys.rst */ #ifndef __ASSEMBLY__ -- cgit v1.2.3 From cc7a21b6fbd945f8d8f61422ccd27203c1fafeb7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 19 Jun 2020 12:02:59 -0700 Subject: ipv6: icmp6: avoid indirect call for icmpv6_send() If IPv6 is builtin, we do not need an expensive indirect call to reach icmp6_send(). v2: put inline keyword before the type to avoid sparse warnings. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 33d379602314..1b3371ae8193 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -13,12 +13,32 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) #include #if IS_ENABLED(CONFIG_IPV6) -extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr); +#if IS_BUILTIN(CONFIG_IPV6) +void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct in6_addr *force_saddr); +static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +{ + icmp6_send(skb, type, code, info, NULL); +} +static inline int inet6_register_icmp_sender(ip6_icmp_send_t *fn) +{ + BUILD_BUG_ON(fn != icmp6_send); + return 0; +} +static inline int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) +{ + BUILD_BUG_ON(fn != icmp6_send); + return 0; +} +#else +extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); +#endif + int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); -- cgit v1.2.3 From c746053d275c8b6ff1d713addabf049c9c9a58fc Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 18 Jun 2020 14:45:58 +0100 Subject: net: phy: add support for probing MMDs >= 8 for devices-in-package Add support for probing MMDs above 7 for a valid devices-in-package specifier, but only probe the vendor MMDs for this if they also report that there the device is present in status register 2. This avoids issues where the MMD is implemented, but does not provide IEEE 802.3 compliant registers (such as the MV88X3310 PHY.) Reviewed-by: Florian Fainelli Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 8c05d0fb5c00..abe318387331 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -388,6 +388,8 @@ enum phy_state { PHY_CABLETEST, }; +#define MDIO_MMD_NUM 32 + /** * struct phy_c45_device_ids - 802.3-c45 Device Identifiers * @devices_in_package: Bit vector of devices present. -- cgit v1.2.3 From 320ed3bf900075614c43499dc01db8d25717b986 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 18 Jun 2020 14:46:08 +0100 Subject: net: phy: split devices_in_package We have two competing requirements for the devices_in_package field. We want to use it as a bit array indicating which MMDs are present, but we also want to know if the Clause 22 registers are present. Since "devices in package" is a term used in the 802.3 specification, keep this as the as-specified values read from the PHY, and introduce a new member "mmds_present" to indicate which MMDs are actually present in the PHY, derived from the "devices in package" value. Reviewed-by: Florian Fainelli Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index abe318387331..19d9e040ad84 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -392,11 +392,13 @@ enum phy_state { /** * struct phy_c45_device_ids - 802.3-c45 Device Identifiers - * @devices_in_package: Bit vector of devices present. + * @devices_in_package: IEEE 802.3 devices in package register value. + * @mmds_present: bit vector of MMDs present. * @device_ids: The device identifer for each present device. */ struct phy_c45_device_ids { u32 devices_in_package; + u32 mmds_present; u32 device_ids[8]; }; -- cgit v1.2.3 From 389a338999875b6e7b111096e8b6484434556449 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 18 Jun 2020 14:46:13 +0100 Subject: net: phy: read MMD ID from all present MMDs Expand the device_ids[] array to allow all MMD IDs to be read rather than just the first 8 MMDs, but only read the ID if the MDIO_STAT2 register reports that a device really is present here for these new devices to maintain compatibility with our current behaviour. Note that only a limited number of devices have MDIO_STAT2. 88X3310 PHY vendor MMDs do are marked as present in the devices_in_package, but do not contain IEE 802.3 compatible register sets in their lower space. This avoids reading incorrect values as MMD identifiers. Reviewed-by: Florian Fainelli Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 19d9e040ad84..9248dd2ce4ca 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -399,7 +399,7 @@ enum phy_state { struct phy_c45_device_ids { u32 devices_in_package; u32 mmds_present; - u32 device_ids[8]; + u32 device_ids[MDIO_MMD_NUM]; }; struct macsec_context; -- cgit v1.2.3 From 775f43facfe89af605d77a9669aa311b5b95cd07 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Wed, 17 Jun 2020 18:46:42 +0200 Subject: Drivers: hv: vmbus: Remove the lock field from the vmbus_channel struct The spinlock is (now) *not used to protect test-and-set accesses to attributes of the structure or sc_list operations. There is, AFAICT, a distinct lack of {WRITE,READ}_ONCE()s in the handling of channel->state, but the changes below do not seem to make things "worse". ;-) Signed-off-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/20200617164642.37393-9-parri.andrea@gmail.com Reviewed-by: Michael Kelley Signed-off-by: Wei Liu --- include/linux/hyperv.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 690394b79d72..38100e80360a 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -840,12 +840,6 @@ struct vmbus_channel { */ void (*chn_rescind_callback)(struct vmbus_channel *channel); - /* - * The spinlock to protect the structure. It is being used to protect - * test-and-set access to various attributes of the structure as well - * as all sc_list operations. - */ - spinlock_t lock; /* * All Sub-channels of a primary channel are linked here. */ -- cgit v1.2.3 From 481e980a7c199c5a4634fd7ea308067dd4ba75fa Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 15 Jun 2020 12:57:58 +0000 Subject: mm: Allow arches to provide ptep_get() Since commit 9e343b467c70 ("READ_ONCE: Enforce atomicity for {READ,WRITE}_ONCE() memory accesses") it is not possible anymore to use READ_ONCE() to access complex page table entries like the one defined for powerpc 8xx with 16k size pages. Define a ptep_get() helper that architectures can override instead of performing a READ_ONCE() on the page table entry pointer. Fixes: 9e343b467c70 ("READ_ONCE: Enforce atomicity for {READ,WRITE}_ONCE() memory accesses") Signed-off-by: Christophe Leroy Acked-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/087fa12b6e920e32315136b998aa834f99242695.1592225558.git.christophe.leroy@csgroup.eu --- include/linux/pgtable.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 32b6c52d41b9..56c1e8eb7bb0 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -249,6 +249,13 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #endif +#ifndef __HAVE_ARCH_PTEP_GET +static inline pte_t ptep_get(pte_t *ptep) +{ + return READ_ONCE(*ptep); +} +#endif + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, -- cgit v1.2.3 From f11d59d87b8622d4cf9f856c0b8029fb030d8612 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 25 May 2020 14:38:53 +0300 Subject: iio: Move attach/detach of the poll func to the core All devices using a triggered buffer need to attach and detach the trigger to the device in order to properly work. Instead of doing this in each and every driver by hand move this into the core. At this point in time, all drivers should have been resolved to attach/detach the poll-function in the same order. This patch removes all explicit calls of iio_triggered_buffer_postenable() & iio_triggered_buffer_predisable() in all drivers, since the core handles now the pollfunc attach/detach. The more peculiar change is for the 'at91-sama5d2_adc' driver, since it's not immediately obvious that removing the hooks doesn't break anything. Eugen was able to test on at91-sama5d2-adc driver, sama5d2-xplained board. All seems to be fine. Signed-off-by: Lars-Peter Clausen Signed-off-by: Alexandru Ardelean Tested-by: Eugen Hristev #for at91-sama5d2-adc Signed-off-by: Jonathan Cameron --- include/linux/iio/trigger_consumer.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/trigger_consumer.h b/include/linux/iio/trigger_consumer.h index c3c6ba5ec423..3aa2f132dd67 100644 --- a/include/linux/iio/trigger_consumer.h +++ b/include/linux/iio/trigger_consumer.h @@ -50,11 +50,4 @@ irqreturn_t iio_pollfunc_store_time(int irq, void *p); void iio_trigger_notify_done(struct iio_trigger *trig); -/* - * Two functions for common case where all that happens is a pollfunc - * is attached and detached from a trigger - */ -int iio_triggered_buffer_postenable(struct iio_dev *indio_dev); -int iio_triggered_buffer_predisable(struct iio_dev *indio_dev); - #endif -- cgit v1.2.3 From b3337eb24831db058231ea87838f316d9eb86253 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 15 Jun 2020 18:05:41 +0300 Subject: gpiolib: Introduce for_each_requested_gpio_in_range() macro Introduce for_each_requested_gpio_in_range() macro which helps to iterate over requested GPIO in a range. There are already potential users of it, which are going to be converted by the following patches. For most of them for_each_requested_gpio() shortcut has been added. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200615150545.87964-2-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index c4f272af7af5..11cdcb195635 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -474,6 +474,22 @@ struct gpio_chip { extern const char *gpiochip_is_requested(struct gpio_chip *gc, unsigned int offset); +/** + * for_each_requested_gpio_in_range - iterates over requested GPIOs in a given range + * @chip: the chip to query + * @i: loop variable + * @base: first GPIO in the range + * @size: amount of GPIOs to check starting from @base + * @label: label of current GPIO + */ +#define for_each_requested_gpio_in_range(chip, i, base, size, label) \ + for (i = 0; i < size; i++) \ + if ((label = gpiochip_is_requested(chip, base + i)) == NULL) {} else + +/* Iterates over all requested GPIO of the given @chip */ +#define for_each_requested_gpio(chip, i, label) \ + for_each_requested_gpio_in_range(chip, i, 0, chip->ngpio, label) + /* add/remove chips */ extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, struct lock_class_key *lock_key, -- cgit v1.2.3 From 5a473e8311b582a40c10409a0f4bb39f42aa8123 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 4 Jun 2020 11:23:39 -0600 Subject: block: provide plug based way of signaling forced no-wait semantics Provide a way for the caller to specify that IO should be marked with REQ_NOWAIT to avoid blocking on allocation. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8fd900998b4e..6e067dca94cf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1189,6 +1189,7 @@ struct blk_plug { struct list_head cb_list; /* md requires an unplug callback */ unsigned short rq_count; bool multiple_queues; + bool nowait; }; #define BLK_MAX_REQUEST_COUNT 16 #define BLK_PLUG_FLUSH_SIZE (128 * 1024) -- cgit v1.2.3 From c7510ab2cf5ccd997fe7f194edfe09cc511abf99 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 23 May 2020 08:22:14 -0600 Subject: mm: abstract out wake_page_match() from wake_page_function() No functional changes in this patch, just in preparation for allowing more callers. Acked-by: Johannes Weiner Signed-off-by: Jens Axboe --- include/linux/pagemap.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index cf2468da68e9..2f18221bb5c8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -496,6 +496,43 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma, return pgoff; } +/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */ +struct wait_page_key { + struct page *page; + int bit_nr; + int page_match; +}; + +struct wait_page_queue { + struct page *page; + int bit_nr; + wait_queue_entry_t wait; +}; + +static inline int wake_page_match(struct wait_page_queue *wait_page, + struct wait_page_key *key) +{ + if (wait_page->page != key->page) + return 0; + key->page_match = 1; + + if (wait_page->bit_nr != key->bit_nr) + return 0; + + /* + * Stop walking if it's locked. + * Is this safe if put_and_wait_on_page_locked() is in use? + * Yes: the waker must hold a reference to this page, and if PG_locked + * has now already been set by another task, that task must also hold + * a reference to the *same usage* of this page; so there is no need + * to walk on to wake even the put_and_wait_on_page_locked() callers. + */ + if (test_bit(key->bit_nr, &key->page->flags)) + return -1; + + return 1; +} + extern void __lock_page(struct page *page); extern int __lock_page_killable(struct page *page); extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, -- cgit v1.2.3 From dd3e6d5039de1cbff4e20e2b34390ff44cdb182f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 22 May 2020 09:12:09 -0600 Subject: mm: add support for async page locking Normally waiting for a page to become unlocked, or locking the page, requires waiting for IO to complete. Add support for lock_page_async() and wait_on_page_locked_async(), which are callback based instead. This allows a caller to get notified when a page becomes unlocked, rather than wait for it. We add a new iocb field, ki_waitq, to pass in the necessary data for this to happen. We can unionize this with ki_cookie, since that is only used for polled IO. Polled IO can never co-exist with async callbacks, as it is (by definition) polled completions. struct wait_page_key is made public, and we define struct wait_page_async as the interface between the caller and the core. Acked-by: Johannes Weiner Signed-off-by: Jens Axboe --- include/linux/fs.h | 7 ++++++- include/linux/pagemap.h | 17 +++++++++++++++++ 2 files changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3f881a892ea7..2a5cf6080e68 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -315,6 +315,8 @@ enum rw_hint { #define IOCB_SYNC (1 << 5) #define IOCB_WRITE (1 << 6) #define IOCB_NOWAIT (1 << 7) +/* iocb->ki_waitq is valid */ +#define IOCB_WAITQ (1 << 8) struct kiocb { struct file *ki_filp; @@ -328,7 +330,10 @@ struct kiocb { int ki_flags; u16 ki_hint; u16 ki_ioprio; /* See linux/ioprio.h */ - unsigned int ki_cookie; /* for ->iopoll */ + union { + unsigned int ki_cookie; /* for ->iopoll */ + struct wait_page_queue *ki_waitq; /* for async buffered IO */ + }; randomized_struct_fields_end }; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 2f18221bb5c8..e053e1d9a4d7 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -535,6 +535,7 @@ static inline int wake_page_match(struct wait_page_queue *wait_page, extern void __lock_page(struct page *page); extern int __lock_page_killable(struct page *page); +extern int __lock_page_async(struct page *page, struct wait_page_queue *wait); extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags); extern void unlock_page(struct page *page); @@ -571,6 +572,22 @@ static inline int lock_page_killable(struct page *page) return 0; } +/* + * lock_page_async - Lock the page, unless this would block. If the page + * is already locked, then queue a callback when the page becomes unlocked. + * This callback can then retry the operation. + * + * Returns 0 if the page is locked successfully, or -EIOCBQUEUED if the page + * was already locked and the callback defined in 'wait' was queued. + */ +static inline int lock_page_async(struct page *page, + struct wait_page_queue *wait) +{ + if (!trylock_page(page)) + return __lock_page_async(page, wait); + return 0; +} + /* * lock_page_or_retry - Lock the page, unless this would block and the * caller indicated that it can handle a retry. -- cgit v1.2.3 From c2a25ec0f1005dde004cd671484f578a9c8ca7de Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 22 May 2020 09:12:51 -0600 Subject: fs: add FMODE_BUF_RASYNC If set, this indicates that the file system supports IOCB_WAITQ for buffered reads. Signed-off-by: Jens Axboe --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2a5cf6080e68..4090320360f4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -175,6 +175,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) +/* File supports async buffered reads */ +#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) + /* * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector * that indicates that they should check the contents of the iovec are -- cgit v1.2.3 From d1932dc3dc268f8dd5201c64971324d06ba977cc Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 22 May 2020 10:18:23 -0600 Subject: mm: add kiocb_wait_page_queue_init() helper Checks if the file supports it, and initializes the values that we need. Caller passes in 'data' pointer, if any, and the callback function to be used. Acked-by: Johannes Weiner Signed-off-by: Jens Axboe --- include/linux/pagemap.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e053e1d9a4d7..7386bc67cc5a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -533,6 +533,27 @@ static inline int wake_page_match(struct wait_page_queue *wait_page, return 1; } +static inline int kiocb_wait_page_queue_init(struct kiocb *kiocb, + struct wait_page_queue *wait, + wait_queue_func_t func, + void *data) +{ + /* Can't support async wakeup with polled IO */ + if (kiocb->ki_flags & IOCB_HIPRI) + return -EINVAL; + if (kiocb->ki_filp->f_mode & FMODE_BUF_RASYNC) { + wait->wait.func = func; + wait->wait.private = data; + wait->wait.flags = 0; + INIT_LIST_HEAD(&wait->wait.entry); + kiocb->ki_flags |= IOCB_WAITQ; + kiocb->ki_waitq = wait; + return 0; + } + + return -EOPNOTSUPP; +} + extern void __lock_page(struct page *page); extern int __lock_page_killable(struct page *page); extern int __lock_page_async(struct page *page, struct wait_page_queue *wait); -- cgit v1.2.3 From 613c2e2c7e69e574411e2a3609459e18e91ae3fb Mon Sep 17 00:00:00 2001 From: Dennis YC Hsieh Date: Sun, 21 Jun 2020 22:18:26 +0800 Subject: soc: mediatek: cmdq: add assign function Add assign function in cmdq helper which assign constant value into internal register by index. Signed-off-by: Dennis YC Hsieh Link: https://lore.kernel.org/r/1592749115-24158-3-git-send-email-dennis-yc.hsieh@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/mailbox/mtk-cmdq-mailbox.h | 1 + include/linux/soc/mediatek/mtk-cmdq.h | 14 ++++++++++++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index a4dc45fbec0a..70b740a552c2 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -59,6 +59,7 @@ enum cmdq_code { CMDQ_CODE_JUMP = 0x10, CMDQ_CODE_WFE = 0x20, CMDQ_CODE_EOC = 0x40, + CMDQ_CODE_LOGIC = 0xa0, }; enum cmdq_cb_status { diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index a74c1d5acdf3..83340211e1d3 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -152,6 +152,20 @@ int cmdq_pkt_poll(struct cmdq_pkt *pkt, u8 subsys, */ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value, u32 mask); + +/** + * cmdq_pkt_assign() - Append logic assign command to the CMDQ packet, ask GCE + * to execute an instruction that set a constant value into + * internal register and use as value, mask or address in + * read/write instruction. + * @pkt: the CMDQ packet + * @reg_idx: the CMDQ internal register ID + * @value: the specified value + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value); + /** * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ * packet and call back at the end of done packet -- cgit v1.2.3 From 995818588b6deedbed6b2b9d4c67e59b9afd6c60 Mon Sep 17 00:00:00 2001 From: Dennis YC Hsieh Date: Sun, 21 Jun 2020 22:18:32 +0800 Subject: soc: mediatek: cmdq: export finalize function Export finalize function to client which helps append eoc and jump command to pkt. Let client decide call finalize or not. Signed-off-by: Dennis YC Hsieh Reviewed-by: CK Hu Acked-by: Chun-Kuang Hu Link: https://lore.kernel.org/r/1592749115-24158-9-git-send-email-dennis-yc.hsieh@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-cmdq.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 83340211e1d3..c331255eacd1 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -166,6 +166,14 @@ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys, */ int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value); +/** + * cmdq_pkt_finalize() - Append EOC and jump command to pkt. + * @pkt: the CMDQ packet + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_finalize(struct cmdq_pkt *pkt); + /** * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ * packet and call back at the end of done packet -- cgit v1.2.3 From 7de796cac48c0f55974cfe9cff683dfb3b7c71b6 Mon Sep 17 00:00:00 2001 From: Dennis YC Hsieh Date: Sun, 21 Jun 2020 22:18:35 +0800 Subject: soc: mediatek: cmdq: add set event function Add set event function in cmdq helper functions to set specific event. Signed-off-by: Dennis YC Hsieh Link: https://lore.kernel.org/r/1592749115-24158-12-git-send-email-dennis-yc.hsieh@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/mailbox/mtk-cmdq-mailbox.h | 1 + include/linux/soc/mediatek/mtk-cmdq.h | 9 +++++++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index 70b740a552c2..a96e8c252bac 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -17,6 +17,7 @@ #define CMDQ_JUMP_PASS CMDQ_INST_SIZE #define CMDQ_WFE_UPDATE BIT(31) +#define CMDQ_WFE_UPDATE_VALUE BIT(16) #define CMDQ_WFE_WAIT BIT(15) #define CMDQ_WFE_WAIT_VALUE 0x1 diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index c331255eacd1..2249ecaf77e4 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -120,6 +120,15 @@ int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event); */ int cmdq_pkt_clear_event(struct cmdq_pkt *pkt, u16 event); +/** + * cmdq_pkt_set_event() - append set event command to the CMDQ packet + * @pkt: the CMDQ packet + * @event: the desired event to be set + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_set_event(struct cmdq_pkt *pkt, u16 event); + /** * cmdq_pkt_poll() - Append polling command to the CMDQ packet, ask GCE to * execute an instruction that wait for a specified -- cgit v1.2.3 From 3af8588c77186bf08e55e7281da83d88373481d7 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 8 Jun 2020 17:28:50 +0200 Subject: fork: fold legacy_clone_args_valid() into _do_fork() This separate helper only existed to guarantee the mutual exclusivity of CLONE_PIDFD and CLONE_PARENT_SETTID for legacy clone since CLONE_PIDFD abuses the parent_tid field to return the pidfd. But we can actually handle this uniformely thus removing the helper. For legacy clone we can detect that CLONE_PIDFD is specified in conjunction with CLONE_PARENT_SETTID because they will share the same memory which is invalid and for clone3() setting the separate pidfd and parent_tid fields to the same memory is bogus as well. So fold that helper directly into _do_fork() by detecting this case. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Al Viro Cc: Geert Uytterhoeven Cc: "Matthew Wilcox (Oracle)" Cc: "Peter Zijlstra (Intel)" Cc: linux-m68k@lists.linux-m68k.org Cc: x86@kernel.org Signed-off-by: Christian Brauner --- include/linux/sched/task.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 38359071236a..ddce0ea515d1 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -96,7 +96,6 @@ extern void exit_files(struct task_struct *); extern void exit_itimers(struct signal_struct *); extern long _do_fork(struct kernel_clone_args *kargs); -extern bool legacy_clone_args_valid(const struct kernel_clone_args *kargs); extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); -- cgit v1.2.3 From 53f13319d13197dd1f4c8ce5fc1ef4c32509b4e2 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 9 Jun 2020 18:10:39 +0300 Subject: thunderbolt: Get rid of E2E workaround The end-to-end (E2E) workaround is needed for Falcon Ridge (TBT 2) controller when E2E is enabled for both ends of the host-to-host connection. However, we never supported full E2E in the first place so this code is not necessary at the moment. Further this allows us to use all available rings for data except ring 0 which is reserved for the control path. The complete E2E flow control is explained in the USB4 spec so we may add it back later if needed but at least the networking driver seems to work fine without, and the higher level stack, like TCP will retransmit lost packets anyway. Signed-off-by: Mika Westerberg --- include/linux/thunderbolt.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index ff397c0d5c07..5db2b11ab085 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -504,8 +504,6 @@ struct tb_ring { #define RING_FLAG_NO_SUSPEND BIT(0) /* Configure the ring to be in frame mode */ #define RING_FLAG_FRAME BIT(1) -/* Enable end-to-end flow control */ -#define RING_FLAG_E2E BIT(2) struct ring_frame; typedef void (*ring_cb)(struct tb_ring *, struct ring_frame *, bool canceled); -- cgit v1.2.3 From 4bc799dcb67066e0531004d5bdbe755bb02b5488 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Mon, 15 Jun 2020 11:12:32 -0700 Subject: security: fix the key_permission LSM hook function type Commit 8c0637e950d6 ("keys: Make the KEY_NEED_* perms an enum rather than a mask") changed the type of the key_permission callback functions, but didn't change the type of the hook, which trips indirect call checking with Control-Flow Integrity (CFI). This change fixes the issue by changing the hook type to match the functions. Fixes: 8c0637e950d6 ("keys: Make the KEY_NEED_* perms an enum rather than a mask") Signed-off-by: Sami Tolvanen Acked-by: Kees Cook Signed-off-by: James Morris --- include/linux/lsm_hook_defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 6791813cd439..24f6683f1cfc 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -360,7 +360,7 @@ LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred, unsigned long flags) LSM_HOOK(void, LSM_RET_VOID, key_free, struct key *key) LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred, - unsigned perm) + enum key_need_perm need_perm) LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **_buffer) #endif /* CONFIG_KEYS */ -- cgit v1.2.3 From 41c48f3a98231738c5ce79f6f2aa6e40ba924d18 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 19 Jun 2020 14:11:43 -0700 Subject: bpf: Support access to bpf map fields There are multiple use-cases when it's convenient to have access to bpf map fields, both `struct bpf_map` and map type specific struct-s such as `struct bpf_array`, `struct bpf_htab`, etc. For example while working with sock arrays it can be necessary to calculate the key based on map->max_entries (some_hash % max_entries). Currently this is solved by communicating max_entries via "out-of-band" channel, e.g. via additional map with known key to get info about target map. That works, but is not very convenient and error-prone while working with many maps. In other cases necessary data is dynamic (i.e. unknown at loading time) and it's impossible to get it at all. For example while working with a hash table it can be convenient to know how much capacity is already used (bpf_htab.count.counter for BPF_F_NO_PREALLOC case). At the same time kernel knows this info and can provide it to bpf program. Fill this gap by adding support to access bpf map fields from bpf program for both `struct bpf_map` and map type specific fields. Support is implemented via btf_struct_access() so that a user can define their own `struct bpf_map` or map type specific struct in their program with only necessary fields and preserve_access_index attribute, cast a map to this struct and use a field. For example: struct bpf_map { __u32 max_entries; } __attribute__((preserve_access_index)); struct bpf_array { struct bpf_map map; __u32 elem_size; } __attribute__((preserve_access_index)); struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 4); __type(key, __u32); __type(value, __u32); } m_array SEC(".maps"); SEC("cgroup_skb/egress") int cg_skb(void *ctx) { struct bpf_array *array = (struct bpf_array *)&m_array; struct bpf_map *map = (struct bpf_map *)&m_array; /* .. use map->max_entries or array->map.max_entries .. */ } Similarly to other btf_struct_access() use-cases (e.g. struct tcp_sock in net/ipv4/bpf_tcp_ca.c) the patch allows access to any fields of corresponding struct. Only reading from map fields is supported. For btf_struct_access() to work there should be a way to know btf id of a struct that corresponds to a map type. To get btf id there should be a way to get a stringified name of map-specific struct, such as "bpf_array", "bpf_htab", etc for a map type. Two new fields are added to `struct bpf_map_ops` to handle it: * .map_btf_name keeps a btf name of a struct returned by map_alloc(); * .map_btf_id is used to cache btf id of that struct. To make btf ids calculation cheaper they're calculated once while preparing btf_vmlinux and cached same way as it's done for btf_id field of `struct bpf_func_proto` While calculating btf ids, struct names are NOT checked for collision. Collisions will be checked as a part of the work to prepare btf ids used in verifier in compile time that should land soon. The only known collision for `struct bpf_htab` (kernel/bpf/hashtab.c vs net/core/sock_map.c) was fixed earlier. Both new fields .map_btf_name and .map_btf_id must be set for a map type for the feature to work. If neither is set for a map type, verifier will return ENOTSUPP on a try to access map_ptr of corresponding type. If just one of them set, it's verifier misconfiguration. Only `struct bpf_array` for BPF_MAP_TYPE_ARRAY and `struct bpf_htab` for BPF_MAP_TYPE_HASH are supported by this patch. Other map types will be supported separately. The feature is available only for CONFIG_DEBUG_INFO_BTF=y and gated by perfmon_capable() so that unpriv programs won't have access to bpf map fields. Signed-off-by: Andrey Ignatov Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/6479686a0cd1e9067993df57b4c3eef0e276fec9.1592600985.git.rdna@fb.com --- include/linux/bpf.h | 9 +++++++++ include/linux/bpf_verifier.h | 1 + 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 07052d44bca1..1e1501ee53ce 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -92,6 +92,10 @@ struct bpf_map_ops { int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); + + /* BTF name and id of struct allocated by map_alloc */ + const char * const map_btf_name; + int *map_btf_id; }; struct bpf_map_memory { @@ -1109,6 +1113,11 @@ static inline bool bpf_allow_ptr_leaks(void) return perfmon_capable(); } +static inline bool bpf_allow_ptr_to_map_access(void) +{ + return perfmon_capable(); +} + static inline bool bpf_bypass_spec_v1(void) { return perfmon_capable(); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index ca08db4ffb5f..53c7bd568c5d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -379,6 +379,7 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; + bool allow_ptr_to_map_access; bool bpf_capable; bool bypass_spec_v1; bool bypass_spec_v4; -- cgit v1.2.3 From fa997825ebeca820f4001a9e6d285345d3a535ba Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 19 Jun 2020 03:32:50 +0000 Subject: net/mlx5: Constify mac address pointer Since none of the functions need to modify the input mac address, constify them. Signed-off-by: Parav Pandit Reviewed-by: Roi Dayan Signed-off-by: David S. Miller --- include/linux/mlx5/vport.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 8170da1e9f70..4db87bcfce7b 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -75,7 +75,7 @@ void mlx5_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline); int mlx5_modify_nic_vport_min_inline(struct mlx5_core_dev *mdev, u16 vport, u8 min_inline); int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev, - u16 vport, u8 *addr); + u16 vport, const u8 *addr); int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu); int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu); int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, -- cgit v1.2.3 From a602ea86e9f0d82f5c7ba1d3f7487d4097380b96 Mon Sep 17 00:00:00 2001 From: Maxim Kochetkov Date: Sun, 21 Jun 2020 10:59:51 +0300 Subject: net: phy: marvell: Add Marvell 88E1340S support Add support for this new phy ID. Signed-off-by: Maxim Kochetkov Signed-off-by: David S. Miller --- include/linux/marvell_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index af6b11d4d673..c4390e9cbf15 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -15,6 +15,7 @@ #define MARVELL_PHY_ID_88E1149R 0x01410e50 #define MARVELL_PHY_ID_88E1240 0x01410e30 #define MARVELL_PHY_ID_88E1318S 0x01410e90 +#define MARVELL_PHY_ID_88E1340S 0x01410dc0 #define MARVELL_PHY_ID_88E1116R 0x01410e40 #define MARVELL_PHY_ID_88E1510 0x01410dd0 #define MARVELL_PHY_ID_88E1540 0x01410eb0 -- cgit v1.2.3 From f59babf95ef969a18744082ee16e4dfd17743c0b Mon Sep 17 00:00:00 2001 From: Maxim Kochetkov Date: Sun, 21 Jun 2020 10:59:52 +0300 Subject: net: phy: marvell: Add Marvell 88E1548P support Add support for this new phy ID. Signed-off-by: Maxim Kochetkov Signed-off-by: David S. Miller --- include/linux/marvell_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index c4390e9cbf15..ff7b7607c8cf 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -20,6 +20,7 @@ #define MARVELL_PHY_ID_88E1510 0x01410dd0 #define MARVELL_PHY_ID_88E1540 0x01410eb0 #define MARVELL_PHY_ID_88E1545 0x01410ea0 +#define MARVELL_PHY_ID_88E1548P 0x01410ec0 #define MARVELL_PHY_ID_88E3016 0x01410e60 #define MARVELL_PHY_ID_88X3310 0x002b09a0 #define MARVELL_PHY_ID_88E2110 0x002b09b0 -- cgit v1.2.3 From 169caf692567897da35382503a5caeb64ab4b8c7 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Fri, 5 Jun 2020 09:59:31 +0800 Subject: firmware: imx: add resource management api Add resource management API, when we have multiple partition running together, resources not owned to current partition should not be used. Reviewed-by: Leonard Crestez Reviewed-by: Dong Aisheng Signed-off-by: Peng Fan Signed-off-by: Shawn Guo --- include/linux/firmware/imx/sci.h | 1 + include/linux/firmware/imx/svc/rm.h | 69 +++++++++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+) create mode 100644 include/linux/firmware/imx/svc/rm.h (limited to 'include/linux') diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h index 3fa418a4ca67..3c459f54a88f 100644 --- a/include/linux/firmware/imx/sci.h +++ b/include/linux/firmware/imx/sci.h @@ -14,6 +14,7 @@ #include #include +#include int imx_scu_enable_general_irq_channel(struct device *dev); int imx_scu_irq_register_notifier(struct notifier_block *nb); diff --git a/include/linux/firmware/imx/svc/rm.h b/include/linux/firmware/imx/svc/rm.h new file mode 100644 index 000000000000..456b6a59d29b --- /dev/null +++ b/include/linux/firmware/imx/svc/rm.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2016 Freescale Semiconductor, Inc. + * Copyright 2017-2020 NXP + * + * Header file containing the public API for the System Controller (SC) + * Resource Management (RM) function. This includes functions for + * partitioning resources, pads, and memory regions. + * + * RM_SVC (SVC) Resource Management Service + * + * Module for the Resource Management (RM) service. + */ + +#ifndef _SC_RM_API_H +#define _SC_RM_API_H + +#include + +/* + * This type is used to indicate RPC RM function calls. + */ +enum imx_sc_rm_func { + IMX_SC_RM_FUNC_UNKNOWN = 0, + IMX_SC_RM_FUNC_PARTITION_ALLOC = 1, + IMX_SC_RM_FUNC_SET_CONFIDENTIAL = 31, + IMX_SC_RM_FUNC_PARTITION_FREE = 2, + IMX_SC_RM_FUNC_GET_DID = 26, + IMX_SC_RM_FUNC_PARTITION_STATIC = 3, + IMX_SC_RM_FUNC_PARTITION_LOCK = 4, + IMX_SC_RM_FUNC_GET_PARTITION = 5, + IMX_SC_RM_FUNC_SET_PARENT = 6, + IMX_SC_RM_FUNC_MOVE_ALL = 7, + IMX_SC_RM_FUNC_ASSIGN_RESOURCE = 8, + IMX_SC_RM_FUNC_SET_RESOURCE_MOVABLE = 9, + IMX_SC_RM_FUNC_SET_SUBSYS_RSRC_MOVABLE = 28, + IMX_SC_RM_FUNC_SET_MASTER_ATTRIBUTES = 10, + IMX_SC_RM_FUNC_SET_MASTER_SID = 11, + IMX_SC_RM_FUNC_SET_PERIPHERAL_PERMISSIONS = 12, + IMX_SC_RM_FUNC_IS_RESOURCE_OWNED = 13, + IMX_SC_RM_FUNC_GET_RESOURCE_OWNER = 33, + IMX_SC_RM_FUNC_IS_RESOURCE_MASTER = 14, + IMX_SC_RM_FUNC_IS_RESOURCE_PERIPHERAL = 15, + IMX_SC_RM_FUNC_GET_RESOURCE_INFO = 16, + IMX_SC_RM_FUNC_MEMREG_ALLOC = 17, + IMX_SC_RM_FUNC_MEMREG_SPLIT = 29, + IMX_SC_RM_FUNC_MEMREG_FRAG = 32, + IMX_SC_RM_FUNC_MEMREG_FREE = 18, + IMX_SC_RM_FUNC_FIND_MEMREG = 30, + IMX_SC_RM_FUNC_ASSIGN_MEMREG = 19, + IMX_SC_RM_FUNC_SET_MEMREG_PERMISSIONS = 20, + IMX_SC_RM_FUNC_IS_MEMREG_OWNED = 21, + IMX_SC_RM_FUNC_GET_MEMREG_INFO = 22, + IMX_SC_RM_FUNC_ASSIGN_PAD = 23, + IMX_SC_RM_FUNC_SET_PAD_MOVABLE = 24, + IMX_SC_RM_FUNC_IS_PAD_OWNED = 25, + IMX_SC_RM_FUNC_DUMP = 27, +}; + +#if IS_ENABLED(CONFIG_IMX_SCU) +bool imx_sc_rm_is_resource_owned(struct imx_sc_ipc *ipc, u16 resource); +#else +static inline bool +imx_sc_rm_is_resource_owned(struct imx_sc_ipc *ipc, u16 resource) +{ + return true; +} +#endif +#endif -- cgit v1.2.3 From 16ecf10e815d70d11d2300243f4a3b4c7c5acac7 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 23 Jun 2020 07:13:41 +0800 Subject: iommu/vt-d: Set U/S bit in first level page table by default When using first-level translation for IOVA, currently the U/S bit in the page table is cleared which implies DMA requests with user privilege are blocked. As the result, following error messages might be observed when passing through a device to user level: DMAR: DRHD: handling fault status reg 3 DMAR: [DMA Read] Request device [41:00.0] PASID 1 fault addr 7ecdcd000 [fault reason 129] SM: U/S set 0 for first-level translation with user privilege This fixes it by setting U/S bit in the first level page table and makes IOVA over first level compatible with previous second-level translation. Fixes: b802d070a52a1 ("iommu/vt-d: Use iova over first level") Reported-by: Xin Zeng Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20200622231345.29722-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4100bd224f5c..3e8fa1c7a1e6 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -41,6 +41,7 @@ #define DMA_PTE_SNP BIT_ULL(11) #define DMA_FL_PTE_PRESENT BIT_ULL(0) +#define DMA_FL_PTE_US BIT_ULL(2) #define DMA_FL_PTE_XD BIT_ULL(63) #define ADDR_WIDTH_5LEVEL (57) -- cgit v1.2.3 From 809b1b04df898b6d182069146231a3cbf5f2d9cc Mon Sep 17 00:00:00 2001 From: Robin Gong Date: Wed, 17 Jun 2020 06:42:08 +0800 Subject: spi: introduce fallback to pio Add fallback to pio mode in case dma transfer failed with error status SPI_TRANS_FAIL_NO_START. If spi client driver want to enable this feature please set xfer->error in the proper place such as dmaengine_prep_slave_sg() failure detect(but no any data put into spi bus yet). Besides, add master->fallback checking in its can_dma() so that spi core could switch to pio next time. Please refer to spi-imx.c. Signed-off-by: Robin Gong Link: https://lore.kernel.org/r/1592347329-28363-2-git-send-email-yibin.gong@nxp.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index aac57b5b7c21..b4917df79637 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -447,6 +447,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * If the driver does not set this, the SPI core takes the snapshot as * close to the driver hand-over as possible. * @irq_flags: Interrupt enable state during PTP system timestamping + * @fallback: fallback to pio if dma transfer return failure with + * SPI_TRANS_FAIL_NO_START. * * Each SPI controller can communicate with one or more @spi_device * children. These make a small bus, sharing MOSI, MISO and SCK signals @@ -602,6 +604,7 @@ struct spi_controller { bool auto_runtime_pm; bool cur_msg_prepared; bool cur_msg_mapped; + bool fallback; struct completion xfer_completion; size_t max_dma_len; @@ -847,6 +850,7 @@ extern void spi_res_release(struct spi_controller *ctlr, * back unset and they need the better resolution. * @timestamped_post: See above. The reason why both exist is that these * booleans are also used to keep state in the core SPI logic. + * @error: Error status logged by spi controller driver. * * SPI transfers always write the same number of bytes as they read. * Protocol drivers should always provide @rx_buf and/or @tx_buf. @@ -940,6 +944,9 @@ struct spi_transfer { bool timestamped; struct list_head transfer_list; + +#define SPI_TRANS_FAIL_NO_START BIT(0) + u16 error; }; /** -- cgit v1.2.3 From d63cc24933c774ea464090af1998a7b63f11c166 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Wed, 8 Apr 2020 12:42:09 +0300 Subject: net/mlx5: Export resource dump interface Export some of the resource dump API. mlx5_ib driver will use it in downstream patches. Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- include/linux/mlx5/rsc_dump.h | 48 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 include/linux/mlx5/rsc_dump.h (limited to 'include/linux') diff --git a/include/linux/mlx5/rsc_dump.h b/include/linux/mlx5/rsc_dump.h new file mode 100644 index 000000000000..87415fa754fe --- /dev/null +++ b/include/linux/mlx5/rsc_dump.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies inc. */ + +#include + +#ifndef __MLX5_RSC_DUMP +#define __MLX5_RSC_DUMP + +enum mlx5_sgmt_type { + MLX5_SGMT_TYPE_HW_CQPC, + MLX5_SGMT_TYPE_HW_SQPC, + MLX5_SGMT_TYPE_HW_RQPC, + MLX5_SGMT_TYPE_FULL_SRQC, + MLX5_SGMT_TYPE_FULL_CQC, + MLX5_SGMT_TYPE_FULL_EQC, + MLX5_SGMT_TYPE_FULL_QPC, + MLX5_SGMT_TYPE_SND_BUFF, + MLX5_SGMT_TYPE_RCV_BUFF, + MLX5_SGMT_TYPE_SRQ_BUFF, + MLX5_SGMT_TYPE_CQ_BUFF, + MLX5_SGMT_TYPE_EQ_BUFF, + MLX5_SGMT_TYPE_SX_SLICE, + MLX5_SGMT_TYPE_SX_SLICE_ALL, + MLX5_SGMT_TYPE_RDB, + MLX5_SGMT_TYPE_RX_SLICE_ALL, + MLX5_SGMT_TYPE_MENU, + MLX5_SGMT_TYPE_TERMINATE, + + MLX5_SGMT_TYPE_NUM, /* Keep last */ +}; + +struct mlx5_rsc_key { + enum mlx5_sgmt_type rsc; + int index1; + int index2; + int num_of_obj1; + int num_of_obj2; + int size; +}; + +struct mlx5_rsc_dump_cmd; + +struct mlx5_rsc_dump_cmd *mlx5_rsc_dump_cmd_create(struct mlx5_core_dev *dev, + struct mlx5_rsc_key *key); +void mlx5_rsc_dump_cmd_destroy(struct mlx5_rsc_dump_cmd *cmd); +int mlx5_rsc_dump_next(struct mlx5_core_dev *dev, struct mlx5_rsc_dump_cmd *cmd, + struct page *page, int *size); +#endif /* __MLX5_RSC_DUMP */ -- cgit v1.2.3 From 608ca553c9a2008908120e0e45b1cfc4aefcfd49 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Wed, 8 Apr 2020 12:36:20 +0300 Subject: net/mlx5: Add support in query QP, CQ and MKEY segments Introduce new resource dump segments - PRM_QUERY_QP, PRM_QUERY_CQ and PRM_QUERY_MKEY. These segments contains the resource dump in PRM query format. Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- include/linux/mlx5/rsc_dump.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/rsc_dump.h b/include/linux/mlx5/rsc_dump.h index 87415fa754fe..d11c0b228620 100644 --- a/include/linux/mlx5/rsc_dump.h +++ b/include/linux/mlx5/rsc_dump.h @@ -23,6 +23,9 @@ enum mlx5_sgmt_type { MLX5_SGMT_TYPE_SX_SLICE_ALL, MLX5_SGMT_TYPE_RDB, MLX5_SGMT_TYPE_RX_SLICE_ALL, + MLX5_SGMT_TYPE_PRM_QUERY_QP, + MLX5_SGMT_TYPE_PRM_QUERY_CQ, + MLX5_SGMT_TYPE_PRM_QUERY_MKEY, MLX5_SGMT_TYPE_MENU, MLX5_SGMT_TYPE_TERMINATE, -- cgit v1.2.3 From 97dd1abd026ae4e6a82fa68645928404ad483409 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 23 Jun 2020 16:51:29 +0300 Subject: net: qed: fix left elements count calculation qed_chain_get_element_left{,_u32} returned 0 when the difference between producer and consumer page count was equal to the total page count. Fix this by conditional expanding of producer value (vs unconditional). This allowed to eliminate normalizaton against total page count, which was the cause of this bug. Misc: replace open-coded constants with common defines. Fixes: a91eb52abb50 ("qed: Revisit chain implementation") Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 733fad7dfbed..6d15040c642c 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -207,28 +207,34 @@ static inline u32 qed_chain_get_cons_idx_u32(struct qed_chain *p_chain) static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain) { + u16 elem_per_page = p_chain->elem_per_page; + u32 prod = p_chain->u.chain16.prod_idx; + u32 cons = p_chain->u.chain16.cons_idx; u16 used; - used = (u16) (((u32)0x10000 + - (u32)p_chain->u.chain16.prod_idx) - - (u32)p_chain->u.chain16.cons_idx); + if (prod < cons) + prod += (u32)U16_MAX + 1; + + used = (u16)(prod - cons); if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) - used -= p_chain->u.chain16.prod_idx / p_chain->elem_per_page - - p_chain->u.chain16.cons_idx / p_chain->elem_per_page; + used -= prod / elem_per_page - cons / elem_per_page; return (u16)(p_chain->capacity - used); } static inline u32 qed_chain_get_elem_left_u32(struct qed_chain *p_chain) { + u16 elem_per_page = p_chain->elem_per_page; + u64 prod = p_chain->u.chain32.prod_idx; + u64 cons = p_chain->u.chain32.cons_idx; u32 used; - used = (u32) (((u64)0x100000000ULL + - (u64)p_chain->u.chain32.prod_idx) - - (u64)p_chain->u.chain32.cons_idx); + if (prod < cons) + prod += (u64)U32_MAX + 1; + + used = (u32)(prod - cons); if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) - used -= p_chain->u.chain32.prod_idx / p_chain->elem_per_page - - p_chain->u.chain32.cons_idx / p_chain->elem_per_page; + used -= (u32)(prod / elem_per_page - cons / elem_per_page); return p_chain->capacity - used; } -- cgit v1.2.3 From e678e9ddea96590888b034e2a7ad1128bf1ea1ea Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Tue, 23 Jun 2020 09:42:31 -0700 Subject: indirect_call_wrapper: extend indirect wrapper to support up to 4 calls There are many places where 2 annotations are not enough. This patch adds INDIRECT_CALL_3 and INDIRECT_CALL_4 to cover such cases. Signed-off-by: Brian Vazquez Acked-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/indirect_call_wrapper.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 00d7e8e919c6..54c02c84906a 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -23,6 +23,16 @@ likely(f == f2) ? f2(__VA_ARGS__) : \ INDIRECT_CALL_1(f, f1, __VA_ARGS__); \ }) +#define INDIRECT_CALL_3(f, f3, f2, f1, ...) \ + ({ \ + likely(f == f3) ? f3(__VA_ARGS__) : \ + INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__); \ + }) +#define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) \ + ({ \ + likely(f == f4) ? f4(__VA_ARGS__) : \ + INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__); \ + }) #define INDIRECT_CALLABLE_DECLARE(f) f #define INDIRECT_CALLABLE_SCOPE @@ -30,6 +40,8 @@ #else #define INDIRECT_CALL_1(f, f1, ...) f(__VA_ARGS__) #define INDIRECT_CALL_2(f, f2, f1, ...) f(__VA_ARGS__) +#define INDIRECT_CALL_3(f, f3, f2, f1, ...) f(__VA_ARGS__) +#define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) f(__VA_ARGS__) #define INDIRECT_CALLABLE_DECLARE(f) #define INDIRECT_CALLABLE_SCOPE static #endif -- cgit v1.2.3 From 23e390cdbe6f85827a43d38f9288dcd3066fa376 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Mon, 22 Jun 2020 00:21:35 +0200 Subject: security: Fix hook iteration and default value for inode_copy_up_xattr inode_copy_up_xattr returns 0 to indicate the acceptance of the xattr and 1 to reject it. If the LSM does not know about the xattr, it's expected to return -EOPNOTSUPP, which is the correct default value for this hook. BPF LSM, currently, uses 0 as the default value and thereby falsely allows all overlay fs xattributes to be copied up. The iteration logic is also updated from the "bail-on-fail" call_int_hook to continue on the non-decisive -EOPNOTSUPP and bail out on other values. Fixes: 98e828a0650f ("security: Refactor declaration of LSM hooks") Signed-off-by: KP Singh Signed-off-by: James Morris --- include/linux/lsm_hook_defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 24f6683f1cfc..af998f93d256 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -150,7 +150,7 @@ LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer, size_t buffer_size) LSM_HOOK(void, LSM_RET_VOID, inode_getsecid, struct inode *inode, u32 *secid) LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new) -LSM_HOOK(int, 0, inode_copy_up_xattr, const char *name) +LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, const char *name) LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir, struct kernfs_node *kn) LSM_HOOK(int, 0, file_permission, struct file *file, int mask) -- cgit v1.2.3 From 8e6cf365e1d5c70e275a77a3c5ad7e3dc685474c Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Thu, 4 Jun 2020 09:20:49 -0400 Subject: audit: log nftables configuration change events iptables, ip6tables, arptables and ebtables table registration, replacement and unregistration configuration events are logged for the native (legacy) iptables setsockopt api, but not for the nftables netlink api which is used by the nft-variant of iptables in addition to nftables itself. Add calls to log the configuration actions in the nftables netlink api. This uses the same NETFILTER_CFG record format but overloads the table field. type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.878:162) : table=?:0;?:0 family=unspecified entries=2 op=nft_register_gen pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld ... type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.878:162) : table=firewalld:1;?:0 family=inet entries=0 op=nft_register_table pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld ... type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.911:163) : table=firewalld:1;filter_FORWARD:85 family=inet entries=8 op=nft_register_chain pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld ... type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.911:163) : table=firewalld:1;filter_FORWARD:85 family=inet entries=101 op=nft_register_rule pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld ... type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.911:163) : table=firewalld:1;__set0:87 family=inet entries=87 op=nft_register_setelem pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld ... type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.911:163) : table=firewalld:1;__set0:87 family=inet entries=0 op=nft_register_set pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld For further information please see issue https://github.com/linux-audit/audit-kernel/issues/124 Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 3fcd9ee49734..604ede630580 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -12,6 +12,7 @@ #include #include #include +#include #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) @@ -98,6 +99,23 @@ enum audit_nfcfgop { AUDIT_XT_OP_REGISTER, AUDIT_XT_OP_REPLACE, AUDIT_XT_OP_UNREGISTER, + AUDIT_NFT_OP_TABLE_REGISTER, + AUDIT_NFT_OP_TABLE_UNREGISTER, + AUDIT_NFT_OP_CHAIN_REGISTER, + AUDIT_NFT_OP_CHAIN_UNREGISTER, + AUDIT_NFT_OP_RULE_REGISTER, + AUDIT_NFT_OP_RULE_UNREGISTER, + AUDIT_NFT_OP_SET_REGISTER, + AUDIT_NFT_OP_SET_UNREGISTER, + AUDIT_NFT_OP_SETELEM_REGISTER, + AUDIT_NFT_OP_SETELEM_UNREGISTER, + AUDIT_NFT_OP_GEN_REGISTER, + AUDIT_NFT_OP_OBJ_REGISTER, + AUDIT_NFT_OP_OBJ_UNREGISTER, + AUDIT_NFT_OP_OBJ_RESET, + AUDIT_NFT_OP_FLOWTABLE_REGISTER, + AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, + AUDIT_NFT_OP_INVALID, }; extern int is_audit_feature_set(int which); -- cgit v1.2.3 From 0cc8fecf041d3e5285380da62cc6662bdc942d8c Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Mon, 22 Jun 2020 20:35:32 +0530 Subject: net: phy: Allow mdio buses to auto-probe c45 devices The mdiobus_scan logic is currently hardcoded to only work with c22 devices. This works fairly well in most cases, but its possible that a c45 device doesn't respond despite being a standard phy. If the parent hardware is capable, it makes sense to scan for c22 devices before falling back to c45. As we want this to reflect the capabilities of the STA, lets add a field to the mii_bus structure to represent the capability. That way devices can opt into the extended scanning. Existing users should continue to default to c22 only scanning as long as they are zero'ing the structure before use. Signed-off-by: Jeremy Linton Signed-off-by: Calvin Johnson Signed-off-by: David S. Miller --- include/linux/phy.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 9248dd2ce4ca..7860d56c6bf5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -298,6 +298,14 @@ struct mii_bus { /* RESET GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; + /* bus capabilities, used for probing */ + enum { + MDIOBUS_NO_CAP = 0, + MDIOBUS_C22, + MDIOBUS_C45, + MDIOBUS_C22_C45, + } probe_capabilities; + /* protect access to the shared element */ struct mutex shared_lock; -- cgit v1.2.3 From aad4b4d15f30de087c5972cfb767fadb5dbc3c52 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:13:02 +0200 Subject: scsi: libata: Fix the ata_scsi_dma_need_drain stub We not only need the stub when libata is disabled, but also if it is modular and there are built-in SAS drivers (which can happen when SCSI_SAS_ATA is disabled). Link: https://lore.kernel.org/r/20200620071302.462974-2-hch@lst.de Fixes: b8f1d1e05817 ("scsi: Wire up ata_scsi_dma_need_drain for SAS HBA drivers") Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 042e584daca7..c57bf6749681 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1092,7 +1092,7 @@ extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd, #define ATA_SCSI_COMPAT_IOCTL /* empty */ #endif extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd); -#if IS_ENABLED(CONFIG_ATA) +#if IS_REACHABLE(CONFIG_ATA) bool ata_scsi_dma_need_drain(struct request *rq); #else #define ata_scsi_dma_need_drain NULL -- cgit v1.2.3 From feee1b8c490821f29aae416a5422795f5a29263d Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Wed, 24 Jun 2020 15:33:29 +0300 Subject: gcc-plugins/stackleak: Use asm instrumentation to avoid useless register saving The kernel code instrumentation in stackleak gcc plugin works in two stages. At first, stack tracking is added to GIMPLE representation of every function (except some special cases). And later, when stack frame size info is available, stack tracking is removed from the RTL representation of the functions with small stack frame. There is an unwanted side-effect for these functions: some of them do useless work with caller-saved registers. As an example of such case, proc_sys_write without() instrumentation: 55 push %rbp 41 b8 01 00 00 00 mov $0x1,%r8d 48 89 e5 mov %rsp,%rbp e8 11 ff ff ff callq ffffffff81284610 5d pop %rbp c3 retq 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1) 00 00 00 proc_sys_write() with instrumentation: 55 push %rbp 48 89 e5 mov %rsp,%rbp 41 56 push %r14 41 55 push %r13 41 54 push %r12 53 push %rbx 49 89 f4 mov %rsi,%r12 48 89 fb mov %rdi,%rbx 49 89 d5 mov %rdx,%r13 49 89 ce mov %rcx,%r14 4c 89 f1 mov %r14,%rcx 4c 89 ea mov %r13,%rdx 4c 89 e6 mov %r12,%rsi 48 89 df mov %rbx,%rdi 41 b8 01 00 00 00 mov $0x1,%r8d e8 f2 fe ff ff callq ffffffff81298e80 5b pop %rbx 41 5c pop %r12 41 5d pop %r13 41 5e pop %r14 5d pop %rbp c3 retq 66 0f 1f 84 00 00 00 nopw 0x0(%rax,%rax,1) 00 00 Let's improve the instrumentation to avoid this: 1. Make stackleak_track_stack() save all register that it works with. Use no_caller_saved_registers attribute for that function. This attribute is available for x86_64 and i386 starting from gcc-7. 2. Insert calling stackleak_track_stack() in asm: asm volatile("call stackleak_track_stack" :: "r" (current_stack_pointer)) Here we use ASM_CALL_CONSTRAINT trick from arch/x86/include/asm/asm.h. The input constraint is taken into account during gcc shrink-wrapping optimization. It is needed to be sure that stackleak_track_stack() call is inserted after the prologue of the containing function, when the stack frame is prepared. This work is a deep reengineering of the idea described on grsecurity blog https://grsecurity.net/resolving_an_unfortunate_stackleak_interaction Signed-off-by: Alexander Popov Acked-by: Miguel Ojeda Link: https://lore.kernel.org/r/20200624123330.83226-5-alex.popov@linux.com Signed-off-by: Kees Cook --- include/linux/compiler_attributes.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index cdf016596659..551ea8cb70b1 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -37,6 +37,7 @@ # define __GCC4_has_attribute___copy__ 0 # define __GCC4_has_attribute___designated_init__ 0 # define __GCC4_has_attribute___externally_visible__ 1 +# define __GCC4_has_attribute___no_caller_saved_registers__ 0 # define __GCC4_has_attribute___noclone__ 1 # define __GCC4_has_attribute___nonstring__ 0 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) @@ -175,6 +176,18 @@ */ #define __mode(x) __attribute__((__mode__(x))) +/* + * Optional: only supported since gcc >= 7 + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/x86-Function-Attributes.html#index-no_005fcaller_005fsaved_005fregisters-function-attribute_002c-x86 + * clang: https://clang.llvm.org/docs/AttributeReference.html#no-caller-saved-registers + */ +#if __has_attribute(__no_caller_saved_registers__) +# define __no_caller_saved_registers __attribute__((__no_caller_saved_registers__)) +#else +# define __no_caller_saved_registers +#endif + /* * Optional: not supported by clang * -- cgit v1.2.3 From 28bc24fc46f9c9f39ddefb424d6072041805b563 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 15 Jun 2020 09:48:33 +0200 Subject: vc: separate state There are two copies of some members of struct vc_data. This is because we need to save them and restore later. Move these memebers to a separate structure called vc_state. So now instead of members like: vc_x, vc_y and vc_saved_x, vc_saved_y we have state and saved_state (of type: struct vc_state) containing state.x, state.y and saved_state.x, saved_state.y This change: * makes clear what is saved & restored * eases save & restore by using memcpy (see save_cur and restore_cur) Finally, we document the newly added struct vc_state using kernel-doc. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20200615074910.19267-1-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/console_struct.h | 54 ++++++++++++++++++++++++++---------------- 1 file changed, 33 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 24d4c16e3ae0..162f4337c767 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -22,6 +22,37 @@ struct uni_screen; #define NPAR 16 +/** + * struct vc_state -- state of a VC + * @x: cursor's x-position + * @y: cursor's y-position + * @color: foreground & background colors + * @G0_charset: what's G0 slot set to (like GRAF_MAP, LAT1_MAP) + * @G1_charset: what's G1 slot set to (like GRAF_MAP, LAT1_MAP) + * @charset: what character set to use (0=G0 or 1=G1) + * @intensity: 0=half-bright, 1=normal, 2=bold + * @reverse: reversed foreground/background colors + * + * These members are defined separately from struct vc_data as we save & + * restore them at times. + */ +struct vc_state { + unsigned int x, y; + + unsigned char color; + + unsigned char G0_charset; + unsigned char G1_charset; + unsigned int charset : 1; + + /* attribute flags */ + unsigned int intensity : 2; + unsigned int italic : 1; + unsigned int underline : 1; + unsigned int blink : 1; + unsigned int reverse : 1; +}; + /* * Example: vc_data of a console that was scrolled 3 lines down. * @@ -57,6 +88,8 @@ struct uni_screen; struct vc_data { struct tty_port port; /* Upper level data */ + struct vc_state state, saved_state; + unsigned short vc_num; /* Console number */ unsigned int vc_cols; /* [#] Console size */ unsigned int vc_rows; @@ -73,8 +106,6 @@ struct vc_data { /* attributes for all characters on screen */ unsigned char vc_attr; /* Current attributes */ unsigned char vc_def_color; /* Default colors */ - unsigned char vc_color; /* Foreground & background */ - unsigned char vc_s_color; /* Saved foreground & background */ unsigned char vc_ulcolor; /* Color for underline mode */ unsigned char vc_itcolor; unsigned char vc_halfcolor; /* Color for half intensity mode */ @@ -82,8 +113,6 @@ struct vc_data { unsigned int vc_cursor_type; unsigned short vc_complement_mask; /* [#] Xor mask for mouse pointer */ unsigned short vc_s_complement_mask; /* Saved mouse pointer mask */ - unsigned int vc_x, vc_y; /* Cursor position */ - unsigned int vc_saved_x, vc_saved_y; unsigned long vc_pos; /* Cursor address */ /* fonts */ unsigned short vc_hi_font_mask; /* [#] Attribute set for upper 256 chars of font or 0 if not supported */ @@ -98,8 +127,6 @@ struct vc_data { int vt_newvt; wait_queue_head_t paste_wait; /* mode flags */ - unsigned int vc_charset : 1; /* Character set G0 / G1 */ - unsigned int vc_s_charset : 1; /* Saved character set */ unsigned int vc_disp_ctrl : 1; /* Display chars < 32? */ unsigned int vc_toggle_meta : 1; /* Toggle high bit? */ unsigned int vc_decscnm : 1; /* Screen Mode */ @@ -107,17 +134,6 @@ struct vc_data { unsigned int vc_decawm : 1; /* Autowrap Mode */ unsigned int vc_deccm : 1; /* Cursor Visible */ unsigned int vc_decim : 1; /* Insert Mode */ - /* attribute flags */ - unsigned int vc_intensity : 2; /* 0=half-bright, 1=normal, 2=bold */ - unsigned int vc_italic:1; - unsigned int vc_underline : 1; - unsigned int vc_blink : 1; - unsigned int vc_reverse : 1; - unsigned int vc_s_intensity : 2; /* saved rendition */ - unsigned int vc_s_italic:1; - unsigned int vc_s_underline : 1; - unsigned int vc_s_blink : 1; - unsigned int vc_s_reverse : 1; /* misc */ unsigned int vc_priv : 3; unsigned int vc_need_wrap : 1; @@ -129,10 +145,6 @@ struct vc_data { unsigned int vc_tab_stop[8]; /* Tab stops. 256 columns. */ unsigned char vc_palette[16*3]; /* Colour palette for VGA+ */ unsigned short * vc_translate; - unsigned char vc_G0_charset; - unsigned char vc_G1_charset; - unsigned char vc_saved_G0; - unsigned char vc_saved_G1; unsigned int vc_resize_user; /* resize request from user */ unsigned int vc_bell_pitch; /* Console bell pitch */ unsigned int vc_bell_duration; /* Console bell duration */ -- cgit v1.2.3 From b84ae3dc70fedf4bdee2dbfa487fd23b606fbb82 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 15 Jun 2020 09:48:34 +0200 Subject: vt: introduce enum vc_intensity for intensity Introduce names (en enum) for 0, 1, and 2 constants. We now have VCI_HALF_BRIGHT, VCI_NORMAL, and VCI_BOLD instead. Apart from the cleanup, 1) the enum allows for better type checking, and 2) this saves some code. No more fiddling with bits is needed in assembly now. (OTOH, the structure is larger.) Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20200615074910.19267-2-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/console.h | 5 ++++- include/linux/console_struct.h | 11 +++++++++-- 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 75dd20650fbe..10c04779ae49 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -35,6 +35,8 @@ enum con_scroll { SM_DOWN, }; +enum vc_intensity; + /** * struct consw - callbacks for consoles * @@ -74,7 +76,8 @@ struct consw { void (*con_scrolldelta)(struct vc_data *vc, int lines); int (*con_set_origin)(struct vc_data *vc); void (*con_save_screen)(struct vc_data *vc); - u8 (*con_build_attr)(struct vc_data *vc, u8 color, u8 intensity, + u8 (*con_build_attr)(struct vc_data *vc, u8 color, + enum vc_intensity intensity, u8 blink, u8 underline, u8 reverse, u8 italic); void (*con_invert_region)(struct vc_data *vc, u16 *p, int count); u16 *(*con_screen_pos)(struct vc_data *vc, int offset); diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 162f4337c767..e901d98790bf 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -22,6 +22,13 @@ struct uni_screen; #define NPAR 16 +enum vc_intensity { + VCI_HALF_BRIGHT, + VCI_NORMAL, + VCI_BOLD, + VCI_MASK = 0x3, +}; + /** * struct vc_state -- state of a VC * @x: cursor's x-position @@ -30,7 +37,7 @@ struct uni_screen; * @G0_charset: what's G0 slot set to (like GRAF_MAP, LAT1_MAP) * @G1_charset: what's G1 slot set to (like GRAF_MAP, LAT1_MAP) * @charset: what character set to use (0=G0 or 1=G1) - * @intensity: 0=half-bright, 1=normal, 2=bold + * @intensity: see enum vc_intensity for values * @reverse: reversed foreground/background colors * * These members are defined separately from struct vc_data as we save & @@ -46,7 +53,7 @@ struct vc_state { unsigned int charset : 1; /* attribute flags */ - unsigned int intensity : 2; + enum vc_intensity intensity; unsigned int italic : 1; unsigned int underline : 1; unsigned int blink : 1; -- cgit v1.2.3 From 77bc14f273c2dfecbf87f41fdc00345d99597e13 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 15 Jun 2020 09:48:35 +0200 Subject: vc: switch state to bool The code currently uses bitfields to store true-false values. Switch all of that to bools. Apart from the cleanup, it saves 20B of code as many shifts, ANDs, and ORs became simple movzb's. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20200615074910.19267-3-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/console.h | 2 +- include/linux/console_struct.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 10c04779ae49..964b67912b04 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -78,7 +78,7 @@ struct consw { void (*con_save_screen)(struct vc_data *vc); u8 (*con_build_attr)(struct vc_data *vc, u8 color, enum vc_intensity intensity, - u8 blink, u8 underline, u8 reverse, u8 italic); + bool blink, bool underline, bool reverse, bool italic); void (*con_invert_region)(struct vc_data *vc, u16 *p, int count); u16 *(*con_screen_pos)(struct vc_data *vc, int offset); unsigned long (*con_getxy)(struct vc_data *vc, unsigned long position, diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index e901d98790bf..fa1abffe64be 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -54,10 +54,10 @@ struct vc_state { /* attribute flags */ enum vc_intensity intensity; - unsigned int italic : 1; - unsigned int underline : 1; - unsigned int blink : 1; - unsigned int reverse : 1; + bool italic; + bool underline; + bool blink; + bool reverse; }; /* -- cgit v1.2.3 From b70ec4d97f4cc4f6f804ca57419d070b80a9874e Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 15 Jun 2020 09:48:37 +0200 Subject: vt: switch G0/1_charset to an array Declare Gx_charset[2] instead of G0_charset and G1_charset. It makes the code simpler (without ternary operators). Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20200615074910.19267-5-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/console_struct.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index fa1abffe64be..623e86689c3a 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -34,8 +34,7 @@ enum vc_intensity { * @x: cursor's x-position * @y: cursor's y-position * @color: foreground & background colors - * @G0_charset: what's G0 slot set to (like GRAF_MAP, LAT1_MAP) - * @G1_charset: what's G1 slot set to (like GRAF_MAP, LAT1_MAP) + * @Gx_charset: what's G0/G1 slot set to (like GRAF_MAP, LAT1_MAP) * @charset: what character set to use (0=G0 or 1=G1) * @intensity: see enum vc_intensity for values * @reverse: reversed foreground/background colors @@ -48,8 +47,7 @@ struct vc_state { unsigned char color; - unsigned char G0_charset; - unsigned char G1_charset; + unsigned char Gx_charset[2]; unsigned int charset : 1; /* attribute flags */ -- cgit v1.2.3 From dbee4cffa1bfe23263edde1d17cdbef0de3a6ac0 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 15 Jun 2020 09:48:38 +0200 Subject: vt: convert vc_tab_stop to bitmap vc_tab_stop is used as a bitmap, but defined as an unsigned int array. Switch it to bitmap and convert all users to the bitmap interface. Note the difference in behavior! We no longer mask the top 24 bits away from x, hence we do not wrap tabs at 256th column. Instead, we silently drop attempts to set a tab behind 256 columns. And we will also seek by '\t' to the rightmost column, when behind that boundary. I do not think the original behavior was desired and that someone relies on that. If this turns out to be the case, we can change the added 'if's back to masks here and there instead... (Or we can increase the limit as fb consoles now have 240 chars here. And they could have more with higher than my resolution, of course.) Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20200615074910.19267-6-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/console_struct.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 623e86689c3a..81f7afcd061a 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -21,6 +21,7 @@ struct uni_pagedir; struct uni_screen; #define NPAR 16 +#define VC_TABSTOPS_COUNT 256U enum vc_intensity { VCI_HALF_BRIGHT, @@ -147,7 +148,7 @@ struct vc_data { unsigned char vc_utf : 1; /* Unicode UTF-8 encoding */ unsigned char vc_utf_count; int vc_utf_char; - unsigned int vc_tab_stop[8]; /* Tab stops. 256 columns. */ + DECLARE_BITMAP(vc_tab_stop, VC_TABSTOPS_COUNT); /* Tab stops. 256 columns. */ unsigned char vc_palette[16*3]; /* Colour palette for VGA+ */ unsigned short * vc_translate; unsigned int vc_resize_user; /* resize request from user */ -- cgit v1.2.3 From 7d4a3112f07878ba9c6bffbcdb2dea2dcfc5c1f9 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 15 Jun 2020 09:48:39 +0200 Subject: vt: remove 25 years stale comment vc_cons was made global (non-static) in 1.3.38, almost 25 years ago. Remove a comment which says that it would be a disadvantage to do so :P. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20200615074910.19267-7-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/console_struct.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 81f7afcd061a..40ed52f67bc5 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -167,8 +167,7 @@ struct vc { struct work_struct SAK_work; /* might add scrmem, kbd at some time, - to have everything in one place - the disadvantage - would be that vc_cons etc can no longer be static */ + to have everything in one place */ }; extern struct vc vc_cons [MAX_NR_CONSOLES]; -- cgit v1.2.3 From 9a6f72d9b6c121415bc2867329fe77b0d2a52dc1 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 15 Jun 2020 09:48:41 +0200 Subject: vt: get rid of VT10.ID macros VT100ID is unused, but defined twice. Kill it. VT102ID is used only in respond_ID. Define there a variable with proper type and use that instead. Then drop both defines of VT102ID too. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20200615074910.19267-9-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/console.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 964b67912b04..0670d3491e0e 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -24,12 +24,6 @@ struct module; struct tty_struct; struct notifier_block; -/* - * this is what the terminal answers to a ESC-Z or csi0c query. - */ -#define VT100ID "\033[?1;2c" -#define VT102ID "\033[?6c" - enum con_scroll { SM_UP, SM_DOWN, -- cgit v1.2.3 From a018180cc3485e71f7912e36bf93caa635e0e4af Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 15 Jun 2020 09:48:42 +0200 Subject: vt: move vc_translate to vt.c and rename it vc_translate is used only in vt.c, so move the definition from a header there. Also, it used to be a macro, so be modern and make a static inline from it. This makes the code actually readable. And as a preparation for next patches, rename it to vc_translate_ascii. vc_translate will be a wrapper for both unicode and this one. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20200615074910.19267-10-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/vt_kern.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index abf5bccf906a..349e39c3ab60 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -74,8 +74,6 @@ int con_set_default_unimap(struct vc_data *vc); void con_free_unimap(struct vc_data *vc); int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc); -#define vc_translate(vc, c) ((vc)->vc_translate[(c) | \ - ((vc)->vc_toggle_meta ? 0x80 : 0)]) #else static inline int con_set_trans_old(unsigned char __user *table) { @@ -124,7 +122,6 @@ int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc) return 0; } -#define vc_translate(vc, c) (c) #endif /* vt.c */ -- cgit v1.2.3 From 4dfa3c54f908d7ec20b88671329d6a3205d37d36 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 15 Jun 2020 09:48:57 +0200 Subject: vt: redefine world of cursor macros The cursor code used to use magic constants, ANDs, ORs, and some macros. Redefine all this to make some sense. In particular: * Drop CUR_DEFAULT, which is CUR_UNDERLINE. CUR_DEFAULT was used only for cur_default variable initialization, so use CUR_UNDERLINE there to make obvious what's the default. * Drop CUR_HWMASK. Instead, define CUR_SIZE() which explains it more. And use it all over the places. * Define few more masks and bits which will be used in next patches instead of magic constants. * Define CUR_MAKE to build up cursor value. Signed-off-by: Jiri Slaby Cc: Bartlomiej Zolnierkiewicz Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Link: https://lore.kernel.org/r/20200615074910.19267-25-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/console_struct.h | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 40ed52f67bc5..153734816b49 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -173,17 +173,23 @@ struct vc { extern struct vc vc_cons [MAX_NR_CONSOLES]; extern void vc_SAK(struct work_struct *work); -#define CUR_DEF 0 -#define CUR_NONE 1 -#define CUR_UNDERLINE 2 -#define CUR_LOWER_THIRD 3 -#define CUR_LOWER_HALF 4 -#define CUR_TWO_THIRDS 5 -#define CUR_BLOCK 6 -#define CUR_HWMASK 0x0f -#define CUR_SWMASK 0xfff0 - -#define CUR_DEFAULT CUR_UNDERLINE +#define CUR_MAKE(size, change, set) ((size) | ((change) << 8) | \ + ((set) << 16)) +#define CUR_SIZE(c) ((c) & 0x00000f) +# define CUR_DEF 0 +# define CUR_NONE 1 +# define CUR_UNDERLINE 2 +# define CUR_LOWER_THIRD 3 +# define CUR_LOWER_HALF 4 +# define CUR_TWO_THIRDS 5 +# define CUR_BLOCK 6 +#define CUR_SW 0x000010 +#define CUR_ALWAYS_BG 0x000020 +#define CUR_INVERT_FG_BG 0x000040 +#define CUR_FG 0x000700 +#define CUR_BG 0x007000 +#define CUR_CHANGE(c) ((c) & 0x00ff00) +#define CUR_SET(c) (((c) & 0xff0000) >> 8) bool con_is_visible(const struct vc_data *vc); -- cgit v1.2.3 From 521b512b157a1315ff2bf11c11ab184c79515aea Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 May 2020 10:58:47 +0100 Subject: PM / EM: change naming convention from 'capacity' to 'performance' The Energy Model uses concept of performance domain and capacity states in order to calculate power used by CPUs. Change naming convention from capacity to performance state would enable wider usage in future, e.g. upcoming support for other devices other than CPUs. Acked-by: Daniel Lezcano Acked-by: Quentin Perret Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 86 +++++++++++++++++++++++--------------------- 1 file changed, 46 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index ade6486a3382..fe336a9eb5d4 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -10,13 +10,13 @@ #include /** - * em_cap_state - Capacity state of a performance domain + * em_perf_state - Performance state of a performance domain * @frequency: The CPU frequency in KHz, for consistency with CPUFreq * @power: The power consumed by 1 CPU at this level, in milli-watts * @cost: The cost coefficient associated with this level, used during * energy calculation. Equal to: power * max_frequency / frequency */ -struct em_cap_state { +struct em_perf_state { unsigned long frequency; unsigned long power; unsigned long cost; @@ -24,8 +24,8 @@ struct em_cap_state { /** * em_perf_domain - Performance domain - * @table: List of capacity states, in ascending order - * @nr_cap_states: Number of capacity states + * @table: List of performance states, in ascending order + * @nr_perf_states: Number of performance states * @cpus: Cpumask covering the CPUs of the domain * * A "performance domain" represents a group of CPUs whose performance is @@ -34,22 +34,27 @@ struct em_cap_state { * CPUFreq policies. */ struct em_perf_domain { - struct em_cap_state *table; - int nr_cap_states; + struct em_perf_state *table; + int nr_perf_states; unsigned long cpus[]; }; +#define em_span_cpus(em) (to_cpumask((em)->cpus)) + #ifdef CONFIG_ENERGY_MODEL #define EM_CPU_MAX_POWER 0xFFFF struct em_data_callback { /** - * active_power() - Provide power at the next capacity state of a CPU - * @power : Active power at the capacity state in mW (modified) - * @freq : Frequency at the capacity state in kHz (modified) + * active_power() - Provide power at the next performance state of + * a CPU + * @power : Active power at the performance state in mW + * (modified) + * @freq : Frequency at the performance state in kHz + * (modified) * @cpu : CPU for which we do this operation * - * active_power() must find the lowest capacity state of 'cpu' above + * active_power() must find the lowest performance state of 'cpu' above * 'freq' and update 'power' and 'freq' to the matching active power * and frequency. * @@ -80,46 +85,46 @@ static inline unsigned long em_pd_energy(struct em_perf_domain *pd, unsigned long max_util, unsigned long sum_util) { unsigned long freq, scale_cpu; - struct em_cap_state *cs; + struct em_perf_state *ps; int i, cpu; /* - * In order to predict the capacity state, map the utilization of the - * most utilized CPU of the performance domain to a requested frequency, - * like schedutil. + * In order to predict the performance state, map the utilization of + * the most utilized CPU of the performance domain to a requested + * frequency, like schedutil. */ cpu = cpumask_first(to_cpumask(pd->cpus)); scale_cpu = arch_scale_cpu_capacity(cpu); - cs = &pd->table[pd->nr_cap_states - 1]; - freq = map_util_freq(max_util, cs->frequency, scale_cpu); + ps = &pd->table[pd->nr_perf_states - 1]; + freq = map_util_freq(max_util, ps->frequency, scale_cpu); /* - * Find the lowest capacity state of the Energy Model above the + * Find the lowest performance state of the Energy Model above the * requested frequency. */ - for (i = 0; i < pd->nr_cap_states; i++) { - cs = &pd->table[i]; - if (cs->frequency >= freq) + for (i = 0; i < pd->nr_perf_states; i++) { + ps = &pd->table[i]; + if (ps->frequency >= freq) break; } /* - * The capacity of a CPU in the domain at that capacity state (cs) + * The capacity of a CPU in the domain at the performance state (ps) * can be computed as: * - * cs->freq * scale_cpu - * cs->cap = -------------------- (1) + * ps->freq * scale_cpu + * ps->cap = -------------------- (1) * cpu_max_freq * * So, ignoring the costs of idle states (which are not available in - * the EM), the energy consumed by this CPU at that capacity state is - * estimated as: + * the EM), the energy consumed by this CPU at that performance state + * is estimated as: * - * cs->power * cpu_util + * ps->power * cpu_util * cpu_nrg = -------------------- (2) - * cs->cap + * ps->cap * - * since 'cpu_util / cs->cap' represents its percentage of busy time. + * since 'cpu_util / ps->cap' represents its percentage of busy time. * * NOTE: Although the result of this computation actually is in * units of power, it can be manipulated as an energy value @@ -129,34 +134,35 @@ static inline unsigned long em_pd_energy(struct em_perf_domain *pd, * By injecting (1) in (2), 'cpu_nrg' can be re-expressed as a product * of two terms: * - * cs->power * cpu_max_freq cpu_util + * ps->power * cpu_max_freq cpu_util * cpu_nrg = ------------------------ * --------- (3) - * cs->freq scale_cpu + * ps->freq scale_cpu * - * The first term is static, and is stored in the em_cap_state struct - * as 'cs->cost'. + * The first term is static, and is stored in the em_perf_state struct + * as 'ps->cost'. * * Since all CPUs of the domain have the same micro-architecture, they - * share the same 'cs->cost', and the same CPU capacity. Hence, the + * share the same 'ps->cost', and the same CPU capacity. Hence, the * total energy of the domain (which is the simple sum of the energy of * all of its CPUs) can be factorized as: * - * cs->cost * \Sum cpu_util + * ps->cost * \Sum cpu_util * pd_nrg = ------------------------ (4) * scale_cpu */ - return cs->cost * sum_util / scale_cpu; + return ps->cost * sum_util / scale_cpu; } /** - * em_pd_nr_cap_states() - Get the number of capacity states of a perf. domain + * em_pd_nr_perf_states() - Get the number of performance states of a perf. + * domain * @pd : performance domain for which this must be done * - * Return: the number of capacity states in the performance domain table + * Return: the number of performance states in the performance domain table */ -static inline int em_pd_nr_cap_states(struct em_perf_domain *pd) +static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) { - return pd->nr_cap_states; + return pd->nr_perf_states; } #else @@ -177,7 +183,7 @@ static inline unsigned long em_pd_energy(struct em_perf_domain *pd, { return 0; } -static inline int em_pd_nr_cap_states(struct em_perf_domain *pd) +static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) { return 0; } -- cgit v1.2.3 From 7d9895c7fbfc9c70afce7029b7de0f3f974adb88 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 May 2020 10:58:48 +0100 Subject: PM / EM: introduce em_dev_register_perf_domain function Add now function in the Energy Model framework which is going to support new devices. This function will help in transition and make it smoother. For now it still checks if the cpumask is a valid pointer, which will be removed later when the new structures and infrastructure will be ready. Acked-by: Daniel Lezcano Acked-by: Quentin Perret Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index fe336a9eb5d4..7c048df98447 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -2,6 +2,7 @@ #ifndef _LINUX_ENERGY_MODEL_H #define _LINUX_ENERGY_MODEL_H #include +#include #include #include #include @@ -42,7 +43,7 @@ struct em_perf_domain { #define em_span_cpus(em) (to_cpumask((em)->cpus)) #ifdef CONFIG_ENERGY_MODEL -#define EM_CPU_MAX_POWER 0xFFFF +#define EM_MAX_POWER 0xFFFF struct em_data_callback { /** @@ -59,7 +60,7 @@ struct em_data_callback { * and frequency. * * The power is the one of a single CPU in the domain, expressed in - * milli-watts. It is expected to fit in the [0, EM_CPU_MAX_POWER] + * milli-watts. It is expected to fit in the [0, EM_MAX_POWER] * range. * * Return 0 on success. @@ -71,6 +72,8 @@ struct em_data_callback { struct em_perf_domain *em_cpu_get(int cpu); int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, struct em_data_callback *cb); +int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, + struct em_data_callback *cb, cpumask_t *span); /** * em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain @@ -174,6 +177,12 @@ static inline int em_register_perf_domain(cpumask_t *span, { return -EINVAL; } +static inline +int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, + struct em_data_callback *cb, cpumask_t *span) +{ + return -EINVAL; +} static inline struct em_perf_domain *em_cpu_get(int cpu) { return NULL; -- cgit v1.2.3 From d0351cc3b0f57214d157e4d589564730af2aedae Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 May 2020 10:58:49 +0100 Subject: PM / EM: update callback structure and add device pointer The Energy Model framework is going to support devices other that CPUs. In order to make this happen change the callback function and add pointer to a device as an argument. Update the related users to use new function and new callback from the Energy Model. Acked-by: Quentin Perret Signed-off-by: Lukasz Luba Acked-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 7c048df98447..7076cb22b247 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -48,24 +48,25 @@ struct em_perf_domain { struct em_data_callback { /** * active_power() - Provide power at the next performance state of - * a CPU + * a device * @power : Active power at the performance state in mW * (modified) * @freq : Frequency at the performance state in kHz * (modified) - * @cpu : CPU for which we do this operation + * @dev : Device for which we do this operation (can be a CPU) * - * active_power() must find the lowest performance state of 'cpu' above + * active_power() must find the lowest performance state of 'dev' above * 'freq' and update 'power' and 'freq' to the matching active power * and frequency. * - * The power is the one of a single CPU in the domain, expressed in - * milli-watts. It is expected to fit in the [0, EM_MAX_POWER] - * range. + * In case of CPUs, the power is the one of a single CPU in the domain, + * expressed in milli-watts. It is expected to fit in the + * [0, EM_MAX_POWER] range. * * Return 0 on success. */ - int (*active_power)(unsigned long *power, unsigned long *freq, int cpu); + int (*active_power)(unsigned long *power, unsigned long *freq, + struct device *dev); }; #define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb } -- cgit v1.2.3 From c3077b5d97a39223a2d4b95a21ccff660836170f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Jun 2020 08:44:41 +0200 Subject: blk-mq: merge blk-softirq.c into blk-mq.c __blk_complete_request is only called from the blk-mq code, and duplicates a lot of code from blk-mq.c. Move it there to prepare for better code sharing and simplifications. Signed-off-by: Christoph Hellwig Reviewed-by: Daniel Wagner Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8fd900998b4e..98712cfc7a34 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1078,7 +1078,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq); extern bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); /* -- cgit v1.2.3 From 15f73f5b3e5958f2d169fe13c420eeeeae07bbf2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Jun 2020 08:44:47 +0200 Subject: blk-mq: move failure injection out of blk_mq_complete_request Move the call to blk_should_fake_timeout out of blk_mq_complete_request and into the drivers, skipping call sites that are obvious error handlers, and remove the now superflous blk_mq_force_complete_rq helper. This ensures we don't keep injecting errors into completions that just terminate the Linux request after the hardware has been reset or the command has been aborted. Reviewed-by: Daniel Wagner Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d6fcae17da5a..8e6ab766aef7 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -503,8 +503,7 @@ void __blk_mq_end_request(struct request *rq, blk_status_t error); void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); -bool blk_mq_complete_request(struct request *rq); -void blk_mq_force_complete_rq(struct request *rq); +void blk_mq_complete_request(struct request *rq); bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs); bool blk_mq_queue_stopped(struct request_queue *q); @@ -537,6 +536,15 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); +bool __blk_should_fake_timeout(struct request_queue *q); +static inline bool blk_should_fake_timeout(struct request_queue *q) +{ + if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) && + test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags)) + return __blk_should_fake_timeout(q); + return false; +} + /** * blk_mq_rq_from_pdu - cast a PDU to a request * @pdu: the PDU (Protocol Data Unit) to be casted -- cgit v1.2.3 From 40d09b53bfc557af7481b9d80f060a7ac9c7d314 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Jun 2020 08:44:50 +0200 Subject: blk-mq: add a new blk_mq_complete_request_remote API This is a variant of blk_mq_complete_request_remote that only completes the request if it needs to be bounced to another CPU or a softirq. If the request can be completed locally the function returns false and lets the driver complete it without requring and indirect function call. Reviewed-by: Daniel Wagner Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8e6ab766aef7..1641ec6cd7e5 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -504,6 +504,7 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_complete_request(struct request *rq); +bool blk_mq_complete_request_remote(struct request *rq); bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs); bool blk_mq_queue_stopped(struct request_queue *q); -- cgit v1.2.3 From e8c7d14ac6c37c173ec606907d38802b00302988 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 19 Jun 2020 20:47:25 +0000 Subject: block: revert back to synchronous request_queue removal Commit dc9edc44de6c ("block: Fix a blk_exit_rl() regression") merged on v4.12 moved the work behind blk_release_queue() into a workqueue after a splat floated around which indicated some work on blk_release_queue() could sleep in blk_exit_rl(). This splat would be possible when a driver called blk_put_queue() or blk_cleanup_queue() (which calls blk_put_queue() as its final call) from an atomic context. blk_put_queue() decrements the refcount for the request_queue kobject, and upon reaching 0 blk_release_queue() is called. Although blk_exit_rl() is now removed through commit db6d99523560 ("block: remove request_list code") on v5.0, we reserve the right to be able to sleep within blk_release_queue() context. The last reference for the request_queue must not be called from atomic context. *When* the last reference to the request_queue reaches 0 varies, and so let's take the opportunity to document when that is expected to happen and also document the context of the related calls as best as possible so we can avoid future issues, and with the hopes that the synchronous request_queue removal sticks. We revert back to synchronous request_queue removal because asynchronous removal creates a regression with expected userspace interaction with several drivers. An example is when removing the loopback driver, one uses ioctls from userspace to do so, but upon return and if successful, one expects the device to be removed. Likewise if one races to add another device the new one may not be added as it is still being removed. This was expected behavior before and it now fails as the device is still present and busy still. Moving to asynchronous request_queue removal could have broken many scripts which relied on the removal to have been completed if there was no error. Document this expectation as well so that this doesn't regress userspace again. Using asynchronous request_queue removal however has helped us find other bugs. In the future we can test what could break with this arrangement by enabling CONFIG_DEBUG_KOBJECT_RELEASE. While at it, update the docs with the context expectations for the request_queue / gendisk refcount decrement, and make these expectations explicit by using might_sleep(). Fixes: dc9edc44de6c ("block: Fix a blk_exit_rl() regression") Suggested-by: Nicolai Stange Signed-off-by: Luis Chamberlain Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Cc: Bart Van Assche Cc: Omar Sandoval Cc: Hannes Reinecke Cc: Nicolai Stange Cc: Greg Kroah-Hartman Cc: Michal Hocko Cc: yu kuai Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 98712cfc7a34..e214e0e9f868 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -584,8 +584,6 @@ struct request_queue { size_t cmd_size; - struct work_struct release_work; - #define BLK_MAX_WRITE_HINTS 5 u64 write_hints[BLK_MAX_WRITE_HINTS]; }; -- cgit v1.2.3 From 85e0cbbb8a79537dbc465e9deb449a08b2b092a6 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 19 Jun 2020 20:47:30 +0000 Subject: block: create the request_queue debugfs_dir on registration We were only creating the request_queue debugfs_dir only for make_request block drivers (multiqueue), but never for request-based block drivers. We did this as we were only creating non-blktrace additional debugfs files on that directory for make_request drivers. However, since blktrace *always* creates that directory anyway, we special-case the use of that directory on blktrace. Other than this being an eye-sore, this exposes request-based block drivers to the same debugfs fragile race that used to exist with make_request block drivers where if we start adding files onto that directory we can later run a race with a double removal of dentries on the directory if we don't deal with this carefully on blktrace. Instead, just simplify things by always creating the request_queue debugfs_dir on request_queue registration. Rename the mutex also to reflect the fact that this is used outside of the blktrace context. Signed-off-by: Luis Chamberlain Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e214e0e9f868..c0701237116d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -528,9 +528,9 @@ struct request_queue { unsigned int sg_timeout; unsigned int sg_reserved_size; int node; + struct mutex debugfs_mutex; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; - struct mutex blk_trace_mutex; #endif /* * for flush operations @@ -574,8 +574,9 @@ struct request_queue { struct list_head tag_set_list; struct bio_set bio_split; -#ifdef CONFIG_BLK_DEBUG_FS struct dentry *debugfs_dir; + +#ifdef CONFIG_BLK_DEBUG_FS struct dentry *sched_debugfs_dir; struct dentry *rqos_debugfs_dir; #endif -- cgit v1.2.3 From b818f09e46f9f6a66471f81bf83094ff0a477d0c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:35 +0200 Subject: tty/sysrq: emergency_thaw_all does not depend on CONFIG_BLOCK We can also thaw non-block file systems. Remove the CONFIG_BLOCK in sysrq.c after making the prototype available unconditionally. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Reviewed-by: Greg Kroah-Hartman Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3f881a892ea7..7f40dbafbf6d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2593,7 +2593,6 @@ extern void invalidate_bdev(struct block_device *); extern void iterate_bdevs(void (*)(struct block_device *, void *), void *); extern int sync_blockdev(struct block_device *bdev); extern struct super_block *freeze_bdev(struct block_device *); -extern void emergency_thaw_all(void); extern void emergency_thaw_bdev(struct super_block *sb); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); @@ -2633,6 +2632,7 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb) return false; } #endif +void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; -- cgit v1.2.3 From 764b23bd9af8ff8ecc664816e39d4791b6a72bfd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:36 +0200 Subject: block: mark bd_finish_claiming static Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7f40dbafbf6d..b1c960e9b84e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2646,8 +2646,6 @@ extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); extern struct block_device *bd_start_claiming(struct block_device *bdev, void *holder); -extern void bd_finish_claiming(struct block_device *bdev, - struct block_device *whole, void *holder); extern void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void *holder); extern void blkdev_put(struct block_device *bdev, fmode_t mode); -- cgit v1.2.3 From 7dbac5baa887facf80373825b8f66c626703621f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:37 +0200 Subject: fs: remove an unused block_device_operations forward declaration Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b1c960e9b84e..0d282c853691 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1774,8 +1774,6 @@ struct dir_context { loff_t pos; }; -struct block_device_operations; - /* These macros are for out of kernel modules to test that * the kernel supports the unlocked_ioctl and compat_ioctl * fields in struct file_operations. */ -- cgit v1.2.3 From 4e24566a134ea167441a1ffa3d439a27cf400880 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:38 +0200 Subject: fs: remove the HAVE_UNLOCKED_IOCTL and HAVE_COMPAT_IOCTL defines These are not defined anywhere, and contrary to the comments we really do not care about out of tree code at all. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/fs.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 0d282c853691..224edcc5b56e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1774,12 +1774,6 @@ struct dir_context { loff_t pos; }; -/* These macros are for out of kernel modules to test that - * the kernel supports the unlocked_ioctl and compat_ioctl - * fields in struct file_operations. */ -#define HAVE_COMPAT_IOCTL 1 -#define HAVE_UNLOCKED_IOCTL 1 - /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. -- cgit v1.2.3 From 75362a1792d16a61f0277d3610dea2f50a16bf3e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:39 +0200 Subject: fs: remove the mount_bdev and kill_block_super stubs No one calls these functions without CONFIG_BLOCK, so don't bother stubbing them out. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 224edcc5b56e..9ee09e2b5a97 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2256,18 +2256,9 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) -#ifdef CONFIG_BLOCK extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); -#else -static inline struct dentry *mount_bdev(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, void *, int)) -{ - return ERR_PTR(-ENODEV); -} -#endif extern struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); @@ -2276,14 +2267,7 @@ extern struct dentry *mount_nodev(struct file_system_type *fs_type, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void generic_shutdown_super(struct super_block *sb); -#ifdef CONFIG_BLOCK void kill_block_super(struct super_block *sb); -#else -static inline void kill_block_super(struct super_block *sb) -{ - BUG(); -} -#endif void kill_anon_super(struct super_block *sb); void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); -- cgit v1.2.3 From dd0dca223e091bbacdd3c7ce9cf06b373da59816 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:40 +0200 Subject: block: simplify sb_is_blkdev_sb Just use IS_ENABLED instead of providing a stub for !CONFIG_BLOCK. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/fs.h | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9ee09e2b5a97..7f3ae38335d4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2557,6 +2557,12 @@ extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) +extern struct super_block *blockdev_superblock; +static inline bool sb_is_blkdev_sb(struct super_block *sb) +{ + return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; +} + #ifdef CONFIG_BLOCK extern int register_blkdev(unsigned int, const char *); extern void unregister_blkdev(unsigned int, const char *); @@ -2572,13 +2578,6 @@ extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_bdev(struct super_block *sb); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); - -extern struct super_block *blockdev_superblock; - -static inline bool sb_is_blkdev_sb(struct super_block *sb) -{ - return sb == blockdev_superblock; -} #else static inline void bd_forget(struct inode *inode) {} static inline int sync_blockdev(struct block_device *bdev) { return 0; } @@ -2602,11 +2601,6 @@ static inline int emergency_thaw_bdev(struct super_block *sb) static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) { } - -static inline bool sb_is_blkdev_sb(struct super_block *sb) -{ - return false; -} #endif void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); -- cgit v1.2.3 From 3f1266f1f82d7b8c72472a8921e80aa3e611fb62 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:41 +0200 Subject: block: move block-related definitions out of fs.h Move most of the block related definition out of fs.h into more suitable headers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 46 +++++++++++++++++++++++++ include/linux/fs.h | 92 -------------------------------------------------- include/linux/genhd.h | 27 +++++++++++++++ include/linux/jbd2.h | 1 + 4 files changed, 74 insertions(+), 92 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c0701237116d..cf8f692f62a9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1918,4 +1918,50 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) } #endif /* CONFIG_BLOCK */ +int bdev_read_only(struct block_device *bdev); +int set_blocksize(struct block_device *bdev, int size); + +const char *bdevname(struct block_device *bdev, char *buffer); +struct block_device *lookup_bdev(const char *); + +void blkdev_show(struct seq_file *seqf, off_t offset); + +#define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ +#define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ +#ifdef CONFIG_BLOCK +#define BLKDEV_MAJOR_MAX 512 +#else +#define BLKDEV_MAJOR_MAX 0 +#endif + +int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); +struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, + void *holder); +struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); +struct block_device *bd_start_claiming(struct block_device *bdev, void *holder); +void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, + void *holder); +void blkdev_put(struct block_device *bdev, fmode_t mode); + +struct block_device *bdget(dev_t); +struct block_device *bdgrab(struct block_device *bdev); +void bdput(struct block_device *); + +#ifdef CONFIG_BLOCK +void invalidate_bdev(struct block_device *bdev); +int sync_blockdev(struct block_device *bdev); +#else +static inline void invalidate_bdev(struct block_device *bdev) +{ +} +static inline int sync_blockdev(struct block_device *bdev) +{ + return 0; +} #endif +int fsync_bdev(struct block_device *bdev); + +struct super_block *freeze_bdev(struct block_device *bdev); +int thaw_bdev(struct block_device *bdev, struct super_block *sb); + +#endif /* _LINUX_BLKDEV_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 7f3ae38335d4..add30c3bdf9a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2563,79 +2563,10 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb) return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } -#ifdef CONFIG_BLOCK -extern int register_blkdev(unsigned int, const char *); -extern void unregister_blkdev(unsigned int, const char *); -extern struct block_device *bdget(dev_t); -extern struct block_device *bdgrab(struct block_device *bdev); -extern void bd_set_size(struct block_device *, loff_t size); -extern void bd_forget(struct inode *inode); -extern void bdput(struct block_device *); -extern void invalidate_bdev(struct block_device *); -extern void iterate_bdevs(void (*)(struct block_device *, void *), void *); -extern int sync_blockdev(struct block_device *bdev); -extern struct super_block *freeze_bdev(struct block_device *); -extern void emergency_thaw_bdev(struct super_block *sb); -extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); -extern int fsync_bdev(struct block_device *); -#else -static inline void bd_forget(struct inode *inode) {} -static inline int sync_blockdev(struct block_device *bdev) { return 0; } -static inline void invalidate_bdev(struct block_device *bdev) {} - -static inline struct super_block *freeze_bdev(struct block_device *sb) -{ - return NULL; -} - -static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) -{ - return 0; -} - -static inline int emergency_thaw_bdev(struct super_block *sb) -{ - return 0; -} - -static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) -{ -} -#endif void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; -#ifdef CONFIG_BLOCK -extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); -extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); -extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); -extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, - void *holder); -extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, - void *holder); -extern struct block_device *bd_start_claiming(struct block_device *bdev, - void *holder); -extern void bd_abort_claiming(struct block_device *bdev, - struct block_device *whole, void *holder); -extern void blkdev_put(struct block_device *bdev, fmode_t mode); - -#ifdef CONFIG_SYSFS -extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); -extern void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk); -#else -static inline int bd_link_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ - return 0; -} -static inline void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ -} -#endif -#endif /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 @@ -2666,31 +2597,12 @@ static inline void unregister_chrdev(unsigned int major, const char *name) __unregister_chrdev(major, 0, 256, name); } -/* fs/block_dev.c */ -#define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ -#define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ - -#ifdef CONFIG_BLOCK -#define BLKDEV_MAJOR_MAX 512 -extern const char *bdevname(struct block_device *bdev, char *buffer); -extern struct block_device *lookup_bdev(const char *); -extern void blkdev_show(struct seq_file *,off_t); - -#else -#define BLKDEV_MAJOR_MAX 0 -#endif - extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); -#ifdef CONFIG_BLOCK -extern int revalidate_disk(struct gendisk *); -extern int check_disk_change(struct block_device *); -extern int __invalidate_device(struct block_device *, bool); -#endif unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); @@ -3090,10 +3002,6 @@ static inline void remove_inode_hash(struct inode *inode) extern void inode_sb_list_add(struct inode *inode); -#ifdef CONFIG_BLOCK -extern int bdev_read_only(struct block_device *); -#endif -extern int set_blocksize(struct block_device *, int); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 392aad5e29a2..83f8e0d83228 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -373,6 +373,33 @@ extern void blk_unregister_region(dev_t devt, unsigned long range); #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) +int register_blkdev(unsigned int major, const char *name); +void unregister_blkdev(unsigned int major, const char *name); + +int revalidate_disk(struct gendisk *disk); +int check_disk_change(struct block_device *bdev); +int __invalidate_device(struct block_device *bdev, bool kill_dirty); +void bd_set_size(struct block_device *bdev, loff_t size); + +/* for drivers/char/raw.c: */ +int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); +long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); + +#ifdef CONFIG_SYSFS +int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); +void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); +#else +static inline int bd_link_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ + return 0; +} +static inline void bd_unlink_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ +} +#endif /* CONFIG_SYSFS */ + #else /* CONFIG_BLOCK */ static inline void printk_all_partitions(void) { } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d56128df2aff..4aaa29772bb0 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -27,6 +27,7 @@ #include #include #include +#include #include #endif -- cgit v1.2.3 From d2de7ea48d83195ef1310555f1fdd9e8e1bab0d3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:42 +0200 Subject: fs: move the buffer_heads_over_limit stub to buffer_head.h Move the !CONFIG_BLOCK stub to the same place as the non-stub declaration. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - include/linux/buffer_head.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cf8f692f62a9..c824c6fee35d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1838,7 +1838,6 @@ struct block_device; /* * stubs for when the block layer is configured out */ -#define buffer_heads_over_limit 0 static inline long nr_blockdev_pages(void) { diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 22fb11e2d2e0..6b47f94378c5 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -406,6 +406,7 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } +#define buffer_heads_over_limit 0 #endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ -- cgit v1.2.3 From 1a4dcfa8bc10d6bf4f94ac20adc2b30a1da72cfd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:43 +0200 Subject: block: reduce ifdef CONFIG_BLOCK madness in headers Large part of bio.h, blkdev.h and genhd.h are under ifdef CONFIG_BLOCK for no good reason. Only stub out function that are called from code that is not dependent on CONFIG_BLOCK and leave the harmless other declarations around. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 -- include/linux/blkdev.h | 92 ++++++++++++++++++++++---------------------------- include/linux/genhd.h | 14 ++++---- 3 files changed, 46 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 91676d4b2dfe..0282f8aa8593 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -8,8 +8,6 @@ #include #include #include - -#ifdef CONFIG_BLOCK /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include @@ -824,5 +822,4 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } -#endif /* CONFIG_BLOCK */ #endif /* __LINUX_BIO_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c824c6fee35d..f788bddc9219 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -4,9 +4,6 @@ #include #include - -#ifdef CONFIG_BLOCK - #include #include #include @@ -1163,13 +1160,13 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, return __blk_rq_map_sg(q, rq, sglist, &last_sg); } extern void blk_dump_rq_flags(struct request *, char *); -extern long nr_blockdev_pages(void); bool __must_check blk_get_queue(struct request_queue *); struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); +#ifdef CONFIG_BLOCK /* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests @@ -1229,9 +1226,47 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) !list_empty(&plug->cb_list)); } +int blkdev_issue_flush(struct block_device *, gfp_t); +long nr_blockdev_pages(void); +#else /* CONFIG_BLOCK */ +struct blk_plug { +}; + +static inline void blk_start_plug(struct blk_plug *plug) +{ +} + +static inline void blk_finish_plug(struct blk_plug *plug) +{ +} + +static inline void blk_flush_plug(struct task_struct *task) +{ +} + +static inline void blk_schedule_flush_plug(struct task_struct *task) +{ +} + + +static inline bool blk_needs_flush_plug(struct task_struct *tsk) +{ + return false; +} + +static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask) +{ + return 0; +} + +static inline long nr_blockdev_pages(void) +{ + return 0; +} +#endif /* CONFIG_BLOCK */ + extern void blk_io_schedule(void); -int blkdev_issue_flush(struct block_device *, gfp_t); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); @@ -1831,51 +1866,6 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq) } #endif /* CONFIG_BLK_DEV_ZONED */ -#else /* CONFIG_BLOCK */ - -struct block_device; - -/* - * stubs for when the block layer is configured out - */ - -static inline long nr_blockdev_pages(void) -{ - return 0; -} - -struct blk_plug { -}; - -static inline void blk_start_plug(struct blk_plug *plug) -{ -} - -static inline void blk_finish_plug(struct blk_plug *plug) -{ -} - -static inline void blk_flush_plug(struct task_struct *task) -{ -} - -static inline void blk_schedule_flush_plug(struct task_struct *task) -{ -} - - -static inline bool blk_needs_flush_plug(struct task_struct *tsk) -{ - return false; -} - -static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask) -{ - return 0; -} - -#endif /* CONFIG_BLOCK */ - static inline void blk_wake_io_task(struct task_struct *waiter) { /* @@ -1889,7 +1879,6 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -#ifdef CONFIG_BLOCK unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op); void disk_end_io_acct(struct gendisk *disk, unsigned int op, @@ -1915,7 +1904,6 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time); } -#endif /* CONFIG_BLOCK */ int bdev_read_only(struct block_device *bdev); int set_blocksize(struct block_device *bdev, int size); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 83f8e0d83228..31a54072ffd6 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -19,8 +19,6 @@ #include #include -#ifdef CONFIG_BLOCK - #define dev_to_disk(device) container_of((device), struct gendisk, part0.__dev) #define dev_to_part(device) container_of((device), struct hd_struct, __dev) #define disk_to_dev(disk) (&(disk)->part0.__dev) @@ -337,12 +335,9 @@ static inline void set_capacity(struct gendisk *disk, sector_t size) disk->part0.nr_sects = size; } -extern dev_t blk_lookup_devt(const char *name, int partno); - int bdev_disk_changed(struct block_device *bdev, bool invalidate); int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); int blk_drop_partitions(struct block_device *bdev); -extern void printk_all_partitions(void); extern struct gendisk *__alloc_disk_node(int minors, int node_id); extern struct kobject *get_disk_and_module(struct gendisk *disk); @@ -400,10 +395,13 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, } #endif /* CONFIG_SYSFS */ +#ifdef CONFIG_BLOCK +void printk_all_partitions(void); +dev_t blk_lookup_devt(const char *name, int partno); #else /* CONFIG_BLOCK */ - -static inline void printk_all_partitions(void) { } - +static inline void printk_all_partitions(void) +{ +} static inline dev_t blk_lookup_devt(const char *name, int partno) { dev_t devt = MKDEV(0, 0); -- cgit v1.2.3 From 621c1f42945e76015c3a585e7a9fe6e71665eba0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:44 +0200 Subject: block: move struct block_device to blk_types.h Move the struct block_device definition together with most of the block layer definitions, as it has nothing to do with the rest of fs.h. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 39 ++++++++++++++++++++++++++++++++++++++- include/linux/blkdev.h | 1 + include/linux/dasd_mod.h | 2 ++ include/linux/fs.h | 41 ----------------------------------------- 4 files changed, 41 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index ccb895f911b1..a602132cbe32 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -14,12 +14,49 @@ struct bio_set; struct bio; struct bio_integrity_payload; struct page; -struct block_device; struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; +struct block_device { + dev_t bd_dev; /* not a kdev_t - it's a search key */ + int bd_openers; + struct inode * bd_inode; /* will die */ + struct super_block * bd_super; + struct mutex bd_mutex; /* open/close mutex */ + void * bd_claiming; + void * bd_holder; + int bd_holders; + bool bd_write_holder; +#ifdef CONFIG_SYSFS + struct list_head bd_holder_disks; +#endif + struct block_device * bd_contains; + unsigned bd_block_size; + u8 bd_partno; + struct hd_struct * bd_part; + /* number of times partitions within this device have been opened. */ + unsigned bd_part_count; + int bd_invalidated; + struct gendisk * bd_disk; + struct request_queue * bd_queue; + struct backing_dev_info *bd_bdi; + struct list_head bd_list; + /* + * Private data. You must have bd_claim'ed the block_device + * to use this. NOTE: bd_claim allows an owner to claim + * the same device multiple times, the owner must take special + * care to not mess up bd_private for that case. + */ + unsigned long bd_private; + + /* The counter of freeze processes */ + int bd_fsfreeze_count; + /* Mutex for freeze */ + struct mutex bd_fsfreeze_mutex; +} __randomize_layout; + /* * Block error status values. See block/blk-core:blk_errors for the details. * Alpha cannot write a byte atomically, so we need to use 32-bit value. diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f788bddc9219..15497782c176 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1930,6 +1930,7 @@ void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void *holder); void blkdev_put(struct block_device *bdev, fmode_t mode); +struct block_device *I_BDEV(struct inode *inode); struct block_device *bdget(dev_t); struct block_device *bdgrab(struct block_device *bdev); void bdput(struct block_device *); diff --git a/include/linux/dasd_mod.h b/include/linux/dasd_mod.h index d39abad2ff6e..14e6cf8c6267 100644 --- a/include/linux/dasd_mod.h +++ b/include/linux/dasd_mod.h @@ -4,6 +4,8 @@ #include +struct gendisk; + extern int dasd_biodasdinfo(struct gendisk *disk, dasd_information2_t *info); #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index add30c3bdf9a..1d7c4f7465d2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -470,45 +470,6 @@ struct address_space { * must be enforced here for CRIS, to let the least significant bit * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. */ -struct request_queue; - -struct block_device { - dev_t bd_dev; /* not a kdev_t - it's a search key */ - int bd_openers; - struct inode * bd_inode; /* will die */ - struct super_block * bd_super; - struct mutex bd_mutex; /* open/close mutex */ - void * bd_claiming; - void * bd_holder; - int bd_holders; - bool bd_write_holder; -#ifdef CONFIG_SYSFS - struct list_head bd_holder_disks; -#endif - struct block_device * bd_contains; - unsigned bd_block_size; - u8 bd_partno; - struct hd_struct * bd_part; - /* number of times partitions within this device have been opened. */ - unsigned bd_part_count; - int bd_invalidated; - struct gendisk * bd_disk; - struct request_queue * bd_queue; - struct backing_dev_info *bd_bdi; - struct list_head bd_list; - /* - * Private data. You must have bd_claim'ed the block_device - * to use this. NOTE: bd_claim allows an owner to claim - * the same device multiple times, the owner must take special - * care to not mess up bd_private for that case. - */ - unsigned long bd_private; - - /* The counter of freeze processes */ - int bd_fsfreeze_count; - /* Mutex for freeze */ - struct mutex bd_fsfreeze_mutex; -} __randomize_layout; /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 @@ -907,8 +868,6 @@ static inline unsigned imajor(const struct inode *inode) return MAJOR(inode->i_rdev); } -extern struct block_device *I_BDEV(struct inode *inode); - struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ -- cgit v1.2.3 From 1bc138c622959979eb547be2d3bbc6442a5c80b0 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 10 Jun 2020 11:12:23 +0100 Subject: PM / EM: add support for other devices than CPUs in Energy Model Add support for other devices than CPUs. The registration function does not require a valid cpumask pointer and is ready to handle new devices. Some of the internal structures has been reorganized in order to keep consistent view (like removing per_cpu pd pointers). Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/device.h | 5 +++++ include/linux/energy_model.h | 29 ++++++++++++++++++++++------- 2 files changed, 27 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 15460a5ac024..b72e6f9ad845 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -13,6 +13,7 @@ #define _DEVICE_H_ #include +#include #include #include #include @@ -559,6 +560,10 @@ struct device { struct dev_pm_info power; struct dev_pm_domain *pm_domain; +#ifdef CONFIG_ENERGY_MODEL + struct em_perf_domain *em_pd; +#endif + #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN struct irq_domain *msi_domain; #endif diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 7076cb22b247..2d4689964029 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -12,8 +12,10 @@ /** * em_perf_state - Performance state of a performance domain - * @frequency: The CPU frequency in KHz, for consistency with CPUFreq - * @power: The power consumed by 1 CPU at this level, in milli-watts + * @frequency: The frequency in KHz, for consistency with CPUFreq + * @power: The power consumed at this level, in milli-watts (by 1 CPU or + by a registered device). It can be a total power: static and + dynamic. * @cost: The cost coefficient associated with this level, used during * energy calculation. Equal to: power * max_frequency / frequency */ @@ -27,12 +29,16 @@ struct em_perf_state { * em_perf_domain - Performance domain * @table: List of performance states, in ascending order * @nr_perf_states: Number of performance states - * @cpus: Cpumask covering the CPUs of the domain + * @cpus: Cpumask covering the CPUs of the domain. It's here + * for performance reasons to avoid potential cache + * misses during energy calculations in the scheduler + * and simplifies allocating/freeing that memory region. * - * A "performance domain" represents a group of CPUs whose performance is - * scaled together. All CPUs of a performance domain must have the same - * micro-architecture. Performance domains often have a 1-to-1 mapping with - * CPUFreq policies. + * In case of CPU device, a "performance domain" represents a group of CPUs + * whose performance is scaled together. All CPUs of a performance domain + * must have the same micro-architecture. Performance domains often have + * a 1-to-1 mapping with CPUFreq policies. In case of other devices the @cpus + * field is unused. */ struct em_perf_domain { struct em_perf_state *table; @@ -71,10 +77,12 @@ struct em_data_callback { #define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb } struct em_perf_domain *em_cpu_get(int cpu); +struct em_perf_domain *em_pd_get(struct device *dev); int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, struct em_data_callback *cb); int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span); +void em_dev_unregister_perf_domain(struct device *dev); /** * em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain @@ -184,10 +192,17 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, { return -EINVAL; } +static inline void em_dev_unregister_perf_domain(struct device *dev) +{ +} static inline struct em_perf_domain *em_cpu_get(int cpu) { return NULL; } +static inline struct em_perf_domain *em_pd_get(struct device *dev) +{ + return NULL; +} static inline unsigned long em_pd_energy(struct em_perf_domain *pd, unsigned long max_util, unsigned long sum_util) { -- cgit v1.2.3 From 07891f15d91317b2220a0b610a2d7e324a88105d Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 May 2020 10:58:51 +0100 Subject: PM / EM: remove em_register_perf_domain Remove old function em_register_perf_domain which is no longer needed. There is em_dev_register_perf_domain that covers old use cases and new as well. Acked-by: Daniel Lezcano Acked-by: Quentin Perret Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 2d4689964029..0f94e871a202 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -78,8 +78,6 @@ struct em_data_callback { struct em_perf_domain *em_cpu_get(int cpu); struct em_perf_domain *em_pd_get(struct device *dev); -int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, - struct em_data_callback *cb); int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span); void em_dev_unregister_perf_domain(struct device *dev); @@ -181,11 +179,6 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) struct em_data_callback {}; #define EM_DATA_CB(_active_power_cb) { } -static inline int em_register_perf_domain(cpumask_t *span, - unsigned int nr_states, struct em_data_callback *cb) -{ - return -EINVAL; -} static inline int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, struct em_data_callback *cb, cpumask_t *span) -- cgit v1.2.3 From f0b5694791ce70dba16758c3b838d5ddc7731b02 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 May 2020 10:58:52 +0100 Subject: PM / EM: change name of em_pd_energy to em_cpu_energy Energy Model framework now supports other devices than CPUs. Refactor some of the functions in order to prevent wrong usage. The old function em_pd_energy has to generic name. It must not be used without proper cpumask pointer, which is possible only for CPU devices. Thus, rename it and add proper description to warn of potential wrong usage for other devices. Acked-by: Daniel Lezcano Acked-by: Quentin Perret Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 0f94e871a202..b67a51c574b9 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -83,15 +83,20 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, void em_dev_unregister_perf_domain(struct device *dev); /** - * em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain + * em_cpu_energy() - Estimates the energy consumed by the CPUs of a + performance domain * @pd : performance domain for which energy has to be estimated * @max_util : highest utilization among CPUs of the domain * @sum_util : sum of the utilization of all CPUs in the domain * + * This function must be used only for CPU devices. There is no validation, + * i.e. if the EM is a CPU type and has cpumask allocated. It is called from + * the scheduler code quite frequently and that is why there is not checks. + * * Return: the sum of the energy consumed by the CPUs of the domain assuming * a capacity state satisfying the max utilization of the domain. */ -static inline unsigned long em_pd_energy(struct em_perf_domain *pd, +static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, unsigned long max_util, unsigned long sum_util) { unsigned long freq, scale_cpu; @@ -196,7 +201,7 @@ static inline struct em_perf_domain *em_pd_get(struct device *dev) { return NULL; } -static inline unsigned long em_pd_energy(struct em_perf_domain *pd, +static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, unsigned long max_util, unsigned long sum_util) { return 0; -- cgit v1.2.3 From 0e0ffa855d1590e54ec0033404a49e2e57e294fe Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 May 2020 10:58:54 +0100 Subject: OPP: refactor dev_pm_opp_of_register_em() and update related drivers The Energy Model framework supports not only CPU devices. Drop the CPU specific interface with cpumask and add struct device. Add also a return value, user might use it. This new interface provides easy way to create a simple Energy Model, which then might be used by e.g. thermal subsystem. Acked-by: Daniel Lezcano Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index d5c4a329321d..ee34c553f6bf 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -11,6 +11,7 @@ #ifndef __LINUX_OPP_H__ #define __LINUX_OPP_H__ +#include #include #include @@ -373,7 +374,11 @@ struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev); struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp); int of_get_required_opp_performance_state(struct device_node *np, int index); int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table); -void dev_pm_opp_of_register_em(struct cpumask *cpus); +int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus); +static inline void dev_pm_opp_of_unregister_em(struct device *dev) +{ + em_dev_unregister_perf_domain(dev); +} #else static inline int dev_pm_opp_of_add_table(struct device *dev) { @@ -413,7 +418,13 @@ static inline struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp) return NULL; } -static inline void dev_pm_opp_of_register_em(struct cpumask *cpus) +static inline int dev_pm_opp_of_register_em(struct device *dev, + struct cpumask *cpus) +{ + return -ENOTSUPP; +} + +static inline void dev_pm_opp_of_unregister_em(struct device *dev) { } -- cgit v1.2.3 From aad4a0a9513af962137c4842463d11ed491eec37 Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Sat, 20 Jun 2020 18:30:51 +0300 Subject: tcp: Expose tcp_sock_set_keepidle_locked This is preparation for usage in bpf_setsockopt. v2: - remove redundant EXPORT_SYMBOL (Alexei Starovoitov) Signed-off-by: Dmitry Yakunin Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200620153052.9439-2-zeil@yandex-team.ru --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 9aac824c523c..3bdec31ce8f4 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -499,6 +499,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, void tcp_sock_set_cork(struct sock *sk, bool on); int tcp_sock_set_keepcnt(struct sock *sk, int val); +int tcp_sock_set_keepidle_locked(struct sock *sk, int val); int tcp_sock_set_keepidle(struct sock *sk, int val); int tcp_sock_set_keepintvl(struct sock *sk, int val); void tcp_sock_set_nodelay(struct sock *sk); -- cgit v1.2.3 From 0ef44e5cab8dbf0a0327871b48fe7c8425d0d885 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Tue, 23 Jun 2020 16:30:07 +0200 Subject: net: phy: add support for a common probe between shared PHYs Shared PHYs (PHYs in the same hardware package) may have shared registers and their drivers would usually need to share information. There is currently a way to have a shared (part of the) init, by using phy_package_init_once(). This patch extends the logic to share parts of the probe to allow sharing the initialization of locks or resources retrieval. Signed-off-by: Antoine Tenart Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 7860d56c6bf5..6fb8f302978d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -244,7 +244,8 @@ struct phy_package_shared { }; /* used as bit number in atomic bitops */ -#define PHY_SHARED_F_INIT_DONE 0 +#define PHY_SHARED_F_INIT_DONE 0 +#define PHY_SHARED_F_PROBE_DONE 1 /* * The Bus class for PHYs. Devices which provide access to @@ -1566,14 +1567,25 @@ static inline int __phy_package_write(struct phy_device *phydev, return __mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val); } -static inline bool phy_package_init_once(struct phy_device *phydev) +static inline bool __phy_package_set_once(struct phy_device *phydev, + unsigned int b) { struct phy_package_shared *shared = phydev->shared; if (!shared) return false; - return !test_and_set_bit(PHY_SHARED_F_INIT_DONE, &shared->flags); + return !test_and_set_bit(b, &shared->flags); +} + +static inline bool phy_package_init_once(struct phy_device *phydev) +{ + return __phy_package_set_once(phydev, PHY_SHARED_F_INIT_DONE); +} + +static inline bool phy_package_probe_once(struct phy_device *phydev) +{ + return __phy_package_set_once(phydev, PHY_SHARED_F_PROBE_DONE); } extern struct bus_type mdio_bus_type; -- cgit v1.2.3 From 3dd4ef1bdbac959bb20faec93937720ddd9917c6 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Wed, 24 Jun 2020 15:58:24 +0800 Subject: net: phy: make phy_disable_interrupts() non-static We face an issue with rtl8211f, a pin is shared between INTB and PMEB, and the PHY Register Accessible Interrupt is enabled by default, so the INTB/PMEB pin is always active in polling mode case. As Heiner pointed out "I was thinking about calling phy_disable_interrupts() in phy_init_hw(), to have a defined init state as we don't know in which state the PHY is if the PHY driver is loaded. We shouldn't assume that it's the chip power-on defaults, BIOS or boot loader could have changed this. Or in case of dual-boot systems the other OS could leave the PHY in whatever state." Make phy_disable_interrupts() non-static so that it could be used in phy_init_hw() to have a defined init state. Suggested-by: Heiner Kallweit Signed-off-by: Jisheng Zhang Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 8c05d0fb5c00..b693b609b2f5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1416,6 +1416,7 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev, int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd); +int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); -- cgit v1.2.3 From 1cbf90985f7448f1b0dd630e17ee1070f7d58665 Mon Sep 17 00:00:00 2001 From: David Wilder Date: Mon, 22 Jun 2020 10:10:11 -0700 Subject: netfilter: iptables: Split ipt_unregister_table() into pre_exit and exit helpers. The pre_exit will un-register the underlying hook and .exit will do the table freeing. The netns core does an unconditional synchronize_rcu after the pre_exit hooks insuring no packets are in flight that have picked up the pointer before completing the un-register. Fixes: b9e69e127397 ("netfilter: xtables: don't hook tables by default") Signed-off-by: David Wilder Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv4/ip_tables.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index b394bd4f68a3..c4676d6feeff 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -25,6 +25,12 @@ int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); + +void ipt_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); + +void ipt_unregister_table_exit(struct net *net, struct xt_table *table); + void ipt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops); -- cgit v1.2.3 From 57ea5f18882a3d7cf6135fa8c949a37c89395837 Mon Sep 17 00:00:00 2001 From: David Wilder Date: Mon, 22 Jun 2020 10:10:13 -0700 Subject: netfilter: ip6tables: Split ip6t_unregister_table() into pre_exit and exit helpers. The pre_exit will un-register the underlying hook and .exit will do the table freeing. The netns core does an unconditional synchronize_rcu after the pre_exit hooks insuring no packets are in flight that have picked up the pointer before completing the un-register. Fixes: b9e69e127397 ("netfilter: xtables: don't hook tables by default") Signed-off-by: David Wilder Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6/ip6_tables.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 8225f7821a29..1547d5f9ae06 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -29,6 +29,9 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, const struct nf_hook_ops *ops, struct xt_table **res); void ip6t_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops); +void ip6t_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); +void ip6t_unregister_table_exit(struct net *net, struct xt_table *table); extern unsigned int ip6t_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); -- cgit v1.2.3 From af7ec13833619e17f03aa73a785a2f871da6d66b Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:09 -0700 Subject: bpf: Add bpf_skc_to_tcp6_sock() helper The helper is used in tracing programs to cast a socket pointer to a tcp6_sock pointer. The return value could be NULL if the casting is illegal. A new helper return type RET_PTR_TO_BTF_ID_OR_NULL is added so the verifier is able to deduce proper return types for the helper. Different from the previous BTF_ID based helpers, the bpf_skc_to_tcp6_sock() argument can be several possible btf_ids. More specifically, all possible socket data structures with sock_common appearing in the first in the memory layout. This patch only added socket types related to tcp and udp. All possible argument btf_id and return value btf_id for helper bpf_skc_to_tcp6_sock() are pre-calculcated and cached. In the future, it is even possible to precompute these btf_id's at kernel build time. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200623230809.3988195-1-yhs@fb.com --- include/linux/bpf.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1e1501ee53ce..c0e38ad07848 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -265,6 +265,7 @@ enum bpf_return_type { RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */ RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */ RET_PTR_TO_ALLOC_MEM_OR_NULL, /* returns a pointer to dynamically allocated memory or NULL */ + RET_PTR_TO_BTF_ID_OR_NULL, /* returns a pointer to a btf_id or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -287,6 +288,12 @@ struct bpf_func_proto { enum bpf_arg_type arg_type[5]; }; int *btf_id; /* BTF ids of arguments */ + bool (*check_btf_id)(u32 btf_id, u32 arg); /* if the argument btf_id is + * valid. Often used if more + * than one btf id is permitted + * for this argument. + */ + int *ret_btf_id; /* return value btf_id */ }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is @@ -1524,6 +1531,7 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map) struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); +void init_btf_sock_ids(struct btf *btf); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -1549,6 +1557,9 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) static inline void bpf_map_offload_map_free(struct bpf_map *map) { } +static inline void init_btf_sock_ids(struct btf *btf) +{ +} #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_BPF_STREAM_PARSER) @@ -1638,6 +1649,7 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; +extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From 478cfbdf5f13dfe09cfd0b1cbac821f5e27f6108 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:11 -0700 Subject: bpf: Add bpf_skc_to_{tcp, tcp_timewait, tcp_request}_sock() helpers Three more helpers are added to cast a sock_common pointer to an tcp_sock, tcp_timewait_sock or a tcp_request_sock for tracing programs. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200623230811.3988277-1-yhs@fb.com --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c0e38ad07848..c23998cf6699 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1650,6 +1650,9 @@ extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From 0d4fad3e57df2bf61e8ffc8d12a34b1caf9b8835 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:15 -0700 Subject: bpf: Add bpf_skc_to_udp6_sock() helper The helper is used in tracing programs to cast a socket pointer to a udp6_sock pointer. The return value could be NULL if the casting is illegal. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Cc: Eric Dumazet Link: https://lore.kernel.org/bpf/20200623230815.3988481-1-yhs@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c23998cf6699..3d2ade703a35 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1653,6 +1653,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From 58ffbba6a39979baa22d2f7e69faeffa2d9c0641 Mon Sep 17 00:00:00 2001 From: Akash Asthana Date: Tue, 23 Jun 2020 16:08:50 +0530 Subject: soc: qcom: geni: Support for ICC voting Add necessary macros and structure variables to support ICC BW voting from individual SE drivers. Signed-off-by: Akash Asthana Reviewed-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/1592908737-7068-2-git-send-email-akashast@codeaurora.org Signed-off-by: Bjorn Andersson --- include/linux/qcom-geni-se.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index dd464943f717..80dbc01904d6 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -6,6 +6,8 @@ #ifndef _LINUX_QCOM_GENI_SE #define _LINUX_QCOM_GENI_SE +#include + /* Transfer mode supported by GENI Serial Engines */ enum geni_se_xfer_mode { GENI_SE_INVALID, @@ -25,6 +27,17 @@ enum geni_se_protocol_type { struct geni_wrapper; struct clk; +enum geni_icc_path_index { + GENI_TO_CORE, + CPU_TO_GENI, + GENI_TO_DDR +}; + +struct geni_icc_path { + struct icc_path *path; + unsigned int avg_bw; +}; + /** * struct geni_se - GENI Serial Engine * @base: Base Address of the Serial Engine's register block @@ -33,6 +46,7 @@ struct clk; * @clk: Handle to the core serial engine clock * @num_clk_levels: Number of valid clock levels in clk_perf_tbl * @clk_perf_tbl: Table of clock frequency input to serial engine clock + * @icc_paths: Array of ICC paths for SE */ struct geni_se { void __iomem *base; @@ -41,6 +55,7 @@ struct geni_se { struct clk *clk; unsigned int num_clk_levels; unsigned long *clk_perf_tbl; + struct geni_icc_path icc_paths[3]; }; /* Common SE registers */ @@ -229,6 +244,21 @@ struct geni_se { #define GENI_SE_VERSION_MINOR(ver) ((ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT) #define GENI_SE_VERSION_STEP(ver) (ver & HW_VER_STEP_MASK) +/* + * Define bandwidth thresholds that cause the underlying Core 2X interconnect + * clock to run at the named frequency. These baseline values are recommended + * by the hardware team, and are not dynamically scaled with GENI bandwidth + * beyond basic on/off. + */ +#define CORE_2X_19_2_MHZ 960 +#define CORE_2X_50_MHZ 2500 +#define CORE_2X_100_MHZ 5000 +#define CORE_2X_150_MHZ 7500 +#define CORE_2X_200_MHZ 10000 +#define CORE_2X_236_MHZ 16383 + +#define GENI_DEFAULT_BW Bps_to_icc(1000) + #if IS_ENABLED(CONFIG_QCOM_GENI_SE) u32 geni_se_get_qup_hw_version(struct geni_se *se); @@ -416,5 +446,13 @@ int geni_se_rx_dma_prep(struct geni_se *se, void *buf, size_t len, void geni_se_tx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len); void geni_se_rx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len); + +int geni_icc_get(struct geni_se *se, const char *icc_ddr); + +int geni_icc_set_bw(struct geni_se *se); + +int geni_icc_enable(struct geni_se *se); + +int geni_icc_disable(struct geni_se *se); #endif #endif -- cgit v1.2.3 From 048eb908a1f276ca0346f20a3e6e7d707dcd81f3 Mon Sep 17 00:00:00 2001 From: Akash Asthana Date: Tue, 23 Jun 2020 16:08:51 +0530 Subject: soc: qcom-geni-se: Add interconnect support to fix earlycon crash QUP core clock is shared among all the SE drivers present on particular QUP wrapper, the system will reset(unclocked access) if earlycon used after QUP core clock is put to 0 from other SE drivers before real console comes up. As earlycon can't vote for it's QUP core need, to fix this add ICC support to common/QUP wrapper driver and put vote for QUP core from probe on behalf of earlycon and remove vote during earlycon exit call. Signed-off-by: Akash Asthana Reported-by: Matthias Kaehlcke Reviewed-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/1592908737-7068-3-git-send-email-akashast@codeaurora.org Signed-off-by: Bjorn Andersson --- include/linux/qcom-geni-se.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index 80dbc01904d6..743dd975d1cd 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -454,5 +454,7 @@ int geni_icc_set_bw(struct geni_se *se); int geni_icc_enable(struct geni_se *se); int geni_icc_disable(struct geni_se *se); + +void geni_remove_earlycon_icc_vote(void); #endif #endif -- cgit v1.2.3 From a5819b548af0cc0fd0b84fa3e35723c4c36f157c Mon Sep 17 00:00:00 2001 From: Rajendra Nayak Date: Mon, 15 Jun 2020 17:32:39 +0530 Subject: tty: serial: qcom_geni_serial: Use OPP API to set clk/perf state geni serial needs to express a perforamnce state requirement on CX powerdomain depending on the frequency of the clock rates. Use OPP table from DT to register with OPP framework and use dev_pm_opp_set_rate() to set the clk/perf state. Signed-off-by: Rajendra Nayak Reviewed-by: Matthias Kaehlcke Acked-by: Greg Kroah-Hartman Cc: Akash Asthana Cc: linux-serial@vger.kernel.org Link: https://lore.kernel.org/r/1592222564-13556-2-git-send-email-rnayak@codeaurora.org Signed-off-by: Bjorn Andersson --- include/linux/qcom-geni-se.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index 743dd975d1cd..afa511ef1457 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -47,6 +47,8 @@ struct geni_icc_path { * @num_clk_levels: Number of valid clock levels in clk_perf_tbl * @clk_perf_tbl: Table of clock frequency input to serial engine clock * @icc_paths: Array of ICC paths for SE + * @opp_table: Pointer to the OPP table + * @has_opp_table: Specifies if the SE has an OPP table */ struct geni_se { void __iomem *base; @@ -56,6 +58,8 @@ struct geni_se { unsigned int num_clk_levels; unsigned long *clk_perf_tbl; struct geni_icc_path icc_paths[3]; + struct opp_table *opp_table; + bool has_opp_table; }; /* Common SE registers */ -- cgit v1.2.3 From 5e48a03bb9bff1728164040d71aa03cdb3cdfca2 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 24 Jun 2020 01:09:23 -0700 Subject: platform/chrome: cros_ec: Add TBT pd_ctrl fields To support Thunderbolt compatibility mode, synchronize ec_response_usb_pd_control_v2 with the Chrome EC version, so that we get the Thunderbolt related control fields and macros. Signed-off-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra --- include/linux/platform_data/cros_ec_commands.h | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index a7b0fc440c35..b808570bdd04 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -4917,15 +4917,26 @@ struct ec_response_usb_pd_control_v1 { #define USBC_PD_CC_UFP_ATTACHED 4 /* UFP attached to usbc */ #define USBC_PD_CC_DFP_ATTACHED 5 /* DPF attached to usbc */ +/* Active/Passive Cable */ +#define USB_PD_CTRL_ACTIVE_CABLE BIT(0) +/* Optical/Non-optical cable */ +#define USB_PD_CTRL_OPTICAL_CABLE BIT(1) +/* 3rd Gen TBT device (or AMA)/2nd gen tbt Adapter */ +#define USB_PD_CTRL_TBT_LEGACY_ADAPTER BIT(2) +/* Active Link Uni-Direction */ +#define USB_PD_CTRL_ACTIVE_LINK_UNIDIR BIT(3) + struct ec_response_usb_pd_control_v2 { uint8_t enabled; uint8_t role; uint8_t polarity; char state[32]; - uint8_t cc_state; /* USBC_PD_CC_*Encoded cc state */ - uint8_t dp_mode; /* Current DP pin mode (MODE_DP_PIN_[A-E]) */ - /* CL:1500994 Current cable type */ - uint8_t reserved_cable_type; + uint8_t cc_state; /* enum pd_cc_states representing cc state */ + uint8_t dp_mode; /* Current DP pin mode (MODE_DP_PIN_[A-E]) */ + uint8_t reserved; /* Reserved for future use */ + uint8_t control_flags; /* USB_PD_CTRL_*flags */ + uint8_t cable_speed; /* TBT_SS_* cable speed */ + uint8_t cable_gen; /* TBT_GEN3_* cable rounded support */ } __ec_align1; #define EC_CMD_USB_PD_PORTS 0x0102 -- cgit v1.2.3 From 0c1a7f13c9ec1ceb18d97ef4b1dd20ec71ffba31 Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Wed, 17 Jun 2020 17:01:32 +0530 Subject: ieee80211: Add missing and new AKM suite selector definitions Add the definitions for missing AKM selectors defined in IEEE P802.11-REVmd/D3.0, table 9-151. These definitions will be used by various drivers that support these new AKM suites. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/20200617113132.13477-1-vjakkam@codeaurora.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index fe15f831841b..9f732499ea88 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -3333,13 +3333,17 @@ struct ieee80211_multiple_bssid_configuration { #define WLAN_AKM_SUITE_TDLS SUITE(0x000FAC, 7) #define WLAN_AKM_SUITE_SAE SUITE(0x000FAC, 8) #define WLAN_AKM_SUITE_FT_OVER_SAE SUITE(0x000FAC, 9) +#define WLAN_AKM_SUITE_AP_PEER_KEY SUITE(0x000FAC, 10) #define WLAN_AKM_SUITE_8021X_SUITE_B SUITE(0x000FAC, 11) #define WLAN_AKM_SUITE_8021X_SUITE_B_192 SUITE(0x000FAC, 12) +#define WLAN_AKM_SUITE_FT_8021X_SHA384 SUITE(0x000FAC, 13) #define WLAN_AKM_SUITE_FILS_SHA256 SUITE(0x000FAC, 14) #define WLAN_AKM_SUITE_FILS_SHA384 SUITE(0x000FAC, 15) #define WLAN_AKM_SUITE_FT_FILS_SHA256 SUITE(0x000FAC, 16) #define WLAN_AKM_SUITE_FT_FILS_SHA384 SUITE(0x000FAC, 17) #define WLAN_AKM_SUITE_OWE SUITE(0x000FAC, 18) +#define WLAN_AKM_SUITE_FT_PSK_SHA384 SUITE(0x000FAC, 19) +#define WLAN_AKM_SUITE_PSK_SHA384 SUITE(0x000FAC, 20) #define WLAN_MAX_KEY_LEN 32 -- cgit v1.2.3 From 01e377c539ca52a6c753d0fdbe93b3b8fcd66a1c Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 18 Jun 2020 21:08:10 +0200 Subject: sched/core: Remove mmdrop() definition Commit bf2c59fce4074 ("sched/core: Fix illegal RCU from offline CPUs") introduced a definition for mmdrop() but a a few lines above there is already mmdrop() defined as static inline. Remove the newly introduced mmdrop() definition. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200618190810.790211-1-bigeasy@linutronix.de --- include/linux/sched/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 480a4d1b7dd8..a98604ea76f1 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,8 +49,6 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } -void mmdrop(struct mm_struct *mm); - /* * This has to be called after a get_task_mm()/mmget_not_zero() * followed by taking the mmap_lock for writing before modifying the -- cgit v1.2.3 From a9b59159d338d414acaa8e2f569d129d51c76452 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 24 Jun 2020 15:20:39 -0700 Subject: bpf: Do not allow btf_ctx_access with __int128 types To ensure btf_ctx_access() is safe the verifier checks that the BTF arg type is an int, enum, or pointer. When the function does the BTF arg lookup it uses the calculation 'arg = off / 8' using the fact that registers are 8B. This requires that the first arg is in the first reg, the second in the second, and so on. However, for __int128 the arg will consume two registers by default LLVM implementation. So this will cause the arg layout assumed by the 'arg = off / 8' calculation to be incorrect. Because __int128 is uncommon this patch applies the easiest fix and will force int types to be sizeof(u64) or smaller so that they will fit in a single register. v2: remove unneeded parens per Andrii's feedback Fixes: 9e15db66136a1 ("bpf: Implement accurate raw_tp context access via BTF") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/159303723962.11287.13309537171132420717.stgit@john-Precision-5820-Tower --- include/linux/btf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 5c1ea99b480f..8b81fbb4497c 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -82,6 +82,11 @@ static inline bool btf_type_is_int(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_INT; } +static inline bool btf_type_is_small_int(const struct btf_type *t) +{ + return btf_type_is_int(t) && t->size <= sizeof(u64); +} + static inline bool btf_type_is_enum(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; -- cgit v1.2.3 From 5faafd5685764e4d75376aceac91fdf75b3b16f8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 25 Jun 2020 15:55:14 +0200 Subject: locking/atomics: Provide the arch_atomic_ interface to generic code Architectures with instrumented (KASAN/KCSAN) atomic operations natively provide arch_atomic_ variants that are not instrumented. It turns out that some generic code also requires arch_atomic_ in order to avoid instrumentation, so provide the arch_atomic_ interface as a direct map into the regular atomic_ interface for non-instrumented architectures. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Paul E. McKenney --- include/linux/atomic-fallback.h | 236 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 235 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/atomic-fallback.h b/include/linux/atomic-fallback.h index 2c4927bf7b8d..fd525c71d676 100644 --- a/include/linux/atomic-fallback.h +++ b/include/linux/atomic-fallback.h @@ -77,6 +77,9 @@ #endif /* cmpxchg64_relaxed */ +#define arch_atomic_read atomic_read +#define arch_atomic_read_acquire atomic_read_acquire + #ifndef atomic_read_acquire static __always_inline int atomic_read_acquire(const atomic_t *v) @@ -86,6 +89,9 @@ atomic_read_acquire(const atomic_t *v) #define atomic_read_acquire atomic_read_acquire #endif +#define arch_atomic_set atomic_set +#define arch_atomic_set_release atomic_set_release + #ifndef atomic_set_release static __always_inline void atomic_set_release(atomic_t *v, int i) @@ -95,6 +101,13 @@ atomic_set_release(atomic_t *v, int i) #define atomic_set_release atomic_set_release #endif +#define arch_atomic_add atomic_add + +#define arch_atomic_add_return atomic_add_return +#define arch_atomic_add_return_acquire atomic_add_return_acquire +#define arch_atomic_add_return_release atomic_add_return_release +#define arch_atomic_add_return_relaxed atomic_add_return_relaxed + #ifndef atomic_add_return_relaxed #define atomic_add_return_acquire atomic_add_return #define atomic_add_return_release atomic_add_return @@ -137,6 +150,11 @@ atomic_add_return(int i, atomic_t *v) #endif /* atomic_add_return_relaxed */ +#define arch_atomic_fetch_add atomic_fetch_add +#define arch_atomic_fetch_add_acquire atomic_fetch_add_acquire +#define arch_atomic_fetch_add_release atomic_fetch_add_release +#define arch_atomic_fetch_add_relaxed atomic_fetch_add_relaxed + #ifndef atomic_fetch_add_relaxed #define atomic_fetch_add_acquire atomic_fetch_add #define atomic_fetch_add_release atomic_fetch_add @@ -179,6 +197,13 @@ atomic_fetch_add(int i, atomic_t *v) #endif /* atomic_fetch_add_relaxed */ +#define arch_atomic_sub atomic_sub + +#define arch_atomic_sub_return atomic_sub_return +#define arch_atomic_sub_return_acquire atomic_sub_return_acquire +#define arch_atomic_sub_return_release atomic_sub_return_release +#define arch_atomic_sub_return_relaxed atomic_sub_return_relaxed + #ifndef atomic_sub_return_relaxed #define atomic_sub_return_acquire atomic_sub_return #define atomic_sub_return_release atomic_sub_return @@ -221,6 +246,11 @@ atomic_sub_return(int i, atomic_t *v) #endif /* atomic_sub_return_relaxed */ +#define arch_atomic_fetch_sub atomic_fetch_sub +#define arch_atomic_fetch_sub_acquire atomic_fetch_sub_acquire +#define arch_atomic_fetch_sub_release atomic_fetch_sub_release +#define arch_atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed + #ifndef atomic_fetch_sub_relaxed #define atomic_fetch_sub_acquire atomic_fetch_sub #define atomic_fetch_sub_release atomic_fetch_sub @@ -263,6 +293,8 @@ atomic_fetch_sub(int i, atomic_t *v) #endif /* atomic_fetch_sub_relaxed */ +#define arch_atomic_inc atomic_inc + #ifndef atomic_inc static __always_inline void atomic_inc(atomic_t *v) @@ -272,6 +304,11 @@ atomic_inc(atomic_t *v) #define atomic_inc atomic_inc #endif +#define arch_atomic_inc_return atomic_inc_return +#define arch_atomic_inc_return_acquire atomic_inc_return_acquire +#define arch_atomic_inc_return_release atomic_inc_return_release +#define arch_atomic_inc_return_relaxed atomic_inc_return_relaxed + #ifndef atomic_inc_return_relaxed #ifdef atomic_inc_return #define atomic_inc_return_acquire atomic_inc_return @@ -353,6 +390,11 @@ atomic_inc_return(atomic_t *v) #endif /* atomic_inc_return_relaxed */ +#define arch_atomic_fetch_inc atomic_fetch_inc +#define arch_atomic_fetch_inc_acquire atomic_fetch_inc_acquire +#define arch_atomic_fetch_inc_release atomic_fetch_inc_release +#define arch_atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed + #ifndef atomic_fetch_inc_relaxed #ifdef atomic_fetch_inc #define atomic_fetch_inc_acquire atomic_fetch_inc @@ -434,6 +476,8 @@ atomic_fetch_inc(atomic_t *v) #endif /* atomic_fetch_inc_relaxed */ +#define arch_atomic_dec atomic_dec + #ifndef atomic_dec static __always_inline void atomic_dec(atomic_t *v) @@ -443,6 +487,11 @@ atomic_dec(atomic_t *v) #define atomic_dec atomic_dec #endif +#define arch_atomic_dec_return atomic_dec_return +#define arch_atomic_dec_return_acquire atomic_dec_return_acquire +#define arch_atomic_dec_return_release atomic_dec_return_release +#define arch_atomic_dec_return_relaxed atomic_dec_return_relaxed + #ifndef atomic_dec_return_relaxed #ifdef atomic_dec_return #define atomic_dec_return_acquire atomic_dec_return @@ -524,6 +573,11 @@ atomic_dec_return(atomic_t *v) #endif /* atomic_dec_return_relaxed */ +#define arch_atomic_fetch_dec atomic_fetch_dec +#define arch_atomic_fetch_dec_acquire atomic_fetch_dec_acquire +#define arch_atomic_fetch_dec_release atomic_fetch_dec_release +#define arch_atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed + #ifndef atomic_fetch_dec_relaxed #ifdef atomic_fetch_dec #define atomic_fetch_dec_acquire atomic_fetch_dec @@ -605,6 +659,13 @@ atomic_fetch_dec(atomic_t *v) #endif /* atomic_fetch_dec_relaxed */ +#define arch_atomic_and atomic_and + +#define arch_atomic_fetch_and atomic_fetch_and +#define arch_atomic_fetch_and_acquire atomic_fetch_and_acquire +#define arch_atomic_fetch_and_release atomic_fetch_and_release +#define arch_atomic_fetch_and_relaxed atomic_fetch_and_relaxed + #ifndef atomic_fetch_and_relaxed #define atomic_fetch_and_acquire atomic_fetch_and #define atomic_fetch_and_release atomic_fetch_and @@ -647,6 +708,8 @@ atomic_fetch_and(int i, atomic_t *v) #endif /* atomic_fetch_and_relaxed */ +#define arch_atomic_andnot atomic_andnot + #ifndef atomic_andnot static __always_inline void atomic_andnot(int i, atomic_t *v) @@ -656,6 +719,11 @@ atomic_andnot(int i, atomic_t *v) #define atomic_andnot atomic_andnot #endif +#define arch_atomic_fetch_andnot atomic_fetch_andnot +#define arch_atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire +#define arch_atomic_fetch_andnot_release atomic_fetch_andnot_release +#define arch_atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed + #ifndef atomic_fetch_andnot_relaxed #ifdef atomic_fetch_andnot #define atomic_fetch_andnot_acquire atomic_fetch_andnot @@ -737,6 +805,13 @@ atomic_fetch_andnot(int i, atomic_t *v) #endif /* atomic_fetch_andnot_relaxed */ +#define arch_atomic_or atomic_or + +#define arch_atomic_fetch_or atomic_fetch_or +#define arch_atomic_fetch_or_acquire atomic_fetch_or_acquire +#define arch_atomic_fetch_or_release atomic_fetch_or_release +#define arch_atomic_fetch_or_relaxed atomic_fetch_or_relaxed + #ifndef atomic_fetch_or_relaxed #define atomic_fetch_or_acquire atomic_fetch_or #define atomic_fetch_or_release atomic_fetch_or @@ -779,6 +854,13 @@ atomic_fetch_or(int i, atomic_t *v) #endif /* atomic_fetch_or_relaxed */ +#define arch_atomic_xor atomic_xor + +#define arch_atomic_fetch_xor atomic_fetch_xor +#define arch_atomic_fetch_xor_acquire atomic_fetch_xor_acquire +#define arch_atomic_fetch_xor_release atomic_fetch_xor_release +#define arch_atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed + #ifndef atomic_fetch_xor_relaxed #define atomic_fetch_xor_acquire atomic_fetch_xor #define atomic_fetch_xor_release atomic_fetch_xor @@ -821,6 +903,11 @@ atomic_fetch_xor(int i, atomic_t *v) #endif /* atomic_fetch_xor_relaxed */ +#define arch_atomic_xchg atomic_xchg +#define arch_atomic_xchg_acquire atomic_xchg_acquire +#define arch_atomic_xchg_release atomic_xchg_release +#define arch_atomic_xchg_relaxed atomic_xchg_relaxed + #ifndef atomic_xchg_relaxed #define atomic_xchg_acquire atomic_xchg #define atomic_xchg_release atomic_xchg @@ -863,6 +950,11 @@ atomic_xchg(atomic_t *v, int i) #endif /* atomic_xchg_relaxed */ +#define arch_atomic_cmpxchg atomic_cmpxchg +#define arch_atomic_cmpxchg_acquire atomic_cmpxchg_acquire +#define arch_atomic_cmpxchg_release atomic_cmpxchg_release +#define arch_atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed + #ifndef atomic_cmpxchg_relaxed #define atomic_cmpxchg_acquire atomic_cmpxchg #define atomic_cmpxchg_release atomic_cmpxchg @@ -905,6 +997,11 @@ atomic_cmpxchg(atomic_t *v, int old, int new) #endif /* atomic_cmpxchg_relaxed */ +#define arch_atomic_try_cmpxchg atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_acquire atomic_try_cmpxchg_acquire +#define arch_atomic_try_cmpxchg_release atomic_try_cmpxchg_release +#define arch_atomic_try_cmpxchg_relaxed atomic_try_cmpxchg_relaxed + #ifndef atomic_try_cmpxchg_relaxed #ifdef atomic_try_cmpxchg #define atomic_try_cmpxchg_acquire atomic_try_cmpxchg @@ -1002,6 +1099,8 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) #endif /* atomic_try_cmpxchg_relaxed */ +#define arch_atomic_sub_and_test atomic_sub_and_test + #ifndef atomic_sub_and_test /** * atomic_sub_and_test - subtract value from variable and test result @@ -1020,6 +1119,8 @@ atomic_sub_and_test(int i, atomic_t *v) #define atomic_sub_and_test atomic_sub_and_test #endif +#define arch_atomic_dec_and_test atomic_dec_and_test + #ifndef atomic_dec_and_test /** * atomic_dec_and_test - decrement and test @@ -1037,6 +1138,8 @@ atomic_dec_and_test(atomic_t *v) #define atomic_dec_and_test atomic_dec_and_test #endif +#define arch_atomic_inc_and_test atomic_inc_and_test + #ifndef atomic_inc_and_test /** * atomic_inc_and_test - increment and test @@ -1054,6 +1157,8 @@ atomic_inc_and_test(atomic_t *v) #define atomic_inc_and_test atomic_inc_and_test #endif +#define arch_atomic_add_negative atomic_add_negative + #ifndef atomic_add_negative /** * atomic_add_negative - add and test if negative @@ -1072,6 +1177,8 @@ atomic_add_negative(int i, atomic_t *v) #define atomic_add_negative atomic_add_negative #endif +#define arch_atomic_fetch_add_unless atomic_fetch_add_unless + #ifndef atomic_fetch_add_unless /** * atomic_fetch_add_unless - add unless the number is already a given value @@ -1097,6 +1204,8 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u) #define atomic_fetch_add_unless atomic_fetch_add_unless #endif +#define arch_atomic_add_unless atomic_add_unless + #ifndef atomic_add_unless /** * atomic_add_unless - add unless the number is already a given value @@ -1115,6 +1224,8 @@ atomic_add_unless(atomic_t *v, int a, int u) #define atomic_add_unless atomic_add_unless #endif +#define arch_atomic_inc_not_zero atomic_inc_not_zero + #ifndef atomic_inc_not_zero /** * atomic_inc_not_zero - increment unless the number is zero @@ -1131,6 +1242,8 @@ atomic_inc_not_zero(atomic_t *v) #define atomic_inc_not_zero atomic_inc_not_zero #endif +#define arch_atomic_inc_unless_negative atomic_inc_unless_negative + #ifndef atomic_inc_unless_negative static __always_inline bool atomic_inc_unless_negative(atomic_t *v) @@ -1147,6 +1260,8 @@ atomic_inc_unless_negative(atomic_t *v) #define atomic_inc_unless_negative atomic_inc_unless_negative #endif +#define arch_atomic_dec_unless_positive atomic_dec_unless_positive + #ifndef atomic_dec_unless_positive static __always_inline bool atomic_dec_unless_positive(atomic_t *v) @@ -1163,6 +1278,8 @@ atomic_dec_unless_positive(atomic_t *v) #define atomic_dec_unless_positive atomic_dec_unless_positive #endif +#define arch_atomic_dec_if_positive atomic_dec_if_positive + #ifndef atomic_dec_if_positive static __always_inline int atomic_dec_if_positive(atomic_t *v) @@ -1184,6 +1301,9 @@ atomic_dec_if_positive(atomic_t *v) #include #endif +#define arch_atomic64_read atomic64_read +#define arch_atomic64_read_acquire atomic64_read_acquire + #ifndef atomic64_read_acquire static __always_inline s64 atomic64_read_acquire(const atomic64_t *v) @@ -1193,6 +1313,9 @@ atomic64_read_acquire(const atomic64_t *v) #define atomic64_read_acquire atomic64_read_acquire #endif +#define arch_atomic64_set atomic64_set +#define arch_atomic64_set_release atomic64_set_release + #ifndef atomic64_set_release static __always_inline void atomic64_set_release(atomic64_t *v, s64 i) @@ -1202,6 +1325,13 @@ atomic64_set_release(atomic64_t *v, s64 i) #define atomic64_set_release atomic64_set_release #endif +#define arch_atomic64_add atomic64_add + +#define arch_atomic64_add_return atomic64_add_return +#define arch_atomic64_add_return_acquire atomic64_add_return_acquire +#define arch_atomic64_add_return_release atomic64_add_return_release +#define arch_atomic64_add_return_relaxed atomic64_add_return_relaxed + #ifndef atomic64_add_return_relaxed #define atomic64_add_return_acquire atomic64_add_return #define atomic64_add_return_release atomic64_add_return @@ -1244,6 +1374,11 @@ atomic64_add_return(s64 i, atomic64_t *v) #endif /* atomic64_add_return_relaxed */ +#define arch_atomic64_fetch_add atomic64_fetch_add +#define arch_atomic64_fetch_add_acquire atomic64_fetch_add_acquire +#define arch_atomic64_fetch_add_release atomic64_fetch_add_release +#define arch_atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed + #ifndef atomic64_fetch_add_relaxed #define atomic64_fetch_add_acquire atomic64_fetch_add #define atomic64_fetch_add_release atomic64_fetch_add @@ -1286,6 +1421,13 @@ atomic64_fetch_add(s64 i, atomic64_t *v) #endif /* atomic64_fetch_add_relaxed */ +#define arch_atomic64_sub atomic64_sub + +#define arch_atomic64_sub_return atomic64_sub_return +#define arch_atomic64_sub_return_acquire atomic64_sub_return_acquire +#define arch_atomic64_sub_return_release atomic64_sub_return_release +#define arch_atomic64_sub_return_relaxed atomic64_sub_return_relaxed + #ifndef atomic64_sub_return_relaxed #define atomic64_sub_return_acquire atomic64_sub_return #define atomic64_sub_return_release atomic64_sub_return @@ -1328,6 +1470,11 @@ atomic64_sub_return(s64 i, atomic64_t *v) #endif /* atomic64_sub_return_relaxed */ +#define arch_atomic64_fetch_sub atomic64_fetch_sub +#define arch_atomic64_fetch_sub_acquire atomic64_fetch_sub_acquire +#define arch_atomic64_fetch_sub_release atomic64_fetch_sub_release +#define arch_atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed + #ifndef atomic64_fetch_sub_relaxed #define atomic64_fetch_sub_acquire atomic64_fetch_sub #define atomic64_fetch_sub_release atomic64_fetch_sub @@ -1370,6 +1517,8 @@ atomic64_fetch_sub(s64 i, atomic64_t *v) #endif /* atomic64_fetch_sub_relaxed */ +#define arch_atomic64_inc atomic64_inc + #ifndef atomic64_inc static __always_inline void atomic64_inc(atomic64_t *v) @@ -1379,6 +1528,11 @@ atomic64_inc(atomic64_t *v) #define atomic64_inc atomic64_inc #endif +#define arch_atomic64_inc_return atomic64_inc_return +#define arch_atomic64_inc_return_acquire atomic64_inc_return_acquire +#define arch_atomic64_inc_return_release atomic64_inc_return_release +#define arch_atomic64_inc_return_relaxed atomic64_inc_return_relaxed + #ifndef atomic64_inc_return_relaxed #ifdef atomic64_inc_return #define atomic64_inc_return_acquire atomic64_inc_return @@ -1460,6 +1614,11 @@ atomic64_inc_return(atomic64_t *v) #endif /* atomic64_inc_return_relaxed */ +#define arch_atomic64_fetch_inc atomic64_fetch_inc +#define arch_atomic64_fetch_inc_acquire atomic64_fetch_inc_acquire +#define arch_atomic64_fetch_inc_release atomic64_fetch_inc_release +#define arch_atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed + #ifndef atomic64_fetch_inc_relaxed #ifdef atomic64_fetch_inc #define atomic64_fetch_inc_acquire atomic64_fetch_inc @@ -1541,6 +1700,8 @@ atomic64_fetch_inc(atomic64_t *v) #endif /* atomic64_fetch_inc_relaxed */ +#define arch_atomic64_dec atomic64_dec + #ifndef atomic64_dec static __always_inline void atomic64_dec(atomic64_t *v) @@ -1550,6 +1711,11 @@ atomic64_dec(atomic64_t *v) #define atomic64_dec atomic64_dec #endif +#define arch_atomic64_dec_return atomic64_dec_return +#define arch_atomic64_dec_return_acquire atomic64_dec_return_acquire +#define arch_atomic64_dec_return_release atomic64_dec_return_release +#define arch_atomic64_dec_return_relaxed atomic64_dec_return_relaxed + #ifndef atomic64_dec_return_relaxed #ifdef atomic64_dec_return #define atomic64_dec_return_acquire atomic64_dec_return @@ -1631,6 +1797,11 @@ atomic64_dec_return(atomic64_t *v) #endif /* atomic64_dec_return_relaxed */ +#define arch_atomic64_fetch_dec atomic64_fetch_dec +#define arch_atomic64_fetch_dec_acquire atomic64_fetch_dec_acquire +#define arch_atomic64_fetch_dec_release atomic64_fetch_dec_release +#define arch_atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed + #ifndef atomic64_fetch_dec_relaxed #ifdef atomic64_fetch_dec #define atomic64_fetch_dec_acquire atomic64_fetch_dec @@ -1712,6 +1883,13 @@ atomic64_fetch_dec(atomic64_t *v) #endif /* atomic64_fetch_dec_relaxed */ +#define arch_atomic64_and atomic64_and + +#define arch_atomic64_fetch_and atomic64_fetch_and +#define arch_atomic64_fetch_and_acquire atomic64_fetch_and_acquire +#define arch_atomic64_fetch_and_release atomic64_fetch_and_release +#define arch_atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed + #ifndef atomic64_fetch_and_relaxed #define atomic64_fetch_and_acquire atomic64_fetch_and #define atomic64_fetch_and_release atomic64_fetch_and @@ -1754,6 +1932,8 @@ atomic64_fetch_and(s64 i, atomic64_t *v) #endif /* atomic64_fetch_and_relaxed */ +#define arch_atomic64_andnot atomic64_andnot + #ifndef atomic64_andnot static __always_inline void atomic64_andnot(s64 i, atomic64_t *v) @@ -1763,6 +1943,11 @@ atomic64_andnot(s64 i, atomic64_t *v) #define atomic64_andnot atomic64_andnot #endif +#define arch_atomic64_fetch_andnot atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire +#define arch_atomic64_fetch_andnot_release atomic64_fetch_andnot_release +#define arch_atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed + #ifndef atomic64_fetch_andnot_relaxed #ifdef atomic64_fetch_andnot #define atomic64_fetch_andnot_acquire atomic64_fetch_andnot @@ -1844,6 +2029,13 @@ atomic64_fetch_andnot(s64 i, atomic64_t *v) #endif /* atomic64_fetch_andnot_relaxed */ +#define arch_atomic64_or atomic64_or + +#define arch_atomic64_fetch_or atomic64_fetch_or +#define arch_atomic64_fetch_or_acquire atomic64_fetch_or_acquire +#define arch_atomic64_fetch_or_release atomic64_fetch_or_release +#define arch_atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed + #ifndef atomic64_fetch_or_relaxed #define atomic64_fetch_or_acquire atomic64_fetch_or #define atomic64_fetch_or_release atomic64_fetch_or @@ -1886,6 +2078,13 @@ atomic64_fetch_or(s64 i, atomic64_t *v) #endif /* atomic64_fetch_or_relaxed */ +#define arch_atomic64_xor atomic64_xor + +#define arch_atomic64_fetch_xor atomic64_fetch_xor +#define arch_atomic64_fetch_xor_acquire atomic64_fetch_xor_acquire +#define arch_atomic64_fetch_xor_release atomic64_fetch_xor_release +#define arch_atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed + #ifndef atomic64_fetch_xor_relaxed #define atomic64_fetch_xor_acquire atomic64_fetch_xor #define atomic64_fetch_xor_release atomic64_fetch_xor @@ -1928,6 +2127,11 @@ atomic64_fetch_xor(s64 i, atomic64_t *v) #endif /* atomic64_fetch_xor_relaxed */ +#define arch_atomic64_xchg atomic64_xchg +#define arch_atomic64_xchg_acquire atomic64_xchg_acquire +#define arch_atomic64_xchg_release atomic64_xchg_release +#define arch_atomic64_xchg_relaxed atomic64_xchg_relaxed + #ifndef atomic64_xchg_relaxed #define atomic64_xchg_acquire atomic64_xchg #define atomic64_xchg_release atomic64_xchg @@ -1970,6 +2174,11 @@ atomic64_xchg(atomic64_t *v, s64 i) #endif /* atomic64_xchg_relaxed */ +#define arch_atomic64_cmpxchg atomic64_cmpxchg +#define arch_atomic64_cmpxchg_acquire atomic64_cmpxchg_acquire +#define arch_atomic64_cmpxchg_release atomic64_cmpxchg_release +#define arch_atomic64_cmpxchg_relaxed atomic64_cmpxchg_relaxed + #ifndef atomic64_cmpxchg_relaxed #define atomic64_cmpxchg_acquire atomic64_cmpxchg #define atomic64_cmpxchg_release atomic64_cmpxchg @@ -2012,6 +2221,11 @@ atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) #endif /* atomic64_cmpxchg_relaxed */ +#define arch_atomic64_try_cmpxchg atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg_acquire +#define arch_atomic64_try_cmpxchg_release atomic64_try_cmpxchg_release +#define arch_atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg_relaxed + #ifndef atomic64_try_cmpxchg_relaxed #ifdef atomic64_try_cmpxchg #define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg @@ -2109,6 +2323,8 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) #endif /* atomic64_try_cmpxchg_relaxed */ +#define arch_atomic64_sub_and_test atomic64_sub_and_test + #ifndef atomic64_sub_and_test /** * atomic64_sub_and_test - subtract value from variable and test result @@ -2127,6 +2343,8 @@ atomic64_sub_and_test(s64 i, atomic64_t *v) #define atomic64_sub_and_test atomic64_sub_and_test #endif +#define arch_atomic64_dec_and_test atomic64_dec_and_test + #ifndef atomic64_dec_and_test /** * atomic64_dec_and_test - decrement and test @@ -2144,6 +2362,8 @@ atomic64_dec_and_test(atomic64_t *v) #define atomic64_dec_and_test atomic64_dec_and_test #endif +#define arch_atomic64_inc_and_test atomic64_inc_and_test + #ifndef atomic64_inc_and_test /** * atomic64_inc_and_test - increment and test @@ -2161,6 +2381,8 @@ atomic64_inc_and_test(atomic64_t *v) #define atomic64_inc_and_test atomic64_inc_and_test #endif +#define arch_atomic64_add_negative atomic64_add_negative + #ifndef atomic64_add_negative /** * atomic64_add_negative - add and test if negative @@ -2179,6 +2401,8 @@ atomic64_add_negative(s64 i, atomic64_t *v) #define atomic64_add_negative atomic64_add_negative #endif +#define arch_atomic64_fetch_add_unless atomic64_fetch_add_unless + #ifndef atomic64_fetch_add_unless /** * atomic64_fetch_add_unless - add unless the number is already a given value @@ -2204,6 +2428,8 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) #define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif +#define arch_atomic64_add_unless atomic64_add_unless + #ifndef atomic64_add_unless /** * atomic64_add_unless - add unless the number is already a given value @@ -2222,6 +2448,8 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u) #define atomic64_add_unless atomic64_add_unless #endif +#define arch_atomic64_inc_not_zero atomic64_inc_not_zero + #ifndef atomic64_inc_not_zero /** * atomic64_inc_not_zero - increment unless the number is zero @@ -2238,6 +2466,8 @@ atomic64_inc_not_zero(atomic64_t *v) #define atomic64_inc_not_zero atomic64_inc_not_zero #endif +#define arch_atomic64_inc_unless_negative atomic64_inc_unless_negative + #ifndef atomic64_inc_unless_negative static __always_inline bool atomic64_inc_unless_negative(atomic64_t *v) @@ -2254,6 +2484,8 @@ atomic64_inc_unless_negative(atomic64_t *v) #define atomic64_inc_unless_negative atomic64_inc_unless_negative #endif +#define arch_atomic64_dec_unless_positive atomic64_dec_unless_positive + #ifndef atomic64_dec_unless_positive static __always_inline bool atomic64_dec_unless_positive(atomic64_t *v) @@ -2270,6 +2502,8 @@ atomic64_dec_unless_positive(atomic64_t *v) #define atomic64_dec_unless_positive atomic64_dec_unless_positive #endif +#define arch_atomic64_dec_if_positive atomic64_dec_if_positive + #ifndef atomic64_dec_if_positive static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) @@ -2288,4 +2522,4 @@ atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 1fac0941c79bf0ae100723cc2ac9b94061f0b67a +// 9d95b56f98d82a2a26c7b79ccdd0c47572d50a6f -- cgit v1.2.3 From b58e733fd774f3f4b49d9e7640d172a57e35200e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 15 Jun 2020 18:24:27 +0200 Subject: rcu: Fixup noinstr warnings A KCSAN build revealed we have explicit annoations through atomic_*() usage, switch to arch_atomic_*() for the respective functions. vmlinux.o: warning: objtool: rcu_nmi_exit()+0x4d: call to __kcsan_check_access() leaves .noinstr.text section vmlinux.o: warning: objtool: rcu_dynticks_eqs_enter()+0x25: call to __kcsan_check_access() leaves .noinstr.text section vmlinux.o: warning: objtool: rcu_nmi_enter()+0x4f: call to __kcsan_check_access() leaves .noinstr.text section vmlinux.o: warning: objtool: rcu_dynticks_eqs_exit()+0x2a: call to __kcsan_check_access() leaves .noinstr.text section vmlinux.o: warning: objtool: __rcu_is_watching()+0x25: call to __kcsan_check_access() leaves .noinstr.text section Additionally, without the NOP in instrumentation_begin(), objtool would not detect the lack of the 'else instrumentation_begin();' branch in rcu_nmi_enter(). Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Paul E. McKenney --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 30827f82ad62..204e76856435 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -123,7 +123,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #ifdef CONFIG_DEBUG_ENTRY /* Begin/end of an instrumentation safe region */ #define instrumentation_begin() ({ \ - asm volatile("%c0:\n\t" \ + asm volatile("%c0: nop\n\t" \ ".pushsection .discard.instr_begin\n\t" \ ".long %c0b - .\n\t" \ ".popsection\n\t" : : "i" (__COUNTER__)); \ -- cgit v1.2.3 From da6690767cbd344998f36081815c85f3d467e78c Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 25 Jun 2020 17:36:05 +0100 Subject: regulator: consumer: Supply missing prototypes for 3 core functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit regulator_suspend_enable(), regulator_suspend_disable() and regulator_set_suspend_voltage() are all exported members of the API, but are all missing prototypes. Fixes the following W=1 warning(s): drivers/regulator/core.c:3805:5: warning: no previous prototype for ‘regulator_suspend_enable’ [-Wmissing-prototypes] 3805 | int regulator_suspend_enable(struct regulator_dev *rdev, | ^~~~~~~~~~~~~~~~~~~~~~~~ drivers/regulator/core.c:3812:5: warning: no previous prototype for ‘regulator_suspend_disable’ [-Wmissing-prototypes] 3812 | int regulator_suspend_disable(struct regulator_dev *rdev, | ^~~~~~~~~~~~~~~~~~~~~~~~~ drivers/regulator/core.c:3851:5: warning: no previous prototype for ‘regulator_set_suspend_voltage’ [-Wmissing-prototypes] 3851 | int regulator_set_suspend_voltage(struct regulator *regulator, int min_uV, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20200625163614.4001403-2-lee.jones@linaro.org Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 6a92fd3105a3..2024944fd2f7 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -32,10 +32,12 @@ #define __LINUX_REGULATOR_CONSUMER_H_ #include +#include struct device; struct notifier_block; struct regmap; +struct regulator_dev; /* * Regulator operating modes. @@ -277,6 +279,14 @@ int regulator_unregister_notifier(struct regulator *regulator, void devm_regulator_unregister_notifier(struct regulator *regulator, struct notifier_block *nb); +/* regulator suspend */ +int regulator_suspend_enable(struct regulator_dev *rdev, + suspend_state_t state); +int regulator_suspend_disable(struct regulator_dev *rdev, + suspend_state_t state); +int regulator_set_suspend_voltage(struct regulator *regulator, int min_uV, + int max_uV, suspend_state_t state); + /* driver data - core doesn't touch */ void *regulator_get_drvdata(struct regulator *regulator); void regulator_set_drvdata(struct regulator *regulator, void *data); -- cgit v1.2.3 From c6d5d843d9b6e8dca3768250970f0d0a1e3d4fb0 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 24 Jun 2020 11:06:54 +0100 Subject: net: phylink: add phylink_speed_(up|down) interface Add an interface for the phy_speed_(up|down) functions when a driver makes use of phylink. These pass the call through to phylib when we have a normal PHY attached (i.o.w., not a PHY on a SFP module.) Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index cc5b452a184e..b32b8b45421b 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -392,6 +392,8 @@ int phylink_init_eee(struct phylink *, bool); int phylink_ethtool_get_eee(struct phylink *, struct ethtool_eee *); int phylink_ethtool_set_eee(struct phylink *, struct ethtool_eee *); int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); +int phylink_speed_down(struct phylink *pl, bool sync); +int phylink_speed_up(struct phylink *pl); #define phylink_zero(bm) \ bitmap_zero(bm, __ETHTOOL_LINK_MODE_MASK_NBITS) -- cgit v1.2.3 From 92252eec913b2dd5e7b5de11ea3efa2e64d65cf4 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Wed, 24 Jun 2020 07:16:02 -0500 Subject: net: phy: Add a helper to return the index for of the internal delay Add a helper function that will return the index in the array for the passed in internal delay value. The helper requires the array, size and delay value. The helper will then return the index for the exact match or return the index for the index to the closest smaller value. Signed-off-by: Dan Murphy Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 6fb8f302978d..2c00374dc996 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1443,6 +1443,10 @@ void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); bool phy_validate_pause(struct phy_device *phydev, struct ethtool_pauseparam *pp); void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause); + +s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, + const int *delay_values, int size, bool is_rx); + void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv, bool *tx_pause, bool *rx_pause); -- cgit v1.2.3 From d037cb4ae20407df89491f9c2d521ac0723aa15d Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 18 Jun 2020 17:00:22 +1000 Subject: crypto: api - Prune inclusions in crypto.h We haven't used string.h since the memcpy calls were removed so this patch removes its inclusion. The file uaccess.h isn't needed at all. However, removing it reveals that we do need to add an inclusion for refcount.h. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 763863dbc079..bc5d2d4bfc3d 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -16,9 +16,8 @@ #include #include #include +#include #include -#include -#include #include /* -- cgit v1.2.3 From fe21b6c3a65ca74cc4d0909635649bea48b115b3 Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Mon, 4 May 2020 09:43:48 -0700 Subject: i40e: Move client header location Move i40e_client.h to include/linux/net/intel/* since its shared between i40iw and i40e. Signed-off-by: Shiraz Saleem Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/net/intel/i40e_client.h | 203 ++++++++++++++++++++++++++++++++++ 1 file changed, 203 insertions(+) create mode 100644 include/linux/net/intel/i40e_client.h (limited to 'include/linux') diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h new file mode 100644 index 000000000000..72994baf4941 --- /dev/null +++ b/include/linux/net/intel/i40e_client.h @@ -0,0 +1,203 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _I40E_CLIENT_H_ +#define _I40E_CLIENT_H_ + +#define I40E_CLIENT_STR_LENGTH 10 + +/* Client interface version should be updated anytime there is a change in the + * existing APIs or data structures. + */ +#define I40E_CLIENT_VERSION_MAJOR 0 +#define I40E_CLIENT_VERSION_MINOR 01 +#define I40E_CLIENT_VERSION_BUILD 00 +#define I40E_CLIENT_VERSION_STR \ + __stringify(I40E_CLIENT_VERSION_MAJOR) "." \ + __stringify(I40E_CLIENT_VERSION_MINOR) "." \ + __stringify(I40E_CLIENT_VERSION_BUILD) + +struct i40e_client_version { + u8 major; + u8 minor; + u8 build; + u8 rsvd; +}; + +enum i40e_client_state { + __I40E_CLIENT_NULL, + __I40E_CLIENT_REGISTERED +}; + +enum i40e_client_instance_state { + __I40E_CLIENT_INSTANCE_NONE, + __I40E_CLIENT_INSTANCE_OPENED, +}; + +struct i40e_ops; +struct i40e_client; + +/* HW does not define a type value for AEQ; only for RX/TX and CEQ. + * In order for us to keep the interface simple, SW will define a + * unique type value for AEQ. + */ +#define I40E_QUEUE_TYPE_PE_AEQ 0x80 +#define I40E_QUEUE_INVALID_IDX 0xFFFF + +struct i40e_qv_info { + u32 v_idx; /* msix_vector */ + u16 ceq_idx; + u16 aeq_idx; + u8 itr_idx; +}; + +struct i40e_qvlist_info { + u32 num_vectors; + struct i40e_qv_info qv_info[1]; +}; + +#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF + +/* set of LAN parameters useful for clients managed by LAN */ + +/* Struct to hold per priority info */ +struct i40e_prio_qos_params { + u16 qs_handle; /* qs handle for prio */ + u8 tc; /* TC mapped to prio */ + u8 reserved; +}; + +#define I40E_CLIENT_MAX_USER_PRIORITY 8 +/* Struct to hold Client QoS */ +struct i40e_qos_params { + struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY]; +}; + +struct i40e_params { + struct i40e_qos_params qos; + u16 mtu; +}; + +/* Structure to hold Lan device info for a client device */ +struct i40e_info { + struct i40e_client_version version; + u8 lanmac[6]; + struct net_device *netdev; + struct pci_dev *pcidev; + u8 __iomem *hw_addr; + u8 fid; /* function id, PF id or VF id */ +#define I40E_CLIENT_FTYPE_PF 0 +#define I40E_CLIENT_FTYPE_VF 1 + u8 ftype; /* function type, PF or VF */ + void *pf; + + /* All L2 params that could change during the life span of the PF + * and needs to be communicated to the client when they change + */ + struct i40e_qvlist_info *qvlist_info; + struct i40e_params params; + struct i40e_ops *ops; + + u16 msix_count; /* number of msix vectors*/ + /* Array down below will be dynamically allocated based on msix_count */ + struct msix_entry *msix_entries; + u16 itr_index; /* Which ITR index the PE driver is suppose to use */ + u16 fw_maj_ver; /* firmware major version */ + u16 fw_min_ver; /* firmware minor version */ + u32 fw_build; /* firmware build number */ +}; + +#define I40E_CLIENT_RESET_LEVEL_PF 1 +#define I40E_CLIENT_RESET_LEVEL_CORE 2 +#define I40E_CLIENT_VSI_FLAG_TCP_ENABLE BIT(1) + +struct i40e_ops { + /* setup_q_vector_list enables queues with a particular vector */ + int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client, + struct i40e_qvlist_info *qv_info); + + int (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client, + u32 vf_id, u8 *msg, u16 len); + + /* If the PE Engine is unresponsive, RDMA driver can request a reset. + * The level helps determine the level of reset being requested. + */ + void (*request_reset)(struct i40e_info *ldev, + struct i40e_client *client, u32 level); + + /* API for the RDMA driver to set certain VSI flags that control + * PE Engine. + */ + int (*update_vsi_ctxt)(struct i40e_info *ldev, + struct i40e_client *client, + bool is_vf, u32 vf_id, + u32 flag, u32 valid_flag); +}; + +struct i40e_client_ops { + /* Should be called from register_client() or whenever PF is ready + * to create a specific client instance. + */ + int (*open)(struct i40e_info *ldev, struct i40e_client *client); + + /* Should be called when netdev is unavailable or when unregister + * call comes in. If the close is happenening due to a reset being + * triggered set the reset bit to true. + */ + void (*close)(struct i40e_info *ldev, struct i40e_client *client, + bool reset); + + /* called when some l2 managed parameters changes - mtu */ + void (*l2_param_change)(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_params *params); + + int (*virtchnl_receive)(struct i40e_info *ldev, + struct i40e_client *client, u32 vf_id, + u8 *msg, u16 len); + + /* called when a VF is reset by the PF */ + void (*vf_reset)(struct i40e_info *ldev, + struct i40e_client *client, u32 vf_id); + + /* called when the number of VFs changes */ + void (*vf_enable)(struct i40e_info *ldev, + struct i40e_client *client, u32 num_vfs); + + /* returns true if VF is capable of specified offload */ + int (*vf_capable)(struct i40e_info *ldev, + struct i40e_client *client, u32 vf_id); +}; + +/* Client device */ +struct i40e_client_instance { + struct list_head list; + struct i40e_info lan_info; + struct i40e_client *client; + unsigned long state; +}; + +struct i40e_client { + struct list_head list; /* list of registered clients */ + char name[I40E_CLIENT_STR_LENGTH]; + struct i40e_client_version version; + unsigned long state; /* client state */ + atomic_t ref_cnt; /* Count of all the client devices of this kind */ + u32 flags; +#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0) +#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2) + u8 type; +#define I40E_CLIENT_IWARP 0 + const struct i40e_client_ops *ops; /* client ops provided by the client */ +}; + +static inline bool i40e_client_is_registered(struct i40e_client *client) +{ + return test_bit(__I40E_CLIENT_REGISTERED, &client->state); +} + +/* used by clients */ +int i40e_register_client(struct i40e_client *client); +int i40e_unregister_client(struct i40e_client *client); + +#endif /* _I40E_CLIENT_H_ */ -- cgit v1.2.3 From 3c98f9ee6bc280499cbcb6f8e42c001c3bd7caa1 Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Mon, 6 Jan 2020 16:09:33 -0800 Subject: i40e: remove unused defines Remove all the unused defines as they are just dead weight. Signed-off-by: Jesse Brandeburg Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/net/intel/i40e_client.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index 72994baf4941..f41387a8969f 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -37,11 +37,6 @@ enum i40e_client_instance_state { struct i40e_ops; struct i40e_client; -/* HW does not define a type value for AEQ; only for RX/TX and CEQ. - * In order for us to keep the interface simple, SW will define a - * unique type value for AEQ. - */ -#define I40E_QUEUE_TYPE_PE_AEQ 0x80 #define I40E_QUEUE_INVALID_IDX 0xFFFF struct i40e_qv_info { @@ -56,7 +51,6 @@ struct i40e_qvlist_info { struct i40e_qv_info qv_info[1]; }; -#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF /* set of LAN parameters useful for clients managed by LAN */ @@ -87,7 +81,6 @@ struct i40e_info { u8 __iomem *hw_addr; u8 fid; /* function id, PF id or VF id */ #define I40E_CLIENT_FTYPE_PF 0 -#define I40E_CLIENT_FTYPE_VF 1 u8 ftype; /* function type, PF or VF */ void *pf; @@ -184,8 +177,6 @@ struct i40e_client { unsigned long state; /* client state */ atomic_t ref_cnt; /* Count of all the client devices of this kind */ u32 flags; -#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0) -#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2) u8 type; #define I40E_CLIENT_IWARP 0 const struct i40e_client_ops *ops; /* client ops provided by the client */ -- cgit v1.2.3 From 33d226f504ed72cba3a2b42bbe2a993b3d6d9548 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 02:25:06 +0200 Subject: mtd: nand: Move nand_device forward declaration to the top This structure might be used earlier in this file, let's move the forward declaration at the top. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200529002517.3546-10-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 0c7483843a32..a1f38c778d0e 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -12,6 +12,8 @@ #include +struct nand_device; + /** * struct nand_memory_organization - Memory organization structure * @bits_per_cell: number of bits per NAND cell @@ -133,8 +135,6 @@ struct nand_bbt { unsigned long *cache; }; -struct nand_device; - /** * struct nand_ops - NAND operations * @erase: erase a specific block. No need to check if the block is bad before -- cgit v1.2.3 From 85f54c5588885cc3b5be4a07498dd0755de9f5cf Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 02:25:10 +0200 Subject: mtd: nand: Rename a core structure Prepare the migration to a generic ECC engine by renaming the nand_ecc_req structure into nand_ecc_props. This structure will be the base of a wider 'nand_ecc' structure. In nand_device, these properties are still named "eccreq" even if "eccprops" might be more descriptive. This is just a transition step, this field is being replaced very soon by a much wider structure. The impact of renaming this field would be huge compared to its interest. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200529002517.3546-14-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 8 ++++---- include/linux/mtd/spinand.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index a1f38c778d0e..af99041ceaa9 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -116,11 +116,11 @@ struct nand_page_io_req { }; /** - * struct nand_ecc_req - NAND ECC requirements + * struct nand_ecc_props - NAND ECC properties * @strength: ECC strength - * @step_size: ECC step/block size + * @step_size: Number of bytes per step */ -struct nand_ecc_req { +struct nand_ecc_props { unsigned int strength; unsigned int step_size; }; @@ -179,7 +179,7 @@ struct nand_ops { struct nand_device { struct mtd_info mtd; struct nand_memory_organization memorg; - struct nand_ecc_req eccreq; + struct nand_ecc_props eccreq; struct nand_row_converter rowconv; struct nand_bbt bbt; const struct nand_ops *ops; diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 1077c45721ff..7b78c4ba9b3e 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -309,7 +309,7 @@ struct spinand_info { struct spinand_devid devid; u32 flags; struct nand_memory_organization memorg; - struct nand_ecc_req eccreq; + struct nand_ecc_props eccreq; struct spinand_ecc_info eccinfo; struct { const struct spinand_op_variants *read_cache; -- cgit v1.2.3 From c4cabc08d09e4b107b685e08bdec8a38a91089d8 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 13:12:55 +0200 Subject: mtd: rawnand: Use unsigned types for nand_chip unsigned values page_shift, phys_erase_shift, bbt_erase_shift, chip_shift, pagemask, subpagesize and badblockbits are all positive values, so declare them as unsigned. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-2-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 65b1c1c18b41..830f2d08937f 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1110,11 +1110,11 @@ struct nand_chip { unsigned int options; unsigned int bbt_options; - int page_shift; - int phys_erase_shift; - int bbt_erase_shift; - int chip_shift; - int pagemask; + unsigned int page_shift; + unsigned int phys_erase_shift; + unsigned int bbt_erase_shift; + unsigned int chip_shift; + unsigned int pagemask; u8 *data_buf; struct { @@ -1122,10 +1122,10 @@ struct nand_chip { int page; } pagecache; - int subpagesize; + unsigned int subpagesize; int onfi_timing_mode_default; unsigned int badblockpos; - int badblockbits; + unsigned int badblockbits; struct nand_id id; struct nand_parameters parameters; -- cgit v1.2.3 From d1f3837a507d73746f9e2118fad20ee5e57e86cc Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 13:12:56 +0200 Subject: mtd: rawnand: Only use u8 instead of uint8_t in nand_chip structure Mechanical change to avoid using old types. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-3-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 830f2d08937f..cea137778224 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1141,13 +1141,13 @@ struct nand_chip { int (*suspend)(struct nand_chip *chip); void (*resume)(struct nand_chip *chip); - uint8_t *oob_poi; + u8 *oob_poi; struct nand_controller *controller; struct nand_ecc_ctrl ecc; unsigned long buf_align; - uint8_t *bbt; + u8 *bbt; struct nand_bbt_descr *bbt_td; struct nand_bbt_descr *bbt_md; -- cgit v1.2.3 From 8e8b2706e15d16443b1ea61a6f994c08ec5b9486 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 13:12:57 +0200 Subject: mtd: rawnand: Create a nand_chip operations structure And move nand_chip hooks there. While moving entries from one structure to the other, adapt the documentation style. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-4-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index cea137778224..7f9be95ca8dc 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1027,16 +1027,31 @@ struct nand_legacy { struct nand_controller dummy_controller; }; +/** + * struct nand_chip_ops - NAND chip operations + * @suspend: Suspend operation + * @resume: Resume operation + * @lock_area: Lock operation + * @unlock_area: Unlock operation + * @setup_read_retry: Set the read-retry mode (mostly needed for MLC NANDs) + */ +struct nand_chip_ops { + int (*suspend)(struct nand_chip *chip); + void (*resume)(struct nand_chip *chip); + int (*lock_area)(struct nand_chip *chip, loff_t ofs, uint64_t len); + int (*unlock_area)(struct nand_chip *chip, loff_t ofs, uint64_t len); + int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); +}; + /** * struct nand_chip - NAND Private Flash Chip Data * @base: Inherit from the generic NAND device + * @ops: NAND chip operations * @legacy: All legacy fields/hooks. If you develop a new driver, * don't even try to use any of these fields/hooks, and if * you're modifying an existing driver that is using those * fields/hooks, you should consider reworking the driver * avoid using them. - * @setup_read_retry: [FLASHSPECIFIC] flash (vendor) specific function for - * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure * @buf_align: minimum buffer alignment required by a platform * @oob_poi: "poison value buffer," used for laying out OOB data @@ -1081,8 +1096,6 @@ struct nand_legacy { * @lock: lock protecting the suspended field. Also used to * serialize accesses to the NAND device. * @suspended: set to 1 when the device is suspended, 0 when it's not. - * @suspend: [REPLACEABLE] specific NAND device suspend operation - * @resume: [REPLACEABLE] specific NAND device resume operation * @bbt: [INTERN] bad block table pointer * @bbt_td: [REPLACEABLE] bad block table descriptor for flash * lookup. @@ -1096,17 +1109,13 @@ struct nand_legacy { * @manufacturer: [INTERN] Contains manufacturer information * @manufacturer.desc: [INTERN] Contains manufacturer's description * @manufacturer.priv: [INTERN] Contains manufacturer private information - * @lock_area: [REPLACEABLE] specific NAND chip lock operation - * @unlock_area: [REPLACEABLE] specific NAND chip unlock operation */ struct nand_chip { struct nand_device base; - + struct nand_chip_ops ops; struct nand_legacy legacy; - int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); - unsigned int options; unsigned int bbt_options; @@ -1138,8 +1147,6 @@ struct nand_chip { struct mutex lock; unsigned int suspended : 1; - int (*suspend)(struct nand_chip *chip); - void (*resume)(struct nand_chip *chip); u8 *oob_poi; struct nand_controller *controller; @@ -1159,9 +1166,6 @@ struct nand_chip { const struct nand_manufacturer *desc; void *priv; } manufacturer; - - int (*lock_area)(struct nand_chip *chip, loff_t ofs, uint64_t len); - int (*unlock_area)(struct nand_chip *chip, loff_t ofs, uint64_t len); }; extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops; -- cgit v1.2.3 From 271de009b7c0c1c15f63491a352ab08835462977 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 13:12:58 +0200 Subject: mtd: rawnand: Rename the manufacturer structure It is currently called nand_manufacturer but could actually be called nand_manufacturer_desc, like its instances, so that the former name is left unused for now. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-5-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 7f9be95ca8dc..860d3c1020ef 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1163,7 +1163,7 @@ struct nand_chip { void *priv; struct { - const struct nand_manufacturer *desc; + const struct nand_manufacturer_desc *desc; void *priv; } manufacturer; }; -- cgit v1.2.3 From 36017af430e6b2fad0b2ee5476103706160f1379 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 13:12:59 +0200 Subject: mtd: rawnand: Declare the nand_manufacturer structure out of nand_chip Now that struct nand_manufacturer type is free, use it to store the nand_manufacturer_desc and the manufacturer's private data. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-6-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 860d3c1020ef..a3dfa36a9fd5 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1043,10 +1043,21 @@ struct nand_chip_ops { int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); }; +/** + * struct nand_manufacturer - NAND manufacturer structure + * @desc: The manufacturer description + * @priv: Private information for the manufacturer driver + */ +struct nand_manufacturer { + const struct nand_manufacturer_desc *desc; + void *priv; +}; + /** * struct nand_chip - NAND Private Flash Chip Data * @base: Inherit from the generic NAND device * @ops: NAND chip operations + * @manufacturer: Manufacturer information * @legacy: All legacy fields/hooks. If you develop a new driver, * don't even try to use any of these fields/hooks, and if * you're modifying an existing driver that is using those @@ -1106,13 +1117,11 @@ struct nand_chip_ops { * structure which is shared among multiple independent * devices. * @priv: [OPTIONAL] pointer to private chip data - * @manufacturer: [INTERN] Contains manufacturer information - * @manufacturer.desc: [INTERN] Contains manufacturer's description - * @manufacturer.priv: [INTERN] Contains manufacturer private information */ struct nand_chip { struct nand_device base; + struct nand_manufacturer manufacturer; struct nand_chip_ops ops; struct nand_legacy legacy; @@ -1161,11 +1170,6 @@ struct nand_chip { struct nand_bbt_descr *badblock_pattern; void *priv; - - struct { - const struct nand_manufacturer_desc *desc; - void *priv; - } manufacturer; }; extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops; -- cgit v1.2.3 From a63674c7cfe62221e05ba73107d9e15d73ff8bbd Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 13:13:00 +0200 Subject: mtd: rawnand: Reorganize the nand_chip structure Reorder fields in this structure and pack entries by theme: * The main descriptive structures * The data interface details * Bad block information * The device layout * Extra buffers matching the device layout * Internal values * External objects like the ECC controller, the ECC engine and a private data pointer. While at it, adapt the documentation style. I changed on purpose the description of @oob_poi which was weird. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-7-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 166 ++++++++++++++++++++------------------------ 1 file changed, 76 insertions(+), 90 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index a3dfa36a9fd5..544ec8736793 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1055,120 +1055,106 @@ struct nand_manufacturer { /** * struct nand_chip - NAND Private Flash Chip Data - * @base: Inherit from the generic NAND device - * @ops: NAND chip operations - * @manufacturer: Manufacturer information - * @legacy: All legacy fields/hooks. If you develop a new driver, - * don't even try to use any of these fields/hooks, and if - * you're modifying an existing driver that is using those - * fields/hooks, you should consider reworking the driver - * avoid using them. - * @ecc: [BOARDSPECIFIC] ECC control structure - * @buf_align: minimum buffer alignment required by a platform - * @oob_poi: "poison value buffer," used for laying out OOB data - * before writing - * @page_shift: [INTERN] number of address bits in a page (column - * address bits). - * @phys_erase_shift: [INTERN] number of address bits in a physical eraseblock - * @bbt_erase_shift: [INTERN] number of address bits in a bbt entry - * @chip_shift: [INTERN] number of address bits in one chip - * @options: [BOARDSPECIFIC] various chip options. They can partly - * be set to inform nand_scan about special functionality. - * See the defines for further explanation. - * @bbt_options: [INTERN] bad block specific options. All options used - * here must come from bbm.h. By default, these options - * will be copied to the appropriate nand_bbt_descr's. - * @badblockpos: [INTERN] position of the bad block marker in the oob - * area. - * @badblockbits: [INTERN] minimum number of set bits in a good block's - * bad block marker position; i.e., BBM == 11110111b is - * not bad when badblockbits == 7 - * @onfi_timing_mode_default: [INTERN] default ONFI timing mode. This field is - * set to the actually used ONFI mode if the chip is - * ONFI compliant or deduced from the datasheet if - * the NAND chip is not ONFI compliant. - * @pagemask: [INTERN] page number mask = number of (pages / chip) - 1 - * @data_buf: [INTERN] buffer for data, size is (page size + oobsize). - * @pagecache: Structure containing page cache related fields - * @pagecache.bitflips: Number of bitflips of the cached page - * @pagecache.page: Page number currently in the cache. -1 means no page is - * currently cached - * @subpagesize: [INTERN] holds the subpagesize - * @id: [INTERN] holds NAND ID - * @parameters: [INTERN] holds generic parameters under an easily - * readable form. - * @data_interface: [INTERN] NAND interface timing information - * @cur_cs: currently selected target. -1 means no target selected, - * otherwise we should always have cur_cs >= 0 && - * cur_cs < nanddev_ntargets(). NAND Controller drivers - * should not modify this value, but they're allowed to - * read it. - * @read_retries: [INTERN] the number of read retry modes supported - * @lock: lock protecting the suspended field. Also used to - * serialize accesses to the NAND device. - * @suspended: set to 1 when the device is suspended, 0 when it's not. - * @bbt: [INTERN] bad block table pointer - * @bbt_td: [REPLACEABLE] bad block table descriptor for flash - * lookup. - * @bbt_md: [REPLACEABLE] bad block table mirror descriptor - * @badblock_pattern: [REPLACEABLE] bad block scan pattern used for initial - * bad block scan. - * @controller: [REPLACEABLE] a pointer to a hardware controller - * structure which is shared among multiple independent - * devices. - * @priv: [OPTIONAL] pointer to private chip data + * @base: Inherit from the generic NAND device + * @id: Holds NAND ID + * @parameters: Holds generic parameters under an easily readable form + * @manufacturer: Manufacturer information + * @ops: NAND chip operations + * @legacy: All legacy fields/hooks. If you develop a new driver, don't even try + * to use any of these fields/hooks, and if you're modifying an + * existing driver that is using those fields/hooks, you should + * consider reworking the driver and avoid using them. + * @options: Various chip options. They can partly be set to inform nand_scan + * about special functionality. See the defines for further + * explanation. + * @onfi_timing_mode_default: Default ONFI timing mode. This field is set to the + * actually used ONFI mode if the chip is ONFI + * compliant or deduced from the datasheet otherwise + * @data_interface: NAND interface timing information + * @bbt_erase_shift: Number of address bits in a bbt entry + * @bbt_options: Bad block table specific options. All options used here must + * come from bbm.h. By default, these options will be copied to + * the appropriate nand_bbt_descr's. + * @badblockpos: Bad block marker position in the oob area + * @badblockbits: Minimum number of set bits in a good block's bad block marker + * position; i.e., BBM = 11110111b is good when badblockbits = 7 + * @bbt_td: Bad block table descriptor for flash lookup + * @bbt_md: Bad block table mirror descriptor + * @badblock_pattern: Bad block scan pattern used for initial bad block scan + * @bbt: Bad block table pointer + * @page_shift: Number of address bits in a page (column address bits) + * @phys_erase_shift: Number of address bits in a physical eraseblock + * @chip_shift: Number of address bits in one chip + * @pagemask: Page number mask = number of (pages / chip) - 1 + * @subpagesize: Holds the subpagesize + * @data_buf: Buffer for data, size is (page size + oobsize) + * @oob_poi: pointer on the OOB area covered by data_buf + * @pagecache: Structure containing page cache related fields + * @pagecache.bitflips: Number of bitflips of the cached page + * @pagecache.page: Page number currently in the cache. -1 means no page is + * currently cached + * @buf_align: Minimum buffer alignment required by a platform + * @lock: Lock protecting the suspended field. Also used to serialize accesses + * to the NAND device + * @suspended: Set to 1 when the device is suspended, 0 when it's not + * @cur_cs: Currently selected target. -1 means no target selected, otherwise we + * should always have cur_cs >= 0 && cur_cs < nanddev_ntargets(). + * NAND Controller drivers should not modify this value, but they're + * allowed to read it. + * @read_retries: The number of read retry modes supported + * @controller: The hardware controller structure which is shared among multiple + * independent devices + * @ecc: The ECC controller structure + * @priv: Chip private data */ - struct nand_chip { struct nand_device base; + struct nand_id id; + struct nand_parameters parameters; struct nand_manufacturer manufacturer; struct nand_chip_ops ops; struct nand_legacy legacy; - unsigned int options; + + /* Data interface */ + int onfi_timing_mode_default; + struct nand_data_interface data_interface; + + /* Bad block information */ + unsigned int bbt_erase_shift; unsigned int bbt_options; + unsigned int badblockpos; + unsigned int badblockbits; + struct nand_bbt_descr *bbt_td; + struct nand_bbt_descr *bbt_md; + struct nand_bbt_descr *badblock_pattern; + u8 *bbt; + /* Device internal layout */ unsigned int page_shift; unsigned int phys_erase_shift; - unsigned int bbt_erase_shift; unsigned int chip_shift; unsigned int pagemask; - u8 *data_buf; + unsigned int subpagesize; + /* Buffers */ + u8 *data_buf; + u8 *oob_poi; struct { unsigned int bitflips; int page; } pagecache; + unsigned long buf_align; - unsigned int subpagesize; - int onfi_timing_mode_default; - unsigned int badblockpos; - unsigned int badblockbits; - - struct nand_id id; - struct nand_parameters parameters; - - struct nand_data_interface data_interface; - - int cur_cs; - - int read_retries; - + /* Internals */ struct mutex lock; unsigned int suspended : 1; + int cur_cs; + int read_retries; - u8 *oob_poi; + /* Externals */ struct nand_controller *controller; - struct nand_ecc_ctrl ecc; - unsigned long buf_align; - - u8 *bbt; - struct nand_bbt_descr *bbt_td; - struct nand_bbt_descr *bbt_md; - - struct nand_bbt_descr *badblock_pattern; - void *priv; }; -- cgit v1.2.3 From e0160cd41fb81fde9ee4612a7ea2dfd631de2638 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 13:13:12 +0200 Subject: mtd: rawnand: Hide the chip->data_interface indirection As a preparation for allocating the data interface structure dynamically (and rename it), let's avoid accessing chip->data_interface directly. Instead, we introduce a helper, nand_get_interface_config(), and use it to retrieve the current data interface configuration out of a nand_chip object. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-19-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 544ec8736793..0852df941130 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1203,6 +1203,17 @@ static inline struct device_node *nand_get_flash_node(struct nand_chip *chip) return mtd_get_of_node(nand_to_mtd(chip)); } +/** + * nand_get_interface_config - Retrieve the current interface configuration + * of a NAND chip + * @chip: The NAND chip + */ +static inline const struct nand_data_interface * +nand_get_interface_config(struct nand_chip *chip) +{ + return &chip->data_interface; +} + /* * A helper for defining older NAND chips where the second ID byte fully * defined the chip, including the geometry (chip size, eraseblock size, page -- cgit v1.2.3 From 4c46667b3d67253604ee42840917844548c86657 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 13:13:13 +0200 Subject: mtd: rawnand: s/data_interface/interface_config/ The name/suffix data_interface is a bit misleading in that the field or functions actually represent a configuration that can be applied by the controller/chip. Let's rename all fields/functions/hooks that are worth renaming. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 0852df941130..2ca56eef0f07 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -492,22 +492,22 @@ struct nand_sdr_timings { }; /** - * enum nand_data_interface_type - NAND interface timing type + * enum nand_interface_type - NAND interface type * @NAND_SDR_IFACE: Single Data Rate interface */ -enum nand_data_interface_type { +enum nand_interface_type { NAND_SDR_IFACE, }; /** - * struct nand_data_interface - NAND interface timing + * struct nand_interface_config - NAND interface timing * @type: type of the timing * @timings: The timing information * @timings.mode: Timing mode as defined in the specification * @timings.sdr: Use it when @type is %NAND_SDR_IFACE. */ -struct nand_data_interface { - enum nand_data_interface_type type; +struct nand_interface_config { + enum nand_interface_type type; struct nand_timings { unsigned int mode; union { @@ -521,7 +521,7 @@ struct nand_data_interface { * @conf: The data interface */ static inline const struct nand_sdr_timings * -nand_get_sdr_timings(const struct nand_data_interface *conf) +nand_get_sdr_timings(const struct nand_interface_config *conf) { if (conf->type != NAND_SDR_IFACE) return ERR_PTR(-EINVAL); @@ -944,11 +944,10 @@ static inline void nand_op_trace(const char *prefix, * This method replaces chip->legacy.cmdfunc(), * chip->legacy.{read,write}_{buf,byte,word}(), * chip->legacy.dev_ready() and chip->legacy.waifunc(). - * @setup_data_interface: setup the data interface and timing. If - * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this - * means the configuration should not be applied but - * only checked. - * This hook is optional. + * @setup_interface: setup the data interface and timing. If chipnr is set to + * %NAND_DATA_IFACE_CHECK_ONLY this means the configuration + * should not be applied but only checked. + * This hook is optional. */ struct nand_controller_ops { int (*attach_chip)(struct nand_chip *chip); @@ -956,8 +955,8 @@ struct nand_controller_ops { int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); - int (*setup_data_interface)(struct nand_chip *chip, int chipnr, - const struct nand_data_interface *conf); + int (*setup_interface)(struct nand_chip *chip, int chipnr, + const struct nand_interface_config *conf); }; /** @@ -1070,7 +1069,7 @@ struct nand_manufacturer { * @onfi_timing_mode_default: Default ONFI timing mode. This field is set to the * actually used ONFI mode if the chip is ONFI * compliant or deduced from the datasheet otherwise - * @data_interface: NAND interface timing information + * @interface_config: NAND interface timing information * @bbt_erase_shift: Number of address bits in a bbt entry * @bbt_options: Bad block table specific options. All options used here must * come from bbm.h. By default, these options will be copied to @@ -1118,7 +1117,7 @@ struct nand_chip { /* Data interface */ int onfi_timing_mode_default; - struct nand_data_interface data_interface; + struct nand_interface_config interface_config; /* Bad block information */ unsigned int bbt_erase_shift; @@ -1208,10 +1207,10 @@ static inline struct device_node *nand_get_flash_node(struct nand_chip *chip) * of a NAND chip * @chip: The NAND chip */ -static inline const struct nand_data_interface * +static inline const struct nand_interface_config * nand_get_interface_config(struct nand_chip *chip) { - return &chip->data_interface; + return &chip->interface_config; } /* -- cgit v1.2.3 From 26d014f0400e5ff54cc80c8329e3adbd74db1e04 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 13:13:16 +0200 Subject: mtd: rawnand: Add the ->choose_interface_config() hook This hook can be overloaded by NAND manufacturer drivers to propose alternative timings when not following the main standards. In this case, the manufacturer drivers is responsible for choosing the best interface configuration that fits both the controller and chip capabilities. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-23-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 2ca56eef0f07..316a02189da1 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1033,6 +1033,7 @@ struct nand_legacy { * @lock_area: Lock operation * @unlock_area: Unlock operation * @setup_read_retry: Set the read-retry mode (mostly needed for MLC NANDs) + * @choose_interface_config: Choose the best interface configuration */ struct nand_chip_ops { int (*suspend)(struct nand_chip *chip); @@ -1040,6 +1041,8 @@ struct nand_chip_ops { int (*lock_area)(struct nand_chip *chip, loff_t ofs, uint64_t len); int (*unlock_area)(struct nand_chip *chip, loff_t ofs, uint64_t len); int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); + int (*choose_interface_config)(struct nand_chip *chip, + struct nand_interface_config *iface); }; /** -- cgit v1.2.3 From a69ad11168dca68b3f0adc6882422f4a2e2cb050 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 13:13:21 +0200 Subject: mtd: rawnand: Get rid of the default ONFI timing mode The ->choose_interface() hook is here for manufacturer drivers to provide a better timing interface than the default one, this field is not needed anymore. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-28-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 316a02189da1..a2427c67d38b 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1069,9 +1069,6 @@ struct nand_manufacturer { * @options: Various chip options. They can partly be set to inform nand_scan * about special functionality. See the defines for further * explanation. - * @onfi_timing_mode_default: Default ONFI timing mode. This field is set to the - * actually used ONFI mode if the chip is ONFI - * compliant or deduced from the datasheet otherwise * @interface_config: NAND interface timing information * @bbt_erase_shift: Number of address bits in a bbt entry * @bbt_options: Bad block table specific options. All options used here must @@ -1119,7 +1116,6 @@ struct nand_chip { unsigned int options; /* Data interface */ - int onfi_timing_mode_default; struct nand_interface_config interface_config; /* Bad block information */ @@ -1268,10 +1264,6 @@ nand_get_interface_config(struct nand_chip *chip) * @ecc_step_ds in nand_chip{}, also from the datasheet. * For example, the "4bit ECC for each 512Byte" can be set with * NAND_ECC_INFO(4, 512). - * @onfi_timing_mode_default: the default ONFI timing mode entered after a NAND - * reset. Should be deduced from timings described - * in the datasheet. - * */ struct nand_flash_dev { char *name; @@ -1292,7 +1284,6 @@ struct nand_flash_dev { uint16_t strength_ds; uint16_t step_ds; } ecc; - int onfi_timing_mode_default; }; int nand_create_bbt(struct nand_chip *chip); -- cgit v1.2.3 From 35b6bcc970f759d4a86d6221d09ca28ea20467c8 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 29 May 2020 13:13:22 +0200 Subject: mtd: rawnand: Allocate the interface configurations dynamically Instead of manipulating the statically allocated structure and copy timings around, allocate one at identification time and save it in the nand_chip structure once it has been initialized. All NAND chips using the same interface configuration during reset and startup, we define a helper to retrieve a single reset interface configuration object, shared across all NAND chips. We use a second pointer to always have a reference on the currently applied interface configuration, which may either point to the "best interface configuration" or to the "default reset interface configuration". Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20200529111322.7184-29-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index a2427c67d38b..a725b620aca2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1069,7 +1069,11 @@ struct nand_manufacturer { * @options: Various chip options. They can partly be set to inform nand_scan * about special functionality. See the defines for further * explanation. - * @interface_config: NAND interface timing information + * @current_interface_config: The currently used NAND interface configuration + * @best_interface_config: The best NAND interface configuration which fits both + * the NAND chip and NAND controller constraints. If + * unset, the default reset interface configuration must + * be used. * @bbt_erase_shift: Number of address bits in a bbt entry * @bbt_options: Bad block table specific options. All options used here must * come from bbm.h. By default, these options will be copied to @@ -1116,7 +1120,8 @@ struct nand_chip { unsigned int options; /* Data interface */ - struct nand_interface_config interface_config; + const struct nand_interface_config *current_interface_config; + struct nand_interface_config *best_interface_config; /* Bad block information */ unsigned int bbt_erase_shift; @@ -1209,7 +1214,7 @@ static inline struct device_node *nand_get_flash_node(struct nand_chip *chip) static inline const struct nand_interface_config * nand_get_interface_config(struct nand_chip *chip) { - return &chip->interface_config; + return chip->current_interface_config; } /* -- cgit v1.2.3 From 31d8fcac00fcf4007f3921edc69ab4dcb3abcd4d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 25 Jun 2020 20:30:31 -0700 Subject: mm: workingset: age nonresident information alongside anonymous pages Patch series "fix for "mm: balance LRU lists based on relative thrashing" patchset" This patchset fixes some problems of the patchset, "mm: balance LRU lists based on relative thrashing", which is now merged on the mainline. Patch "mm: workingset: let cache workingset challenge anon fix" is the result of discussion with Johannes. See following link. http://lkml.kernel.org/r/20200520232525.798933-6-hannes@cmpxchg.org And, the other two are minor things which are found when I try to rebase my patchset. This patch (of 3): After ("mm: workingset: let cache workingset challenge anon fix"), we compare refault distances to active_file + anon. But age of the non-resident information is only driven by the file LRU. As a result, we may overestimate the recency of any incoming refaults and activate them too eagerly, causing unnecessary LRU churn in certain situations. Make anon aging drive nonresident age as well to address that. Link: http://lkml.kernel.org/r/1592288204-27734-1-git-send-email-iamjoonsoo.kim@lge.com Link: http://lkml.kernel.org/r/1592288204-27734-2-git-send-email-iamjoonsoo.kim@lge.com Fixes: 34e58cac6d8f2a ("mm: workingset: let cache workingset challenge anon") Reported-by: Joonsoo Kim Signed-off-by: Johannes Weiner Signed-off-by: Joonsoo Kim Cc: Rik van Riel Cc: Minchan Kim Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 4 ++-- include/linux/swap.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c4c37fd12104..f6f884970511 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -257,8 +257,8 @@ struct lruvec { */ unsigned long anon_cost; unsigned long file_cost; - /* Evictions & activations on the inactive file list */ - atomic_long_t inactive_age; + /* Non-resident age, driven by LRU movement */ + atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults; /* Various lruvec state flags (enum lruvec_flags) */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 4c5974bb9ba9..5b3216ba39a9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -313,6 +313,7 @@ struct vma_swap_readahead { }; /* linux/mm/workingset.c */ +void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); -- cgit v1.2.3 From 7a0e27b2a0ce2735e27e21ebc8b777550fe0ed81 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 25 Jun 2020 20:30:47 -0700 Subject: mm: remove vmalloc_exec Merge vmalloc_exec into its only caller. Note that for !CONFIG_MMU __vmalloc_node_range maps to __vmalloc, which directly clears the __GFP_HIGHMEM added by the vmalloc_exec stub anyway. Link: http://lkml.kernel.org/r/20200618064307.32739-4-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: David Hildenbrand Acked-by: Peter Zijlstra (Intel) Cc: Catalin Marinas Cc: Dexuan Cui Cc: Jessica Yu Cc: Vitaly Kuznetsov Cc: Wei Liu Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 48bb681e6c2a..0221f852a7e1 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -106,7 +106,6 @@ extern void *vzalloc(unsigned long size); extern void *vmalloc_user(unsigned long size); extern void *vmalloc_node(unsigned long size, int node); extern void *vzalloc_node(unsigned long size, int node); -extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); extern void *__vmalloc(unsigned long size, gfp_t gfp_mask); -- cgit v1.2.3 From 5946d1f5b309381805bad3ddc3054c04f4ae9c24 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Thu, 4 Jun 2020 15:31:19 +0530 Subject: kdb: Switch to use safer dbg_io_ops over console APIs In kgdb context, calling console handlers aren't safe due to locks used in those handlers which could in turn lead to a deadlock. Although, using oops_in_progress increases the chance to bypass locks in most console handlers but it might not be sufficient enough in case a console uses more locks (VT/TTY is good example). Currently when a driver provides both polling I/O and a console then kdb will output using the console. We can increase robustness by using the currently active polling I/O driver (which should be lockless) instead of the corresponding console. For several common cases (e.g. an embedded system with a single serial port that is used both for console output and debugger I/O) this will result in no console handler being used. In order to achieve this we need to reverse the order of preference to use dbg_io_ops (uses polling I/O mode) over console APIs. So we just store "struct console" that represents debugger I/O in dbg_io_ops and while emitting kdb messages, skip console that matches dbg_io_ops console in order to avoid duplicate messages. After this change, "is_console" param becomes redundant and hence removed. Suggested-by: Daniel Thompson Signed-off-by: Sumit Garg Link: https://lore.kernel.org/r/1591264879-25920-5-git-send-email-sumit.garg@linaro.org Reviewed-by: Douglas Anderson Reviewed-by: Petr Mladek Acked-by: Greg Kroah-Hartman Signed-off-by: Daniel Thompson --- include/linux/kgdb.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index c62d76478adc..529116b0cabe 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -276,8 +276,7 @@ struct kgdb_arch { * the I/O driver. * @post_exception: Pointer to a function that will do any cleanup work * for the I/O driver. - * @is_console: 1 if the end device is a console 0 if the I/O device is - * not a console + * @cons: valid if the I/O device is a console; else NULL. */ struct kgdb_io { const char *name; @@ -288,7 +287,7 @@ struct kgdb_io { void (*deinit) (void); void (*pre_exception) (void); void (*post_exception) (void); - int is_console; + struct console *cons; }; extern const struct kgdb_arch arch_kgdb_ops; -- cgit v1.2.3 From 5c45a918263e4da142b9cf40a1dfcb4134d454a2 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 23 Jun 2020 09:08:59 +0200 Subject: net: netdevice.h: add a description for napi_defer_hard_irqs Changeset 6f8b12d661d0 ("net: napi: add hard irqs deferral feature") added a new element at struct net_device. Add a description for it, based on what's described at the changeset which added such feature. Fixes: 6f8b12d661d0 ("net: napi: add hard irqs deferral feature") Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/807a3840e7bc1562adefadb0535c9f47e6ab52e0.1592895969.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6fc613ed8eae..f3ca52958a17 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1742,6 +1742,8 @@ enum netdev_priv_flags { * @real_num_rx_queues: Number of RX queues currently active in device * @xdp_prog: XDP sockets filter program pointer * @gro_flush_timeout: timeout for GRO layer in NAPI + * @napi_defer_hard_irqs: If not zero, provides a counter that would + * allow to avoid NIC hard IRQ, on busy queues. * * @rx_handler: handler for received packets * @rx_handler_data: XXX: need comments on this one -- cgit v1.2.3 From 5d682f5ec9d1c49e7fe2945e586aa264692859f0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 23 Jun 2020 09:09:01 +0200 Subject: net: pylink.h: add kernel-doc descriptions for new fields at phylink_config Some fields were moved from struct phylink into phylink_config. Update the kernel-doc markups for the config struct accordingly Fixes: 5c05c1dbb177 ("net: phylink, dsa: eliminate phylink_fixed_state_cb()") Reviewed-by: Russell King Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/34970f447ff86415a6cef10a785fbef81c2819a7.1592895969.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/phylink.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index cc5b452a184e..02ff1419d4be 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -62,6 +62,10 @@ enum phylink_op_type { * @dev: a pointer to a struct device associated with the MAC * @type: operation type of PHYLINK instance * @pcs_poll: MAC PCS cannot provide link change interrupt + * @poll_fixed_state: if true, starts link_poll, + * if MAC link is at %MLO_AN_FIXED mode. + * @get_fixed_state: callback to execute to determine the fixed link state, + * if MAC link is at %MLO_AN_FIXED mode. */ struct phylink_config { struct device *dev; -- cgit v1.2.3 From 21b9cb34385d93d661a9134adf19eae2bd734218 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 23 Jun 2020 09:09:03 +0200 Subject: fs: fs.h: fix a kernel-doc parameter description Changeset 3b0311e7ca71 ("vfs: track per-sb writeback errors and report them to syncfs") added a variant of filemap_sample_wb_err(), but it forgot to rename the arguments at the kernel-doc markup. Fix it. Fix those warnings: ./include/linux/fs.h:2845: warning: Function parameter or member 'file' not described in 'file_sample_sb_err' ./include/linux/fs.h:2845: warning: Excess function parameter 'mapping' description in 'file_sample_sb_err' Fixes: 3b0311e7ca71 ("vfs: track per-sb writeback errors and report them to syncfs") Signed-off-by: Mauro Carvalho Chehab Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/7b33bbceb29ac80874622a2bc84127bb10103245.1592895969.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6c4ab4dc1cd7..7e17ecc461d5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2829,7 +2829,7 @@ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) /** * file_sample_sb_err - sample the current errseq_t to test for later errors - * @mapping: mapping to be sampled + * @file: file pointer to be sampled * * Grab the most current superblock-level errseq_t value for the given * struct file. -- cgit v1.2.3 From 15d737f8a14e73fcf25f6f797630279a203ce99c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 23 Jun 2020 09:09:04 +0200 Subject: kcsan: fix a kernel-doc warning One of the kernel-doc markups there have two "note" sections: ./include/linux/kcsan-checks.h:346: warning: duplicate section name 'Note' While this is not the case here, duplicated sections can cause build issues on Sphinx. So, let's change the notes section to use, instead, a list for those 2 notes at the same function. Signed-off-by: Mauro Carvalho Chehab Acked-by: Marco Elver Link: https://lore.kernel.org/r/20f7995fab2ba85ce723203e9a7c822a55cca2af.1592895969.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/kcsan-checks.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 7b0b9c44f5f3..c5f6c1dcf7e3 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -337,11 +337,13 @@ static inline void __kcsan_disable_current(void) { } * release_for_reuse(obj); * } * - * Note: ASSERT_EXCLUSIVE_ACCESS_SCOPED(), if applicable, performs more thorough - * checking if a clear scope where no concurrent accesses are expected exists. + * Note: * - * Note: For cases where the object is freed, `KASAN `_ is a better - * fit to detect use-after-free bugs. + * 1. ASSERT_EXCLUSIVE_ACCESS_SCOPED(), if applicable, performs more thorough + * checking if a clear scope where no concurrent accesses are expected exists. + * + * 2. For cases where the object is freed, `KASAN `_ is a better + * fit to detect use-after-free bugs. * * @var: variable to assert on */ -- cgit v1.2.3 From 985098a05eee6bf5caca7e997e02a5b15242cfa0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 23 Jun 2020 09:09:10 +0200 Subject: docs: fix references for DMA*.txt files As we moved those files to core-api, fix references to point to their newer locations. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/37b2fd159fbc7655dbf33b3eb1215396a25f6344.1592895969.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/dma-mapping.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 78f677cf45ab..ef2b153ddbd9 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -14,7 +14,7 @@ /** * List of possible attributes associated with a DMA mapping. The semantics - * of each attribute should be defined in Documentation/DMA-attributes.txt. + * of each attribute should be defined in Documentation/core-api/dma-attributes.rst. */ /* -- cgit v1.2.3 From 333740981f94fa80326cc8e5d2da105f17bc1dd5 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 26 Jun 2020 17:53:23 +0200 Subject: net: mdio: add a forward declaration for reset_control to mdio.h This header refers to struct reset_control but doesn't include any reset header. The structure definition is probably somehow indirectly pulled in since no warnings are reported but for the sake of correctness add the forward declaration for struct reset_control. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 36d2e0673d03..898cbf00332a 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -18,6 +18,7 @@ struct gpio_desc; struct mii_bus; +struct reset_control; /* Multiple levels of nesting are possible. However typically this is * limited to nested DSA like layer, a MUX layer, and the normal -- cgit v1.2.3 From adf4f9d49c74a812757c5c67879ece0e54b75417 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 7 Jun 2020 23:51:23 +0200 Subject: irqchip/vic: Drop cascaded intialization call We got rid of the last user of the cascaded intialization from board files so drop this API. Signed-off-by: Linus Walleij Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20200607215124.48638-1-linus.walleij@linaro.org --- include/linux/irqchip/arm-vic.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-vic.h b/include/linux/irqchip/arm-vic.h index a158b97242c7..2a4b6a5d8522 100644 --- a/include/linux/irqchip/arm-vic.h +++ b/include/linux/irqchip/arm-vic.h @@ -19,7 +19,5 @@ struct pt_regs; void __vic_init(void __iomem *base, int parent_irq, int irq_start, u32 vic_sources, u32 resume_sources, struct device_node *node); void vic_init(void __iomem *base, unsigned int irq_start, u32 vic_sources, u32 resume_sources); -int vic_init_cascaded(void __iomem *base, unsigned int parent_irq, - u32 vic_sources, u32 resume_sources); #endif -- cgit v1.2.3 From b0b92ab6a86e59779c2b17c5f611b04120fdfbb6 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 7 Jun 2020 23:51:24 +0200 Subject: irqchip/vic: Cut down the external API There are registers and functions in the header file that are only used inside the driver. Move these into the driver. Signed-off-by: Linus Walleij Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20200607215124.48638-2-linus.walleij@linaro.org --- include/linux/irqchip/arm-vic.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-vic.h b/include/linux/irqchip/arm-vic.h index 2a4b6a5d8522..f2b11d1df23d 100644 --- a/include/linux/irqchip/arm-vic.h +++ b/include/linux/irqchip/arm-vic.h @@ -9,15 +9,6 @@ #include -#define VIC_RAW_STATUS 0x08 -#define VIC_INT_ENABLE 0x10 /* 1 = enable, 0 = disable */ -#define VIC_INT_ENABLE_CLEAR 0x14 - -struct device_node; -struct pt_regs; - -void __vic_init(void __iomem *base, int parent_irq, int irq_start, - u32 vic_sources, u32 resume_sources, struct device_node *node); void vic_init(void __iomem *base, unsigned int irq_start, u32 vic_sources, u32 resume_sources); #endif -- cgit v1.2.3 From 89778093d38d547cd80f6097659d1cf1c2dd4d9d Mon Sep 17 00:00:00 2001 From: Oscar Carter Date: Sat, 30 May 2020 16:34:28 +0200 Subject: drivers/acpi: Add new macro ACPI_DECLARE_SUBTABLE_PROBE_ENTRY In an effort to enable -Wcast-function-type in the top-level Makefile to support Control Flow Integrity builds, there are the need to remove all the function callback casts. To do this, create a new macro called ACPI_DECLARE_SUBTABLE_PROBE_ENTRY to initialize the acpi_probe_entry struct using the probe_subtbl field instead of the probe_table field. This is a previous work to be able to modify the IRQCHIP_ACPI_DECLARE macro to use this new defined macro. Even though these two commented fields are part of a union, this is necessary to avoid function cast mismatches. That is, due to the IRQCHIP_ACPI_DECLARE invocations use as last parameter a function with the protoype "int (*func)(struct acpi_subtable_header *, const unsigned long)" it's necessary that this macro initialize the probe_subtbl field of the acpi_probe_entry struct and not the probe_table field. Co-developed-by: Marc Zyngier Signed-off-by: Marc Zyngier Signed-off-by: Oscar Carter Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20200530143430.5203-2-oscar.carter@gmx.com --- include/linux/acpi.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d661cd0ee64d..cf74e044a570 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1154,6 +1154,17 @@ struct acpi_probe_entry { .driver_data = data, \ } +#define ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(table, name, table_id, \ + subtable, valid, data, fn) \ + static const struct acpi_probe_entry __acpi_probe_##name \ + __used __section(__##table##_acpi_probe_table) = { \ + .id = table_id, \ + .type = subtable, \ + .subtable_valid = valid, \ + .probe_subtbl = fn, \ + .driver_data = data, \ + } + #define ACPI_PROBE_TABLE(name) __##name##_acpi_probe_table #define ACPI_PROBE_TABLE_END(name) __##name##_acpi_probe_table_end -- cgit v1.2.3 From aba3c7ed3fcf74524b7072615028827d5e5750d7 Mon Sep 17 00:00:00 2001 From: Oscar Carter Date: Sat, 30 May 2020 16:34:29 +0200 Subject: drivers/irqchip: Use new macro ACPI_DECLARE_SUBTABLE_PROBE_ENTRY In an effort to enable -Wcast-function-type in the top-level Makefile to support Control Flow Integrity builds, there are the need to remove all the function callback casts. To do this, modify the IRQCHIP_ACPI_DECLARE macro to use the new defined macro ACPI_DECLARE_SUBTABLE_PROBE_ENTRY instead of the macro ACPI_DECLARE_PROBE_ENTRY. This is necessary to be able to initialize the the acpi_probe_entry struct using the probe_subtbl field instead of the probe_table field and avoid function cast mismatches. Also, modify the prototype of the functions used by the invocation of the IRQCHIP_ACPI_DECLARE macro to match all the parameters. Co-developed-by: Marc Zyngier Signed-off-by: Marc Zyngier Signed-off-by: Oscar Carter Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20200530143430.5203-3-oscar.carter@gmx.com --- include/linux/irqchip.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index 950e4b2458f0..447f22880a69 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -39,8 +39,9 @@ * @fn: initialization function */ #define IRQCHIP_ACPI_DECLARE(name, subtable, validate, data, fn) \ - ACPI_DECLARE_PROBE_ENTRY(irqchip, name, ACPI_SIG_MADT, \ - subtable, validate, data, fn) + ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(irqchip, name, \ + ACPI_SIG_MADT, subtable, \ + validate, data, fn) #ifdef CONFIG_IRQCHIP void irqchip_init(void); -- cgit v1.2.3 From 8ebf642f3d809b59f57d0d408189a2218294e269 Mon Sep 17 00:00:00 2001 From: Oscar Carter Date: Sat, 30 May 2020 16:34:30 +0200 Subject: drivers/acpi: Remove function cast Remove the function cast in the ACPI_DECLARE_PROBE_ENTRY macro to ensure that the functions passed as a last parameter to this macro have the right prototype. This is an effort to enable -Wcast-function-type in the top-level Makefile to support Control Flow Integrity builds. Suggested-by: Marc Zyngier Signed-off-by: Oscar Carter Signed-off-by: Marc Zyngier Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20200530143430.5203-4-oscar.carter@gmx.com --- include/linux/acpi.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index cf74e044a570..1cda2d32e4c4 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1143,16 +1143,16 @@ struct acpi_probe_entry { kernel_ulong_t driver_data; }; -#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \ +#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, \ + valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ - __used __section(__##table##_acpi_probe_table) \ - = { \ + __used __section(__##table##_acpi_probe_table) = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ - .probe_table = (acpi_tbl_table_handler)fn, \ - .driver_data = data, \ - } + .probe_table = fn, \ + .driver_data = data, \ + } #define ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(table, name, table_id, \ subtable, valid, data, fn) \ -- cgit v1.2.3 From 167cbce27444be3203081b97ea65178c4088b062 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 10 Jun 2020 17:51:21 +0200 Subject: serial: core: drop unnecessary gpio include Drop the recently added gpio include from the serial-core header in favour of a forward declaration and instead include the gpio header only where needed. Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20200610155121.14014-1-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 9fd550e7946a..653c653ad0c2 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include @@ -30,6 +29,7 @@ struct uart_port; struct serial_struct; struct device; +struct gpio_desc; /* * This structure describes all the operations that can be done on the -- cgit v1.2.3 From 10652a9e9fe3fbcaca090f99cd3060ac3fee2913 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 10 Jun 2020 17:22:30 +0200 Subject: Revert "serial: core: Refactor uart_unlock_and_check_sysrq()" This reverts commit da9a5aa3402db0ff3b57216d8dbf2478e1046cae. In order to ease backporting a fix for a sysrq regression, revert this rewrite which was since added on top. The other sysrq helpers now bail out early when sysrq is not enabled; it's better to keep that pattern here as well. Note that the __releases() attribute won't be needed after the follow-on fix either. Fixes: da9a5aa3402d ("serial: core: Refactor uart_unlock_and_check_sysrq()") Cc: stable Signed-off-by: Johan Hovold Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200610152232.16925-2-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 9fd550e7946a..ef4921ddbe97 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -464,7 +464,8 @@ extern void uart_insert_char(struct uart_port *port, unsigned int status, extern int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch); extern int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch); -extern void uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long flags); +extern void uart_unlock_and_check_sysrq(struct uart_port *port, + unsigned long irqflags); extern int uart_handle_break(struct uart_port *port); /* -- cgit v1.2.3 From 08d5470308ac3598e7709d08b8979ce6e9de8da2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 10 Jun 2020 17:22:31 +0200 Subject: serial: core: fix sysrq overhead regression Commit 8e20fc391711 ("serial_core: Move sysrq functions from header file") converted the inline sysrq helpers to exported functions which are now called for every received character, interrupt and break signal also on systems without CONFIG_MAGIC_SYSRQ_SERIAL instead of being optimised away by the compiler. Inlining these helpers again also avoids the function call overhead when CONFIG_MAGIC_SYSRQ_SERIAL is enabled (e.g. when the port is not used as a console). Fixes: 8e20fc391711 ("serial_core: Move sysrq functions from header file") Cc: Dmitry Safonov <0x7f454c46@gmail.com> Signed-off-by: Johan Hovold Cc: stable Reviewed-by: Andy Shevchenko Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com> Link: https://lore.kernel.org/r/20200610152232.16925-3-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 103 +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 98 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index ef4921ddbe97..03fa7b967103 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -462,11 +462,104 @@ extern void uart_handle_cts_change(struct uart_port *uport, extern void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, unsigned int ch, unsigned int flag); -extern int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch); -extern int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch); -extern void uart_unlock_and_check_sysrq(struct uart_port *port, - unsigned long irqflags); -extern int uart_handle_break(struct uart_port *port); +#ifdef CONFIG_MAGIC_SYSRQ_SERIAL +#define SYSRQ_TIMEOUT (HZ * 5) + +bool uart_try_toggle_sysrq(struct uart_port *port, unsigned int ch); + +static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) +{ + if (!port->has_sysrq || !port->sysrq) + return 0; + + if (ch && time_before(jiffies, port->sysrq)) { + if (sysrq_mask()) { + handle_sysrq(ch); + port->sysrq = 0; + return 1; + } + if (uart_try_toggle_sysrq(port, ch)) + return 1; + } + port->sysrq = 0; + + return 0; +} + +static inline int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch) +{ + if (!port->has_sysrq || !port->sysrq) + return 0; + + if (ch && time_before(jiffies, port->sysrq)) { + if (sysrq_mask()) { + port->sysrq_ch = ch; + port->sysrq = 0; + return 1; + } + if (uart_try_toggle_sysrq(port, ch)) + return 1; + } + port->sysrq = 0; + + return 0; +} + +static inline void uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags) +{ + int sysrq_ch; + + if (!port->has_sysrq) { + spin_unlock_irqrestore(&port->lock, irqflags); + return; + } + + sysrq_ch = port->sysrq_ch; + port->sysrq_ch = 0; + + spin_unlock_irqrestore(&port->lock, irqflags); + + if (sysrq_ch) + handle_sysrq(sysrq_ch); +} +#else /* CONFIG_MAGIC_SYSRQ_SERIAL */ +static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) +{ + return 0; +} +static inline int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch) +{ + return 0; +} +static inline void uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags) +{ + spin_unlock_irqrestore(&port->lock, irqflags); +} +#endif /* CONFIG_MAGIC_SYSRQ_SERIAL */ + +/* + * We do the SysRQ and SAK checking like this... + */ +static inline int uart_handle_break(struct uart_port *port) +{ + struct uart_state *state = port->state; + + if (port->handle_break) + port->handle_break(port); + +#ifdef CONFIG_MAGIC_SYSRQ_SERIAL + if (port->has_sysrq && uart_console(port)) { + if (!port->sysrq) { + port->sysrq = jiffies + SYSRQ_TIMEOUT; + return 1; + } + port->sysrq = 0; + } +#endif + if (port->flags & UPF_SAK) + do_SAK(state->port.tty); + return 0; +} /* * UART_ENABLE_MS - determine if port should enable modem status irqs -- cgit v1.2.3 From 225385657b7d81a99e17e04cd01f9ed5bb3109a8 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 10 Jun 2020 17:22:32 +0200 Subject: serial: core: drop redundant sysrq checks The sysrq timestamp will never be set unless port->has_sysrq is set (see uart_handle_break()) so drop the redundant checks that were added by commit 1997e9dfdc84 ("serial_core: Un-ifdef sysrq SUPPORT_SYSRQ"). Signed-off-by: Johan Hovold Reviewed-by: Andy Shevchenko Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com> Link: https://lore.kernel.org/r/20200610152232.16925-4-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 03fa7b967103..791f4844efeb 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -469,7 +469,7 @@ bool uart_try_toggle_sysrq(struct uart_port *port, unsigned int ch); static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) { - if (!port->has_sysrq || !port->sysrq) + if (!port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { @@ -488,7 +488,7 @@ static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch static inline int uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch) { - if (!port->has_sysrq || !port->sysrq) + if (!port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { -- cgit v1.2.3 From 9205d7b1c1cffa827c23bdbf35e04c7cbe1e1f10 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Thu, 25 Jun 2020 22:59:41 -0700 Subject: net/mlx5: Avoid RDMA file inclusion in core driver mlx5 cq.h does not depend on RDMA verbs. Remove RDMA verbs file inclusion. Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/cq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index b5a9399e07ee..7bfb67363434 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -33,7 +33,6 @@ #ifndef MLX5_CORE_CQ_H #define MLX5_CORE_CQ_H -#include #include #include -- cgit v1.2.3 From 2d1b69ed65ee033aa541518cc9f6a815296ac493 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 25 Jun 2020 22:59:43 -0700 Subject: net/mlx5: kTLS, Improve TLS params layout structures Add explicit WQE segment structures for the TLS static and progress params. According to the HW spec, TISN is not part of the progress params context, take it out of it. Rename the control segment tisn field as it could hold either a TIS or a TIR number. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 9 +++++++++ include/linux/mlx5/mlx5_ifc.h | 5 +---- include/linux/mlx5/qp.h | 2 +- 3 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 1bc27aca648b..57db125e5802 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -458,6 +458,15 @@ enum { MLX5_OPC_MOD_TLS_TIR_PROGRESS_PARAMS = 0x2, }; +struct mlx5_wqe_tls_static_params_seg { + u8 ctx[MLX5_ST_SZ_BYTES(tls_static_params)]; +}; + +struct mlx5_wqe_tls_progress_params_seg { + __be32 tis_tir_num; + u8 ctx[MLX5_ST_SZ_BYTES(tls_progress_params)]; +}; + enum { MLX5_SET_PORT_RESET_QKEY = 0, MLX5_SET_PORT_GUID0 = 16, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 116bd9bb347f..a227518c70cf 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10638,16 +10638,13 @@ struct mlx5_ifc_tls_static_params_bits { }; struct mlx5_ifc_tls_progress_params_bits { - u8 reserved_at_0[0x8]; - u8 tisn[0x18]; - u8 next_record_tcp_sn[0x20]; u8 hw_resync_tcp_sn[0x20]; u8 record_tracker_state[0x2]; u8 auth_state[0x2]; - u8 reserved_at_64[0x4]; + u8 reserved_at_44[0x4]; u8 hw_offset_record_number[0x18]; }; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index b8992b861ae6..36492a1342cf 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -209,7 +209,7 @@ struct mlx5_wqe_ctrl_seg { __be32 general_id; __be32 imm; __be32 umr_mkey; - __be32 tisn; + __be32 tis_tir_num; }; }; -- cgit v1.2.3 From 4f311afc2035f7b33d97e69ffaa2e6cd67fca16d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 10 Jun 2020 12:14:09 +0200 Subject: sched/core: Fix CONFIG_GCC_PLUGIN_RANDSTRUCT build fail As a temporary build fix, the proper cleanup needs more work. Reported-by: Guenter Roeck Reported-by: Eric Biggers Suggested-by: Eric Biggers Suggested-by: Kees Cook Fixes: a148866489fb ("sched: Replace rq::wake_list") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar --- include/linux/sched.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b62e6aaf28f0..224b5de568e7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -654,8 +654,10 @@ struct task_struct { unsigned int ptrace; #ifdef CONFIG_SMP - struct llist_node wake_entry; - unsigned int wake_entry_type; + struct { + struct llist_node wake_entry; + unsigned int wake_entry_type; + }; int on_cpu; #ifdef CONFIG_THREAD_INFO_IN_TASK /* Current CPU: */ -- cgit v1.2.3 From 8c4890d1c3358fb8023d46e1e554c41d54f02878 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 22 Jun 2020 12:01:25 +0200 Subject: smp, irq_work: Continue smp_call_function*() and irq_work*() integration Instead of relying on BUG_ON() to ensure the various data structures line up, use a bunch of horrible unions to make it all automatic. Much of the union magic is to ensure irq_work and smp_call_function do not (yet) see the members of their respective data structures change name. Suggested-by: Linus Torvalds Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Frederic Weisbecker Link: https://lkml.kernel.org/r/20200622100825.844455025@infradead.org --- include/linux/irq_work.h | 26 ++++++------------- include/linux/sched.h | 5 +--- include/linux/smp.h | 23 ++++++----------- include/linux/smp_types.h | 66 +++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 83 insertions(+), 37 deletions(-) create mode 100644 include/linux/smp_types.h (limited to 'include/linux') diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 2735da5f839e..30823780c192 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -2,7 +2,7 @@ #ifndef _LINUX_IRQ_WORK_H #define _LINUX_IRQ_WORK_H -#include +#include /* * An entry can be in one of four states: @@ -13,24 +13,14 @@ * busy NULL, 2 -> {free, claimed} : callback in progress, can be claimed */ -/* flags share CSD_FLAG_ space */ - -#define IRQ_WORK_PENDING BIT(0) -#define IRQ_WORK_BUSY BIT(1) - -/* Doesn't want IPI, wait for tick: */ -#define IRQ_WORK_LAZY BIT(2) -/* Run hard IRQ context, even on RT */ -#define IRQ_WORK_HARD_IRQ BIT(3) - -#define IRQ_WORK_CLAIMED (IRQ_WORK_PENDING | IRQ_WORK_BUSY) - -/* - * structure shares layout with single_call_data_t. - */ struct irq_work { - struct llist_node llnode; - atomic_t flags; + union { + struct __call_single_node node; + struct { + struct llist_node llnode; + atomic_t flags; + }; + }; void (*func)(struct irq_work *); }; diff --git a/include/linux/sched.h b/include/linux/sched.h index 224b5de568e7..692e327d7455 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -654,11 +654,8 @@ struct task_struct { unsigned int ptrace; #ifdef CONFIG_SMP - struct { - struct llist_node wake_entry; - unsigned int wake_entry_type; - }; int on_cpu; + struct __call_single_node wake_entry; #ifdef CONFIG_THREAD_INFO_IN_TASK /* Current CPU: */ unsigned int cpu; diff --git a/include/linux/smp.h b/include/linux/smp.h index 7ee202ad21a6..80d557ef8a11 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -12,29 +12,22 @@ #include #include #include -#include +#include typedef void (*smp_call_func_t)(void *info); typedef bool (*smp_cond_func_t)(int cpu, void *info); -enum { - CSD_FLAG_LOCK = 0x01, - - /* IRQ_WORK_flags */ - - CSD_TYPE_ASYNC = 0x00, - CSD_TYPE_SYNC = 0x10, - CSD_TYPE_IRQ_WORK = 0x20, - CSD_TYPE_TTWU = 0x30, - CSD_FLAG_TYPE_MASK = 0xF0, -}; - /* * structure shares (partial) layout with struct irq_work */ struct __call_single_data { - struct llist_node llist; - unsigned int flags; + union { + struct __call_single_node node; + struct { + struct llist_node llist; + unsigned int flags; + }; + }; smp_call_func_t func; void *info; }; diff --git a/include/linux/smp_types.h b/include/linux/smp_types.h new file mode 100644 index 000000000000..364b3ae3e41d --- /dev/null +++ b/include/linux/smp_types.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_SMP_TYPES_H +#define __LINUX_SMP_TYPES_H + +#include + +enum { + CSD_FLAG_LOCK = 0x01, + + IRQ_WORK_PENDING = 0x01, + IRQ_WORK_BUSY = 0x02, + IRQ_WORK_LAZY = 0x04, /* No IPI, wait for tick */ + IRQ_WORK_HARD_IRQ = 0x08, /* IRQ context on PREEMPT_RT */ + + IRQ_WORK_CLAIMED = (IRQ_WORK_PENDING | IRQ_WORK_BUSY), + + CSD_TYPE_ASYNC = 0x00, + CSD_TYPE_SYNC = 0x10, + CSD_TYPE_IRQ_WORK = 0x20, + CSD_TYPE_TTWU = 0x30, + + CSD_FLAG_TYPE_MASK = 0xF0, +}; + +/* + * struct __call_single_node is the primary type on + * smp.c:call_single_queue. + * + * flush_smp_call_function_queue() only reads the type from + * __call_single_node::u_flags as a regular load, the above + * (anonymous) enum defines all the bits of this word. + * + * Other bits are not modified until the type is known. + * + * CSD_TYPE_SYNC/ASYNC: + * struct { + * struct llist_node node; + * unsigned int flags; + * smp_call_func_t func; + * void *info; + * }; + * + * CSD_TYPE_IRQ_WORK: + * struct { + * struct llist_node node; + * atomic_t flags; + * void (*func)(struct irq_work *); + * }; + * + * CSD_TYPE_TTWU: + * struct { + * struct llist_node node; + * unsigned int flags; + * }; + * + */ + +struct __call_single_node { + struct llist_node llist; + union { + unsigned int u_flags; + atomic_t a_flags; + }; +}; + +#endif /* __LINUX_SMP_TYPES_H */ -- cgit v1.2.3 From bfe373f608cf81b7626dfeb904001b0e867c5110 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Tue, 28 Apr 2020 09:54:56 +0800 Subject: blk-mq-debugfs: update blk_queue_flag_name[] accordingly for new flags Else there may be magic numbers in /sys/kernel/debug/block/*/state. Signed-off-by: Hou Tao Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8fd900998b4e..57241417ff2f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -590,6 +590,7 @@ struct request_queue { u64 write_hints[BLK_MAX_WRITE_HINTS]; }; +/* Keep blk_queue_flag_name[] in sync with the definitions below */ #define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ #define QUEUE_FLAG_DYING 1 /* queue being torn down */ #define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ -- cgit v1.2.3 From db9819c76c1fd48c30699381c94bba5c95dd467e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 27 Jun 2020 09:31:47 +0200 Subject: block: remove bio_disassociate_blkg bio_disassociate_blkg has two callers, of which one immediately assigns a new value to >bi_blkg. Just open code the function in the two callers. Acked-by: Tejun Heo Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 0282f8aa8593..4cd229e175c0 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -497,13 +497,11 @@ static inline void bio_associate_blkg_from_page(struct bio *bio, #endif #ifdef CONFIG_BLK_CGROUP -void bio_disassociate_blkg(struct bio *bio); void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); void bio_clone_blkg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ -static inline void bio_disassociate_blkg(struct bio *bio) { } static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) -- cgit v1.2.3 From a18b9b1590ca64f877588700de32c9ad236f405c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 27 Jun 2020 09:31:50 +0200 Subject: block: move bio_associate_blkg_from_page to mm/page_io.c bio_associate_blkg_from_page is a special purpose helper for swap bios that doesn't need access to bio internals. Move it to the swap code instead of having it in bio.c. Acked-by: Tejun Heo Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 4cd229e175c0..c6d765382926 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -489,13 +489,6 @@ do { \ #define bio_dev(bio) \ disk_devt((bio)->bi_disk) -#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -void bio_associate_blkg_from_page(struct bio *bio, struct page *page); -#else -static inline void bio_associate_blkg_from_page(struct bio *bio, - struct page *page) { } -#endif - #ifdef CONFIG_BLK_CGROUP void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, -- cgit v1.2.3 From 28fc591ff9d64cbc2b780be95ee3fde8f6ade7fd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 27 Jun 2020 09:31:51 +0200 Subject: block: move the bio cgroup associatation helpers to blk-cgroup.c Keep the cgroup code together. Acked-by: Tejun Heo Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 30 ------------------------------ 1 file changed, 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index a57ebe2f00ab..60df97202314 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -183,10 +183,6 @@ extern bool blkcg_debug_stats; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); -struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q); -struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q); int blkcg_init_queue(struct request_queue *q); void blkcg_exit_queue(struct request_queue *q); @@ -480,32 +476,6 @@ static inline bool blkg_tryget(struct blkcg_gq *blkg) return blkg && percpu_ref_tryget(&blkg->refcnt); } -/** - * blkg_tryget_closest - try and get a blkg ref on the closet blkg - * @blkg: blkg to get - * - * This needs to be called rcu protected. As the failure mode here is to walk - * up the blkg tree, this ensure that the blkg->parent pointers are always - * valid. This returns the blkg that it ended up taking a reference on or %NULL - * if no reference was taken. - */ -static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) -{ - struct blkcg_gq *ret_blkg = NULL; - - WARN_ON_ONCE(!rcu_read_lock_held()); - - while (blkg) { - if (blkg_tryget(blkg)) { - ret_blkg = blkg; - break; - } - blkg = blkg->parent; - } - - return ret_blkg; -} - /** * blkg_put - put a blkg reference * @blkg: blkg to put -- cgit v1.2.3 From 81630e27fff3dc1ccbf64ecb48a70170d7071545 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 27 Jun 2020 09:31:55 +0200 Subject: blk-cgroup: remove the !bio->bi_blkg check in blkcg_bio_issue_check This is purely a sanity check for grave programming errors. Remove it to simplify further work in this area. Acked-by: Tejun Heo Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 60df97202314..8e86b598316c 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -543,24 +543,11 @@ static inline void blkcg_bio_issue_init(struct bio *bio) static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { - struct blkcg_gq *blkg; + struct blkcg_gq *blkg = bio->bi_blkg; bool throtl = false; rcu_read_lock(); - - if (!bio->bi_blkg) { - char b[BDEVNAME_SIZE]; - - WARN_ONCE(1, - "no blkg associated for bio on block-device: %s\n", - bio_devname(bio, b)); - bio_associate_blkg(bio); - } - - blkg = bio->bi_blkg; - throtl = blk_throtl_bio(q, blkg, bio); - if (!throtl) { struct blkg_iostat_set *bis; int rwd, cpu; -- cgit v1.2.3 From 93b8063804b62b55248e16499d853e1b20eff905 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 27 Jun 2020 09:31:57 +0200 Subject: blk-cgroup: move rcu locking from blkcg_bio_issue_check to blk_throtl_bio The only thing in blkcg_bio_issue_check that needs to be under rcu_read_lock is blk_throtl_bio, so move the locking there. Acked-by: Tejun Heo Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 8e86b598316c..8ab043c911f2 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -546,7 +546,6 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, struct blkcg_gq *blkg = bio->bi_blkg; bool throtl = false; - rcu_read_lock(); throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { struct blkg_iostat_set *bis; @@ -582,7 +581,6 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkcg_bio_issue_init(bio); - rcu_read_unlock(); return !throtl; } -- cgit v1.2.3 From db18a53e5ba840993a3fc908dec648402ed740bd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 27 Jun 2020 09:31:58 +0200 Subject: blk-cgroup: remove blkcg_bio_issue_check blkcg_bio_issue_check is a giant inline function that does three entirely different things. Factor out the blk-cgroup related bio initalization into a new helper, and the open code the sequence in the only caller, relying on the fact that all the actual functionality is stubbed out for non-cgroup builds. Acked-by: Tejun Heo Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 56 ++-------------------------------------------- 1 file changed, 2 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 8ab043c911f2..431b2d18bf40 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -517,14 +517,6 @@ static inline void blkg_put(struct blkcg_gq *blkg) if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) -#ifdef CONFIG_BLK_DEV_THROTTLING -extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, - struct bio *bio); -#else -static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, - struct bio *bio) { return false; } -#endif - bool __blkcg_punt_bio_submit(struct bio *bio); static inline bool blkcg_punt_bio_submit(struct bio *bio) @@ -540,50 +532,6 @@ static inline void blkcg_bio_issue_init(struct bio *bio) bio_issue_init(&bio->bi_issue, bio_sectors(bio)); } -static inline bool blkcg_bio_issue_check(struct request_queue *q, - struct bio *bio) -{ - struct blkcg_gq *blkg = bio->bi_blkg; - bool throtl = false; - - throtl = blk_throtl_bio(q, blkg, bio); - if (!throtl) { - struct blkg_iostat_set *bis; - int rwd, cpu; - - if (op_is_discard(bio->bi_opf)) - rwd = BLKG_IOSTAT_DISCARD; - else if (op_is_write(bio->bi_opf)) - rwd = BLKG_IOSTAT_WRITE; - else - rwd = BLKG_IOSTAT_READ; - - cpu = get_cpu(); - bis = per_cpu_ptr(blkg->iostat_cpu, cpu); - u64_stats_update_begin(&bis->sync); - - /* - * If the bio is flagged with BIO_CGROUP_ACCT it means this is a - * split bio and we would have already accounted for the size of - * the bio. - */ - if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { - bio_set_flag(bio, BIO_CGROUP_ACCT); - bis->cur.bytes[rwd] += bio->bi_iter.bi_size; - } - bis->cur.ios[rwd]++; - - u64_stats_update_end(&bis->sync); - if (cgroup_subsys_on_dfl(io_cgrp_subsys)) - cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu); - put_cpu(); - } - - blkcg_bio_issue_init(bio); - - return !throtl; -} - static inline void blkcg_use_delay(struct blkcg_gq *blkg) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) @@ -657,6 +605,7 @@ static inline void blkcg_clear_delay(struct blkcg_gq *blkg) atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); } +void blk_cgroup_bio_start(struct bio *bio); void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); @@ -710,8 +659,7 @@ static inline void blkg_put(struct blkcg_gq *blkg) { } static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; } static inline void blkcg_bio_issue_init(struct bio *bio) { } -static inline bool blkcg_bio_issue_check(struct request_queue *q, - struct bio *bio) { return true; } +static inline void blk_cgroup_bio_start(struct bio *bio) { } #define blk_queue_for_each_rl(rl, q) \ for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) -- cgit v1.2.3 From 42fdc5e49c2be97db112d410d07044e0e2c7d5bb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Jun 2020 17:08:34 +0200 Subject: blk-mq: remove the BLK_MQ_REQ_INTERNAL flag Just check for a non-NULL elevator directly to make the code more clear. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 1641ec6cd7e5..8986e88a986b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -447,8 +447,6 @@ enum { BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0), /* allocate from reserved pool */ BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1), - /* allocate internal/sched tag */ - BLK_MQ_REQ_INTERNAL = (__force blk_mq_req_flags_t)(1 << 2), /* set RQF_PREEMPT */ BLK_MQ_REQ_PREEMPT = (__force blk_mq_req_flags_t)(1 << 3), }; -- cgit v1.2.3 From cbba1d719534b77b857267890b0f54f0f0a90de4 Mon Sep 17 00:00:00 2001 From: Andrzej Pietrasiewicz Date: Mon, 29 Jun 2020 14:29:17 +0200 Subject: thermal: Add current mode to thermal zone device Prepare for changing the place where the mode is stored: now it is in drivers, which might or might not implement get_mode()/set_mode() methods. A lot of cleanup can be done thanks to storing it in struct tzd. The get_mode() methods will become redundant. Signed-off-by: Andrzej Pietrasiewicz Reviewed-by: Guenter Roeck Reviewed-by: Bartlomiej Zolnierkiewicz Reviewed-by: Amit Kucheria Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20200629122925.21729-4-andrzej.p@collabora.com --- include/linux/thermal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 216185bb3014..5f91d7f04512 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -128,6 +128,7 @@ struct thermal_cooling_device { * @trip_temp_attrs: attributes for trip points for sysfs: trip temperature * @trip_type_attrs: attributes for trip points for sysfs: trip type * @trip_hyst_attrs: attributes for trip points for sysfs: trip hysteresis + * @mode: current mode of this thermal zone * @devdata: private pointer for device private data * @trips: number of trip points the thermal zone supports * @trips_disabled; bitmap for disabled trips @@ -170,6 +171,7 @@ struct thermal_zone_device { struct thermal_attr *trip_temp_attrs; struct thermal_attr *trip_type_attrs; struct thermal_attr *trip_hyst_attrs; + enum thermal_device_mode mode; void *devdata; int trips; unsigned long trips_disabled; /* bitmap for disabled trips */ -- cgit v1.2.3 From 1ee14820fd8ee79c4fc191155f48c985f28040e2 Mon Sep 17 00:00:00 2001 From: Andrzej Pietrasiewicz Date: Mon, 29 Jun 2020 14:29:19 +0200 Subject: thermal: remove get_mode() operation of drivers get_mode() is now redundant, as the state is stored in struct thermal_zone_device. Consequently the "mode" attribute in sysfs can always be visible, because it is always possible to get the mode from struct tzd. Signed-off-by: Andrzej Pietrasiewicz [for acerhdf] Acked-by: Peter Kaestle Reviewed-by: Bartlomiej Zolnierkiewicz Reviewed-by: Amit Kucheria Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20200629122925.21729-6-andrzej.p@collabora.com --- include/linux/thermal.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 5f91d7f04512..a808f6fa2777 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -76,8 +76,6 @@ struct thermal_zone_device_ops { struct thermal_cooling_device *); int (*get_temp) (struct thermal_zone_device *, int *); int (*set_trips) (struct thermal_zone_device *, int, int); - int (*get_mode) (struct thermal_zone_device *, - enum thermal_device_mode *); int (*set_mode) (struct thermal_zone_device *, enum thermal_device_mode); int (*get_trip_type) (struct thermal_zone_device *, int, -- cgit v1.2.3 From ac5d9ecc74d8beee8c87f1441e4adaf4e9fe90c5 Mon Sep 17 00:00:00 2001 From: Andrzej Pietrasiewicz Date: Mon, 29 Jun 2020 14:29:20 +0200 Subject: thermal: Add mode helpers Prepare for making the drivers not access tzd's private members. Signed-off-by: Andrzej Pietrasiewicz Reviewed-by: Bartlomiej Zolnierkiewicz [staticize thermal_zone_device_set_mode()] Signed-off-by: kernel test robot Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20200629122925.21729-7-andrzej.p@collabora.com --- include/linux/thermal.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index a808f6fa2777..df013c39ba9b 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -416,6 +416,9 @@ int thermal_zone_get_offset(struct thermal_zone_device *tz); void thermal_cdev_update(struct thermal_cooling_device *); void thermal_notify_framework(struct thermal_zone_device *, int); +int thermal_zone_device_enable(struct thermal_zone_device *tz); +int thermal_zone_device_disable(struct thermal_zone_device *tz); +int thermal_zone_device_is_enabled(struct thermal_zone_device *tz); #else static inline struct thermal_zone_device *thermal_zone_device_register( const char *type, int trips, int mask, void *devdata, @@ -463,6 +466,16 @@ static inline void thermal_cdev_update(struct thermal_cooling_device *cdev) static inline void thermal_notify_framework(struct thermal_zone_device *tz, int trip) { } + +static inline int thermal_zone_device_enable(struct thermal_zone_device *tz) +{ return -ENODEV; } + +static inline int thermal_zone_device_disable(struct thermal_zone_device *tz) +{ return -ENODEV; } + +static inline int +thermal_zone_device_is_enabled(struct thermal_zone_device *tz) +{ return -ENODEV; } #endif /* CONFIG_THERMAL */ #endif /* __THERMAL_H__ */ -- cgit v1.2.3 From f5e50bf4d3ef0aba4d5414c9ed51fa4a02e2ed12 Mon Sep 17 00:00:00 2001 From: Andrzej Pietrasiewicz Date: Mon, 29 Jun 2020 14:29:25 +0200 Subject: thermal: Rename set_mode() to change_mode() set_mode() is only called when tzd's mode is about to change. Actual setting is performed in thermal_core, in thermal_zone_device_set_mode(). The meaning of set_mode() callback is actually to notify the driver about the mode being changed and giving the driver a chance to oppose such change. To better reflect the purpose of the method rename it to change_mode() Signed-off-by: Andrzej Pietrasiewicz [for acerhdf] Acked-by: Peter Kaestle Reviewed-by: Bartlomiej Zolnierkiewicz Reviewed-by: Amit Kucheria Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20200629122925.21729-12-andrzej.p@collabora.com --- include/linux/thermal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index df013c39ba9b..b9efaa780d88 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -76,7 +76,7 @@ struct thermal_zone_device_ops { struct thermal_cooling_device *); int (*get_temp) (struct thermal_zone_device *, int *); int (*set_trips) (struct thermal_zone_device *, int, int); - int (*set_mode) (struct thermal_zone_device *, + int (*change_mode) (struct thermal_zone_device *, enum thermal_device_mode); int (*get_trip_type) (struct thermal_zone_device *, int, enum thermal_trip_type *); -- cgit v1.2.3 From 2cdb54c93a7e5beb6f3f8b63575d9fb664dfc603 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 21 Apr 2020 19:04:05 +0200 Subject: docs: RCU: Convert rculist_nulls.txt to ReST - Add a SPDX header; - Adjust document title; - Some whitespace fixes and new line breaks; - Mark literal blocks as such; - Add it to RCU/index.rst. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Paul E. McKenney --- include/linux/rculist_nulls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index 9670b54b484a..ff3e94779e73 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -162,7 +162,7 @@ static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n) * The barrier() is needed to make sure compiler doesn't cache first element [1], * as this loop can be restarted [2] * [1] Documentation/core-api/atomic_ops.rst around line 114 - * [2] Documentation/RCU/rculist_nulls.txt around line 146 + * [2] Documentation/RCU/rculist_nulls.rst around line 146 */ #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \ for (({barrier();}), \ -- cgit v1.2.3 From 24692fa22c30cb8fcfcabdc07a3c82964475b639 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 15 Jun 2020 08:46:49 +0200 Subject: rcu: Fix some kernel-doc warnings The current code provokes some kernel-doc warnings: ./kernel/rcu/tree.c:2915: warning: Function parameter or member 'count' not described in 'kfree_rcu_cpu' ./include/linux/rculist.h:517: warning: bad line: [@right ][node2 ... ] ./include/linux/rculist.h:2: WARNING: Unexpected indentation. This commit therefore moves the comment for "count" to the kernel-doc markup and adds a missing "*" on one kernel-doc continuation line. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index df587d181844..7eed65b5f713 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -512,7 +512,7 @@ static inline void hlist_replace_rcu(struct hlist_node *old, * @right: The hlist head on the right * * The lists start out as [@left ][node1 ... ] and - [@right ][node2 ... ] + * [@right ][node2 ... ] * The lists end up as [@left ][node2 ... ] * [@right ][node1 ... ] */ -- cgit v1.2.3 From c408b215f58f7156bb6bafb64c0263ee907033df Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Mon, 25 May 2020 23:47:55 +0200 Subject: rcu: Rename *_kfree_callback/*_kfree_rcu_offset/kfree_call_* The following changes are introduced: 1. Rename rcu_invoke_kfree_callback() to rcu_invoke_kvfree_callback(), as well as the associated trace events, so the rcu_kfree_callback(), becomes rcu_kvfree_callback(). The reason is to be aligned with kvfree() notation. 2. Rename __is_kfree_rcu_offset to __is_kvfree_rcu_offset. All RCU paths use kvfree() now instead of kfree(), thus rename it. 3. Rename kfree_call_rcu() to the kvfree_call_rcu(). The reason is, it is capable of freeing vmalloc() memory now. Do the same with __kfree_rcu() macro, it becomes __kvfree_rcu(), the goal is the same. Reviewed-by: Joel Fernandes (Google) Co-developed-by: Joel Fernandes (Google) Signed-off-by: Joel Fernandes (Google) Signed-off-by: Uladzislau Rezki (Sony) Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 14 +++++++------- include/linux/rcutiny.h | 2 +- include/linux/rcutree.h | 2 +- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 659cbfa7581a..b344fc800a9b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -828,17 +828,17 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) /* * Does the specified offset indicate that the corresponding rcu_head - * structure can be handled by kfree_rcu()? + * structure can be handled by kvfree_rcu()? */ -#define __is_kfree_rcu_offset(offset) ((offset) < 4096) +#define __is_kvfree_rcu_offset(offset) ((offset) < 4096) /* * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain. */ -#define __kfree_rcu(head, offset) \ +#define __kvfree_rcu(head, offset) \ do { \ - BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \ - kfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ + BUILD_BUG_ON(!__is_kvfree_rcu_offset(offset)); \ + kvfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ } while (0) /** @@ -857,7 +857,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will - * be generated in __kfree_rcu(). If this error is triggered, you can + * be generated in __kvfree_rcu(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * @@ -872,7 +872,7 @@ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) \ - __kfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ + __kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ } while (0) /* diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 8512caeb7682..fb2eb39c484f 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -34,7 +34,7 @@ static inline void synchronize_rcu_expedited(void) synchronize_rcu(); } -static inline void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) +static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { call_rcu(head, func); } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index d5cc9d675987..d2f4064ebd1d 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -33,7 +33,7 @@ static inline void rcu_virt_note_context_switch(int cpu) } void synchronize_rcu_expedited(void); -void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); +void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier(void); bool rcu_eqs_special_set(int cpu); -- cgit v1.2.3 From ce4dce123fdcb5f209752d13f9f06926be65fc78 Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Mon, 25 May 2020 23:47:57 +0200 Subject: rcu: Introduce 2 arg kvfree_rcu() interface kvmalloc() can allocate two types of objects: SLAB backed and vmalloc backed. How it behaves depends on requested object's size and memory pressure. Add a kvfree_rcu() interface that can free memory allocated via kvmalloc(). It is a simple alias to kfree_rcu() which can now handle either type of object. struct test_kvfree_rcu { struct rcu_head rcu; unsigned char array[100]; }; struct test_kvfree_rcu *p; p = kvmalloc(10 * PAGE_SIZE); if (p) kvfree_rcu(p, rcu); Signed-off-by: Uladzislau Rezki (Sony) Co-developed-by: Joel Fernandes (Google) Reviewed-by: Joel Fernandes (Google) Signed-off-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b344fc800a9b..51b26ab02878 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -875,6 +875,15 @@ do { \ __kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ } while (0) +/** + * kvfree_rcu() - kvfree an object after a grace period. + * @ptr: pointer to kvfree + * @rhf: the name of the struct rcu_head within the type of @ptr. + * + * Same as kfree_rcu(), just simple alias. + */ +#define kvfree_rcu(ptr, rhf) kfree_rcu(ptr, rhf) + /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies -- cgit v1.2.3 From 3042f83f19bec2e0cd356f72b39e4d816e8cd5ff Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Mon, 25 May 2020 23:47:58 +0200 Subject: rcu: Support reclaim for head-less object Update the kvfree_call_rcu() function with head-less support. This allows RCU to reclaim objects without an embedded rcu_head. tree-RCU: We introduce two chains of arrays to store SLAB-backed and vmalloc pointers, each. Storage in either of these arrays does not require embedding an rcu_head within the object. Maintaining the arrays may become impossible due to high memory pressure. For such cases there is an emergency path. Objects with rcu_head inside are just queued on a backup rcu_head list. Later on that list is drained. As for the head-less variant, as the current context can sleep, the following emergency measures are applied: a) Synchronously wait until a grace period has elapsed. b) Call kvfree(). tiny-RCU: For double argument calls, there are no new changes in behavior. For single argument call, kvfree() is directly inlined on the current stack after a synchronize_rcu() call. Note that for tiny-RCU, any call to synchronize_rcu() is actually a quiescent state, therefore it does nothing. Reviewed-by: Joel Fernandes (Google) Signed-off-by: Uladzislau Rezki (Sony) Signed-off-by: Joel Fernandes (Google) Co-developed-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index fb2eb39c484f..5cc9637cac16 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -34,9 +34,25 @@ static inline void synchronize_rcu_expedited(void) synchronize_rcu(); } +/* + * Add one more declaration of kvfree() here. It is + * not so straight forward to just include + * where it is defined due to getting many compile + * errors caused by that include. + */ +extern void kvfree(const void *addr); + static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { - call_rcu(head, func); + if (head) { + call_rcu(head, func); + return; + } + + // kvfree_rcu(one_arg) call. + might_sleep(); + synchronize_rcu(); + kvfree((void *) func); } void rcu_qs(void); -- cgit v1.2.3 From 1835f475e3518ade61e25a57572c78b953778656 Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Mon, 25 May 2020 23:47:59 +0200 Subject: rcu: Introduce single argument kvfree_rcu() interface Make kvfree_rcu() capable of freeing objects that will not embed an rcu_head within it. This saves storage overhead in such objects. Reclaiming headless objects this way requires only a single argument (pointer to the object). After this patch, there are two ways to use kvfree_rcu(): a) kvfree_rcu(ptr, rhf); struct X { struct rcu_head rhf; unsigned char data[100]; }; void *ptr = kvmalloc(sizeof(struct X), GFP_KERNEL); if (ptr) kvfree_rcu(ptr, rhf); b) kvfree_rcu(ptr); void *ptr = kvmalloc(some_bytes, GFP_KERNEL); if (ptr) kvfree_rcu(ptr); Note that the headless usage (example b) can only be used in a code that can sleep. This is enforced by the CONFIG_DEBUG_ATOMIC_SLEEP option. Co-developed-by: Joel Fernandes (Google) Reviewed-by: Joel Fernandes (Google) Signed-off-by: Uladzislau Rezki (Sony) Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 38 ++++++++++++++++++++++++++++++++++---- 1 file changed, 34 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 51b26ab02878..d15d46db61f7 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -877,12 +877,42 @@ do { \ /** * kvfree_rcu() - kvfree an object after a grace period. - * @ptr: pointer to kvfree - * @rhf: the name of the struct rcu_head within the type of @ptr. * - * Same as kfree_rcu(), just simple alias. + * This macro consists of one or two arguments and it is + * based on whether an object is head-less or not. If it + * has a head then a semantic stays the same as it used + * to be before: + * + * kvfree_rcu(ptr, rhf); + * + * where @ptr is a pointer to kvfree(), @rhf is the name + * of the rcu_head structure within the type of @ptr. + * + * When it comes to head-less variant, only one argument + * is passed and that is just a pointer which has to be + * freed after a grace period. Therefore the semantic is + * + * kvfree_rcu(ptr); + * + * where @ptr is a pointer to kvfree(). + * + * Please note, head-less way of freeing is permitted to + * use from a context that has to follow might_sleep() + * annotation. Otherwise, please switch and embed the + * rcu_head structure within the type of @ptr. */ -#define kvfree_rcu(ptr, rhf) kfree_rcu(ptr, rhf) +#define kvfree_rcu(...) KVFREE_GET_MACRO(__VA_ARGS__, \ + kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__) + +#define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME +#define kvfree_rcu_arg_2(ptr, rhf) kfree_rcu(ptr, rhf) +#define kvfree_rcu_arg_1(ptr) \ +do { \ + typeof(ptr) ___p = (ptr); \ + \ + if (___p) \ + kvfree_call_rcu(NULL, (rcu_callback_t) (___p)); \ +} while (0) /* * Place this after a lock-acquisition primitive to guarantee that -- cgit v1.2.3 From c7dcf8106f7570b133b05ff68fd4100064965d9d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 12 Jun 2020 13:11:29 -0700 Subject: rcu-tasks: Fix synchronize_rcu_tasks_trace() header comment The synchronize_rcu_tasks_trace() header comment incorrectly claims that any number of things delimit RCU Tasks Trace read-side critical sections, when in fact only rcu_read_lock_trace() and rcu_read_unlock_trace() do so. This commit therefore fixes this comment, and, while in the area, fixes a typo in the rcu_read_lock_trace() header comment. Reported-by: Alexei Starovoitov Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_trace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index 4c25a41f8b27..d9015aac78c6 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -36,8 +36,8 @@ void rcu_read_unlock_trace_special(struct task_struct *t, int nesting); /** * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section * - * When synchronize_rcu_trace() is invoked by one task, then that task - * is guaranteed to block until all other tasks exit their read-side + * When synchronize_rcu_tasks_trace() is invoked by one task, then that + * task is guaranteed to block until all other tasks exit their read-side * critical sections. Similarly, if call_rcu_trace() is invoked on one * task while other tasks are within RCU read-side critical sections, * invocation of the corresponding RCU callback is deferred until after -- cgit v1.2.3 From 4a5f133c15b77c4018e8d7996541868ac94afb4f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 24 Apr 2020 11:21:40 -0700 Subject: rcutorture: Add races with task-exit processing Several variants of Linux-kernel RCU interact with task-exit processing, including preemptible RCU, Tasks RCU, and Tasks Trace RCU. This commit therefore adds testing of this interaction to rcutorture by adding rcutorture.read_exit_burst and rcutorture.read_exit_delay kernel-boot parameters. These kernel parameters control the frequency and spacing of special read-then-exit kthreads that are spawned. [ paulmck: Apply feedback from Dan Carpenter's static checker. ] [ paulmck: Reduce latency to avoid false-positive shutdown hangs. ] Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/torture.h b/include/linux/torture.h index 629b66e6c161..7f65bd1dd307 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -55,6 +55,11 @@ struct torture_random_state { #define DEFINE_TORTURE_RANDOM_PERCPU(name) \ DEFINE_PER_CPU(struct torture_random_state, name) unsigned long torture_random(struct torture_random_state *trsp); +static inline void torture_random_init(struct torture_random_state *trsp) +{ + trsp->trs_state = 0; + trsp->trs_count = 0; +} /* Task shuffler, which causes CPUs to occasionally go idle. */ void torture_shuffle_task_register(struct task_struct *tp); -- cgit v1.2.3 From c93773c1a3fedf6c3f6fa12833e2b74a9897c3e3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 12 Feb 2020 13:29:15 -0800 Subject: rculist: Add ASSERT_EXCLUSIVE_ACCESS() to __list_splice_init_rcu() After the sync() in __list_splice_init_rcu(), there should be no readers traversing the old list. This commit therefore enlists the help of KCSAN to verify this condition via a pair of calls to ASSERT_EXCLUSIVE_ACCESS(). Signed-off-by: Paul E. McKenney Cc: Marco Elver --- include/linux/rculist.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index df587d181844..2ebd112f86f7 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -248,6 +248,8 @@ static inline void __list_splice_init_rcu(struct list_head *list, */ sync(); + ASSERT_EXCLUSIVE_ACCESS(*first); + ASSERT_EXCLUSIVE_ACCESS(*last); /* * Readers are finished with the source list, so perform splice. -- cgit v1.2.3 From 0fb8125635e8eb5483fb095f98dcf0651206a7b8 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 9 Jun 2020 22:04:44 +0200 Subject: video: fbdev: amba-clcd: Retire elder CLCD driver All the functionality in this driver has been reimplemented in the new DRM driver in drivers/gpu/drm/pl111/* and all the boards using it have been migrated to use the DRM driver with all configuration coming from the device tree. I started the work to migrate the CLCD driver to DRM in april 2017 and it took a little more than 3 years to do this properly without leaving any platforms behind. Reviewed-by: Eric Anholt Signed-off-by: Linus Walleij Cc: Russell King Link: https://patchwork.freedesktop.org/patch/msgid/20200609200446.153209-2-linus.walleij@linaro.org --- include/linux/amba/clcd.h | 290 ---------------------------------------------- 1 file changed, 290 deletions(-) delete mode 100644 include/linux/amba/clcd.h (limited to 'include/linux') diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h deleted file mode 100644 index b6e0cbeaf533..000000000000 --- a/include/linux/amba/clcd.h +++ /dev/null @@ -1,290 +0,0 @@ -/* - * linux/include/asm-arm/hardware/amba_clcd.h -- Integrator LCD panel. - * - * David A Rusling - * - * Copyright (C) 2001 ARM Limited - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of this archive - * for more details. - */ -#include -#include - -enum { - /* individual formats */ - CLCD_CAP_RGB444 = (1 << 0), - CLCD_CAP_RGB5551 = (1 << 1), - CLCD_CAP_RGB565 = (1 << 2), - CLCD_CAP_RGB888 = (1 << 3), - CLCD_CAP_BGR444 = (1 << 4), - CLCD_CAP_BGR5551 = (1 << 5), - CLCD_CAP_BGR565 = (1 << 6), - CLCD_CAP_BGR888 = (1 << 7), - - /* connection layouts */ - CLCD_CAP_444 = CLCD_CAP_RGB444 | CLCD_CAP_BGR444, - CLCD_CAP_5551 = CLCD_CAP_RGB5551 | CLCD_CAP_BGR5551, - CLCD_CAP_565 = CLCD_CAP_RGB565 | CLCD_CAP_BGR565, - CLCD_CAP_888 = CLCD_CAP_RGB888 | CLCD_CAP_BGR888, - - /* red/blue ordering */ - CLCD_CAP_RGB = CLCD_CAP_RGB444 | CLCD_CAP_RGB5551 | - CLCD_CAP_RGB565 | CLCD_CAP_RGB888, - CLCD_CAP_BGR = CLCD_CAP_BGR444 | CLCD_CAP_BGR5551 | - CLCD_CAP_BGR565 | CLCD_CAP_BGR888, - - CLCD_CAP_ALL = CLCD_CAP_BGR | CLCD_CAP_RGB, -}; - -struct backlight_device; - -struct clcd_panel { - struct fb_videomode mode; - signed short width; /* width in mm */ - signed short height; /* height in mm */ - u32 tim2; - u32 tim3; - u32 cntl; - u32 caps; - unsigned int bpp:8, - fixedtimings:1, - grayscale:1; - unsigned int connector; - struct backlight_device *backlight; - /* - * If the B/R lines are switched between the CLCD - * and the panel we need to know this and not try to - * compensate with the BGR bit in the control register. - */ - bool bgr_connection; -}; - -struct clcd_regs { - u32 tim0; - u32 tim1; - u32 tim2; - u32 tim3; - u32 cntl; - unsigned long pixclock; -}; - -struct clcd_fb; - -/* - * the board-type specific routines - */ -struct clcd_board { - const char *name; - - /* - * Optional. Hardware capability flags. - */ - u32 caps; - - /* - * Optional. Check whether the var structure is acceptable - * for this display. - */ - int (*check)(struct clcd_fb *fb, struct fb_var_screeninfo *var); - - /* - * Compulsory. Decode fb->fb.var into regs->*. In the case of - * fixed timing, set regs->* to the register values required. - */ - void (*decode)(struct clcd_fb *fb, struct clcd_regs *regs); - - /* - * Optional. Disable any extra display hardware. - */ - void (*disable)(struct clcd_fb *); - - /* - * Optional. Enable any extra display hardware. - */ - void (*enable)(struct clcd_fb *); - - /* - * Setup platform specific parts of CLCD driver - */ - int (*setup)(struct clcd_fb *); - - /* - * mmap the framebuffer memory - */ - int (*mmap)(struct clcd_fb *, struct vm_area_struct *); - - /* - * Remove platform specific parts of CLCD driver - */ - void (*remove)(struct clcd_fb *); -}; - -struct amba_device; -struct clk; - -/* this data structure describes each frame buffer device we find */ -struct clcd_fb { - struct fb_info fb; - struct amba_device *dev; - struct clk *clk; - struct clcd_panel *panel; - struct clcd_board *board; - void *board_data; - void __iomem *regs; - u16 off_ienb; - u16 off_cntl; - u32 clcd_cntl; - u32 cmap[16]; - bool clk_enabled; -}; - -static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs) -{ - struct fb_var_screeninfo *var = &fb->fb.var; - u32 val, cpl; - - /* - * Program the CLCD controller registers and start the CLCD - */ - val = ((var->xres / 16) - 1) << 2; - val |= (var->hsync_len - 1) << 8; - val |= (var->right_margin - 1) << 16; - val |= (var->left_margin - 1) << 24; - regs->tim0 = val; - - val = var->yres; - if (fb->panel->cntl & CNTL_LCDDUAL) - val /= 2; - val -= 1; - val |= (var->vsync_len - 1) << 10; - val |= var->lower_margin << 16; - val |= var->upper_margin << 24; - regs->tim1 = val; - - val = fb->panel->tim2; - val |= var->sync & FB_SYNC_HOR_HIGH_ACT ? 0 : TIM2_IHS; - val |= var->sync & FB_SYNC_VERT_HIGH_ACT ? 0 : TIM2_IVS; - - cpl = var->xres_virtual; - if (fb->panel->cntl & CNTL_LCDTFT) /* TFT */ - /* / 1 */; - else if (!var->grayscale) /* STN color */ - cpl = cpl * 8 / 3; - else if (fb->panel->cntl & CNTL_LCDMONO8) /* STN monochrome, 8bit */ - cpl /= 8; - else /* STN monochrome, 4bit */ - cpl /= 4; - - regs->tim2 = val | ((cpl - 1) << 16); - - regs->tim3 = fb->panel->tim3; - - val = fb->panel->cntl; - if (var->grayscale) - val |= CNTL_LCDBW; - - if (fb->panel->caps && fb->board->caps && var->bits_per_pixel >= 16) { - /* - * if board and panel supply capabilities, we can support - * changing BGR/RGB depending on supplied parameters. Here - * we switch to what the framebuffer is providing if need - * be, so if the framebuffer is BGR but the display connection - * is RGB (first case) we switch it around. Vice versa mutatis - * mutandis if the framebuffer is RGB but the display connection - * is BGR, we flip it around. - */ - if (var->red.offset == 0) - val &= ~CNTL_BGR; - else - val |= CNTL_BGR; - if (fb->panel->bgr_connection) - val ^= CNTL_BGR; - } - - switch (var->bits_per_pixel) { - case 1: - val |= CNTL_LCDBPP1; - break; - case 2: - val |= CNTL_LCDBPP2; - break; - case 4: - val |= CNTL_LCDBPP4; - break; - case 8: - val |= CNTL_LCDBPP8; - break; - case 16: - /* - * PL110 cannot choose between 5551 and 565 modes in its - * control register. It is possible to use 565 with - * custom external wiring. - */ - if (amba_part(fb->dev) == 0x110 || - var->green.length == 5) - val |= CNTL_LCDBPP16; - else if (var->green.length == 6) - val |= CNTL_LCDBPP16_565; - else - val |= CNTL_LCDBPP16_444; - break; - case 32: - val |= CNTL_LCDBPP24; - break; - } - - regs->cntl = val; - regs->pixclock = var->pixclock; -} - -static inline int clcdfb_check(struct clcd_fb *fb, struct fb_var_screeninfo *var) -{ - var->xres_virtual = var->xres = (var->xres + 15) & ~15; - var->yres_virtual = var->yres = (var->yres + 1) & ~1; - -#define CHECK(e,l,h) (var->e < l || var->e > h) - if (CHECK(right_margin, (5+1), 256) || /* back porch */ - CHECK(left_margin, (5+1), 256) || /* front porch */ - CHECK(hsync_len, (5+1), 256) || - var->xres > 4096 || - var->lower_margin > 255 || /* back porch */ - var->upper_margin > 255 || /* front porch */ - var->vsync_len > 32 || - var->yres > 1024) - return -EINVAL; -#undef CHECK - - /* single panel mode: PCD = max(PCD, 1) */ - /* dual panel mode: PCD = max(PCD, 5) */ - - /* - * You can't change the grayscale setting, and - * we can only do non-interlaced video. - */ - if (var->grayscale != fb->fb.var.grayscale || - (var->vmode & FB_VMODE_MASK) != FB_VMODE_NONINTERLACED) - return -EINVAL; - -#define CHECK(e) (var->e != fb->fb.var.e) - if (fb->panel->fixedtimings && - (CHECK(xres) || - CHECK(yres) || - CHECK(bits_per_pixel) || - CHECK(pixclock) || - CHECK(left_margin) || - CHECK(right_margin) || - CHECK(upper_margin) || - CHECK(lower_margin) || - CHECK(hsync_len) || - CHECK(vsync_len) || - CHECK(sync))) - return -EINVAL; -#undef CHECK - - var->nonstd = 0; - var->accel_flags = 0; - - return 0; -} -- cgit v1.2.3 From 7e4e589db76a3cf4c1f534eb5a09cc6422766b93 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 9 Jun 2020 22:04:45 +0200 Subject: drm: pl111: Absorb the external register header The PL111 DRM driver is now the sole user of the external CLCD registers header file, so let's absorb that into the pl111_drm.h file and save the external include. Reviewed-by: Eric Anholt Signed-off-by: Linus Walleij Cc: Russell King Link: https://patchwork.freedesktop.org/patch/msgid/20200609200446.153209-3-linus.walleij@linaro.org --- include/linux/amba/clcd-regs.h | 87 ------------------------------------------ 1 file changed, 87 deletions(-) delete mode 100644 include/linux/amba/clcd-regs.h (limited to 'include/linux') diff --git a/include/linux/amba/clcd-regs.h b/include/linux/amba/clcd-regs.h deleted file mode 100644 index 421b0fa90d6a..000000000000 --- a/include/linux/amba/clcd-regs.h +++ /dev/null @@ -1,87 +0,0 @@ -/* - * David A Rusling - * - * Copyright (C) 2001 ARM Limited - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of this archive - * for more details. - */ - -#ifndef AMBA_CLCD_REGS_H -#define AMBA_CLCD_REGS_H - -/* - * CLCD Controller Internal Register addresses - */ -#define CLCD_TIM0 0x00000000 -#define CLCD_TIM1 0x00000004 -#define CLCD_TIM2 0x00000008 -#define CLCD_TIM3 0x0000000c -#define CLCD_UBAS 0x00000010 -#define CLCD_LBAS 0x00000014 - -#define CLCD_PL110_IENB 0x00000018 -#define CLCD_PL110_CNTL 0x0000001c -#define CLCD_PL110_STAT 0x00000020 -#define CLCD_PL110_INTR 0x00000024 -#define CLCD_PL110_UCUR 0x00000028 -#define CLCD_PL110_LCUR 0x0000002C - -#define CLCD_PL111_CNTL 0x00000018 -#define CLCD_PL111_IENB 0x0000001c -#define CLCD_PL111_RIS 0x00000020 -#define CLCD_PL111_MIS 0x00000024 -#define CLCD_PL111_ICR 0x00000028 -#define CLCD_PL111_UCUR 0x0000002c -#define CLCD_PL111_LCUR 0x00000030 - -#define CLCD_PALL 0x00000200 -#define CLCD_PALETTE 0x00000200 - -#define TIM2_PCD_LO_MASK GENMASK(4, 0) -#define TIM2_PCD_LO_BITS 5 -#define TIM2_CLKSEL (1 << 5) -#define TIM2_ACB_MASK GENMASK(10, 6) -#define TIM2_IVS (1 << 11) -#define TIM2_IHS (1 << 12) -#define TIM2_IPC (1 << 13) -#define TIM2_IOE (1 << 14) -#define TIM2_BCD (1 << 26) -#define TIM2_PCD_HI_MASK GENMASK(31, 27) -#define TIM2_PCD_HI_BITS 5 -#define TIM2_PCD_HI_SHIFT 27 - -#define CNTL_LCDEN (1 << 0) -#define CNTL_LCDBPP1 (0 << 1) -#define CNTL_LCDBPP2 (1 << 1) -#define CNTL_LCDBPP4 (2 << 1) -#define CNTL_LCDBPP8 (3 << 1) -#define CNTL_LCDBPP16 (4 << 1) -#define CNTL_LCDBPP16_565 (6 << 1) -#define CNTL_LCDBPP16_444 (7 << 1) -#define CNTL_LCDBPP24 (5 << 1) -#define CNTL_LCDBW (1 << 4) -#define CNTL_LCDTFT (1 << 5) -#define CNTL_LCDMONO8 (1 << 6) -#define CNTL_LCDDUAL (1 << 7) -#define CNTL_BGR (1 << 8) -#define CNTL_BEBO (1 << 9) -#define CNTL_BEPO (1 << 10) -#define CNTL_LCDPWR (1 << 11) -#define CNTL_LCDVCOMP(x) ((x) << 12) -#define CNTL_LDMAFIFOTIME (1 << 15) -#define CNTL_WATERMARK (1 << 16) - -/* ST Microelectronics variant bits */ -#define CNTL_ST_1XBPP_444 0x0 -#define CNTL_ST_1XBPP_5551 (1 << 17) -#define CNTL_ST_1XBPP_565 (1 << 18) -#define CNTL_ST_CDWID_12 0x0 -#define CNTL_ST_CDWID_16 (1 << 19) -#define CNTL_ST_CDWID_18 (1 << 20) -#define CNTL_ST_CDWID_24 ((1 << 19)|(1 << 20)) -#define CNTL_ST_CEAEN (1 << 21) -#define CNTL_ST_LCDBPP24_PACKED (6 << 1) - -#endif /* AMBA_CLCD_REGS_H */ -- cgit v1.2.3 From 142240398e50e5fe3171bcf2459856603be13a39 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Sat, 27 Jun 2020 23:24:19 -0400 Subject: audit: add gfp parameter to audit_log_nfcfg Fixed an inconsistent use of GFP flags in nft_obj_notify() that used GFP_KERNEL when a GFP flag was passed in to that function. Given this allocated memory was then used in audit_log_nfcfg() it led to an audit of all other GFP allocations in net/netfilter/nf_tables_api.c and a modification of audit_log_nfcfg() to accept a GFP parameter. Reported-by: Dan Carptenter Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 604ede630580..d93739f7a35a 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -404,7 +404,7 @@ extern void __audit_fanotify(unsigned int response); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, - enum audit_nfcfgop op); + enum audit_nfcfgop op, gfp_t gfp); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { @@ -542,10 +542,10 @@ static inline void audit_ntp_log(const struct audit_ntp_data *ad) static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, - enum audit_nfcfgop op) + enum audit_nfcfgop op, gfp_t gfp) { if (audit_enabled) - __audit_log_nfcfg(name, af, nentries, op); + __audit_log_nfcfg(name, af, nentries, op, gfp); } extern int audit_n_rules; @@ -683,7 +683,7 @@ static inline void audit_ptrace(struct task_struct *t) static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, - enum audit_nfcfgop op) + enum audit_nfcfgop op, gfp_t gfp) { } #define audit_n_rules 0 -- cgit v1.2.3 From ecc31c60240b9808a274befc5db6b8a249a6ade1 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Mon, 29 Jun 2020 23:46:16 +0300 Subject: ethtool: Add link extended state Currently, drivers can only tell whether the link is up/down using LINKSTATE_GET, but no additional information is given. Add attributes to LINKSTATE_GET command in order to allow drivers to expose the user more information in addition to link state to ease the debug process, for example, reason for link down state. Extended state consists of two attributes - link_ext_state and link_ext_substate. The idea is to avoid 'vendor specific' states in order to prevent drivers to use specific link_ext_state that can be in the future common link_ext_state. The substates allows drivers to add more information to the common link_ext_state. For example, vendor can expose 'Autoneg' as link_ext_state and add 'No partner detected during force mode' as link_ext_substate. If a driver cannot pinpoint the extended state with the substate accuracy, it is free to expose only the extended state and omit the substate attribute. Signed-off-by: Amit Cohen Reviewed-by: Jiri Pirko Reviewed-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/ethtool.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index a23b26eab479..48ad3b6a0150 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -86,6 +86,22 @@ struct net_device; u32 ethtool_op_get_link(struct net_device *dev); int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *eti); + +/** + * struct ethtool_link_ext_state_info - link extended state and substate. + */ +struct ethtool_link_ext_state_info { + enum ethtool_link_ext_state link_ext_state; + union { + enum ethtool_link_ext_substate_autoneg autoneg; + enum ethtool_link_ext_substate_link_training link_training; + enum ethtool_link_ext_substate_link_logical_mismatch link_logical_mismatch; + enum ethtool_link_ext_substate_bad_signal_integrity bad_signal_integrity; + enum ethtool_link_ext_substate_cable_issue cable_issue; + u8 __link_ext_substate; + }; +}; + /** * ethtool_rxfh_indir_default - get default value for RX flow hash indirection * @index: Index in RX flow hash indirection table @@ -245,6 +261,11 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * @get_link: Report whether physical link is up. Will only be called if * the netdev is up. Should usually be set to ethtool_op_get_link(), * which uses netif_carrier_ok(). + * @get_link_ext_state: Report link extended state. Should set link_ext_state and + * link_ext_substate (link_ext_substate of 0 means link_ext_substate is unknown, + * do not attach ext_substate attribute to netlink message). If link_ext_state + * and link_ext_substate are unknown, return -ENODATA. If not implemented, + * link_ext_state and link_ext_substate will not be sent to userspace. * @get_eeprom: Read data from the device EEPROM. * Should fill in the magic field. Don't need to check len for zero * or wraparound. Fill in the data argument with the eeprom values @@ -384,6 +405,8 @@ struct ethtool_ops { void (*set_msglevel)(struct net_device *, u32); int (*nway_reset)(struct net_device *); u32 (*get_link)(struct net_device *); + int (*get_link_ext_state)(struct net_device *, + struct ethtool_link_ext_state_info *); int (*get_eeprom_len)(struct net_device *); int (*get_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); -- cgit v1.2.3 From ca37faf3d7005b5588f045edfac1d82799c408a7 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Tue, 30 Jun 2020 10:17:56 +0200 Subject: iommu: Move sg_table wrapper out of CONFIG_IOMMU_SUPPORT Move the recently added sg_table wrapper out of CONFIG_IOMMU_SUPPORT to let the client code copile also when IOMMU support is disabled. Fixes: 48530d9fab0d ("iommu: add generic helper for mapping sgtable objects") Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20200630081756.18526-1-m.szyprowski@samsung.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 5f0b7859d2eb..5657d4fef9f2 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -457,22 +457,6 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t io extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); -/** - * iommu_map_sgtable - Map the given buffer to the IOMMU domain - * @domain: The IOMMU domain to perform the mapping - * @iova: The start address to map the buffer - * @sgt: The sg_table object describing the buffer - * @prot: IOMMU protection bits - * - * Creates a mapping at @iova for the buffer described by a scatterlist - * stored in the given sg_table object in the provided IOMMU domain. - */ -static inline size_t iommu_map_sgtable(struct iommu_domain *domain, - unsigned long iova, struct sg_table *sgt, int prot) -{ - return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot); -} - extern void iommu_get_resv_regions(struct device *dev, struct list_head *list); extern void iommu_put_resv_regions(struct device *dev, struct list_head *list); extern void generic_iommu_put_resv_regions(struct device *dev, @@ -1079,6 +1063,22 @@ static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) } #endif /* CONFIG_IOMMU_API */ +/** + * iommu_map_sgtable - Map the given buffer to the IOMMU domain + * @domain: The IOMMU domain to perform the mapping + * @iova: The start address to map the buffer + * @sgt: The sg_table object describing the buffer + * @prot: IOMMU protection bits + * + * Creates a mapping at @iova for the buffer described by a scatterlist + * stored in the given sg_table object in the provided IOMMU domain. + */ +static inline size_t iommu_map_sgtable(struct iommu_domain *domain, + unsigned long iova, struct sg_table *sgt, int prot) +{ + return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot); +} + #ifdef CONFIG_IOMMU_DEBUGFS extern struct dentry *iommu_debugfs_dir; void iommu_debugfs_setup(void); -- cgit v1.2.3 From 1909872ff20fc378ec6a44ea1a2b2966d834e504 Mon Sep 17 00:00:00 2001 From: Nicola Mazzucato Date: Wed, 17 Jun 2020 10:43:31 +0100 Subject: firmware: arm_scmi: Add fast_switch_possible() interface Add a new fast_switch_possible interface to the existing perf_ops to export the information of whether or not fast_switch is possible for a given device. This can be used by the cpufreq driver and framework to choose proper mechanism for frequency change. Link: https://lore.kernel.org/r/20200617094332.8391-1-nicola.mazzucato@arm.com Suggested-by: Lukasz Luba Signed-off-by: Nicola Mazzucato Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index ce2f5c28b2df..73911d156a39 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -118,6 +118,8 @@ struct scmi_perf_ops { unsigned long *rate, bool poll); int (*est_power_get)(const struct scmi_handle *handle, u32 domain, unsigned long *rate, unsigned long *power); + bool (*fast_switch_possible)(const struct scmi_handle *handle, + struct device *dev); }; /** -- cgit v1.2.3 From 7999096fa9cfd0253497c8d2ed9a5a1537521d25 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 12 Jun 2020 16:57:37 +1000 Subject: iov_iter: Move unnecessary inclusion of crypto/hash.h The header file linux/uio.h includes crypto/hash.h which pulls in most of the Crypto API. Since linux/uio.h is used throughout the kernel this means that every tiny bit of change to the Crypto API causes the entire kernel to get rebuilt. This patch fixes this by moving it into lib/iov_iter.c instead where it is actually used. This patch also fixes the ifdef to use CRYPTO_HASH instead of just CRYPTO which does not guarantee the existence of ahash. Unfortunately a number of drivers were relying on linux/uio.h to provide access to linux/slab.h. This patch adds inclusions of linux/slab.h as detected by build failures. Also skbuff.h was relying on this to provide a declaration for ahash_request. This patch adds a forward declaration instead. Signed-off-by: Herbert Xu Signed-off-by: Al Viro --- include/linux/skbuff.h | 1 + include/linux/socket.h | 1 + include/linux/uio.h | 1 - 3 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0c0377fc00c2..1530e81a6cce 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -238,6 +238,7 @@ SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) +struct ahash_request; struct net_device; struct scatterlist; struct pipe_inode_info; diff --git a/include/linux/socket.h b/include/linux/socket.h index 04d2bc97f497..e9cb30d8cbfb 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -10,6 +10,7 @@ #include /* __user */ #include +struct file; struct pid; struct cred; struct socket; diff --git a/include/linux/uio.h b/include/linux/uio.h index 9576fd8158d7..3835a8a8e9ea 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -7,7 +7,6 @@ #include #include -#include #include struct page; -- cgit v1.2.3 From 3aa91625007807bfca4155df1867a5c924a08662 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Jun 2020 15:03:56 +0200 Subject: dma-mapping: Add a new dma_need_sync API Add a new API to check if calls to dma_sync_single_for_{device,cpu} are required for a given DMA streaming mapping. Signed-off-by: Christoph Hellwig Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200629130359.2690853-2-hch@lst.de --- include/linux/dma-direct.h | 1 + include/linux/dma-mapping.h | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 136f984df0d9..8b006730687b 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -87,4 +87,5 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); int dma_direct_supported(struct device *dev, u64 mask); +bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr); #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 78f677cf45ab..a33ed3954ed4 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -461,6 +461,7 @@ int dma_set_mask(struct device *dev, u64 mask); int dma_set_coherent_mask(struct device *dev, u64 mask); u64 dma_get_required_mask(struct device *dev); size_t dma_max_mapping_size(struct device *dev); +bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); unsigned long dma_get_merge_boundary(struct device *dev); #else /* CONFIG_HAS_DMA */ static inline dma_addr_t dma_map_page_attrs(struct device *dev, @@ -571,6 +572,10 @@ static inline size_t dma_max_mapping_size(struct device *dev) { return 0; } +static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return false; +} static inline unsigned long dma_get_merge_boundary(struct device *dev) { return 0; -- cgit v1.2.3 From 65c763694398a2de63803b264dcf906b47f9d4c1 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 30 Jun 2020 18:24:56 +0800 Subject: blk-mq: pass request queue into get/put budget callback blk-mq budget is abstract from scsi's device queue depth, and it is always per-request-queue instead of hctx. It can be quite absurd to get a budget from one hctx, then dequeue a request from scheduler queue, and this request may not belong to this hctx, at least for bfq and deadline. So fix the mess and always pass request queue to get/put budget callback. Signed-off-by: Ming Lei Tested-by: Baolin Wang Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Reviewed-by: Douglas Anderson Reviewed-by: Sagi Grimberg Cc: Sagi Grimberg Cc: Baolin Wang Cc: Christoph Hellwig Cc: Douglas Anderson Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8986e88a986b..faa340b70123 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -270,8 +270,8 @@ struct blk_mq_queue_data { typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); typedef void (commit_rqs_fn)(struct blk_mq_hw_ctx *); -typedef bool (get_budget_fn)(struct blk_mq_hw_ctx *); -typedef void (put_budget_fn)(struct blk_mq_hw_ctx *); +typedef bool (get_budget_fn)(struct request_queue *); +typedef void (put_budget_fn)(struct request_queue *); typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool); typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int); typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int); -- cgit v1.2.3 From e3f88cdb8fdd5876ef3a0373e35ba7f2598fcf17 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 9 Jun 2020 04:54:33 +0800 Subject: soundwire: add definitions for 1.2 spec Add definitions for register offsets and bit fields from the MIPI SoundWire 1.2 specification (available to MIPI members at https://members.mipi.org/wg/All-Members/document/download/78371) Signed-off-by: Pierre-Louis Bossart Reviewed-by: Kai Vehmanen Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20200608205436.2402-2-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_registers.h | 107 +++++++++++++++++++++++++++++++- 1 file changed, 106 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h index a686f7988156..12f9ffc3eb3b 100644 --- a/include/linux/soundwire/sdw_registers.h +++ b/include/linux/soundwire/sdw_registers.h @@ -12,7 +12,7 @@ #define SDW_REG_SHIFT(n) (ffs(n) - 1) /* - * SDW registers as defined by MIPI 1.1 Spec + * SDW registers as defined by MIPI 1.2 Spec */ #define SDW_REGADDR GENMASK(14, 0) #define SDW_SCP_ADDRPAGE2_MASK GENMASK(22, 15) @@ -43,6 +43,8 @@ #define SDW_DP0_INT_TEST_FAIL BIT(0) #define SDW_DP0_INT_PORT_READY BIT(1) #define SDW_DP0_INT_BRA_FAILURE BIT(2) +#define SDW_DP0_SDCA_CASCADE BIT(3) +/* BIT(4) not allocated in SoundWire specification 1.2 */ #define SDW_DP0_INT_IMPDEF1 BIT(5) #define SDW_DP0_INT_IMPDEF2 BIT(6) #define SDW_DP0_INT_IMPDEF3 BIT(7) @@ -106,6 +108,10 @@ #define SDW_SCP_ADDRPAGE2 0x49 #define SDW_SCP_KEEPEREN 0x4A #define SDW_SCP_BANKDELAY 0x4B +#define SDW_SCP_COMMIT 0x4C +#define SDW_SCP_BUS_CLOCK_BASE 0x4D +#define SDW_SCP_BASE_CLOCK_FREQ GENMASK(2, 0) +/* 0x4E is not allocated in SoundWire specification 1.2 */ #define SDW_SCP_TESTMODE 0x4F #define SDW_SCP_DEVID_0 0x50 #define SDW_SCP_DEVID_1 0x51 @@ -114,12 +120,111 @@ #define SDW_SCP_DEVID_4 0x54 #define SDW_SCP_DEVID_5 0x55 +/* Both INT and STATUS register are same */ +#define SDW_SCP_SDCA_INT1 0x58 +#define SDW_SCP_SDCA_INT_SDCA_0 BIT(0) +#define SDW_SCP_SDCA_INT_SDCA_1 BIT(1) +#define SDW_SCP_SDCA_INT_SDCA_2 BIT(2) +#define SDW_SCP_SDCA_INT_SDCA_3 BIT(3) +#define SDW_SCP_SDCA_INT_SDCA_4 BIT(4) +#define SDW_SCP_SDCA_INT_SDCA_5 BIT(5) +#define SDW_SCP_SDCA_INT_SDCA_6 BIT(6) +#define SDW_SCP_SDCA_INT_SDCA_7 BIT(7) + +#define SDW_SCP_SDCA_INT2 0x59 +#define SDW_SCP_SDCA_INT_SDCA_8 BIT(0) +#define SDW_SCP_SDCA_INT_SDCA_9 BIT(1) +#define SDW_SCP_SDCA_INT_SDCA_10 BIT(2) +#define SDW_SCP_SDCA_INT_SDCA_11 BIT(3) +#define SDW_SCP_SDCA_INT_SDCA_12 BIT(4) +#define SDW_SCP_SDCA_INT_SDCA_13 BIT(5) +#define SDW_SCP_SDCA_INT_SDCA_14 BIT(6) +#define SDW_SCP_SDCA_INT_SDCA_15 BIT(7) + +#define SDW_SCP_SDCA_INT3 0x5A +#define SDW_SCP_SDCA_INT_SDCA_16 BIT(0) +#define SDW_SCP_SDCA_INT_SDCA_17 BIT(1) +#define SDW_SCP_SDCA_INT_SDCA_18 BIT(2) +#define SDW_SCP_SDCA_INT_SDCA_19 BIT(3) +#define SDW_SCP_SDCA_INT_SDCA_20 BIT(4) +#define SDW_SCP_SDCA_INT_SDCA_21 BIT(5) +#define SDW_SCP_SDCA_INT_SDCA_22 BIT(6) +#define SDW_SCP_SDCA_INT_SDCA_23 BIT(7) + +#define SDW_SCP_SDCA_INT4 0x5B +#define SDW_SCP_SDCA_INT_SDCA_24 BIT(0) +#define SDW_SCP_SDCA_INT_SDCA_25 BIT(1) +#define SDW_SCP_SDCA_INT_SDCA_26 BIT(2) +#define SDW_SCP_SDCA_INT_SDCA_27 BIT(3) +#define SDW_SCP_SDCA_INT_SDCA_28 BIT(4) +#define SDW_SCP_SDCA_INT_SDCA_29 BIT(5) +#define SDW_SCP_SDCA_INT_SDCA_30 BIT(6) +/* BIT(7) not allocated in SoundWire 1.2 specification */ + +#define SDW_SCP_SDCA_INTMASK1 0x5C +#define SDW_SCP_SDCA_INTMASK_SDCA_0 BIT(0) +#define SDW_SCP_SDCA_INTMASK_SDCA_1 BIT(1) +#define SDW_SCP_SDCA_INTMASK_SDCA_2 BIT(2) +#define SDW_SCP_SDCA_INTMASK_SDCA_3 BIT(3) +#define SDW_SCP_SDCA_INTMASK_SDCA_4 BIT(4) +#define SDW_SCP_SDCA_INTMASK_SDCA_5 BIT(5) +#define SDW_SCP_SDCA_INTMASK_SDCA_6 BIT(6) +#define SDW_SCP_SDCA_INTMASK_SDCA_7 BIT(7) + +#define SDW_SCP_SDCA_INTMASK2 0x5D +#define SDW_SCP_SDCA_INTMASK_SDCA_8 BIT(0) +#define SDW_SCP_SDCA_INTMASK_SDCA_9 BIT(1) +#define SDW_SCP_SDCA_INTMASK_SDCA_10 BIT(2) +#define SDW_SCP_SDCA_INTMASK_SDCA_11 BIT(3) +#define SDW_SCP_SDCA_INTMASK_SDCA_12 BIT(4) +#define SDW_SCP_SDCA_INTMASK_SDCA_13 BIT(5) +#define SDW_SCP_SDCA_INTMASK_SDCA_14 BIT(6) +#define SDW_SCP_SDCA_INTMASK_SDCA_15 BIT(7) + +#define SDW_SCP_SDCA_INTMASK3 0x5E +#define SDW_SCP_SDCA_INTMASK_SDCA_16 BIT(0) +#define SDW_SCP_SDCA_INTMASK_SDCA_17 BIT(1) +#define SDW_SCP_SDCA_INTMASK_SDCA_18 BIT(2) +#define SDW_SCP_SDCA_INTMASK_SDCA_19 BIT(3) +#define SDW_SCP_SDCA_INTMASK_SDCA_20 BIT(4) +#define SDW_SCP_SDCA_INTMASK_SDCA_21 BIT(5) +#define SDW_SCP_SDCA_INTMASK_SDCA_22 BIT(6) +#define SDW_SCP_SDCA_INTMASK_SDCA_23 BIT(7) + +#define SDW_SCP_SDCA_INTMASK4 0x5F +#define SDW_SCP_SDCA_INTMASK_SDCA_24 BIT(0) +#define SDW_SCP_SDCA_INTMASK_SDCA_25 BIT(1) +#define SDW_SCP_SDCA_INTMASK_SDCA_26 BIT(2) +#define SDW_SCP_SDCA_INTMASK_SDCA_27 BIT(3) +#define SDW_SCP_SDCA_INTMASK_SDCA_28 BIT(4) +#define SDW_SCP_SDCA_INTMASK_SDCA_29 BIT(5) +#define SDW_SCP_SDCA_INTMASK_SDCA_30 BIT(6) +/* BIT(7) not allocated in SoundWire 1.2 specification */ + /* Banked Registers */ #define SDW_SCP_FRAMECTRL_B0 0x60 #define SDW_SCP_FRAMECTRL_B1 (0x60 + SDW_BANK1_OFFSET) #define SDW_SCP_NEXTFRAME_B0 0x61 #define SDW_SCP_NEXTFRAME_B1 (0x61 + SDW_BANK1_OFFSET) +#define SDW_SCP_BUSCLOCK_SCALE_B0 0x62 +#define SDW_SCP_BUSCLOCK_SCALE_B1 (0x62 + SDW_BANK1_OFFSET) +#define SDW_SCP_CLOCK_SCALE GENMASK(3, 0) + +/* PHY registers - CTRL and STAT are the same address */ +#define SDW_SCP_PHY_OUT_CTRL_0 0x80 +#define SDW_SCP_PHY_OUT_CTRL_1 0x81 +#define SDW_SCP_PHY_OUT_CTRL_2 0x82 +#define SDW_SCP_PHY_OUT_CTRL_3 0x83 +#define SDW_SCP_PHY_OUT_CTRL_4 0x84 +#define SDW_SCP_PHY_OUT_CTRL_5 0x85 +#define SDW_SCP_PHY_OUT_CTRL_6 0x86 +#define SDW_SCP_PHY_OUT_CTRL_7 0x87 + +#define SDW_SCP_CAP_LOAD_CTRL GENMASK(2, 0) +#define SDW_SCP_DRIVE_STRENGTH_CTRL GENMASK(5, 3) +#define SDW_SCP_SLEW_TIME_CTRL GENMASK(7, 6) + /* Both INT and STATUS register is same */ #define SDW_DPN_INT(n) (0x0 + SDW_DPN_SIZE * (n)) #define SDW_DPN_INTMASK(n) (0x1 + SDW_DPN_SIZE * (n)) -- cgit v1.2.3 From b5924268d6700821fbd8afe815073b05cebaa308 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 9 Jun 2020 04:54:35 +0800 Subject: soundwire: extend SDW_SLAVE_ENTRY The SoundWire 1.2 specification adds new capabilities that were not present in previous version, such as the class ID. To enable support for class drivers, and well as drivers that address a specific version, all fields of the sdw_device_id structure need to be exposed. For SoundWire 1.0 and 1.1 devices, a wildcard is used so class and version information are ignored. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Reviewed-by: Guennadi Liakhovetski Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20200608205436.2402-4-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/mod_devicetable.h | 2 ++ include/linux/soundwire/sdw.h | 11 +++++++---- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 8d764aab29de..f8585e3a2c43 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -251,6 +251,8 @@ struct hda_device_id { struct sdw_device_id { __u16 mfg_id; __u16 part_id; + __u8 sdw_version; + __u8 class_id; kernel_ulong_t driver_data; }; diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 9c27a32df9bb..64c9314cb903 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -426,8 +426,7 @@ int sdw_slave_read_prop(struct sdw_slave *slave); * struct sdw_slave_id - Slave ID * @mfg_id: MIPI Manufacturer ID * @part_id: Device Part ID - * @class_id: MIPI Class ID, unused now. - * Currently a placeholder in MIPI SoundWire Spec + * @class_id: MIPI Class ID (defined starting with SoundWire 1.2 spec) * @unique_id: Device unique ID * @sdw_version: SDW version implemented * @@ -659,10 +658,14 @@ struct sdw_driver { struct device_driver driver; }; -#define SDW_SLAVE_ENTRY(_mfg_id, _part_id, _drv_data) \ - { .mfg_id = (_mfg_id), .part_id = (_part_id), \ +#define SDW_SLAVE_ENTRY_EXT(_mfg_id, _part_id, _version, _c_id, _drv_data) \ + { .mfg_id = (_mfg_id), .part_id = (_part_id), \ + .sdw_version = (_version), .class_id = (_c_id), \ .driver_data = (unsigned long)(_drv_data) } +#define SDW_SLAVE_ENTRY(_mfg_id, _part_id, _drv_data) \ + SDW_SLAVE_ENTRY_EXT((_mfg_id), (_part_id), 0, 0, (_drv_data)) + int sdw_handle_slave_status(struct sdw_bus *bus, enum sdw_slave_status status[]); -- cgit v1.2.3 From 29d158f906907ce8e52ea75ec87b4e35461f2018 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 9 Jun 2020 04:54:36 +0800 Subject: soundwire: bus: initialize bus clock base and scale registers The SoundWire 1.2 specification adds new registers to allow for seamless clock changes while audio transfers are on-going. Program them following the specification. Note that dynamic clock changes are not supported for now, this only adds the register initialization. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Kai Vehmanen Reviewed-by: Guennadi Liakhovetski Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20200608205436.2402-5-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_registers.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h index 12f9ffc3eb3b..5d3c271af7d1 100644 --- a/include/linux/soundwire/sdw_registers.h +++ b/include/linux/soundwire/sdw_registers.h @@ -109,8 +109,18 @@ #define SDW_SCP_KEEPEREN 0x4A #define SDW_SCP_BANKDELAY 0x4B #define SDW_SCP_COMMIT 0x4C + #define SDW_SCP_BUS_CLOCK_BASE 0x4D #define SDW_SCP_BASE_CLOCK_FREQ GENMASK(2, 0) +#define SDW_SCP_BASE_CLOCK_UNKNOWN 0x0 +#define SDW_SCP_BASE_CLOCK_19200000_HZ 0x1 +#define SDW_SCP_BASE_CLOCK_24000000_HZ 0x2 +#define SDW_SCP_BASE_CLOCK_24576000_HZ 0x3 +#define SDW_SCP_BASE_CLOCK_22579200_HZ 0x4 +#define SDW_SCP_BASE_CLOCK_32000000_HZ 0x5 +#define SDW_SCP_BASE_CLOCK_RESERVED 0x6 +#define SDW_SCP_BASE_CLOCK_IMP_DEF 0x7 + /* 0x4E is not allocated in SoundWire specification 1.2 */ #define SDW_SCP_TESTMODE 0x4F #define SDW_SCP_DEVID_0 0x50 -- cgit v1.2.3 From 4ac2add65974e4efafb8d4ccd8fc5660417ea312 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 29 Jun 2020 10:56:26 +0100 Subject: bpf: flow_dissector: Check value of unused flags to BPF_PROG_DETACH Using BPF_PROG_DETACH on a flow dissector program supports neither attach_flags nor attach_bpf_fd. Yet no value is enforced for them. Enforce that attach_flags are zero, and require the current program to be passed via attach_bpf_fd. This allows us to remove the check for CAP_SYS_ADMIN, since userspace can now no longer remove arbitrary flow dissector programs. Fixes: b27f7bb590ba ("flow_dissector: Move out netns_bpf prog callbacks") Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200629095630.7933-3-lmb@cloudflare.com --- include/linux/bpf-netns.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h index 4052d649f36d..47d5b0c708c9 100644 --- a/include/linux/bpf-netns.h +++ b/include/linux/bpf-netns.h @@ -33,7 +33,7 @@ int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); -int netns_bpf_prog_detach(const union bpf_attr *attr); +int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog); #else @@ -49,7 +49,8 @@ static inline int netns_bpf_prog_attach(const union bpf_attr *attr, return -EOPNOTSUPP; } -static inline int netns_bpf_prog_detach(const union bpf_attr *attr) +static inline int netns_bpf_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) { return -EOPNOTSUPP; } -- cgit v1.2.3 From bb0de3131f4c60a9bf976681e0fe4d1e55c7a821 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 29 Jun 2020 10:56:28 +0100 Subject: bpf: sockmap: Require attach_bpf_fd when detaching a program The sockmap code currently ignores the value of attach_bpf_fd when detaching a program. This is contrary to the usual behaviour of checking that attach_bpf_fd represents the currently attached program. Ensure that attach_bpf_fd is indeed the currently attached program. It turns out that all sockmap selftests already do this, which indicates that this is unlikely to cause breakage. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200629095630.7933-5-lmb@cloudflare.com --- include/linux/bpf.h | 13 +++++++++++-- include/linux/skmsg.h | 13 +++++++++++++ 2 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 07052d44bca1..9750a1902ee5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1543,13 +1543,16 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_BPF_STREAM_PARSER) -int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which); +int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + struct bpf_prog *old, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int sock_map_prog_update(struct bpf_map *map, - struct bpf_prog *prog, u32 which) + struct bpf_prog *prog, + struct bpf_prog *old, u32 which) { return -EOPNOTSUPP; } @@ -1559,6 +1562,12 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr, { return -EINVAL; } + +static inline int sock_map_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_STREAM_PARSER */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 08674cd14d5a..1e9ed840b9fc 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -430,6 +430,19 @@ static inline void psock_set_prog(struct bpf_prog **pprog, bpf_prog_put(prog); } +static inline int psock_replace_prog(struct bpf_prog **pprog, + struct bpf_prog *prog, + struct bpf_prog *old) +{ + if (cmpxchg(pprog, old, prog) != old) + return -ENOENT; + + if (old) + bpf_prog_put(old); + + return 0; +} + static inline void psock_progs_drop(struct sk_psock_progs *progs) { psock_set_prog(&progs->msg_parser, NULL); -- cgit v1.2.3 From e91b48162332480f5840902268108bb7fb7a44c7 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 30 Jun 2020 17:32:54 +0200 Subject: task_work: teach task_work_add() to do signal_wake_up() So that the target task will exit the wait_event_interruptible-like loop and call task_work_run() asap. The patch turns "bool notify" into 0,TWA_RESUME,TWA_SIGNAL enum, the new TWA_SIGNAL flag implies signal_wake_up(). However, it needs to avoid the race with recalc_sigpending(), so the patch also adds the new JOBCTL_TASK_WORK bit included in JOBCTL_PENDING_MASK. TODO: once this patch is merged we need to change all current users of task_work_add(notify = true) to use TWA_RESUME. Cc: stable@vger.kernel.org # v5.7 Acked-by: Peter Zijlstra (Intel) Signed-off-by: Oleg Nesterov Signed-off-by: Jens Axboe --- include/linux/sched/jobctl.h | 4 +++- include/linux/task_work.h | 5 ++++- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index fa067de9f1a9..d2b4204ba4d3 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -19,6 +19,7 @@ struct task_struct; #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ +#define JOBCTL_TASK_WORK_BIT 24 /* set by TWA_SIGNAL */ #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) @@ -28,9 +29,10 @@ struct task_struct; #define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) #define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) +#define JOBCTL_TASK_WORK (1UL << JOBCTL_TASK_WORK_BIT) #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) -#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) +#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK | JOBCTL_TASK_WORK) extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask); extern void task_clear_jobctl_trapping(struct task_struct *task); diff --git a/include/linux/task_work.h b/include/linux/task_work.h index bd9a6a91c097..0fb93aafa478 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -13,7 +13,10 @@ init_task_work(struct callback_head *twork, task_work_func_t func) twork->func = func; } -int task_work_add(struct task_struct *task, struct callback_head *twork, bool); +#define TWA_RESUME 1 +#define TWA_SIGNAL 2 +int task_work_add(struct task_struct *task, struct callback_head *twork, int); + struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t); void task_work_run(void); -- cgit v1.2.3 From b23d7a5f4a07af02343cdd28fe1f7488bac3afda Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 25 Jun 2020 15:34:03 +1000 Subject: ring-buffer: speed up buffer resets by avoiding synchronize_rcu for each CPU On a 144 thread system, `perf ftrace` takes about 20 seconds to start up, due to calling synchronize_rcu() for each CPU. cat /proc/108560/stack 0xc0003e7eb336f470 __switch_to+0x2e0/0x480 __wait_rcu_gp+0x20c/0x220 synchronize_rcu+0x9c/0xc0 ring_buffer_reset_cpu+0x88/0x2e0 tracing_reset_online_cpus+0x84/0xe0 tracing_open+0x1d4/0x1f0 On a system with 10x more threads, it starts to become an annoyance. Batch these up so we disable all the per-cpu buffers first, then synchronize_rcu() once, then reset each of the buffers. This brings the time down to about 0.5s. Link: https://lkml.kernel.org/r/20200625053403.2386972-1-npiggin@gmail.com Tested-by: Anton Blanchard Acked-by: Paul E. McKenney Signed-off-by: Nicholas Piggin Signed-off-by: Steven Rostedt (VMware) --- include/linux/ring_buffer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index c76b2f3b3ac4..136ea0997e6d 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -143,6 +143,7 @@ bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter); unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu); void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu); +void ring_buffer_reset_online_cpus(struct trace_buffer *buffer); void ring_buffer_reset(struct trace_buffer *buffer); #ifdef CONFIG_RING_BUFFER_ALLOW_SWAP -- cgit v1.2.3 From 5396956cc7c6874180c9bfc1ceceb02b739a6a87 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 22 Jun 2020 19:12:48 +0300 Subject: PCI: Make pcie_find_root_port() work for Root Ports Commit 6ae72bfa656e ("PCI: Unify pcie_find_root_port() and pci_find_pcie_root_port()") broke acpi_pci_bridge_d3() because calling pcie_find_root_port() on a Root Port returned NULL when it should return the Root Port, which in turn broke power management of PCIe hierarchies. Rework pcie_find_root_port() so it returns its argument when it is already a Root Port. [bhelgaas: test device only once, test for PCIe] Fixes: 6ae72bfa656e ("PCI: Unify pcie_find_root_port() and pci_find_pcie_root_port()") Link: https://lore.kernel.org/r/20200622161248.51099-1-mika.westerberg@linux.intel.com Signed-off-by: Mika Westerberg Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c79d83304e52..34c1c4f45288 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2169,12 +2169,11 @@ static inline int pci_pcie_type(const struct pci_dev *dev) */ static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) { - struct pci_dev *bridge = pci_upstream_bridge(dev); - - while (bridge) { - if (pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT) - return bridge; - bridge = pci_upstream_bridge(bridge); + while (dev) { + if (pci_is_pcie(dev) && + pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) + return dev; + dev = pci_upstream_bridge(dev); } return NULL; -- cgit v1.2.3 From ab81e23cf77905896a5e51422eb58e8763507b85 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 29 Jun 2020 14:05:07 +0300 Subject: net: qed: correct existing SPDX tags QLogic QED drivers source code is dual licensed under GPL-2.0/BSD-3-Clause. Correct already existing but wrong SPDX tags to match the actual license. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/fcoe_common.h | 2 +- include/linux/qed/qed_fcoe_if.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h index 98cfc195abe2..a669d7d84284 100644 --- a/include/linux/qed/fcoe_common.h +++ b/include/linux/qed/fcoe_common.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015 QLogic Corporation */ diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h index 46082480a2c3..65d0317ef67e 100644 --- a/include/linux/qed/qed_fcoe_if.h +++ b/include/linux/qed/qed_fcoe_if.h @@ -1,4 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ + #ifndef _QED_FCOE_IF_H #define _QED_FCOE_IF_H #include -- cgit v1.2.3 From 1f4d4ed6acc5b74974fa038e5e9d2e19f3b532f3 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 29 Jun 2020 14:05:08 +0300 Subject: net: qed: convert to SPDX License Identifiers QLogic QED drivers source code is dual licensed under GPL-2.0/BSD-3-Clause. Remove all the boilerplates in the existing code and replace it with the correct SPDX tag. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 29 +---------------------------- include/linux/qed/eth_common.h | 29 +---------------------------- include/linux/qed/iscsi_common.h | 29 +---------------------------- include/linux/qed/iwarp_common.h | 29 +---------------------------- include/linux/qed/qed_chain.h | 29 +---------------------------- include/linux/qed/qed_eth_if.h | 29 +---------------------------- include/linux/qed/qed_if.h | 29 +---------------------------- include/linux/qed/qed_iov_if.h | 29 +---------------------------- include/linux/qed/qed_iscsi_if.h | 29 +---------------------------- include/linux/qed/qed_ll2_if.h | 29 +---------------------------- include/linux/qed/qed_rdma_if.h | 30 ++---------------------------- include/linux/qed/qede_rdma.h | 30 ++---------------------------- include/linux/qed/rdma_common.h | 29 +---------------------------- include/linux/qed/roce_common.h | 29 +---------------------------- include/linux/qed/storage_common.h | 29 +---------------------------- include/linux/qed/tcp_common.h | 29 +---------------------------- 16 files changed, 18 insertions(+), 448 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 2c4737e6694a..294d01eae5cb 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2016 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _COMMON_HSI_H diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index 95f5fd615852..a9566ef3c2ce 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __ETH_COMMON__ diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index 2f0a771a9176..7ca89fb9247f 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __ISCSI_COMMON__ diff --git a/include/linux/qed/iwarp_common.h b/include/linux/qed/iwarp_common.h index c6cfd39cd910..23583e644257 100644 --- a/include/linux/qed/iwarp_common.h +++ b/include/linux/qed/iwarp_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __IWARP_COMMON__ diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 6d15040c642c..e6e25197f7cb 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _QED_CHAIN_H diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index a1310482c4ed..7803dedbcb52 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _QED_ETH_IF_H diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8cb76405cbce..4a36608ff3a8 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _QED_IF_H diff --git a/include/linux/qed/qed_iov_if.h b/include/linux/qed/qed_iov_if.h index ac2e6a3199a3..c2ca8196def9 100644 --- a/include/linux/qed/qed_iov_if.h +++ b/include/linux/qed/qed_iov_if.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _QED_IOV_IF_H diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h index d0df1bec5357..89912c6c440c 100644 --- a/include/linux/qed/qed_iscsi_if.h +++ b/include/linux/qed/qed_iscsi_if.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _QED_ISCSI_IF_H diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index 1313c34d9a68..79cac277e38b 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _QED_LL2_IF_H diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index 2d3ddd2b85e0..041a5b005a82 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -1,34 +1,8 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ + #ifndef _QED_RDMA_IF_H #define _QED_RDMA_IF_H #include diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index 5a00c7a473bf..20ed7f2c55bb 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -1,34 +1,8 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qedr NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ + #ifndef QEDE_ROCE_H #define QEDE_ROCE_H diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h index 480a57eb36cc..3e3f01136c06 100644 --- a/include/linux/qed/rdma_common.h +++ b/include/linux/qed/rdma_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __RDMA_COMMON__ diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h index 473fba76aa77..89065f023813 100644 --- a/include/linux/qed/roce_common.h +++ b/include/linux/qed/roce_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __ROCE_COMMON__ diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h index 9a973ffbbff5..34f069c79067 100644 --- a/include/linux/qed/storage_common.h +++ b/include/linux/qed/storage_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __STORAGE_COMMON__ diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h index 4a4845193539..925e7cb7a582 100644 --- a/include/linux/qed/tcp_common.h +++ b/include/linux/qed/tcp_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __TCP_COMMON__ -- cgit v1.2.3 From 663eacd899ac131dcfc2279184c1ce3c4fd2815f Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 29 Jun 2020 14:05:09 +0300 Subject: net: qed: update copyright years Set the actual copyright holder and years in all qed source files. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 1 + include/linux/qed/eth_common.h | 1 + include/linux/qed/fcoe_common.h | 1 + include/linux/qed/iscsi_common.h | 1 + include/linux/qed/iwarp_common.h | 1 + include/linux/qed/qed_chain.h | 1 + include/linux/qed/qed_eth_if.h | 1 + include/linux/qed/qed_fcoe_if.h | 1 + include/linux/qed/qed_if.h | 1 + include/linux/qed/qed_iov_if.h | 1 + include/linux/qed/qed_iscsi_if.h | 1 + include/linux/qed/qed_ll2_if.h | 1 + include/linux/qed/qed_rdma_if.h | 1 + include/linux/qed/qede_rdma.h | 1 + include/linux/qed/rdma_common.h | 1 + include/linux/qed/roce_common.h | 1 + include/linux/qed/storage_common.h | 1 + include/linux/qed/tcp_common.h | 1 + 18 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 294d01eae5cb..977807e1be53 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2016 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _COMMON_HSI_H diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index a9566ef3c2ce..cd1207ad4ada 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __ETH_COMMON__ diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h index a669d7d84284..68eda1c21cde 100644 --- a/include/linux/qed/fcoe_common.h +++ b/include/linux/qed/fcoe_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __FCOE_COMMON__ diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index 7ca89fb9247f..157019f716f1 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __ISCSI_COMMON__ diff --git a/include/linux/qed/iwarp_common.h b/include/linux/qed/iwarp_common.h index 23583e644257..14f9e4c0ddd9 100644 --- a/include/linux/qed/iwarp_common.h +++ b/include/linux/qed/iwarp_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __IWARP_COMMON__ diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index e6e25197f7cb..92cdc79e5019 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_CHAIN_H diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 7803dedbcb52..812a4d751163 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_ETH_IF_H diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h index 65d0317ef67e..16752eca5cbd 100644 --- a/include/linux/qed/qed_fcoe_if.h +++ b/include/linux/qed/qed_fcoe_if.h @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_FCOE_IF_H #define _QED_FCOE_IF_H diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 4a36608ff3a8..5ca081cd2ed9 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_IF_H diff --git a/include/linux/qed/qed_iov_if.h b/include/linux/qed/qed_iov_if.h index c2ca8196def9..8e31a28e51b9 100644 --- a/include/linux/qed/qed_iov_if.h +++ b/include/linux/qed/qed_iov_if.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_IOV_IF_H diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h index 89912c6c440c..04180d9af560 100644 --- a/include/linux/qed/qed_iscsi_if.h +++ b/include/linux/qed/qed_iscsi_if.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_ISCSI_IF_H diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index 79cac277e38b..2f64ed79cee9 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_LL2_IF_H diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index 041a5b005a82..f464d85e88a4 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_RDMA_IF_H diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index 20ed7f2c55bb..072da2f6da37 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qedr NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef QEDE_ROCE_H diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h index 3e3f01136c06..bab078b25834 100644 --- a/include/linux/qed/rdma_common.h +++ b/include/linux/qed/rdma_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __RDMA_COMMON__ diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h index 89065f023813..ccddd7a96b67 100644 --- a/include/linux/qed/roce_common.h +++ b/include/linux/qed/roce_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __ROCE_COMMON__ diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h index 34f069c79067..91896e8793bf 100644 --- a/include/linux/qed/storage_common.h +++ b/include/linux/qed/storage_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __STORAGE_COMMON__ diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h index 925e7cb7a582..2b2c87d10e0a 100644 --- a/include/linux/qed/tcp_common.h +++ b/include/linux/qed/tcp_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __TCP_COMMON__ -- cgit v1.2.3 From 8b11c20a658de159fcf18ebce4f2acfdf747ff25 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 29 Jun 2020 14:03:41 +0200 Subject: phy: un-inline devm_mdiobus_register() Functions should only be static inline if they're very short. This devres helper is already over 10 lines and it will grow soon as we'll be improving upon its approach. Pull it into mdio_devres.c. Signed-off-by: Bartosz Golaszewski Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index ecc7640705b9..7c75e1c90141 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -322,20 +322,9 @@ static inline struct mii_bus *mdiobus_alloc(void) } int __mdiobus_register(struct mii_bus *bus, struct module *owner); +int __devm_mdiobus_register(struct mii_bus *bus, struct module *owner); #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) -static inline int devm_mdiobus_register(struct mii_bus *bus) -{ - int ret; - - if (!bus->is_managed) - return -EPERM; - - ret = mdiobus_register(bus); - if (!ret) - bus->is_managed_registered = 1; - - return ret; -} +#define devm_mdiobus_register(bus) __devm_mdiobus_register(bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); -- cgit v1.2.3 From ac3a68d56651c3dad2c12c7afce065fe15267f44 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 29 Jun 2020 14:03:43 +0200 Subject: net: phy: don't abuse devres in devm_mdiobus_register() We currently have two managed helpers for mdiobus - devm_mdiobus_alloc() and devm_mdiobus_register(). The idea behind devres is that the release callback releases whatever resource the devm function allocates. In the mdiobus case however there's no devres associated with the device by devm_mdiobus_register(). Instead the release callback for devm_mdiobus_alloc(): _devm_mdiobus_free() unregisters the device if it is marked as managed. This all seems wrong. The managed structure shouldn't need to know or care about whether it's managed or not - and this is the case now for struct mii_bus. The devres wrapper should be opaque to the managed resource. This changeset makes devm_mdiobus_alloc() and devm_mdiobus_register() conform to common devres standards: devm_mdiobus_alloc() allocates a devres structure and registers a callback that will call mdiobus_free(). __devm_mdiobus_register() allocated another devres and registers a callback that will unregister the bus. Signed-off-by: Bartosz Golaszewski Signed-off-by: David S. Miller --- include/linux/phy.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 7c75e1c90141..101a48fa6750 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -261,9 +261,6 @@ struct mii_bus { int (*reset)(struct mii_bus *bus); struct mdio_bus_stats stats[PHY_MAX_ADDR]; - unsigned int is_managed:1; /* is device-managed */ - unsigned int is_managed_registered:1; - /* * A lock to ensure that only one thing can read/write * the MDIO bus at a time @@ -322,9 +319,11 @@ static inline struct mii_bus *mdiobus_alloc(void) } int __mdiobus_register(struct mii_bus *bus, struct module *owner); -int __devm_mdiobus_register(struct mii_bus *bus, struct module *owner); +int __devm_mdiobus_register(struct device *dev, struct mii_bus *bus, + struct module *owner); #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) -#define devm_mdiobus_register(bus) __devm_mdiobus_register(bus, THIS_MODULE) +#define devm_mdiobus_register(dev, bus) \ + __devm_mdiobus_register(dev, bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); @@ -335,7 +334,6 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) } struct mii_bus *mdio_find_bus(const char *mdio_name); -void devm_mdiobus_free(struct device *dev, struct mii_bus *bus); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); #define PHY_INTERRUPT_DISABLED false -- cgit v1.2.3 From a0bd96f5aed2108505386733abe76f37362c2f50 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 29 Jun 2020 14:03:44 +0200 Subject: of: mdio: remove the 'extern' keyword from function declarations The 'extern' keyword in headers doesn't have any benefit. Remove them all from the of_mdio.h header. Signed-off-by: Bartosz Golaszewski Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 37 ++++++++++++++++++------------------- 1 file changed, 18 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 0f61a4ac6bcf..ba8e157f24ad 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -12,27 +12,26 @@ #include #if IS_ENABLED(CONFIG_OF_MDIO) -extern bool of_mdiobus_child_is_phy(struct device_node *child); -extern int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); -extern struct phy_device *of_phy_find_device(struct device_node *phy_np); -extern struct phy_device *of_phy_connect(struct net_device *dev, - struct device_node *phy_np, - void (*hndlr)(struct net_device *), - u32 flags, phy_interface_t iface); -extern struct phy_device * +bool of_mdiobus_child_is_phy(struct device_node *child); +int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); +struct phy_device *of_phy_find_device(struct device_node *phy_np); +struct phy_device * +of_phy_connect(struct net_device *dev, struct device_node *phy_np, + void (*hndlr)(struct net_device *), u32 flags, + phy_interface_t iface); +struct phy_device * of_phy_get_and_connect(struct net_device *dev, struct device_node *np, void (*hndlr)(struct net_device *)); -struct phy_device *of_phy_attach(struct net_device *dev, - struct device_node *phy_np, u32 flags, - phy_interface_t iface); - -extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); -extern int of_phy_register_fixed_link(struct device_node *np); -extern void of_phy_deregister_fixed_link(struct device_node *np); -extern bool of_phy_is_fixed_link(struct device_node *np); -extern int of_mdiobus_phy_device_register(struct mii_bus *mdio, - struct phy_device *phy, - struct device_node *child, u32 addr); +struct phy_device * +of_phy_attach(struct net_device *dev, struct device_node *phy_np, + u32 flags, phy_interface_t iface); + +struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); +int of_phy_register_fixed_link(struct device_node *np); +void of_phy_deregister_fixed_link(struct device_node *np); +bool of_phy_is_fixed_link(struct device_node *np); +int of_mdiobus_phy_device_register(struct mii_bus *mdio, struct phy_device *phy, + struct device_node *child, u32 addr); static inline int of_mdio_parse_addr(struct device *dev, const struct device_node *np) -- cgit v1.2.3 From 14eeb6e086d6b9004c600e5f0f62bacb458ecfba Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 29 Jun 2020 14:03:45 +0200 Subject: of: mdio: provide devm_of_mdiobus_register() Implement a managed variant of of_mdiobus_register(). We need to make mdio_devres into its own module because otherwise we'd hit circular sumbol dependencies between phylib and of_mdio. Signed-off-by: Bartosz Golaszewski Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index ba8e157f24ad..1efb88d9f892 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -8,12 +8,15 @@ #ifndef __LINUX_OF_MDIO_H #define __LINUX_OF_MDIO_H +#include #include #include #if IS_ENABLED(CONFIG_OF_MDIO) bool of_mdiobus_child_is_phy(struct device_node *child); int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); +int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, + struct device_node *np); struct phy_device *of_phy_find_device(struct device_node *phy_np); struct phy_device * of_phy_connect(struct net_device *dev, struct device_node *phy_np, -- cgit v1.2.3 From 4ec0a44ba8d797876ff416fc0317a0169483d240 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 1 Jul 2020 10:42:31 +0300 Subject: of_graph: add of_graph_is_present() In some cases it's very useful to silently check whether port node exists at all in a device-tree before proceeding with parsing the graph. The DRM bridges code is one example of such case where absence of a graph in a device-tree is a legit condition. This patch adds of_graph_is_present() which returns true if given device-tree node contains OF graph port. Reviewed-by: Rob Herring Signed-off-by: Dmitry Osipenko Reviewed-by: Laurent Pinchart Signed-off-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20200701074232.13632-2-digetx@gmail.com --- include/linux/of_graph.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h index 01038a6aade0..4d7756087b6b 100644 --- a/include/linux/of_graph.h +++ b/include/linux/of_graph.h @@ -38,6 +38,7 @@ struct of_endpoint { child = of_graph_get_next_endpoint(parent, child)) #ifdef CONFIG_OF +bool of_graph_is_present(const struct device_node *node); int of_graph_parse_endpoint(const struct device_node *node, struct of_endpoint *endpoint); int of_graph_get_endpoint_count(const struct device_node *np); @@ -56,6 +57,11 @@ struct device_node *of_graph_get_remote_node(const struct device_node *node, u32 port, u32 endpoint); #else +static inline bool of_graph_is_present(const struct device_node *node) +{ + return false; +} + static inline int of_graph_parse_endpoint(const struct device_node *node, struct of_endpoint *endpoint) { -- cgit v1.2.3 From e1915eec54a6b4902664eaf6fb7a20de5624c4dd Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 26 Jun 2020 22:37:41 +0200 Subject: backlight: sky81452: Convert to GPIO descriptors The SKY81452 backlight driver just obtains a GPIO (named "gpios" in the device tree) drives it high and leaves it high until the driver is removed. Switch to use GPIO descriptors for this, simple and straight-forward. Cc: Gyungoh Yoo Signed-off-by: Linus Walleij Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- include/linux/platform_data/sky81452-backlight.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/sky81452-backlight.h b/include/linux/platform_data/sky81452-backlight.h index 02653d92d84f..d6f46670d923 100644 --- a/include/linux/platform_data/sky81452-backlight.h +++ b/include/linux/platform_data/sky81452-backlight.h @@ -9,11 +9,13 @@ #ifndef _SKY81452_BACKLIGHT_H #define _SKY81452_BACKLIGHT_H +#include + /** * struct sky81452_platform_data * @name: backlight driver name. If it is not defined, default name is lcd-backlight. - * @gpio_enable:GPIO number which control EN pin + * @gpios_enable:GPIO descriptor which control EN pin * @enable: Enable mask for current sink channel 1, 2, 3, 4, 5 and 6. * @ignore_pwm: true if DPWMI should be ignored. * @dpwm_mode: true is DPWM dimming mode, otherwise Analog dimming mode. @@ -23,7 +25,7 @@ */ struct sky81452_bl_platform_data { const char *name; - int gpio_enable; + struct gpio_desc *gpiod_enable; unsigned int enable; bool ignore_pwm; bool dpwm_mode; -- cgit v1.2.3 From 08bf73a6f056d84fd52a58c5d165523dd84be535 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 26 Jun 2020 22:37:42 +0200 Subject: backlight: sky81452: Privatize platform data The only way the platform data for the SKY81452 ever gets populated is through the device tree. The MFD device is bothered with this for no reason at all. Just allocate the platform data in the driver and be happy. Cc: Gyungoh Yoo Signed-off-by: Linus Walleij Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- include/linux/mfd/sky81452.h | 2 -- include/linux/platform_data/sky81452-backlight.h | 37 ------------------------ 2 files changed, 39 deletions(-) delete mode 100644 include/linux/platform_data/sky81452-backlight.h (limited to 'include/linux') diff --git a/include/linux/mfd/sky81452.h b/include/linux/mfd/sky81452.h index d469aa481243..b08570ff34df 100644 --- a/include/linux/mfd/sky81452.h +++ b/include/linux/mfd/sky81452.h @@ -9,11 +9,9 @@ #ifndef _SKY81452_H #define _SKY81452_H -#include #include struct sky81452_platform_data { - struct sky81452_bl_platform_data *bl_pdata; struct regulator_init_data *regulator_init_data; }; diff --git a/include/linux/platform_data/sky81452-backlight.h b/include/linux/platform_data/sky81452-backlight.h deleted file mode 100644 index d6f46670d923..000000000000 --- a/include/linux/platform_data/sky81452-backlight.h +++ /dev/null @@ -1,37 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * sky81452.h SKY81452 backlight driver - * - * Copyright 2014 Skyworks Solutions Inc. - * Author : Gyungoh Yoo - */ - -#ifndef _SKY81452_BACKLIGHT_H -#define _SKY81452_BACKLIGHT_H - -#include - -/** - * struct sky81452_platform_data - * @name: backlight driver name. - If it is not defined, default name is lcd-backlight. - * @gpios_enable:GPIO descriptor which control EN pin - * @enable: Enable mask for current sink channel 1, 2, 3, 4, 5 and 6. - * @ignore_pwm: true if DPWMI should be ignored. - * @dpwm_mode: true is DPWM dimming mode, otherwise Analog dimming mode. - * @phase_shift:true is phase shift mode. - * @short_detecion_threshold: It should be one of 4, 5, 6 and 7V. - * @boost_current_limit: It should be one of 2300, 2750mA. - */ -struct sky81452_bl_platform_data { - const char *name; - struct gpio_desc *gpiod_enable; - unsigned int enable; - bool ignore_pwm; - bool dpwm_mode; - bool phase_shift; - unsigned int short_detection_threshold; - unsigned int boost_current_limit; -}; - -#endif -- cgit v1.2.3 From 43ff98695cc01779407d489fd546359c188222b4 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 28 Jun 2020 19:54:45 -0700 Subject: usb: fix kernel-doc warnings and formatting in Fix kernel-doc warnings in : ../include/linux/usb.h:713: warning: Function parameter or member 'use_generic_driver' not described in 'usb_device' ../include/linux/usb.h:1253: warning: Function parameter or member 'match' not described in 'usb_device_driver' ../include/linux/usb.h:1253: warning: Function parameter or member 'id_table' not described in 'usb_device_driver' Also drop an extra blank line and fix indentation. Fixes: 77419aa403ca ("USB: Fallback to generic driver when specific driver fails") Fixes: 88b7381a939d ("USB: Select better matching USB drivers when available") Signed-off-by: Randy Dunlap Cc: Bastien Nocera Link: https://lore.kernel.org/r/7014bab2-268c-69f6-7ef5-57fbd45c8b08@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 9f3c721c70dc..c86e4ec4d00f 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -620,9 +620,9 @@ struct usb3_lpm_parameters { * Management to be disabled for this usb_device. This count should only * be manipulated by those functions, with the bandwidth_mutex is held. * @hub_delay: cached value consisting of: - * parent->hub_delay + wHubDelay + tTPTransmissionDelay (40ns) - * + * parent->hub_delay + wHubDelay + tTPTransmissionDelay (40ns) * Will be used as wValue for SetIsochDelay requests. + * @use_generic_driver: ask driver core to reprobe using the generic driver. * * Notes: * Usbcore drivers should not set usbdev->state directly. Instead use @@ -1215,6 +1215,7 @@ struct usb_driver { * struct usb_device_driver - identifies USB device driver to usbcore * @name: The driver name should be unique among USB drivers, * and should normally be the same as the module name. + * @match: If set, used for better device/driver matching. * @probe: Called to see if the driver is willing to manage a particular * device. If it is, probe returns zero and uses dev_set_drvdata() * to associate driver-specific data with the device. If unwilling @@ -1227,13 +1228,16 @@ struct usb_driver { * @dev_groups: Attributes attached to the device that will be created once it * is bound to the driver. * @drvwrap: Driver-model core structure wrapper. + * @id_table: used with @match() to select better matching driver at + * probe() time. * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend * for devices bound to this driver. * @generic_subclass: if set to 1, the generic USB driver's probe, disconnect, * resume and suspend functions will be called in addition to the driver's * own, so this part of the setup does not need to be replicated. * - * USB drivers must provide all the fields listed above except drvwrap. + * USB drivers must provide all the fields listed above except drvwrap, + * match, and id_table. */ struct usb_device_driver { const char *name; -- cgit v1.2.3 From f470a6554854123f763f6273e8266bd6ee89a97a Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Wed, 1 Jul 2020 14:56:15 +0300 Subject: usb: typec: Combine the definitions for Accessory and USB modes There is no need to describe them sparately. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20200701115618.22482-2-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec_altmode.h | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index d834e236c6df..a4b65eaa0f62 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -95,13 +95,7 @@ enum { * * Port drivers can use TYPEC_MODE_AUDIO and TYPEC_MODE_DEBUG as the mode * value for typec_set_mode() when accessory modes are supported. - */ -enum { - TYPEC_MODE_AUDIO = TYPEC_STATE_MODAL, /* Audio Accessory */ - TYPEC_MODE_DEBUG, /* Debug Accessory */ -}; - -/* + * * USB4 also requires that the pins on the connector are repurposed, just like * Alternate Modes. USB4 mode is however not entered with the Enter Mode Command * like the Alternate Modes are, but instead with a special Enter_USB Message. @@ -112,9 +106,11 @@ enum { * state values, just like the Accessory Modes. */ enum { - TYPEC_MODE_USB2 = TYPEC_MODE_DEBUG, /* USB 2.0 mode */ + TYPEC_MODE_USB2 = TYPEC_STATE_MODAL, /* USB 2.0 mode */ TYPEC_MODE_USB3, /* USB 3.2 mode */ - TYPEC_MODE_USB4 /* USB4 mode */ + TYPEC_MODE_USB4, /* USB4 mode */ + TYPEC_MODE_AUDIO, /* Audio Accessory */ + TYPEC_MODE_DEBUG, /* Debug Accessory */ }; #define TYPEC_MODAL_STATE(_state_) ((_state_) + TYPEC_STATE_MODAL) -- cgit v1.2.3 From ad8db94d6813dc659bd4de0531a8a1150559eafb Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Wed, 1 Jul 2020 14:56:16 +0300 Subject: usb: typec: Add data structure for Enter_USB message This data structure can be delivered to the mux drivers when Enter_USB Message is used exactly the same way as the Alternate Mode specific data structures are delivered to the mux drivers when Enter Mode Messages are used. The Enter_USB data structure shall have all details related to the Enter_USB Message, most importantly the Enter_USB Date Object that was used. Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20200701115618.22482-3-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 5daa1c49761c..9cb1bec94b71 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -72,6 +72,20 @@ enum typec_orientation { TYPEC_ORIENTATION_REVERSE, }; +/* + * struct enter_usb_data - Enter_USB Message details + * @eudo: Enter_USB Data Object + * @active_link_training: Active Cable Plug Link Training + * + * @active_link_training is a flag that should be set with uni-directional SBRX + * communication, and left 0 with passive cables and with bi-directional SBRX + * communication. + */ +struct enter_usb_data { + u32 eudo; + unsigned char active_link_training:1; +}; + /* * struct usb_pd_identity - USB Power Delivery identity data * @id_header: ID Header VDO -- cgit v1.2.3 From f695ca3886ce72b027af7aa6040cd420cae2088c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 10:59:39 +0200 Subject: block: remove the request_queue argument from blk_queue_split The queue can be trivially derived from the bio, so pass one less argument. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 15497782c176..d002defc1789 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -871,7 +871,7 @@ extern void blk_rq_unprep_clone(struct request *rq); extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern int blk_rq_append_bio(struct request *rq, struct bio **bio); -extern void blk_queue_split(struct request_queue *, struct bio **); +extern void blk_queue_split(struct bio **); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, unsigned int, void __user *); -- cgit v1.2.3 From c62b37d96b6eb3ec5ae4cbe00db107bf15aebc93 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 10:59:43 +0200 Subject: block: move ->make_request_fn to struct block_device_operations The make_request_fn is a little weird in that it sits directly in struct request_queue instead of an operation vector. Replace it with a block_device_operations method called submit_bio (which describes much better what it does). Also remove the request_queue argument to it, as the queue can be derived pretty trivially from the bio. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 +- include/linux/blkdev.h | 7 ++----- include/linux/lightnvm.h | 3 +-- 3 files changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index faa340b70123..23230c1d031e 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -596,6 +596,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq) rq->q->mq_ops->cleanup_rq(rq); } -blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio); +blk_qc_t blk_mq_submit_bio(struct bio *bio); #endif diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d002defc1789..083ffc5bc51b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -286,8 +286,6 @@ static inline unsigned short req_get_ioprio(struct request *req) struct blk_queue_ctx; -typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); - struct bio_vec; enum blk_eh_timer_return { @@ -398,8 +396,6 @@ struct request_queue { struct blk_queue_stats *stats; struct rq_qos *rq_qos; - make_request_fn *make_request_fn; - const struct blk_mq_ops *mq_ops; /* sw queues */ @@ -1162,7 +1158,7 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, extern void blk_dump_rq_flags(struct request *, char *); bool __must_check blk_get_queue(struct request_queue *); -struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id); +struct request_queue *blk_alloc_queue(int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); @@ -1778,6 +1774,7 @@ static inline void blk_ksm_unregister(struct request_queue *q) { } struct block_device_operations { + blk_qc_t (*submit_bio) (struct bio *bio); int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index ee8ec2e68055..1db223710b28 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -631,7 +631,6 @@ static inline int nvm_next_ppa_in_chk(struct nvm_tgt_dev *dev, return last; } -typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); typedef sector_t (nvm_tgt_capacity_fn)(void *); typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *, int flags); @@ -650,7 +649,7 @@ struct nvm_tgt_type { int flags; /* target entry points */ - nvm_tgt_make_rq_fn *make_rq; + const struct block_device_operations *bops; nvm_tgt_capacity_fn *capacity; /* module-specific init/teardown */ -- cgit v1.2.3 From ed00aabd5eb9fb44d6aff1173234a2e911b9fead Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 10:59:44 +0200 Subject: block: rename generic_make_request to submit_bio_noacct generic_make_request has always been very confusingly misnamed, so rename it to submit_bio_noacct to make it clear that it is submit_bio minus accounting and a few checks. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 083ffc5bc51b..b73cfa6a5141 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -852,7 +852,7 @@ static inline void rq_flush_dcache_pages(struct request *rq) extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); -extern blk_qc_t generic_make_request(struct bio *bio); +blk_qc_t submit_bio_noacct(struct bio *bio); extern blk_qc_t direct_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); -- cgit v1.2.3 From 5a6c35f9af416114588298aa7a90b15bbed15a41 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 10:59:47 +0200 Subject: block: remove direct_make_request Now that submit_bio_noacct has a decent blk-mq fast path there is no more need for this bypass. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b73cfa6a5141..1cc913ffdbe2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -853,7 +853,6 @@ static inline void rq_flush_dcache_pages(struct request *rq) extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); blk_qc_t submit_bio_noacct(struct bio *bio); -extern blk_qc_t direct_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern struct request *blk_get_request(struct request_queue *, unsigned int op, -- cgit v1.2.3 From 6b7b181b67aa8177e57732723106a0411570a86d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Jun 2020 10:01:55 +0200 Subject: block: remove the bd_block_size field from struct block_device We can trivially calculate the block size from the inodes i_blkbits variable. Use that instead of keeping two redundant copies of the information in slightly different formats. Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 1 - include/linux/blkdev.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index a602132cbe32..b01cd19bbe8a 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -33,7 +33,6 @@ struct block_device { struct list_head bd_holder_disks; #endif struct block_device * bd_contains; - unsigned bd_block_size; u8 bd_partno; struct hd_struct * bd_part; /* number of times partitions within this device have been opened. */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1cc913ffdbe2..408eb66a82fd 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1543,7 +1543,7 @@ static inline unsigned int blksize_bits(unsigned int size) static inline unsigned int block_size(struct block_device *bdev) { - return bdev->bd_block_size; + return 1 << bdev->bd_inode->i_blkbits; } int kblockd_schedule_work(struct work_struct *work); -- cgit v1.2.3 From e556f6ba10f0f3c3484a1597382ceaec1e7bc700 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Jun 2020 10:01:56 +0200 Subject: block: remove the bd_queue field from struct block_device Just use bd_disk->queue instead. Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index b01cd19bbe8a..667cd365fd04 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -39,7 +39,6 @@ struct block_device { unsigned bd_part_count; int bd_invalidated; struct gendisk * bd_disk; - struct request_queue * bd_queue; struct backing_dev_info *bd_bdi; struct list_head bd_list; /* -- cgit v1.2.3 From 47b5e00322a3033851ab304f3c3873aebdfb4979 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Jun 2020 10:01:57 +0200 Subject: block: remove the unused bd_private field from struct block_device Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 667cd365fd04..b5f7105806e4 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -41,13 +41,6 @@ struct block_device { struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; struct list_head bd_list; - /* - * Private data. You must have bd_claim'ed the block_device - * to use this. NOTE: bd_claim allows an owner to claim - * the same device multiple times, the owner must take special - * care to not mess up bd_private for that case. - */ - unsigned long bd_private; /* The counter of freeze processes */ int bd_fsfreeze_count; -- cgit v1.2.3 From 1008fe6dc36dd87dfd02d4307f49162f0b4f1665 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Jun 2020 10:01:58 +0200 Subject: block: remove the all_bdevs list Instead just iterate over the inodes for the block device superblock. Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index b5f7105806e4..07facaf62b72 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -40,7 +40,6 @@ struct block_device { int bd_invalidated; struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; - struct list_head bd_list; /* The counter of freeze processes */ int bd_fsfreeze_count; -- cgit v1.2.3 From d141b8bc5773cbbaf5b8530f08f94fc10fff9e8c Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 29 Jun 2020 23:28:43 -0700 Subject: perf: Expose get/put_callchain_entry() Sanitize and expose get/put_callchain_entry(). This would be used by bpf stack map. Suggested-by: Peter Zijlstra Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200630062846.664389-2-songliubraving@fb.com --- include/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b4bb32082342..00ab5efa3833 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1244,6 +1244,8 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); +extern struct perf_callchain_entry *get_callchain_entry(int *rctx); +extern void put_callchain_entry(int rctx); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; -- cgit v1.2.3 From fa28dcb82a38f8e3993b0fae9106b1a80b59e4f0 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 29 Jun 2020 23:28:44 -0700 Subject: bpf: Introduce helper bpf_get_task_stack() Introduce helper bpf_get_task_stack(), which dumps stack trace of given task. This is different to bpf_get_stack(), which gets stack track of current task. One potential use case of bpf_get_task_stack() is to call it from bpf_iter__task and dump all /proc//stack to a seq_file. bpf_get_task_stack() uses stack_trace_save_tsk() instead of get_perf_callchain() for kernel stack. The benefit of this choice is that stack_trace_save_tsk() doesn't require changes in arch/. The downside of using stack_trace_save_tsk() is that stack_trace_save_tsk() dumps the stack trace to unsigned long array. For 32-bit systems, we need to translate it to u64 array. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200630062846.664389-3-songliubraving@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3d2ade703a35..0cd7f6884c5c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1627,6 +1627,7 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; +extern const struct bpf_func_proto bpf_get_task_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; -- cgit v1.2.3 From 1fc2dd1864c2b18860fb619caeee758504c3aac8 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 1 Jul 2020 16:53:40 +0100 Subject: firmware: arm_scmi: Add notification protocol-registration Add the core SCMI notifications protocol-registration support: allow protocols to register their own set of supported events, during their initialization phase. Notification core can track multiple platform instances by their handles. Link: https://lore.kernel.org/r/20200701155348.52864-2-cristian.marussi@arm.com Reviewed-by: Jonathan Cameron Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 73911d156a39..9a34b02a9cce 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -233,6 +233,8 @@ struct scmi_reset_ops { * protocol(for internal use only) * @reset_priv: pointer to private data structure specific to reset * protocol(for internal use only) + * @notify_priv: pointer to private data structure specific to notifications + * (for internal use only) */ struct scmi_handle { struct device *dev; @@ -248,6 +250,7 @@ struct scmi_handle { void *power_priv; void *sensor_priv; void *reset_priv; + void *notify_priv; }; enum scmi_std_protocol { -- cgit v1.2.3 From e7c215f358a350c4bc326b9cea86763f480a97f9 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 1 Jul 2020 16:53:41 +0100 Subject: firmware: arm_scmi: Add notification callbacks-registration Add the core SCMI notifications callbacks-registration support: allow users to register their own callbacks against the desired events. Whenever a registration request is issued against a still non existent event, mark such request as pending for later processing, in order to account for possible late initializations of SCMI Protocols associated to loadable drivers. Link: https://lore.kernel.org/r/20200701155348.52864-3-cristian.marussi@arm.com Reviewed-by: Jonathan Cameron Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 46 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 9a34b02a9cce..26957d6872a5 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -9,6 +9,7 @@ #define _LINUX_SCMI_PROTOCOL_H #include +#include #include #define SCMI_MAX_STR_SIZE 16 @@ -213,6 +214,49 @@ struct scmi_reset_ops { int (*deassert)(const struct scmi_handle *handle, u32 domain); }; +/** + * struct scmi_notify_ops - represents notifications' operations provided by + * SCMI core + * @register_event_notifier: Register a notifier_block for the requested event + * @unregister_event_notifier: Unregister a notifier_block for the requested + * event + * + * A user can register/unregister its own notifier_block against the wanted + * platform instance regarding the desired event identified by the + * tuple: (proto_id, evt_id, src_id) using the provided register/unregister + * interface where: + * + * @handle: The handle identifying the platform instance to use + * @proto_id: The protocol ID as in SCMI Specification + * @evt_id: The message ID of the desired event as in SCMI Specification + * @src_id: A pointer to the desired source ID if different sources are + * possible for the protocol (like domain_id, sensor_id...etc) + * + * @src_id can be provided as NULL if it simply does NOT make sense for + * the protocol at hand, OR if the user is explicitly interested in + * receiving notifications from ANY existent source associated to the + * specified proto_id / evt_id. + * + * Received notifications are finally delivered to the registered users, + * invoking the callback provided with the notifier_block *nb as follows: + * + * int user_cb(nb, evt_id, report) + * + * with: + * + * @nb: The notifier block provided by the user + * @evt_id: The message ID of the delivered event + * @report: A custom struct describing the specific event delivered + */ +struct scmi_notify_ops { + int (*register_event_notifier)(const struct scmi_handle *handle, + u8 proto_id, u8 evt_id, u32 *src_id, + struct notifier_block *nb); + int (*unregister_event_notifier)(const struct scmi_handle *handle, + u8 proto_id, u8 evt_id, u32 *src_id, + struct notifier_block *nb); +}; + /** * struct scmi_handle - Handle returned to ARM SCMI clients for usage. * @@ -223,6 +267,7 @@ struct scmi_reset_ops { * @clk_ops: pointer to set of clock protocol operations * @sensor_ops: pointer to set of sensor protocol operations * @reset_ops: pointer to set of reset protocol operations + * @notify_ops: pointer to set of notifications related operations * @perf_priv: pointer to private data structure specific to performance * protocol(for internal use only) * @clk_priv: pointer to private data structure specific to clock @@ -244,6 +289,7 @@ struct scmi_handle { struct scmi_power_ops *power_ops; struct scmi_sensor_ops *sensor_ops; struct scmi_reset_ops *reset_ops; + struct scmi_notify_ops *notify_ops; /* for protocol internal use */ void *perf_priv; void *clk_priv; -- cgit v1.2.3 From e27077bc04d5a2e09a0860ca086e1d55adf6a16d Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 1 Jul 2020 16:53:44 +0100 Subject: firmware: arm_scmi: Add power notifications support Make SCMI power protocol register with the notification core. Link: https://lore.kernel.org/r/20200701155348.52864-6-cristian.marussi@arm.com Reviewed-by: Jonathan Cameron Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 26957d6872a5..81dc3b132fda 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -375,4 +375,16 @@ typedef int (*scmi_prot_init_fn_t)(struct scmi_handle *); int scmi_protocol_register(int protocol_id, scmi_prot_init_fn_t fn); void scmi_protocol_unregister(int protocol_id); +/* SCMI Notification API - Custom Event Reports */ +enum scmi_notification_events { + SCMI_EVENT_POWER_STATE_CHANGED = 0x0, +}; + +struct scmi_power_state_changed_report { + u64 timestamp; + u32 agent_id; + u32 domain_id; + u32 power_state; +}; + #endif /* _LINUX_SCMI_PROTOCOL_H */ -- cgit v1.2.3 From fb5086dc4746184a9325fc25411226a750fb252c Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 1 Jul 2020 16:53:45 +0100 Subject: firmware: arm_scmi: Add perf notifications support Make SCMI perf protocol register with the notification core. Link: https://lore.kernel.org/r/20200701155348.52864-7-cristian.marussi@arm.com Reviewed-by: Jonathan Cameron Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 81dc3b132fda..65ad83ddde70 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -378,6 +378,8 @@ void scmi_protocol_unregister(int protocol_id); /* SCMI Notification API - Custom Event Reports */ enum scmi_notification_events { SCMI_EVENT_POWER_STATE_CHANGED = 0x0, + SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED = 0x0, + SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1, }; struct scmi_power_state_changed_report { @@ -387,4 +389,19 @@ struct scmi_power_state_changed_report { u32 power_state; }; +struct scmi_perf_limits_report { + u64 timestamp; + u32 agent_id; + u32 domain_id; + u32 range_max; + u32 range_min; +}; + +struct scmi_perf_level_report { + u64 timestamp; + u32 agent_id; + u32 domain_id; + u32 performance_level; +}; + #endif /* _LINUX_SCMI_PROTOCOL_H */ -- cgit v1.2.3 From 128e3e9311a95bab6b267b7a93eb9ebe2347dbda Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 1 Jul 2020 16:53:46 +0100 Subject: firmware: arm_scmi: Add sensor notifications support Make SCMI sensor protocol register with the notification core. Link: https://lore.kernel.org/r/20200701155348.52864-8-cristian.marussi@arm.com Reviewed-by: Jonathan Cameron Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 65ad83ddde70..d0ea4a5037e7 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -176,18 +176,13 @@ enum scmi_sensor_class { * * @count_get: get the count of sensors provided by SCMI * @info_get: get the information of the specified sensor - * @trip_point_notify: control notifications on cross-over events for - * the trip-points * @trip_point_config: selects and configures a trip-point of interest * @reading_get: gets the current value of the sensor */ struct scmi_sensor_ops { int (*count_get)(const struct scmi_handle *handle); - const struct scmi_sensor_info *(*info_get) (const struct scmi_handle *handle, u32 sensor_id); - int (*trip_point_notify)(const struct scmi_handle *handle, - u32 sensor_id, bool enable); int (*trip_point_config)(const struct scmi_handle *handle, u32 sensor_id, u8 trip_id, u64 trip_value); int (*reading_get)(const struct scmi_handle *handle, u32 sensor_id, @@ -380,6 +375,7 @@ enum scmi_notification_events { SCMI_EVENT_POWER_STATE_CHANGED = 0x0, SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED = 0x0, SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1, + SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0, }; struct scmi_power_state_changed_report { @@ -404,4 +400,11 @@ struct scmi_perf_level_report { u32 performance_level; }; +struct scmi_sensor_trip_point_report { + u64 timestamp; + u32 agent_id; + u32 sensor_id; + u32 trip_point_desc; +}; + #endif /* _LINUX_SCMI_PROTOCOL_H */ -- cgit v1.2.3 From 469ca1822d64e4a786935576edb696c52119aa11 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 1 Jul 2020 16:53:47 +0100 Subject: firmware: arm_scmi: Add reset notifications support Make SCMI reset protocol register with the notification core. Link: https://lore.kernel.org/r/20200701155348.52864-9-cristian.marussi@arm.com Reviewed-by: Jonathan Cameron Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index d0ea4a5037e7..d04d66be596d 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -376,6 +376,7 @@ enum scmi_notification_events { SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED = 0x0, SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1, SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0, + SCMI_EVENT_RESET_ISSUED = 0x0, }; struct scmi_power_state_changed_report { @@ -407,4 +408,11 @@ struct scmi_sensor_trip_point_report { u32 trip_point_desc; }; +struct scmi_reset_issued_report { + u64 timestamp; + u32 agent_id; + u32 domain_id; + u32 reset_state; +}; + #endif /* _LINUX_SCMI_PROTOCOL_H */ -- cgit v1.2.3 From 585dfab3fb80e67b3a54790b3d5ef2991feb3950 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 1 Jul 2020 16:53:48 +0100 Subject: firmware: arm_scmi: Add base notifications support Make SCMI base protocol register with the notification core. Link: https://lore.kernel.org/r/20200701155348.52864-10-cristian.marussi@arm.com Reviewed-by: Jonathan Cameron Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index d04d66be596d..46d98be92466 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -377,6 +377,7 @@ enum scmi_notification_events { SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1, SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0, SCMI_EVENT_RESET_ISSUED = 0x0, + SCMI_EVENT_BASE_ERROR_EVENT = 0x0, }; struct scmi_power_state_changed_report { @@ -415,4 +416,12 @@ struct scmi_reset_issued_report { u32 reset_state; }; +struct scmi_base_error_report { + u64 timestamp; + u32 agent_id; + bool fatal; + u16 cmd_count; + u64 reports[0]; +}; + #endif /* _LINUX_SCMI_PROTOCOL_H */ -- cgit v1.2.3 From 3022c6a1b4b76c40aab9dcdf5142c501f3d3ae8c Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 25 Jun 2020 16:51:03 -0700 Subject: driver-core: Introduce DEVICE_ATTR_ADMIN_{RO,RW} A common pattern for using plain DEVICE_ATTR() instead of DEVICE_ATTR_RO() and DEVICE_ATTR_RW() is for attributes that want to limit read to only root. I.e. many users of DEVICE_ATTR() are specifying 0400 or 0600 for permissions. Given the expectation that CAP_SYS_ADMIN is needed to access these sensitive attributes and an explicit helper with the _ADMIN_ identifier for DEVICE_ATTR_ADMIN_{RO,RW}. Cc: "Rafael J. Wysocki" Signed-off-by: Dan Williams Link: https://lore.kernel.org/r/159312906372.1850128.11611897078988158727.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 ++++ include/linux/sysfs.h | 7 +++++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 15460a5ac024..d7c2570368fa 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -128,8 +128,12 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, __ATTR_PREALLOC(_name, _mode, _show, _store) #define DEVICE_ATTR_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW(_name) +#define DEVICE_ATTR_ADMIN_RW(_name) \ + struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600) #define DEVICE_ATTR_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO(_name) +#define DEVICE_ATTR_ADMIN_RO(_name) \ + struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400) #define DEVICE_ATTR_WO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_WO(_name) #define DEVICE_ULONG_ATTR(_name, _mode, _var) \ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 86067dbe7745..34e84122f635 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -123,6 +123,13 @@ struct attribute_group { .show = _name##_show, \ } +#define __ATTR_RW_MODE(_name, _mode) { \ + .attr = { .name = __stringify(_name), \ + .mode = VERIFY_OCTAL_PERMISSIONS(_mode) }, \ + .show = _name##_show, \ + .store = _name##_store, \ +} + #define __ATTR_WO(_name) { \ .attr = { .name = __stringify(_name), .mode = 0200 }, \ .store = _name##_store, \ -- cgit v1.2.3 From 9fc54012d7aec4b23f2042dc37b26738f3e68942 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Tue, 30 Jun 2020 18:17:07 -0400 Subject: audit: remove unused !CONFIG_AUDITSYSCALL __audit_inode* stubs Added 14 years ago in commit 73241ccca0f7 ("[PATCH] Collect more inode information during syscall processing.") but never used however needlessly churned no less than 10 times since. Remove the unused __audit_inode* stubs in the !CONFIG_AUDITSYSCALL case. Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index d93739f7a35a..b5478c64bc69 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -579,14 +579,6 @@ static inline struct filename *audit_reusename(const __user char *name) } static inline void audit_getname(struct filename *name) { } -static inline void __audit_inode(struct filename *name, - const struct dentry *dentry, - unsigned int flags) -{ } -static inline void __audit_inode_child(struct inode *parent, - const struct dentry *dentry, - const unsigned char type) -{ } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) -- cgit v1.2.3 From d40f0b6f2e21f2400ae8b1b120d11877d9ffd8ec Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 29 Jun 2020 16:41:06 -0700 Subject: spi: Avoid setting the chip select if we don't need to On some SPI controllers (like spi-geni-qcom) setting the chip select is a heavy operation. For instance on spi-geni-qcom, with the current code, is was measured as taking upwards of 20 us. Even on SPI controllers that aren't as heavy, setting the chip select is at least something like a MMIO operation over some peripheral bus which isn't as fast as a RAM access. While it would be good to find ways to mitigate problems like this in the drivers for those SPI controllers, it can also be noted that the SPI framework could also help out. Specifically, in some situations, we can see the SPI framework calling the driver's set_cs() with the same parameter several times in a row. This is specifically observed when looking at the way the Chrome OS EC SPI driver (cros_ec_spi) works but other drivers likely trip it to some extent. Let's solve this by caching the chip select state in the core and only calling into the controller if there was a change. We check not only the "enable" state but also the chip select mode (active high or active low) since controllers may care about both the mode and the enable flag in their callback. Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20200629164103.1.Ied8e8ad8bbb2df7f947e3bc5ea1c315e041785a2@changeid Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index b4917df79637..0e67a9a3a1d3 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -368,6 +368,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @cur_msg_prepared: spi_prepare_message was called for the currently * in-flight message * @cur_msg_mapped: message has been mapped for DMA + * @last_cs_enable: was enable true on the last call to set_cs. + * @last_cs_mode_high: was (mode & SPI_CS_HIGH) true on the last call to set_cs. * @xfer_completion: used by core transfer_one_message() * @busy: message pump is busy * @running: message pump is running @@ -604,6 +606,8 @@ struct spi_controller { bool auto_runtime_pm; bool cur_msg_prepared; bool cur_msg_mapped; + bool last_cs_enable; + bool last_cs_mode_high; bool fallback; struct completion xfer_completion; size_t max_dma_len; -- cgit v1.2.3 From 10dd8573b09e84b81539d939d55ebdb6a36c5f3a Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 29 Jun 2020 13:54:59 +0530 Subject: cpufreq: Register governors at core_initcall Currently, most CPUFreq governors are registered at the core_initcall time when the given governor is the default one, and the module_init time otherwise. In preparation for letting users specify the default governor on the kernel command line, change all of them to be registered at the core_initcall unconditionally, as it is already the case for the schedutil and performance governors. This will allow us to assume that builtin governors have been registered before the built-in CPUFreq drivers probe. And since all governors have similar init/exit patterns now, introduce two new macros, cpufreq_governor_{init,exit}(), to factorize the code. Acked-by: Viresh Kumar Signed-off-by: Quentin Perret Signed-off-by: Viresh Kumar [ rjw: Changelog ] Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 3494f6763597..e62b022cb07e 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -577,6 +577,20 @@ unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy); int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); +#define cpufreq_governor_init(__governor) \ +static int __init __governor##_init(void) \ +{ \ + return cpufreq_register_governor(&__governor); \ +} \ +core_initcall(__governor##_init) + +#define cpufreq_governor_exit(__governor) \ +static void __exit __governor##_exit(void) \ +{ \ + return cpufreq_unregister_governor(&__governor); \ +} \ +module_exit(__governor##_exit) + struct cpufreq_governor *cpufreq_default_governor(void); struct cpufreq_governor *cpufreq_fallback_governor(void); -- cgit v1.2.3 From 67dd0772396905a108c37202d4a5949ab69131a0 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 29 Jun 2020 08:50:05 +0200 Subject: device: remove 'extern' attribute from function prototypes in device.h Functions are declared 'extern' implicitly by the compiler. There's no reason to prepend every prototype with it. Remove the 'extern' keyword from all function declarations in linux/device.h. Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20200629065008.27620-4-brgl@bgdev.pl Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 223 ++++++++++++++++++++++++------------------------- 1 file changed, 107 insertions(+), 116 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index d7c2570368fa..9a62f7f43d55 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -149,68 +149,66 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, struct device_attribute dev_attr_##_name = \ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) -extern int device_create_file(struct device *device, - const struct device_attribute *entry); -extern void device_remove_file(struct device *dev, - const struct device_attribute *attr); -extern bool device_remove_file_self(struct device *dev, - const struct device_attribute *attr); -extern int __must_check device_create_bin_file(struct device *dev, +int device_create_file(struct device *device, + const struct device_attribute *entry); +void device_remove_file(struct device *dev, + const struct device_attribute *attr); +bool device_remove_file_self(struct device *dev, + const struct device_attribute *attr); +int __must_check device_create_bin_file(struct device *dev, const struct bin_attribute *attr); -extern void device_remove_bin_file(struct device *dev, - const struct bin_attribute *attr); +void device_remove_bin_file(struct device *dev, + const struct bin_attribute *attr); /* device resource management */ typedef void (*dr_release_t)(struct device *dev, void *res); typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); #ifdef CONFIG_DEBUG_DEVRES -extern void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, - int nid, const char *name) __malloc; +void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, + int nid, const char *name) __malloc; #define devres_alloc(release, size, gfp) \ __devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release) #define devres_alloc_node(release, size, gfp, nid) \ __devres_alloc_node(release, size, gfp, nid, #release) #else -extern void *devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, - int nid) __malloc; +void *devres_alloc_node(dr_release_t release, size_t size, + gfp_t gfp, int nid) __malloc; static inline void *devres_alloc(dr_release_t release, size_t size, gfp_t gfp) { return devres_alloc_node(release, size, gfp, NUMA_NO_NODE); } #endif -extern void devres_for_each_res(struct device *dev, dr_release_t release, - dr_match_t match, void *match_data, - void (*fn)(struct device *, void *, void *), - void *data); -extern void devres_free(void *res); -extern void devres_add(struct device *dev, void *res); -extern void *devres_find(struct device *dev, dr_release_t release, - dr_match_t match, void *match_data); -extern void *devres_get(struct device *dev, void *new_res, - dr_match_t match, void *match_data); -extern void *devres_remove(struct device *dev, dr_release_t release, - dr_match_t match, void *match_data); -extern int devres_destroy(struct device *dev, dr_release_t release, - dr_match_t match, void *match_data); -extern int devres_release(struct device *dev, dr_release_t release, - dr_match_t match, void *match_data); +void devres_for_each_res(struct device *dev, dr_release_t release, + dr_match_t match, void *match_data, + void (*fn)(struct device *, void *, void *), + void *data); +void devres_free(void *res); +void devres_add(struct device *dev, void *res); +void *devres_find(struct device *dev, dr_release_t release, + dr_match_t match, void *match_data); +void *devres_get(struct device *dev, void *new_res, + dr_match_t match, void *match_data); +void *devres_remove(struct device *dev, dr_release_t release, + dr_match_t match, void *match_data); +int devres_destroy(struct device *dev, dr_release_t release, + dr_match_t match, void *match_data); +int devres_release(struct device *dev, dr_release_t release, + dr_match_t match, void *match_data); /* devres group */ -extern void * __must_check devres_open_group(struct device *dev, void *id, - gfp_t gfp); -extern void devres_close_group(struct device *dev, void *id); -extern void devres_remove_group(struct device *dev, void *id); -extern int devres_release_group(struct device *dev, void *id); +void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp); +void devres_close_group(struct device *dev, void *id); +void devres_remove_group(struct device *dev, void *id); +int devres_release_group(struct device *dev, void *id); /* managed devm_k.alloc/kfree for device drivers */ -extern void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __malloc; -extern __printf(3, 0) -char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, - va_list ap) __malloc; -extern __printf(3, 4) -char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...) __malloc; +void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __malloc; +__printf(3, 0) char *devm_kvasprintf(struct device *dev, gfp_t gfp, + const char *fmt, va_list ap) __malloc; +__printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp, + const char *fmt, ...) __malloc; static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) { return devm_kmalloc(dev, size, gfp | __GFP_ZERO); @@ -230,16 +228,14 @@ static inline void *devm_kcalloc(struct device *dev, { return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO); } -extern void devm_kfree(struct device *dev, const void *p); -extern char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc; -extern const char *devm_kstrdup_const(struct device *dev, - const char *s, gfp_t gfp); -extern void *devm_kmemdup(struct device *dev, const void *src, size_t len, - gfp_t gfp); +void devm_kfree(struct device *dev, const void *p); +char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc; +const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp); +void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp); -extern unsigned long devm_get_free_pages(struct device *dev, - gfp_t gfp_mask, unsigned int order); -extern void devm_free_pages(struct device *dev, unsigned long addr); +unsigned long devm_get_free_pages(struct device *dev, + gfp_t gfp_mask, unsigned int order); +void devm_free_pages(struct device *dev, unsigned long addr); void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res); @@ -655,8 +651,7 @@ static inline const char *dev_name(const struct device *dev) return kobject_name(&dev->kobj); } -extern __printf(2, 3) -int dev_set_name(struct device *dev, const char *name, ...); +__printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...); #ifdef CONFIG_NUMA static inline int dev_to_node(struct device *dev) @@ -813,39 +808,38 @@ static inline bool dev_has_sync_state(struct device *dev) /* * High level routines for use by the bus drivers */ -extern int __must_check device_register(struct device *dev); -extern void device_unregister(struct device *dev); -extern void device_initialize(struct device *dev); -extern int __must_check device_add(struct device *dev); -extern void device_del(struct device *dev); -extern int device_for_each_child(struct device *dev, void *data, - int (*fn)(struct device *dev, void *data)); -extern int device_for_each_child_reverse(struct device *dev, void *data, - int (*fn)(struct device *dev, void *data)); -extern struct device *device_find_child(struct device *dev, void *data, - int (*match)(struct device *dev, void *data)); -extern struct device *device_find_child_by_name(struct device *parent, - const char *name); -extern int device_rename(struct device *dev, const char *new_name); -extern int device_move(struct device *dev, struct device *new_parent, - enum dpm_order dpm_order); -extern int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); -extern const char *device_get_devnode(struct device *dev, - umode_t *mode, kuid_t *uid, kgid_t *gid, - const char **tmp); +int __must_check device_register(struct device *dev); +void device_unregister(struct device *dev); +void device_initialize(struct device *dev); +int __must_check device_add(struct device *dev); +void device_del(struct device *dev); +int device_for_each_child(struct device *dev, void *data, + int (*fn)(struct device *dev, void *data)); +int device_for_each_child_reverse(struct device *dev, void *data, + int (*fn)(struct device *dev, void *data)); +struct device *device_find_child(struct device *dev, void *data, + int (*match)(struct device *dev, void *data)); +struct device *device_find_child_by_name(struct device *parent, + const char *name); +int device_rename(struct device *dev, const char *new_name); +int device_move(struct device *dev, struct device *new_parent, + enum dpm_order dpm_order); +int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); +const char *device_get_devnode(struct device *dev, umode_t *mode, kuid_t *uid, + kgid_t *gid, const char **tmp); static inline bool device_supports_offline(struct device *dev) { return dev->bus && dev->bus->offline && dev->bus->online; } -extern void lock_device_hotplug(void); -extern void unlock_device_hotplug(void); -extern int lock_device_hotplug_sysfs(void); -extern int device_offline(struct device *dev); -extern int device_online(struct device *dev); -extern void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); -extern void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); +void lock_device_hotplug(void); +void unlock_device_hotplug(void); +int lock_device_hotplug_sysfs(void); +int device_offline(struct device *dev); +int device_online(struct device *dev); +void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); +void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); static inline int dev_num_vf(struct device *dev) @@ -858,14 +852,13 @@ static inline int dev_num_vf(struct device *dev) /* * Root device objects for grouping under /sys/devices */ -extern struct device *__root_device_register(const char *name, - struct module *owner); +struct device *__root_device_register(const char *name, struct module *owner); /* This is a macro to avoid include problems with THIS_MODULE */ #define root_device_register(name) \ __root_device_register(name, THIS_MODULE) -extern void root_device_unregister(struct device *root); +void root_device_unregister(struct device *root); static inline void *dev_get_platdata(const struct device *dev) { @@ -876,33 +869,31 @@ static inline void *dev_get_platdata(const struct device *dev) * Manual binding of a device to driver. See drivers/base/bus.c * for information on use. */ -extern int __must_check device_bind_driver(struct device *dev); -extern void device_release_driver(struct device *dev); -extern int __must_check device_attach(struct device *dev); -extern int __must_check driver_attach(struct device_driver *drv); -extern void device_initial_probe(struct device *dev); -extern int __must_check device_reprobe(struct device *dev); +int __must_check device_bind_driver(struct device *dev); +void device_release_driver(struct device *dev); +int __must_check device_attach(struct device *dev); +int __must_check driver_attach(struct device_driver *drv); +void device_initial_probe(struct device *dev); +int __must_check device_reprobe(struct device *dev); -extern bool device_is_bound(struct device *dev); +bool device_is_bound(struct device *dev); /* * Easy functions for dynamically creating devices on the fly */ -extern __printf(5, 6) -struct device *device_create(struct class *cls, struct device *parent, - dev_t devt, void *drvdata, - const char *fmt, ...); -extern __printf(6, 7) -struct device *device_create_with_groups(struct class *cls, - struct device *parent, dev_t devt, void *drvdata, - const struct attribute_group **groups, - const char *fmt, ...); -extern void device_destroy(struct class *cls, dev_t devt); - -extern int __must_check device_add_groups(struct device *dev, - const struct attribute_group **groups); -extern void device_remove_groups(struct device *dev, - const struct attribute_group **groups); +__printf(5, 6) struct device * +device_create(struct class *cls, struct device *parent, dev_t devt, + void *drvdata, const char *fmt, ...); +__printf(6, 7) struct device * +device_create_with_groups(struct class *cls, struct device *parent, dev_t devt, + void *drvdata, const struct attribute_group **groups, + const char *fmt, ...); +void device_destroy(struct class *cls, dev_t devt); + +int __must_check device_add_groups(struct device *dev, + const struct attribute_group **groups); +void device_remove_groups(struct device *dev, + const struct attribute_group **groups); static inline int __must_check device_add_group(struct device *dev, const struct attribute_group *grp) @@ -920,14 +911,14 @@ static inline void device_remove_group(struct device *dev, return device_remove_groups(dev, groups); } -extern int __must_check devm_device_add_groups(struct device *dev, +int __must_check devm_device_add_groups(struct device *dev, const struct attribute_group **groups); -extern void devm_device_remove_groups(struct device *dev, - const struct attribute_group **groups); -extern int __must_check devm_device_add_group(struct device *dev, - const struct attribute_group *grp); -extern void devm_device_remove_group(struct device *dev, - const struct attribute_group *grp); +void devm_device_remove_groups(struct device *dev, + const struct attribute_group **groups); +int __must_check devm_device_add_group(struct device *dev, + const struct attribute_group *grp); +void devm_device_remove_group(struct device *dev, + const struct attribute_group *grp); /* * Platform "fixup" functions - allow the platform to have their say @@ -944,21 +935,21 @@ extern int (*platform_notify_remove)(struct device *dev); * get_device - atomically increment the reference count for the device. * */ -extern struct device *get_device(struct device *dev); -extern void put_device(struct device *dev); -extern bool kill_device(struct device *dev); +struct device *get_device(struct device *dev); +void put_device(struct device *dev); +bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS -extern int devtmpfs_mount(void); +int devtmpfs_mount(void); #else static inline int devtmpfs_mount(void) { return 0; } #endif /* drivers/base/power/shutdown.c */ -extern void device_shutdown(void); +void device_shutdown(void); /* debugging and troubleshooting/diagnostic helpers. */ -extern const char *dev_driver_string(const struct device *dev); +const char *dev_driver_string(const struct device *dev); /* Device links interface. */ struct device_link *device_link_add(struct device *consumer, -- cgit v1.2.3 From 36847f9e3e56c192ef95e7669df38189443530a0 Mon Sep 17 00:00:00 2001 From: Richard Gong Date: Mon, 15 Jun 2020 09:29:05 -0500 Subject: firmware: stratix10-svc: correct reconfig flag and timeout values Correct the incorrect flag value for COMMAND_RECONFIG_FLAG_PARTIAL and increase FPGA reconfig timeout values so that Intel service layer and FPGA manager drivers can work with all versions of firmware. Signed-off-by: Richard Gong Link: https://lore.kernel.org/r/1592231348-31334-2-git-send-email-richard.gong@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/intel/stratix10-svc-client.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index 64213c3e82f5..040bc3f3bedd 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -54,18 +54,17 @@ * Flag bit for COMMAND_RECONFIG * * COMMAND_RECONFIG_FLAG_PARTIAL: - * Set to FPGA configuration type (full or partial), the default - * is full reconfig. + * Set to FPGA configuration type (full or partial). */ -#define COMMAND_RECONFIG_FLAG_PARTIAL 0 +#define COMMAND_RECONFIG_FLAG_PARTIAL 1 /** * Timeout settings for service clients: * timeout value used in Stratix10 FPGA manager driver. * timeout value used in RSU driver */ -#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 100 -#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 240 +#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 300 +#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 720 #define SVC_RSU_REQUEST_TIMEOUT_MS 300 struct stratix10_svc_chan; -- cgit v1.2.3 From bf0e5bf68a207b14727caf13da576339590a9504 Mon Sep 17 00:00:00 2001 From: Richard Gong Date: Mon, 15 Jun 2020 09:29:06 -0500 Subject: firmware: stratix10-svc: extend svc to support new RSU features Extend Intel Stratix10 service layer driver to support new RSU DCMF versions and max retry parameter. DCMF = Decision Configuration Management Firmware. The max retry parameter is the maximum times the images is allowed to reload itself before giving up and starting RSU failover flow. Signed-off-by: Richard Gong Link: https://lore.kernel.org/r/1592231348-31334-3-git-send-email-richard.gong@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/intel/stratix10-smc.h | 43 ++++++++++++++++++++++ .../linux/firmware/intel/stratix10-svc-client.h | 8 ++++ 2 files changed, 51 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h index 682dbf694007..c3e5ab014caf 100644 --- a/include/linux/firmware/intel/stratix10-smc.h +++ b/include/linux/firmware/intel/stratix10-smc.h @@ -361,3 +361,46 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) #define INTEL_SIP_SMC_FUNCID_RSU_RETRY_COUNTER 15 #define INTEL_SIP_SMC_RSU_RETRY_COUNTER \ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_RETRY_COUNTER) + +/** + * Request INTEL_SIP_SMC_RSU_DCMF_VERSION + * + * Sync call used by service driver at EL1 to query DCMF (Decision + * Configuration Management Firmware) version from FW + * + * Call register usage: + * a0 INTEL_SIP_SMC_RSU_DCMF_VERSION + * a1-7 not used + * + * Return status + * a0 INTEL_SIP_SMC_STATUS_OK + * a1 dcmf1 | dcmf0 + * a2 dcmf3 | dcmf2 + * + * Or + * + * a0 INTEL_SIP_SMC_RSU_ERROR + */ +#define INTEL_SIP_SMC_FUNCID_RSU_DCMF_VERSION 16 +#define INTEL_SIP_SMC_RSU_DCMF_VERSION \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_DCMF_VERSION) + +/** + * Request INTEL_SIP_SMC_RSU_MAX_RETRY + * + * Sync call used by service driver at EL1 to query max retry value from FW + * + * Call register usage: + * a0 INTEL_SIP_SMC_RSU_MAX_RETRY + * a1-7 not used + * + * Return status + * a0 INTEL_SIP_SMC_STATUS_OK + * a1 max retry value + * + * Or + * a0 INTEL_SIP_SMC_RSU_ERROR + */ +#define INTEL_SIP_SMC_FUNCID_RSU_MAX_RETRY 18 +#define INTEL_SIP_SMC_RSU_MAX_RETRY \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_MAX_RETRY) diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index 040bc3f3bedd..a93d85932eb9 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -98,6 +98,12 @@ struct stratix10_svc_chan; * * @COMMAND_RSU_RETRY: query firmware for the current image's retry counter, * return status is SVC_STATUS_OK or SVC_STATUS_ERROR + * + * @COMMAND_RSU_MAX_RETRY: query firmware for the max retry value, + * return status is SVC_STATUS_OK or SVC_STATUS_ERROR + * + * @COMMAND_RSU_DCMF_VERSION: query firmware for the DCMF version, return status + * is SVC_STATUS_OK or SVC_STATUS_ERROR */ enum stratix10_svc_command_code { COMMAND_NOOP = 0, @@ -109,6 +115,8 @@ enum stratix10_svc_command_code { COMMAND_RSU_UPDATE, COMMAND_RSU_NOTIFY, COMMAND_RSU_RETRY, + COMMAND_RSU_MAX_RETRY, + COMMAND_RSU_DCMF_VERSION, }; /** -- cgit v1.2.3 From c8d141ce1b85d29aba008c8caa1faf174e564843 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Jul 2020 19:15:55 +0200 Subject: USB: Fix up terminology in include files USB is a HOST/DEVICE protocol, as per the specification and all documentation. Fix up terms that are not applicable to make things match up with the terms used through the rest of the USB stack. Acked-by: Felipe Balbi Link: https://lore.kernel.org/r/20200701171555.3198836-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 +- include/linux/usb/ch9.h | 8 ++++---- include/linux/usb/gadget.h | 7 ++++--- 3 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index c86e4ec4d00f..c28fc391444a 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -422,7 +422,7 @@ struct usb_devmap { * Allocated per bus (tree of devices) we have: */ struct usb_bus { - struct device *controller; /* host/master side hardware */ + struct device *controller; /* host side hardware */ struct device *sysdev; /* as seen from firmware or bus */ int busnum; /* Bus number (in order of reg) */ const char *bus_name; /* stable id (PCI slot_name etc) */ diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 58b83066bea4..604c6c514a50 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -6,13 +6,13 @@ * Wireless USB 1.0 (spread around). Linux has several APIs in C that * need these: * - * - the master/host side Linux-USB kernel driver API; + * - the host side Linux-USB kernel driver API; * - the "usbfs" user space API; and - * - the Linux "gadget" slave/device/peripheral side driver API. + * - the Linux "gadget" device/peripheral side driver API. * * USB 2.0 adds an additional "On The Go" (OTG) mode, which lets systems - * act either as a USB master/host or as a USB slave/device. That means - * the master and slave side APIs benefit from working well together. + * act either as a USB host or as a USB device. That means the host and + * device side APIs benefit from working well together. * * There's also "Wireless USB", using low power short range radios for * peripheral interconnection but otherwise building on the USB framework. diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 6a178177e4c9..298b334e2951 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -4,7 +4,8 @@ * * We call the USB code inside a Linux-based peripheral device a "gadget" * driver, except for the hardware-specific bus glue. One USB host can - * master many USB gadgets, but the gadgets are only slaved to one host. + * talk to many USB gadgets, but the gadgets are only able to communicate + * to one host. * * * (C) Copyright 2002-2004 by David Brownell @@ -328,7 +329,7 @@ struct usb_gadget_ops { }; /** - * struct usb_gadget - represents a usb slave device + * struct usb_gadget - represents a usb device * @work: (internal use) Workqueue to be used for sysfs_notify() * @udc: struct usb_udc pointer for this gadget * @ops: Function pointers used to access hardware-specific operations. @@ -602,7 +603,7 @@ static inline int usb_gadget_activate(struct usb_gadget *gadget) /*-------------------------------------------------------------------------*/ /** - * struct usb_gadget_driver - driver for usb 'slave' devices + * struct usb_gadget_driver - driver for usb gadget devices * @function: String describing the gadget's function * @max_speed: Highest speed the driver handles. * @setup: Invoked for ep0 control requests that aren't handled by -- cgit v1.2.3 From 4dca650991e4175b8d5bae7ff6f1637a0c42be4a Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Wed, 20 May 2020 13:59:06 +0300 Subject: net/mlx5: Enable QP number request when creating IPoIB underlay QP If in the process of creating the underlay QP for an IPoIB interface the user has set the address and specifically the 1st-3rd bytes representing the QP number, use the requested QP number when creating the underlay QP. For a user to be able to request a QP number on QP creation, the MKEY_BY_NAME NVCONFIG should be set. As mkey_by_name and qp_by_name are coupled in FW. This requires driver to query the mkey_by_name max cap during initialization and set the current cap if it was enabled in FW. Signed-off-by: Michael Guralnik Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a227518c70cf..3786888cb1ba 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1392,7 +1392,10 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 bf[0x1]; u8 driver_version[0x1]; u8 pad_tx_eth_packet[0x1]; - u8 reserved_at_263[0x8]; + u8 reserved_at_263[0x3]; + u8 mkey_by_name[0x1]; + u8 reserved_at_267[0x4]; + u8 log_bf_reg_size[0x5]; u8 reserved_at_270[0x8]; @@ -7712,8 +7715,10 @@ struct mlx5_ifc_create_qp_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x8]; + u8 input_qpn[0x18]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; u8 ece[0x20]; -- cgit v1.2.3 From d7bf2ebebc2bd61ab95e2a8e33541ef282f303d4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Fri, 3 Jul 2020 22:26:43 +0200 Subject: sched: consistently handle layer3 header accesses in the presence of VLANs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are a couple of places in net/sched/ that check skb->protocol and act on the value there. However, in the presence of VLAN tags, the value stored in skb->protocol can be inconsistent based on whether VLAN acceleration is enabled. The commit quoted in the Fixes tag below fixed the users of skb->protocol to use a helper that will always see the VLAN ethertype. However, most of the callers don't actually handle the VLAN ethertype, but expect to find the IP header type in the protocol field. This means that things like changing the ECN field, or parsing diffserv values, stops working if there's a VLAN tag, or if there are multiple nested VLAN tags (QinQ). To fix this, change the helper to take an argument that indicates whether the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we make sure to skip all of them, so behaviour is consistent even in QinQ mode. To make the helper usable from the ECN code, move it to if_vlan.h instead of pkt_sched.h. v3: - Remove empty lines - Move vlan variable definitions inside loop in skb_protocol() - Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and bpf_skb_ecn_set_ce() v2: - Use eth_type_vlan() helper in skb_protocol() - Also fix code that reads skb->protocol directly - Change a couple of 'if/else if' statements to switch constructs to avoid calling the helper twice Reported-by: Ilya Ponetayev Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index b05e855f1ddd..427a5b8597c2 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -308,6 +308,34 @@ static inline bool eth_type_vlan(__be16 ethertype) } } +/* A getter for the SKB protocol field which will handle VLAN tags consistently + * whether VLAN acceleration is enabled or not. + */ +static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan) +{ + unsigned int offset = skb_mac_offset(skb) + sizeof(struct ethhdr); + __be16 proto = skb->protocol; + + if (!skip_vlan) + /* VLAN acceleration strips the VLAN header from the skb and + * moves it to skb->vlan_proto + */ + return skb_vlan_tag_present(skb) ? skb->vlan_proto : proto; + + while (eth_type_vlan(proto)) { + struct vlan_hdr vhdr, *vh; + + vh = skb_header_pointer(skb, offset, sizeof(vhdr), &vhdr); + if (!vh) + break; + + proto = vh->h_vlan_encapsulated_proto; + offset += sizeof(vhdr); + } + + return proto; +} + static inline bool vlan_hw_offload_capable(netdev_features_t features, __be16 proto) { -- cgit v1.2.3 From 8fa88a88d573093868565a1afba43b5ae5b3a316 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Fri, 3 Jul 2020 16:56:45 +0100 Subject: genirq: Remove preflow handler support That was put in place for sparc64, and blackfin also used it for some time; sparc64 no longer uses those, and blackfin is dead. As there are no more users, remove preflow handlers. Signed-off-by: Valentin Schneider Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20200703155645.29703-3-valentin.schneider@arm.com --- include/linux/irqdesc.h | 15 --------------- include/linux/irqhandler.h | 1 - 2 files changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 8f2820c5e69e..5745491303e0 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -22,7 +22,6 @@ struct pt_regs; * @irq_common_data: per irq and chip data passed down to chip functions * @kstat_irqs: irq stats per cpu * @handle_irq: highlevel irq-events handler - * @preflow_handler: handler called before the flow handler (currently used by sparc) * @action: the irq action chain * @status_use_accessors: status information * @core_internal_state__do_not_mess_with_it: core internal status information @@ -58,9 +57,6 @@ struct irq_desc { struct irq_data irq_data; unsigned int __percpu *kstat_irqs; irq_flow_handler_t handle_irq; -#ifdef CONFIG_IRQ_PREFLOW_FASTEOI - irq_preflow_handler_t preflow_handler; -#endif struct irqaction *action; /* IRQ action list */ unsigned int status_use_accessors; unsigned int core_internal_state__do_not_mess_with_it; @@ -268,15 +264,4 @@ irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class, } } -#ifdef CONFIG_IRQ_PREFLOW_FASTEOI -static inline void -__irq_set_preflow_handler(unsigned int irq, irq_preflow_handler_t handler) -{ - struct irq_desc *desc; - - desc = irq_to_desc(irq); - desc->preflow_handler = handler; -} -#endif - #endif diff --git a/include/linux/irqhandler.h b/include/linux/irqhandler.h index 1e6f4e7123d6..c30f454a9518 100644 --- a/include/linux/irqhandler.h +++ b/include/linux/irqhandler.h @@ -10,6 +10,5 @@ struct irq_desc; struct irq_data; typedef void (*irq_flow_handler_t)(struct irq_desc *desc); -typedef void (*irq_preflow_handler_t)(struct irq_data *data); #endif -- cgit v1.2.3 From ce548396a4334a4c6e9faada8db89dacf35822b2 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 26 Jun 2020 13:53:18 +0200 Subject: media: mach-omap1: board-ams-delta.c: remove soc_camera dependencies The soc_camera driver is about to be removed, so drop camera support from this board. Note that the soc_camera driver itself has long since been deprecated and can't be compiled anymore (it depends on BROKEN), so camera support on this board has been broken for a long time (at least since 4.6 when the omap1_camera.c was removed from soc_camera). Signed-off-by: Hans Verkuil Cc: Tony Lindgren Acked-by: Arnd Bergmann Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/media/omap1_camera.h | 32 ------------------------ 1 file changed, 32 deletions(-) delete mode 100644 include/linux/platform_data/media/omap1_camera.h (limited to 'include/linux') diff --git a/include/linux/platform_data/media/omap1_camera.h b/include/linux/platform_data/media/omap1_camera.h deleted file mode 100644 index 386439db68de..000000000000 --- a/include/linux/platform_data/media/omap1_camera.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Header for V4L2 SoC Camera driver for OMAP1 Camera Interface - * - * Copyright (C) 2010, Janusz Krzysztofik - */ - -#ifndef __MEDIA_OMAP1_CAMERA_H_ -#define __MEDIA_OMAP1_CAMERA_H_ - -#include - -#define OMAP1_CAMERA_IOSIZE 0x1c - -enum omap1_cam_vb_mode { - OMAP1_CAM_DMA_CONTIG = 0, - OMAP1_CAM_DMA_SG, -}; - -#define OMAP1_CAMERA_MIN_BUF_COUNT(x) ((x) == OMAP1_CAM_DMA_CONTIG ? 3 : 2) - -struct omap1_cam_platform_data { - unsigned long camexclk_khz; - unsigned long lclk_khz_max; - unsigned long flags; -}; - -#define OMAP1_CAMERA_LCLK_RISING BIT(0) -#define OMAP1_CAMERA_RST_LOW BIT(1) -#define OMAP1_CAMERA_RST_HIGH BIT(2) - -#endif /* __MEDIA_OMAP1_CAMERA_H_ */ -- cgit v1.2.3 From 5fec25f2cb959cb5f189d7f6127bee3efc782530 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 24 Jun 2020 16:34:57 -0500 Subject: umh: Capture the pid in umh_pipe_setup The pid in struct subprocess_info is only used by umh_clean_and_save_pid to write the pid into umh_info. Instead always capture the pid on struct umh_info in umh_pipe_setup, removing code that is specific to user mode drivers from the common user path of user mode helpers. v1: https://lkml.kernel.org/r/87h7uygf9i.fsf_-_@x220.int.ebiederm.org v2: https://lkml.kernel.org/r/875zb97iix.fsf_-_@x220.int.ebiederm.org Link: https://lkml.kernel.org/r/20200702164140.4468-1-ebiederm@xmission.com Reviewed-by: Greg Kroah-Hartman Acked-by: Alexei Starovoitov Tested-by: Alexei Starovoitov Signed-off-by: "Eric W. Biederman" --- include/linux/umh.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/umh.h b/include/linux/umh.h index 0c08de356d0d..aae16a0ebd0f 100644 --- a/include/linux/umh.h +++ b/include/linux/umh.h @@ -25,7 +25,6 @@ struct subprocess_info { struct file *file; int wait; int retval; - pid_t pid; int (*init)(struct subprocess_info *info, struct cred *new); void (*cleanup)(struct subprocess_info *info); void *data; -- cgit v1.2.3 From 21d598280675c463ea1b264fab06e9614aacd1e1 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 24 Jun 2020 17:01:18 -0500 Subject: umh: Remove call_usermodehelper_setup_file. The only caller of call_usermodehelper_setup_file is fork_usermode_blob. In fork_usermode_blob replace call_usermodehelper_setup_file with call_usermodehelper_setup and delete fork_usermodehelper_setup_file. For this to work the argv_free is moved from umh_clean_and_save_pid to fork_usermode_blob. v1: https://lkml.kernel.org/r/87zh8qf0mp.fsf_-_@x220.int.ebiederm.org v2: https://lkml.kernel.org/r/87o8p163u1.fsf_-_@x220.int.ebiederm.org Link: https://lkml.kernel.org/r/20200702164140.4468-4-ebiederm@xmission.com Reviewed-by: Greg Kroah-Hartman Acked-by: Alexei Starovoitov Tested-by: Alexei Starovoitov Signed-off-by: "Eric W. Biederman" --- include/linux/umh.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/umh.h b/include/linux/umh.h index aae16a0ebd0f..de08af00c68a 100644 --- a/include/linux/umh.h +++ b/include/linux/umh.h @@ -39,9 +39,6 @@ call_usermodehelper_setup(const char *path, char **argv, char **envp, int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *), void *data); -struct subprocess_info *call_usermodehelper_setup_file(struct file *file, - int (*init)(struct subprocess_info *info, struct cred *new), - void (*cleanup)(struct subprocess_info *), void *data); struct umh_info { const char *cmdline; struct file *pipe_to_umh; -- cgit v1.2.3 From 884c5e683b67dbc52892e24c29eed864f330ec08 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 26 Jun 2020 12:23:00 -0500 Subject: umh: Separate the user mode driver and the user mode helper support This makes it clear which code is part of the core user mode helper support and which code is needed to implement user mode drivers. This makes the kernel smaller for everyone who does not use a usermode driver. v1: https://lkml.kernel.org/r/87tuyyf0ln.fsf_-_@x220.int.ebiederm.org v2: https://lkml.kernel.org/r/87imf963s6.fsf_-_@x220.int.ebiederm.org Link: https://lkml.kernel.org/r/20200702164140.4468-5-ebiederm@xmission.com Reviewed-by: Greg Kroah-Hartman Acked-by: Alexei Starovoitov Tested-by: Alexei Starovoitov Signed-off-by: "Eric W. Biederman" --- include/linux/bpfilter.h | 2 +- include/linux/sched.h | 8 -------- include/linux/umh.h | 10 ---------- include/linux/usermode_driver.h | 30 ++++++++++++++++++++++++++++++ 4 files changed, 31 insertions(+), 19 deletions(-) create mode 100644 include/linux/usermode_driver.h (limited to 'include/linux') diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index d815622cd31e..d6d6206052a6 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -3,7 +3,7 @@ #define _LINUX_BPFILTER_H #include -#include +#include struct sock; int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, diff --git a/include/linux/sched.h b/include/linux/sched.h index b62e6aaf28f0..59d1e92bb88e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2020,14 +2020,6 @@ static inline void rseq_execve(struct task_struct *t) #endif -void __exit_umh(struct task_struct *tsk); - -static inline void exit_umh(struct task_struct *tsk) -{ - if (unlikely(tsk->flags & PF_UMH)) - __exit_umh(tsk); -} - #ifdef CONFIG_DEBUG_RSEQ void rseq_syscall(struct pt_regs *regs); diff --git a/include/linux/umh.h b/include/linux/umh.h index de08af00c68a..73173c4a07e5 100644 --- a/include/linux/umh.h +++ b/include/linux/umh.h @@ -39,16 +39,6 @@ call_usermodehelper_setup(const char *path, char **argv, char **envp, int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *), void *data); -struct umh_info { - const char *cmdline; - struct file *pipe_to_umh; - struct file *pipe_from_umh; - struct list_head list; - void (*cleanup)(struct umh_info *info); - pid_t pid; -}; -int fork_usermode_blob(void *data, size_t len, struct umh_info *info); - extern int call_usermodehelper_exec(struct subprocess_info *info, int wait); diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h new file mode 100644 index 000000000000..c5f6dc950227 --- /dev/null +++ b/include/linux/usermode_driver.h @@ -0,0 +1,30 @@ +#ifndef __LINUX_USERMODE_DRIVER_H__ +#define __LINUX_USERMODE_DRIVER_H__ + +#include + +#ifdef CONFIG_BPFILTER +void __exit_umh(struct task_struct *tsk); + +static inline void exit_umh(struct task_struct *tsk) +{ + if (unlikely(tsk->flags & PF_UMH)) + __exit_umh(tsk); +} +#else +static inline void exit_umh(struct task_struct *tsk) +{ +} +#endif + +struct umh_info { + const char *cmdline; + struct file *pipe_to_umh; + struct file *pipe_from_umh; + struct list_head list; + void (*cleanup)(struct umh_info *info); + pid_t pid; +}; +int fork_usermode_blob(void *data, size_t len, struct umh_info *info); + +#endif /* __LINUX_USERMODE_DRIVER_H__ */ -- cgit v1.2.3 From 74be2d3b80af1bb264c3b9905b52c15efc03c0fe Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 26 Jun 2020 11:16:06 -0500 Subject: umd: For clarity rename umh_info umd_info This structure is only used for user mode drivers so change the prefix from umh to umd to make that clear. v1: https://lkml.kernel.org/r/87o8p6f0kw.fsf_-_@x220.int.ebiederm.org v2: https://lkml.kernel.org/r/878sg563po.fsf_-_@x220.int.ebiederm.org Link: https://lkml.kernel.org/r/20200702164140.4468-6-ebiederm@xmission.com Reviewed-by: Greg Kroah-Hartman Acked-by: Alexei Starovoitov Tested-by: Alexei Starovoitov Signed-off-by: "Eric W. Biederman" --- include/linux/bpfilter.h | 2 +- include/linux/usermode_driver.h | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index d6d6206052a6..ec9972d822e0 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -11,7 +11,7 @@ int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen); struct bpfilter_umh_ops { - struct umh_info info; + struct umd_info info; /* since ip_getsockopt() can run in parallel, serialize access to umh */ struct mutex lock; int (*sockopt)(struct sock *sk, int optname, diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h index c5f6dc950227..7131ea611bab 100644 --- a/include/linux/usermode_driver.h +++ b/include/linux/usermode_driver.h @@ -17,14 +17,14 @@ static inline void exit_umh(struct task_struct *tsk) } #endif -struct umh_info { +struct umd_info { const char *cmdline; struct file *pipe_to_umh; struct file *pipe_from_umh; struct list_head list; - void (*cleanup)(struct umh_info *info); + void (*cleanup)(struct umd_info *info); pid_t pid; }; -int fork_usermode_blob(void *data, size_t len, struct umh_info *info); +int fork_usermode_blob(void *data, size_t len, struct umd_info *info); #endif /* __LINUX_USERMODE_DRIVER_H__ */ -- cgit v1.2.3 From 1199c6c3da5197e9924a906b9de71b8d0ac62a01 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 25 Jun 2020 11:38:08 -0500 Subject: umd: Rename umd_info.cmdline umd_info.driver_name The only thing supplied in the cmdline today is the driver name so rename the field to clarify the code. As this value is always supplied stop trying to handle the case of a NULL cmdline. Additionally since we now have a name we can count on use the driver_name any place where the code is looking for a name of the binary. v1: https://lkml.kernel.org/r/87imfef0k3.fsf_-_@x220.int.ebiederm.org v2: https://lkml.kernel.org/r/87366d63os.fsf_-_@x220.int.ebiederm.org Link: https://lkml.kernel.org/r/20200702164140.4468-7-ebiederm@xmission.com Reviewed-by: Greg Kroah-Hartman Acked-by: Alexei Starovoitov Tested-by: Alexei Starovoitov Signed-off-by: "Eric W. Biederman" --- include/linux/usermode_driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h index 7131ea611bab..48cf25e3145d 100644 --- a/include/linux/usermode_driver.h +++ b/include/linux/usermode_driver.h @@ -18,7 +18,7 @@ static inline void exit_umh(struct task_struct *tsk) #endif struct umd_info { - const char *cmdline; + const char *driver_name; struct file *pipe_to_umh; struct file *pipe_from_umh; struct list_head list; -- cgit v1.2.3 From e2dc9bf3f5275ca372001541e5f26af572976e65 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 25 Jun 2020 13:12:59 -0500 Subject: umd: Transform fork_usermode_blob into fork_usermode_driver Instead of loading a binary blob into a temporary file with shmem_kernel_file_setup load a binary blob into a temporary tmpfs filesystem. This means that the blob can be stored in an init section and discared, and it means the binary blob will have a filename so can be executed normally. The only tricky thing about this code is that in the helper function blob_to_mnt __fput_sync is used. That is because a file can not be executed if it is still open for write, and the ordinary delayed close for kernel threads does not happen soon enough, which causes the following exec to fail. The function umd_load_blob is not called with any locks so this should be safe. Executing the blob normally winds up correcting several problems with the user mode driver code discovered by Tetsuo Handa[1]. By passing an ordinary filename into the exec, it is no longer necessary to figure out how to turn a O_RDWR file descriptor into a properly referende counted O_EXEC file descriptor that forbids all writes. For path based LSMs there are no new special cases. [1] https://lore.kernel.org/linux-fsdevel/2a8775b4-1dd5-9d5c-aa42-9872445e0942@i-love.sakura.ne.jp/ v1: https://lkml.kernel.org/r/87d05mf0j9.fsf_-_@x220.int.ebiederm.org v2: https://lkml.kernel.org/r/87wo3p4p35.fsf_-_@x220.int.ebiederm.org Link: https://lkml.kernel.org/r/20200702164140.4468-8-ebiederm@xmission.com Reviewed-by: Greg Kroah-Hartman Acked-by: Alexei Starovoitov Tested-by: Alexei Starovoitov Signed-off-by: "Eric W. Biederman" --- include/linux/usermode_driver.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h index 48cf25e3145d..97c919b7147c 100644 --- a/include/linux/usermode_driver.h +++ b/include/linux/usermode_driver.h @@ -2,6 +2,7 @@ #define __LINUX_USERMODE_DRIVER_H__ #include +#include #ifdef CONFIG_BPFILTER void __exit_umh(struct task_struct *tsk); @@ -23,8 +24,11 @@ struct umd_info { struct file *pipe_from_umh; struct list_head list; void (*cleanup)(struct umd_info *info); + struct path wd; pid_t pid; }; -int fork_usermode_blob(void *data, size_t len, struct umd_info *info); +int umd_load_blob(struct umd_info *info, const void *data, size_t len); +int umd_unload_blob(struct umd_info *info); +int fork_usermode_driver(struct umd_info *info); #endif /* __LINUX_USERMODE_DRIVER_H__ */ -- cgit v1.2.3 From 55e6074e3fa67e1fb9ec140904db7e6cae6eda4b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 25 Jun 2020 13:52:50 -0500 Subject: umh: Stop calling do_execve_file With the user mode driver code changed to not set subprocess_info.file there are no more users of subproces_info.file. Remove this field from struct subprocess_info and remove the only user in call_usermodehelper_exec_async that would call do_execve_file instead of do_execve if file was set. v1: https://lkml.kernel.org/r/877dvuf0i7.fsf_-_@x220.int.ebiederm.org v2: https://lkml.kernel.org/r/87r1tx4p2a.fsf_-_@x220.int.ebiederm.org Link: https://lkml.kernel.org/r/20200702164140.4468-9-ebiederm@xmission.com Reviewed-by: Greg Kroah-Hartman Acked-by: Alexei Starovoitov Tested-by: Alexei Starovoitov Signed-off-by: "Eric W. Biederman" --- include/linux/umh.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/umh.h b/include/linux/umh.h index 73173c4a07e5..244aff638220 100644 --- a/include/linux/umh.h +++ b/include/linux/umh.h @@ -22,7 +22,6 @@ struct subprocess_info { const char *path; char **argv; char **envp; - struct file *file; int wait; int retval; int (*init)(struct subprocess_info *info, struct cred *new); -- cgit v1.2.3 From 25cf336de51b51a3e440e1893751f9532095eff0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 25 Jun 2020 13:56:40 -0500 Subject: exec: Remove do_execve_file Now that the last callser has been removed remove this code from exec. For anyone thinking of resurrecing do_execve_file please note that the code was buggy in several fundamental ways. - It did not ensure the file it was passed was read-only and that deny_write_access had been called on it. Which subtlely breaks invaniants in exec. - The caller of do_execve_file was expected to hold and put a reference to the file, but an extra reference for use by exec was not taken so that when exec put it's reference to the file an underflow occured on the file reference count. - The point of the interface was so that a pathname did not need to exist. Which breaks pathname based LSMs. Tetsuo Handa originally reported these issues[1]. While it was clear that deny_write_access was missing the fundamental incompatibility with the passed in O_RDWR filehandle was not immediately recognized. All of these issues were fixed by modifying the usermode driver code to have a path, so it did not need this hack. Reported-by: Tetsuo Handa [1] https://lore.kernel.org/linux-fsdevel/2a8775b4-1dd5-9d5c-aa42-9872445e0942@i-love.sakura.ne.jp/ v1: https://lkml.kernel.org/r/871rm2f0hi.fsf_-_@x220.int.ebiederm.org v2: https://lkml.kernel.org/r/87lfk54p0m.fsf_-_@x220.int.ebiederm.org Link: https://lkml.kernel.org/r/20200702164140.4468-10-ebiederm@xmission.com Reviewed-by: Greg Kroah-Hartman Acked-by: Alexei Starovoitov Tested-by: Alexei Starovoitov Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 4a20b7517dd0..7c27d7b57871 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -141,6 +141,5 @@ extern int do_execveat(int, struct filename *, const char __user * const __user *, const char __user * const __user *, int); -int do_execve_file(struct file *file, void *__argv, void *__envp); #endif /* _LINUX_BINFMTS_H */ -- cgit v1.2.3 From 1c340ead18ee4b4a84357abdef6d4f39ee08328b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 25 Jun 2020 16:48:26 -0500 Subject: umd: Track user space drivers with struct pid Use struct pid instead of user space pid values that are prone to wrap araound. In addition track the entire thread group instead of just the first thread that is started by exec. There are no multi-threaded user mode drivers today but there is nothing preclucing user drivers from being multi-threaded, so it is just a good idea to track the entire process. Take a reference count on the tgid's in question to make it possible to remove exit_umh in a future change. As a struct pid is available directly use kill_pid_info. The prior process signalling code was iffy in using a userspace pid known to be in the initial pid namespace and then looking up it's task in whatever the current pid namespace is. It worked only because kernel threads always run in the initial pid namespace. As the tgid is now refcounted verify the tgid is NULL at the start of fork_usermode_driver to avoid the possibility of silent pid leaks. v1: https://lkml.kernel.org/r/87mu4qdlv2.fsf_-_@x220.int.ebiederm.org v2: https://lkml.kernel.org/r/a70l4oy8.fsf_-_@x220.int.ebiederm.org Link: https://lkml.kernel.org/r/20200702164140.4468-12-ebiederm@xmission.com Reviewed-by: Greg Kroah-Hartman Acked-by: Alexei Starovoitov Tested-by: Alexei Starovoitov Signed-off-by: "Eric W. Biederman" --- include/linux/usermode_driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h index 97c919b7147c..45adbffb31d9 100644 --- a/include/linux/usermode_driver.h +++ b/include/linux/usermode_driver.h @@ -25,7 +25,7 @@ struct umd_info { struct list_head list; void (*cleanup)(struct umd_info *info); struct path wd; - pid_t pid; + struct pid *tgid; }; int umd_load_blob(struct umd_info *info, const void *data, size_t len); int umd_unload_blob(struct umd_info *info); -- cgit v1.2.3 From ff2a91127b374c75ae024b31d22f23ad49d16eb4 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sun, 24 May 2020 20:57:00 +0200 Subject: fork: remove do_fork() Now that all architectures have been switched to use _do_fork() and the new struct kernel_clone_args calling convention we can remove the legacy do_fork() helper completely. The calling convention used to be brittle and do_fork() didn't buy us anything. The only calling convention accepted should be based on struct kernel_clone_args going forward. It's cleaner and uniform. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Al Viro Cc: "Matthew Wilcox (Oracle)" Cc: "Peter Zijlstra (Intel)" Signed-off-by: Christian Brauner --- include/linux/sched/task.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index ddce0ea515d1..9f03c44941fb 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -96,7 +96,6 @@ extern void exit_files(struct task_struct *); extern void exit_itimers(struct signal_struct *); extern long _do_fork(struct kernel_clone_args *kargs); -extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); -- cgit v1.2.3 From 140c8180eb7c7cbda399f64474788b86db72db32 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sun, 24 May 2020 23:34:20 +0200 Subject: arch: remove HAVE_COPY_THREAD_TLS All architectures support copy_thread_tls() now, so remove the legacy copy_thread() function and the HAVE_COPY_THREAD_TLS config option. Everyone uses the same process creation calling convention based on copy_thread_tls() and struct kernel_clone_args. This will make it easier to maintain the core process creation code under kernel/, simplifies the callpaths and makes the identical for all architectures. Cc: linux-arch@vger.kernel.org Acked-by: Thomas Bogendoerfer Acked-by: Greentime Hu Acked-by: Geert Uytterhoeven Reviewed-by: Kees Cook Signed-off-by: Christian Brauner --- include/linux/sched/task.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 9f03c44941fb..77cbe14c3034 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -65,22 +65,9 @@ extern void fork_init(void); extern void release_task(struct task_struct * p); -#ifdef CONFIG_HAVE_COPY_THREAD_TLS extern int copy_thread_tls(unsigned long, unsigned long, unsigned long, struct task_struct *, unsigned long); -#else -extern int copy_thread(unsigned long, unsigned long, unsigned long, - struct task_struct *); - -/* Architectures that haven't opted into copy_thread_tls get the tls argument - * via pt_regs, so ignore the tls argument passed via C. */ -static inline int copy_thread_tls( - unsigned long clone_flags, unsigned long sp, unsigned long arg, - struct task_struct *p, unsigned long tls) -{ - return copy_thread(clone_flags, sp, arg, p); -} -#endif + extern void flush_thread(void); #ifdef CONFIG_HAVE_EXIT_THREAD -- cgit v1.2.3 From 714acdbd1c94e7e3ab90f6b6938f1ccb27b662f0 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 11 Jun 2020 11:04:15 +0200 Subject: arch: rename copy_thread_tls() back to copy_thread() Now that HAVE_COPY_THREAD_TLS has been removed, rename copy_thread_tls() back simply copy_thread(). It's a simpler name, and doesn't imply that only tls is copied here. This finishes an outstanding chunk of internal process creation work since we've added clone3(). Cc: linux-arch@vger.kernel.org Acked-by: Thomas Bogendoerfer A Acked-by: Stafford Horne Acked-by: Greentime Hu Acked-by: Geert Uytterhoeven A Reviewed-by: Kees Cook Signed-off-by: Christian Brauner --- include/linux/sched/task.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 77cbe14c3034..b6253f2ea96a 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -65,8 +65,8 @@ extern void fork_init(void); extern void release_task(struct task_struct * p); -extern int copy_thread_tls(unsigned long, unsigned long, unsigned long, - struct task_struct *, unsigned long); +extern int copy_thread(unsigned long, unsigned long, unsigned long, + struct task_struct *, unsigned long); extern void flush_thread(void); -- cgit v1.2.3 From b1c7b87443c2c12c4fe095114736b8ad6f963f67 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 5 Jul 2020 19:16:22 +0300 Subject: net: dsa: felix: support half-duplex link modes Ping tested: [ 11.808455] mscc_felix 0000:00:00.5 swp0: Link is Up - 1Gbps/Full - flow control rx/tx [ 11.816497] IPv6: ADDRCONF(NETDEV_CHANGE): swp0: link becomes ready [root@LS1028ARDB ~] # ethtool -s swp0 advertise 0x4 [ 18.844591] mscc_felix 0000:00:00.5 swp0: Link is Down [ 22.048337] mscc_felix 0000:00:00.5 swp0: Link is Up - 100Mbps/Half - flow control off [root@LS1028ARDB ~] # ip addr add 192.168.1.1/24 dev swp0 [root@LS1028ARDB ~] # ping 192.168.1.2 PING 192.168.1.2 (192.168.1.2): 56 data bytes (...) ^C--- 192.168.1.2 ping statistics --- 3 packets transmitted, 3 packets received, 0% packet loss round-trip min/avg/max = 0.383/0.611/1.051 ms [root@LS1028ARDB ~] # ethtool -s swp0 advertise 0x10 [ 355.637747] mscc_felix 0000:00:00.5 swp0: Link is Down [ 358.788034] mscc_felix 0000:00:00.5 swp0: Link is Up - 1Gbps/Half - flow control off [root@LS1028ARDB ~] # ping 192.168.1.2 PING 192.168.1.2 (192.168.1.2): 56 data bytes (...) ^C --- 192.168.1.2 ping statistics --- 16 packets transmitted, 16 packets received, 0% packet loss round-trip min/avg/max = 0.301/0.384/1.138 ms Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Reviewed-by: Russell King Signed-off-by: David S. Miller --- include/linux/fsl/enetc_mdio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fsl/enetc_mdio.h b/include/linux/fsl/enetc_mdio.h index 4875dd38af7e..2d9203314865 100644 --- a/include/linux/fsl/enetc_mdio.h +++ b/include/linux/fsl/enetc_mdio.h @@ -15,6 +15,7 @@ #define ENETC_PCS_IF_MODE_SGMII_EN BIT(0) #define ENETC_PCS_IF_MODE_USE_SGMII_AN BIT(1) #define ENETC_PCS_IF_MODE_SGMII_SPEED(x) (((x) << 2) & GENMASK(3, 2)) +#define ENETC_PCS_IF_MODE_DUPLEX_HALF BIT(3) /* Not a mistake, the SerDes PLL needs to be set at 3.125 GHz by Reset * Configuration Word (RCW, outside Linux control) for 2.5G SGMII mode. The PCS -- cgit v1.2.3 From 821b67fa46390baea0ac5139a60eaa48805261b2 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 25 Jun 2020 10:59:39 +0100 Subject: firmware: smccc: Add ARCH_SOC_ID support SMCCC v1.2 adds a new optional function SMCCC_ARCH_SOC_ID to obtain a SiP defined SoC identification value. Add support for the same. Also using the SoC bus infrastructure, let us expose the platform specific SoC atrributes under sysfs. There are various ways in which it can be represented in shortened form for efficiency and ease of parsing for userspace. The chosen form is described in the ABI document. Link: https://lore.kernel.org/r/20200625095939.50861-1-sudeep.holla@arm.com Cc: Etienne Carriere Reviewed-by: Steven Price Signed-off-by: Sudeep Holla --- include/linux/arm-smccc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 56d6a5c6e353..8254e11ea857 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -71,6 +71,11 @@ ARM_SMCCC_SMC_32, \ 0, 1) +#define ARM_SMCCC_ARCH_SOC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 2) + #define ARM_SMCCC_ARCH_WORKAROUND_1 \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_32, \ -- cgit v1.2.3 From 68d237056e007c88031d80900cdba0945121a287 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Tue, 30 Jun 2020 10:16:02 +0200 Subject: scatterlist: protect parameters of the sg_table related macros Add brackets to protect parameters of the recently added sg_table related macros from side-effects. Fixes: 709d6d73c756 ("scatterlist: add generic wrappers for iterating over sgtable objects") Signed-off-by: Marek Szyprowski Signed-off-by: Christoph Hellwig --- include/linux/scatterlist.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 4f922afb607a..45cf7b69d852 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -155,7 +155,7 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, * Loop over each sg element in the given sg_table object. */ #define for_each_sgtable_sg(sgt, sg, i) \ - for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) + for_each_sg((sgt)->sgl, sg, (sgt)->orig_nents, i) /* * Loop over each sg element in the given *DMA mapped* sg_table object. @@ -163,7 +163,7 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, * of the each element. */ #define for_each_sgtable_dma_sg(sgt, sg, i) \ - for_each_sg(sgt->sgl, sg, sgt->nents, i) + for_each_sg((sgt)->sgl, sg, (sgt)->nents, i) /** * sg_chain - Chain two sglists together @@ -451,7 +451,7 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter) * See also for_each_sg_page(). In each loop it operates on PAGE_SIZE unit. */ #define for_each_sgtable_page(sgt, piter, pgoffset) \ - for_each_sg_page(sgt->sgl, piter, sgt->orig_nents, pgoffset) + for_each_sg_page((sgt)->sgl, piter, (sgt)->orig_nents, pgoffset) /** * for_each_sgtable_dma_page - iterate over the DMA mapped sg_table object @@ -465,7 +465,7 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter) * unit. */ #define for_each_sgtable_dma_page(sgt, dma_iter, pgoffset) \ - for_each_sg_dma_page(sgt->sgl, dma_iter, sgt->nents, pgoffset) + for_each_sg_dma_page((sgt)->sgl, dma_iter, (sgt)->nents, pgoffset) /* -- cgit v1.2.3 From 0935ff5f1f0a44f66a13e075ed49f97ad99d2fdc Mon Sep 17 00:00:00 2001 From: Robin Gong Date: Sat, 4 Jul 2020 00:19:35 +0800 Subject: regulator: pca9450: add pca9450 pmic driver Add NXP pca9450 pmic driver. Signed-off-by: Robin Gong Reviewed-by: Frieder Schrempf Link: https://lore.kernel.org/r/1593793178-9737-2-git-send-email-yibin.gong@nxp.com Signed-off-by: Mark Brown --- include/linux/regulator/pca9450.h | 219 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 219 insertions(+) create mode 100644 include/linux/regulator/pca9450.h (limited to 'include/linux') diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h new file mode 100644 index 000000000000..1bbd3014f906 --- /dev/null +++ b/include/linux/regulator/pca9450.h @@ -0,0 +1,219 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright 2020 NXP. */ + +#ifndef __LINUX_REG_PCA9450_H__ +#define __LINUX_REG_PCA9450_H__ + +#include + +enum pca9450_chip_type { + PCA9450_TYPE_PCA9450A = 0, + PCA9450_TYPE_PCA9450BC, + PCA9450_TYPE_AMOUNT, +}; + +enum { + PCA9450_BUCK1 = 0, + PCA9450_BUCK2, + PCA9450_BUCK3, + PCA9450_BUCK4, + PCA9450_BUCK5, + PCA9450_BUCK6, + PCA9450_LDO1, + PCA9450_LDO2, + PCA9450_LDO3, + PCA9450_LDO4, + PCA9450_LDO5, + PCA9450_REGULATOR_CNT, +}; + +enum { + PCA9450_DVS_LEVEL_RUN = 0, + PCA9450_DVS_LEVEL_STANDBY, + PCA9450_DVS_LEVEL_MAX, +}; + +#define PCA9450_BUCK1_VOLTAGE_NUM 0x80 +#define PCA9450_BUCK2_VOLTAGE_NUM 0x80 +#define PCA9450_BUCK3_VOLTAGE_NUM 0x80 +#define PCA9450_BUCK4_VOLTAGE_NUM 0x80 + +#define PCA9450_BUCK5_VOLTAGE_NUM 0x80 +#define PCA9450_BUCK6_VOLTAGE_NUM 0x80 + +#define PCA9450_LDO1_VOLTAGE_NUM 0x08 +#define PCA9450_LDO2_VOLTAGE_NUM 0x08 +#define PCA9450_LDO3_VOLTAGE_NUM 0x20 +#define PCA9450_LDO4_VOLTAGE_NUM 0x20 +#define PCA9450_LDO5_VOLTAGE_NUM 0x10 + +enum { + PCA9450_REG_DEV_ID = 0x00, + PCA9450_REG_INT1 = 0x01, + PCA9450_REG_INT1_MSK = 0x02, + PCA9450_REG_STATUS1 = 0x03, + PCA9450_REG_STATUS2 = 0x04, + PCA9450_REG_PWRON_STAT = 0x05, + PCA9450_REG_SWRST = 0x06, + PCA9450_REG_PWRCTRL = 0x07, + PCA9450_REG_RESET_CTRL = 0x08, + PCA9450_REG_CONFIG1 = 0x09, + PCA9450_REG_CONFIG2 = 0x0A, + PCA9450_REG_BUCK123_DVS = 0x0C, + PCA9450_REG_BUCK1OUT_LIMIT = 0x0D, + PCA9450_REG_BUCK2OUT_LIMIT = 0x0E, + PCA9450_REG_BUCK3OUT_LIMIT = 0x0F, + PCA9450_REG_BUCK1CTRL = 0x10, + PCA9450_REG_BUCK1OUT_DVS0 = 0x11, + PCA9450_REG_BUCK1OUT_DVS1 = 0x12, + PCA9450_REG_BUCK2CTRL = 0x13, + PCA9450_REG_BUCK2OUT_DVS0 = 0x14, + PCA9450_REG_BUCK2OUT_DVS1 = 0x15, + PCA9450_REG_BUCK3CTRL = 0x16, + PCA9450_REG_BUCK3OUT_DVS0 = 0x17, + PCA9450_REG_BUCK3OUT_DVS1 = 0x18, + PCA9450_REG_BUCK4CTRL = 0x19, + PCA9450_REG_BUCK4OUT = 0x1A, + PCA9450_REG_BUCK5CTRL = 0x1B, + PCA9450_REG_BUCK5OUT = 0x1C, + PCA9450_REG_BUCK6CTRL = 0x1D, + PCA9450_REG_BUCK6OUT = 0x1E, + PCA9450_REG_LDO_AD_CTRL = 0x20, + PCA9450_REG_LDO1CTRL = 0x21, + PCA9450_REG_LDO2CTRL = 0x22, + PCA9450_REG_LDO3CTRL = 0x23, + PCA9450_REG_LDO4CTRL = 0x24, + PCA9450_REG_LDO5CTRL_L = 0x25, + PCA9450_REG_LDO5CTRL_H = 0x26, + PCA9450_REG_LOADSW_CTRL = 0x2A, + PCA9450_REG_VRFLT1_STS = 0x2B, + PCA9450_REG_VRFLT2_STS = 0x2C, + PCA9450_REG_VRFLT1_MASK = 0x2D, + PCA9450_REG_VRFLT2_MASK = 0x2E, + PCA9450_MAX_REGISTER = 0x2F, +}; + +/* PCA9450 BUCK ENMODE bits */ +#define BUCK_ENMODE_OFF 0x00 +#define BUCK_ENMODE_ONREQ 0x01 +#define BUCK_ENMODE_ONREQ_STBYREQ 0x02 +#define BUCK_ENMODE_ON 0x03 + +/* PCA9450_REG_BUCK1_CTRL bits */ +#define BUCK1_RAMP_MASK 0xC0 +#define BUCK1_RAMP_25MV 0x0 +#define BUCK1_RAMP_12P5MV 0x1 +#define BUCK1_RAMP_6P25MV 0x2 +#define BUCK1_RAMP_3P125MV 0x3 +#define BUCK1_DVS_CTRL 0x10 +#define BUCK1_AD 0x08 +#define BUCK1_FPWM 0x04 +#define BUCK1_ENMODE_MASK 0x03 + +/* PCA9450_REG_BUCK2_CTRL bits */ +#define BUCK2_RAMP_MASK 0xC0 +#define BUCK2_RAMP_25MV 0x0 +#define BUCK2_RAMP_12P5MV 0x1 +#define BUCK2_RAMP_6P25MV 0x2 +#define BUCK2_RAMP_3P125MV 0x3 +#define BUCK2_DVS_CTRL 0x10 +#define BUCK2_AD 0x08 +#define BUCK2_FPWM 0x04 +#define BUCK2_ENMODE_MASK 0x03 + +/* PCA9450_REG_BUCK3_CTRL bits */ +#define BUCK3_RAMP_MASK 0xC0 +#define BUCK3_RAMP_25MV 0x0 +#define BUCK3_RAMP_12P5MV 0x1 +#define BUCK3_RAMP_6P25MV 0x2 +#define BUCK3_RAMP_3P125MV 0x3 +#define BUCK3_DVS_CTRL 0x10 +#define BUCK3_AD 0x08 +#define BUCK3_FPWM 0x04 +#define BUCK3_ENMODE_MASK 0x03 + +/* PCA9450_REG_BUCK4_CTRL bits */ +#define BUCK4_AD 0x08 +#define BUCK4_FPWM 0x04 +#define BUCK4_ENMODE_MASK 0x03 + +/* PCA9450_REG_BUCK5_CTRL bits */ +#define BUCK5_AD 0x08 +#define BUCK5_FPWM 0x04 +#define BUCK5_ENMODE_MASK 0x03 + +/* PCA9450_REG_BUCK6_CTRL bits */ +#define BUCK6_AD 0x08 +#define BUCK6_FPWM 0x04 +#define BUCK6_ENMODE_MASK 0x03 + +/* PCA9450_BUCK1OUT_DVS0 bits */ +#define BUCK1OUT_DVS0_MASK 0x7F +#define BUCK1OUT_DVS0_DEFAULT 0x14 + +/* PCA9450_BUCK1OUT_DVS1 bits */ +#define BUCK1OUT_DVS1_MASK 0x7F +#define BUCK1OUT_DVS1_DEFAULT 0x14 + +/* PCA9450_BUCK2OUT_DVS0 bits */ +#define BUCK2OUT_DVS0_MASK 0x7F +#define BUCK2OUT_DVS0_DEFAULT 0x14 + +/* PCA9450_BUCK2OUT_DVS1 bits */ +#define BUCK2OUT_DVS1_MASK 0x7F +#define BUCK2OUT_DVS1_DEFAULT 0x14 + +/* PCA9450_BUCK3OUT_DVS0 bits */ +#define BUCK3OUT_DVS0_MASK 0x7F +#define BUCK3OUT_DVS0_DEFAULT 0x14 + +/* PCA9450_BUCK3OUT_DVS1 bits */ +#define BUCK3OUT_DVS1_MASK 0x7F +#define BUCK3OUT_DVS1_DEFAULT 0x14 + +/* PCA9450_REG_BUCK4OUT bits */ +#define BUCK4OUT_MASK 0x7F +#define BUCK4OUT_DEFAULT 0x6C + +/* PCA9450_REG_BUCK5OUT bits */ +#define BUCK5OUT_MASK 0x7F +#define BUCK5OUT_DEFAULT 0x30 + +/* PCA9450_REG_BUCK6OUT bits */ +#define BUCK6OUT_MASK 0x7F +#define BUCK6OUT_DEFAULT 0x14 + +/* PCA9450_REG_LDO1_VOLT bits */ +#define LDO1_EN_MASK 0xC0 +#define LDO1OUT_MASK 0x07 + +/* PCA9450_REG_LDO2_VOLT bits */ +#define LDO2_EN_MASK 0xC0 +#define LDO2OUT_MASK 0x07 + +/* PCA9450_REG_LDO3_VOLT bits */ +#define LDO3_EN_MASK 0xC0 +#define LDO3OUT_MASK 0x0F + +/* PCA9450_REG_LDO4_VOLT bits */ +#define LDO4_EN_MASK 0xC0 +#define LDO4OUT_MASK 0x0F + +/* PCA9450_REG_LDO5_VOLT bits */ +#define LDO5L_EN_MASK 0xC0 +#define LDO5LOUT_MASK 0x0F + +#define LDO5H_EN_MASK 0xC0 +#define LDO5HOUT_MASK 0x0F + +/* PCA9450_REG_IRQ bits */ +#define IRQ_PWRON 0x80 +#define IRQ_WDOGB 0x40 +#define IRQ_RSVD 0x20 +#define IRQ_VR_FLT1 0x10 +#define IRQ_VR_FLT2 0x08 +#define IRQ_LOWVSYS 0x04 +#define IRQ_THERM_105 0x02 +#define IRQ_THERM_125 0x01 + +#endif /* __LINUX_REG_PCA9450_H__ */ -- cgit v1.2.3 From 5ab903418ad14732131df0af0d63f19b73e377ae Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 6 Jul 2020 18:38:19 +0300 Subject: net: qed: sanitize BE/LE data processing Current code assumes that both host and device operates in Little Endian in lots of places. While this is true for x86 platform, this doesn't mean we should not care about this. This commit addresses all parts of the code that were pointed out by sparse checker. All operations with restricted (__be*/__le*) types are now protected with explicit from/to CPU conversions, even if they're noops on common setups. I'm sure there are more such places, but this implies a deeper code investigation, and is a subject for future works. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 5ca081cd2ed9..90e1060da02b 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1403,16 +1403,15 @@ static inline void qed_sb_ack(struct qed_sb_info *sb_info, enum igu_int_cmd int_cmd, u8 upd_flg) { - struct igu_prod_cons_update igu_ack = { 0 }; + u32 igu_ack; - igu_ack.sb_id_and_flags = - ((sb_info->sb_ack << IGU_PROD_CONS_UPDATE_SB_INDEX_SHIFT) | - (upd_flg << IGU_PROD_CONS_UPDATE_UPDATE_FLAG_SHIFT) | - (int_cmd << IGU_PROD_CONS_UPDATE_ENABLE_INT_SHIFT) | - (IGU_SEG_ACCESS_REG << - IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_SHIFT)); + igu_ack = ((sb_info->sb_ack << IGU_PROD_CONS_UPDATE_SB_INDEX_SHIFT) | + (upd_flg << IGU_PROD_CONS_UPDATE_UPDATE_FLAG_SHIFT) | + (int_cmd << IGU_PROD_CONS_UPDATE_ENABLE_INT_SHIFT) | + (IGU_SEG_ACCESS_REG << + IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_SHIFT)); - DIRECT_REG_WR(sb_info->igu_addr, igu_ack.sb_id_and_flags); + DIRECT_REG_WR(sb_info->igu_addr, igu_ack); /* Both segments (interrupts & acks) are written to same place address; * Need to guarantee all commands will be received (in-order) by HW. -- cgit v1.2.3 From 514acd00f957afa9b2a1fd521b2f180a950ee5e3 Mon Sep 17 00:00:00 2001 From: Andrzej Pietrasiewicz Date: Fri, 3 Jul 2020 12:43:54 +0200 Subject: thermal: Make thermal_zone_device_is_enabled() available to core only This function is not needed by drivers. Signed-off-by: Andrzej Pietrasiewicz Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20200703104354.19657-4-andrzej.p@collabora.com --- include/linux/thermal.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index b9efaa780d88..108251f23e5c 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -418,7 +418,6 @@ void thermal_cdev_update(struct thermal_cooling_device *); void thermal_notify_framework(struct thermal_zone_device *, int); int thermal_zone_device_enable(struct thermal_zone_device *tz); int thermal_zone_device_disable(struct thermal_zone_device *tz); -int thermal_zone_device_is_enabled(struct thermal_zone_device *tz); #else static inline struct thermal_zone_device *thermal_zone_device_register( const char *type, int trips, int mask, void *devdata, @@ -472,10 +471,6 @@ static inline int thermal_zone_device_enable(struct thermal_zone_device *tz) static inline int thermal_zone_device_disable(struct thermal_zone_device *tz) { return -ENODEV; } - -static inline int -thermal_zone_device_is_enabled(struct thermal_zone_device *tz) -{ return -ENODEV; } #endif /* CONFIG_THERMAL */ #endif /* __THERMAL_H__ */ -- cgit v1.2.3 From 7af928851508fb25207806f57e287272dd498981 Mon Sep 17 00:00:00 2001 From: Andrew Scull Date: Thu, 18 Jun 2020 15:55:11 +0100 Subject: smccc: Make constants available to assembly Move constants out of the C-only section of the header next to the other constants that are available to assembly. Signed-off-by: Andrew Scull Reviewed-by: Sudeep Holla Acked-by: Will Deacon Link: https://lore.kernel.org/r/20200618145511.69203-1-ascull@google.com Signed-off-by: Catalin Marinas --- include/linux/arm-smccc.h | 44 ++++++++++++++++++++++---------------------- 1 file changed, 22 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 56d6a5c6e353..efcbde731f03 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -81,6 +81,28 @@ ARM_SMCCC_SMC_32, \ 0, 0x7fff) +/* Paravirtualised time calls (defined by ARM DEN0057A) */ +#define ARM_SMCCC_HV_PV_TIME_FEATURES \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x20) + +#define ARM_SMCCC_HV_PV_TIME_ST \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x21) + +/* + * Return codes defined in ARM DEN 0070A + * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C + */ +#define SMCCC_RET_SUCCESS 0 +#define SMCCC_RET_NOT_SUPPORTED -1 +#define SMCCC_RET_NOT_REQUIRED -2 +#define SMCCC_RET_INVALID_PARAMETER -3 + #ifndef __ASSEMBLY__ #include @@ -331,15 +353,6 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, */ #define arm_smccc_1_1_hvc(...) __arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__) -/* - * Return codes defined in ARM DEN 0070A - * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C - */ -#define SMCCC_RET_SUCCESS 0 -#define SMCCC_RET_NOT_SUPPORTED -1 -#define SMCCC_RET_NOT_REQUIRED -2 -#define SMCCC_RET_INVALID_PARAMETER -3 - /* * Like arm_smccc_1_1* but always returns SMCCC_RET_NOT_SUPPORTED. * Used when the SMCCC conduit is not defined. The empty asm statement @@ -385,18 +398,5 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, method; \ }) -/* Paravirtualised time calls (defined by ARM DEN0057A) */ -#define ARM_SMCCC_HV_PV_TIME_FEATURES \ - ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ - ARM_SMCCC_SMC_64, \ - ARM_SMCCC_OWNER_STANDARD_HYP, \ - 0x20) - -#define ARM_SMCCC_HV_PV_TIME_ST \ - ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ - ARM_SMCCC_SMC_64, \ - ARM_SMCCC_OWNER_STANDARD_HYP, \ - 0x21) - #endif /*__ASSEMBLY__*/ #endif /*__LINUX_ARM_SMCCC_H*/ -- cgit v1.2.3 From 1ce50e7d408ef2bdc8ca021363fd46d1b8bfad00 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Mon, 6 Jul 2020 12:55:37 +0200 Subject: thermal: core: genetlink support for events/cmd/sampling Initially the thermal framework had a very simple notification mechanism to send generic netlink messages to the userspace. The notification function was never called from anywhere and the corresponding dead code was removed. It was probably a first attempt to introduce the netlink notification. At LPC2018, the presentation "Linux thermal: User kernel interface", proposed to create the notifications to the userspace via a kfifo. The advantage of the kfifo is the performance. It is usually used from a 1:1 communication channel where a driver captures data and sends it as fast as possible to a userspace process. The drawback is that only one process uses the notification channel exclusively, thus no other process is allowed to use the channel to get temperature or notifications. This patch defines a generic netlink API to discover the current thermal setup and adds event notifications as well as temperature sampling. As any genetlink protocol, it can evolve and the versioning allows to keep the backward compatibility. In order to prevent the user from getting flooded with data on a single channel, there are two multicast channels, one for the temperature sampling when the thermal zone is updated and another one for the events, so the user can get the events only without the thermal zone temperature sampling. Also, a list of commands to discover the thermal setup is added and can be extended when needed. Reviewed-by: Amit Kucheria Signed-off-by: Daniel Lezcano Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20200706105538.2159-3-daniel.lezcano@linaro.org --- include/linux/thermal.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 108251f23e5c..42ef807e5d84 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -37,18 +37,6 @@ struct thermal_cooling_device; struct thermal_instance; struct thermal_attr; -enum thermal_device_mode { - THERMAL_DEVICE_DISABLED = 0, - THERMAL_DEVICE_ENABLED, -}; - -enum thermal_trip_type { - THERMAL_TRIP_ACTIVE = 0, - THERMAL_TRIP_PASSIVE, - THERMAL_TRIP_HOT, - THERMAL_TRIP_CRITICAL, -}; - enum thermal_trend { THERMAL_TREND_STABLE, /* temperature is stable */ THERMAL_TREND_RAISING, /* temperature is raising */ @@ -303,11 +291,6 @@ struct thermal_zone_params { int offset; }; -struct thermal_genl_event { - u32 orig; - enum events event; -}; - /** * struct thermal_zone_of_device_ops - scallbacks for handling DT based zones * -- cgit v1.2.3 From 38fd525a4c61e7ecdc9ad4dcbf7b767d0a007962 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 1 Jul 2020 07:30:06 -0500 Subject: exit: Factor thread_group_exited out of pidfd_poll Create an independent helper thread_group_exited which returns true when all threads have passed exit_notify in do_exit. AKA all of the threads are at least zombies and might be dead or completely gone. Create this helper by taking the logic out of pidfd_poll where it is already tested, and adding a READ_ONCE on the read of task->exit_state. I will be changing the user mode driver code to use this same logic to know when a user mode driver needs to be restarted. Place the new helper thread_group_exited in kernel/exit.c and EXPORT it so it can be used by modules. Link: https://lkml.kernel.org/r/20200702164140.4468-13-ebiederm@xmission.com Acked-by: Christian Brauner Acked-by: Alexei Starovoitov Tested-by: Alexei Starovoitov Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 0ee5e696c5d8..1bad18a1d8ba 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -674,6 +674,8 @@ static inline int thread_group_empty(struct task_struct *p) #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) +extern bool thread_group_exited(struct pid *pid); + extern struct sighand_struct *__lock_task_sighand(struct task_struct *task, unsigned long *flags); -- cgit v1.2.3 From e80eb1dc868bc1ed93602389d54b27f170ca770c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 25 Jun 2020 17:23:22 -0500 Subject: bpfilter: Take advantage of the facilities of struct pid Instead of relying on the exit_umh cleanup callback use the fact a struct pid can be tested to see if a process still exists, and that struct pid has a wait queue that notifies when the process dies. v1: https://lkml.kernel.org/r/87h7uydlu9.fsf_-_@x220.int.ebiederm.org v2: https://lkml.kernel.org/r/874kqt4owu.fsf_-_@x220.int.ebiederm.org Link: https://lkml.kernel.org/r/20200702164140.4468-14-ebiederm@xmission.com Reviewed-by: Greg Kroah-Hartman Acked-by: Alexei Starovoitov Tested-by: Alexei Starovoitov Signed-off-by: "Eric W. Biederman" --- include/linux/bpfilter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index ec9972d822e0..9b114c718a76 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -10,6 +10,8 @@ int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen); int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen); +void bpfilter_umh_cleanup(struct umd_info *info); + struct bpfilter_umh_ops { struct umd_info info; /* since ip_getsockopt() can run in parallel, serialize access to umh */ @@ -18,7 +20,6 @@ struct bpfilter_umh_ops { char __user *optval, unsigned int optlen, bool is_set); int (*start)(void); - bool stop; }; extern struct bpfilter_umh_ops bpfilter_ops; #endif -- cgit v1.2.3 From 8c2f52663973e643c617663d826e2b0daa008b38 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 25 Jun 2020 17:40:40 -0500 Subject: umd: Remove exit_umh The bpfilter code no longer uses the umd_info.cleanup callback. This callback is what exit_umh exists to call. So remove exit_umh and all of it's associated booking. v1: https://lkml.kernel.org/r/87bll6dlte.fsf_-_@x220.int.ebiederm.org v2: https://lkml.kernel.org/r/87y2o53abg.fsf_-_@x220.int.ebiederm.org Link: https://lkml.kernel.org/r/20200702164140.4468-15-ebiederm@xmission.com Reviewed-by: Greg Kroah-Hartman Acked-by: Alexei Starovoitov Tested-by: Alexei Starovoitov Signed-off-by: "Eric W. Biederman" --- include/linux/sched.h | 1 - include/linux/usermode_driver.h | 16 ---------------- 2 files changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 59d1e92bb88e..edb2020875ad 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1511,7 +1511,6 @@ extern struct pid *cad_pid; #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ -#define PF_UMH 0x02000000 /* I'm an Usermodehelper process */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h index 45adbffb31d9..073a9e0ec07d 100644 --- a/include/linux/usermode_driver.h +++ b/include/linux/usermode_driver.h @@ -4,26 +4,10 @@ #include #include -#ifdef CONFIG_BPFILTER -void __exit_umh(struct task_struct *tsk); - -static inline void exit_umh(struct task_struct *tsk) -{ - if (unlikely(tsk->flags & PF_UMH)) - __exit_umh(tsk); -} -#else -static inline void exit_umh(struct task_struct *tsk) -{ -} -#endif - struct umd_info { const char *driver_name; struct file *pipe_to_umh; struct file *pipe_from_umh; - struct list_head list; - void (*cleanup)(struct umd_info *info); struct path wd; struct pid *tgid; }; -- cgit v1.2.3 From 6d4ebd565d15f374aab3d0f16f156bafec3c61b3 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 30 Jun 2020 07:57:03 +0300 Subject: iio: core: wrap IIO device into an iio_dev_opaque object There are plenty of bad designs we want to discourage or not have to review manually usually about accessing private (marked as [INTERN]) fields of 'struct iio_dev'. Sometimes users copy drivers that are not always the best examples. A better idea is to hide those fields into the framework. For 'struct iio_dev' this is a 'struct iio_dev_opaque' which wraps a public 'struct iio_dev' object. In the next series, some fields will be moved to this new struct, each with it's own rework. This rework will not be complete-able for a while, as many fields need some drivers to be reworked in order to finalize them (e.g. 'indio_dev->mlock'). But some fields can already be moved, and in time, all of them may get there (in the 'struct iio_dev_opaque' object). Since a lot of drivers also call 'iio_priv()', in order to preserve fast-paths (where this matters), the public iio_dev object will have a 'priv' field that will have the pointer to the private information already computed. The reference returned by this field should be guaranteed to be cacheline aligned. The opaque parts will be moved into the 'include/linux/iio/iio-opaque.h' header. Should the hidden information be required for some debugging or some special needs, it can be made available via this header. Otherwise, only the IIO core files should include this file. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio-opaque.h | 17 +++++++++++++++++ include/linux/iio/iio.h | 6 +++++- 2 files changed, 22 insertions(+), 1 deletion(-) create mode 100644 include/linux/iio/iio-opaque.h (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h new file mode 100644 index 000000000000..1375674f14cd --- /dev/null +++ b/include/linux/iio/iio-opaque.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _INDUSTRIAL_IO_OPAQUE_H_ +#define _INDUSTRIAL_IO_OPAQUE_H_ + +/** + * struct iio_dev_opaque - industrial I/O device opaque information + * @indio_dev: public industrial I/O device information + */ +struct iio_dev_opaque { + struct iio_dev indio_dev; +}; + +#define to_iio_dev_opaque(indio_dev) \ + container_of(indio_dev, struct iio_dev_opaque, indio_dev) + +#endif diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 1c1d02107722..c2f6d9ef213a 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -522,6 +522,8 @@ struct iio_buffer_setup_ops { * @flags: [INTERN] file ops related flags including busy flag. * @debugfs_dentry: [INTERN] device specific debugfs dentry. * @cached_reg_addr: [INTERN] cached register address for debugfs reads. + * @priv: [DRIVER] reference to driver's private information + * **MUST** be accessed **ONLY** via iio_priv() helper */ struct iio_dev { int id; @@ -571,6 +573,7 @@ struct iio_dev { char read_buf[20]; unsigned int read_buf_len; #endif + void *priv; }; const struct iio_chan_spec @@ -698,9 +701,10 @@ static inline void *iio_device_get_drvdata(const struct iio_dev *indio_dev) #define IIO_ALIGN L1_CACHE_BYTES struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv); +/* The information at the returned address is guaranteed to be cacheline aligned */ static inline void *iio_priv(const struct iio_dev *indio_dev) { - return (char *)indio_dev + ALIGN(sizeof(struct iio_dev), IIO_ALIGN); + return indio_dev->priv; } static inline struct iio_dev *iio_priv_to_dev(void *priv) -- cgit v1.2.3 From 96fb1b67422ed652e3217a140cf9be505041db07 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 30 Jun 2020 07:57:05 +0300 Subject: iio: core: move debugfs data on the private iio dev info This change moves all iio_dev debugfs fields to the iio_dev_priv object. It's not the biggest advantage yet (to the whole thing of abstractization) but it's a start. The iio_get_debugfs_dentry() function (which is moved in industrialio-core.c) needs to also be guarded against the CONFIG_DEBUG_FS symbol, when it isn't defined. We do want to keep the inline definition in the iio.h header, so that the compiler can better infer when to compile out debugfs code that is related to the IIO debugfs directory. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio-opaque.h | 10 ++++++++++ include/linux/iio/iio.h | 13 +------------ 2 files changed, 11 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 1375674f14cd..b3f234b4c1e9 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -6,9 +6,19 @@ /** * struct iio_dev_opaque - industrial I/O device opaque information * @indio_dev: public industrial I/O device information + * @debugfs_dentry: device specific debugfs dentry + * @cached_reg_addr: cached register address for debugfs reads + * @read_buf: read buffer to be used for the initial reg read + * @read_buf_len: data length in @read_buf */ struct iio_dev_opaque { struct iio_dev indio_dev; +#if defined(CONFIG_DEBUG_FS) + struct dentry *debugfs_dentry; + unsigned cached_reg_addr; + char read_buf[20]; + unsigned int read_buf_len; +#endif }; #define to_iio_dev_opaque(indio_dev) \ diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index c2f6d9ef213a..36915282269b 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -520,8 +520,6 @@ struct iio_buffer_setup_ops { * @groups: [INTERN] attribute groups * @groupcounter: [INTERN] index of next attribute group * @flags: [INTERN] file ops related flags including busy flag. - * @debugfs_dentry: [INTERN] device specific debugfs dentry. - * @cached_reg_addr: [INTERN] cached register address for debugfs reads. * @priv: [DRIVER] reference to driver's private information * **MUST** be accessed **ONLY** via iio_priv() helper */ @@ -567,12 +565,6 @@ struct iio_dev { int groupcounter; unsigned long flags; -#if defined(CONFIG_DEBUG_FS) - struct dentry *debugfs_dentry; - unsigned cached_reg_addr; - char read_buf[20]; - unsigned int read_buf_len; -#endif void *priv; }; @@ -733,10 +725,7 @@ static inline bool iio_buffer_enabled(struct iio_dev *indio_dev) * @indio_dev: IIO device structure for device **/ #if defined(CONFIG_DEBUG_FS) -static inline struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev) -{ - return indio_dev->debugfs_dentry; -} +struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev); #else static inline struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev) { -- cgit v1.2.3 From 207c2d27a010c0154691833960756b60816fe59d Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 30 Jun 2020 07:57:06 +0300 Subject: iio: core: move channel list & group to private iio device object This change bit straightforward and simple, since the 'channel_attr_list' & 'chan_attr_group' fields are only used in 'industrialio-core.c'. This change moves to the private IIO device object Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio-opaque.h | 5 +++++ include/linux/iio/iio.h | 5 ----- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index b3f234b4c1e9..9419a05c698d 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -6,6 +6,9 @@ /** * struct iio_dev_opaque - industrial I/O device opaque information * @indio_dev: public industrial I/O device information + * @channel_attr_list: keep track of automatically created channel + * attributes + * @chan_attr_group: group for all attrs in base directory * @debugfs_dentry: device specific debugfs dentry * @cached_reg_addr: cached register address for debugfs reads * @read_buf: read buffer to be used for the initial reg read @@ -13,6 +16,8 @@ */ struct iio_dev_opaque { struct iio_dev indio_dev; + struct list_head channel_attr_list; + struct attribute_group chan_attr_group; #if defined(CONFIG_DEBUG_FS) struct dentry *debugfs_dentry; unsigned cached_reg_addr; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 36915282269b..61c4bf9c03ec 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -506,9 +506,6 @@ struct iio_buffer_setup_ops { * @pollfunc_event: [DRIVER] function run on events trigger being received * @channels: [DRIVER] channel specification structure table * @num_channels: [DRIVER] number of channels specified in @channels. - * @channel_attr_list: [INTERN] keep track of automatically created channel - * attributes - * @chan_attr_group: [INTERN] group for all attrs in base directory * @name: [DRIVER] name of the device. * @label: [DRIVER] unique name to identify which device this is * @info: [DRIVER] callbacks and constant info from driver @@ -551,8 +548,6 @@ struct iio_dev { struct iio_chan_spec const *channels; int num_channels; - struct list_head channel_attr_list; - struct attribute_group chan_attr_group; const char *name; const char *label; const struct iio_info *info; -- cgit v1.2.3 From 6a8c6b26f7531a85803380911c7c4a05a639afbe Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 30 Jun 2020 07:57:07 +0300 Subject: iio: core: move iio_dev's buffer_list to the private iio device object This change moves the 'buffer_list' away from the public IIO device object into the private part. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio-opaque.h | 2 ++ include/linux/iio/iio.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 9419a05c698d..af6c69a40169 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -6,6 +6,7 @@ /** * struct iio_dev_opaque - industrial I/O device opaque information * @indio_dev: public industrial I/O device information + * @buffer_list: list of all buffers currently attached * @channel_attr_list: keep track of automatically created channel * attributes * @chan_attr_group: group for all attrs in base directory @@ -16,6 +17,7 @@ */ struct iio_dev_opaque { struct iio_dev indio_dev; + struct list_head buffer_list; struct list_head channel_attr_list; struct attribute_group chan_attr_group; #if defined(CONFIG_DEBUG_FS) diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 61c4bf9c03ec..a0110b1e29fe 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -490,7 +490,6 @@ struct iio_buffer_setup_ops { * and owner * @event_interface: [INTERN] event chrdevs associated with interrupt lines * @buffer: [DRIVER] any buffer present - * @buffer_list: [INTERN] list of all buffers currently attached * @scan_bytes: [INTERN] num bytes captured to be fed to buffer demux * @mlock: [INTERN] lock used to prevent simultaneous device state * changes @@ -531,7 +530,6 @@ struct iio_dev { struct iio_event_interface *event_interface; struct iio_buffer *buffer; - struct list_head buffer_list; int scan_bytes; struct mutex mlock; -- cgit v1.2.3 From fa83c3baa539a7ec734c7ee65fad499122f427d7 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Tue, 30 Jun 2020 07:57:08 +0300 Subject: iio: core: move event interface on the opaque struct Same as with other private fields, this moves the event interface reference to the opaque IIO device object, to be invisible to drivers. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio-opaque.h | 2 ++ include/linux/iio/iio.h | 3 --- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index af6c69a40169..f2e94196d31f 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -6,6 +6,7 @@ /** * struct iio_dev_opaque - industrial I/O device opaque information * @indio_dev: public industrial I/O device information + * @event_interface: event chrdevs associated with interrupt lines * @buffer_list: list of all buffers currently attached * @channel_attr_list: keep track of automatically created channel * attributes @@ -17,6 +18,7 @@ */ struct iio_dev_opaque { struct iio_dev indio_dev; + struct iio_event_interface *event_interface; struct list_head buffer_list; struct list_head channel_attr_list; struct attribute_group chan_attr_group; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index a0110b1e29fe..30c9c9502478 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -488,7 +488,6 @@ struct iio_buffer_setup_ops { * @currentmode: [DRIVER] current operating mode * @dev: [DRIVER] device structure, should be assigned a parent * and owner - * @event_interface: [INTERN] event chrdevs associated with interrupt lines * @buffer: [DRIVER] any buffer present * @scan_bytes: [INTERN] num bytes captured to be fed to buffer demux * @mlock: [INTERN] lock used to prevent simultaneous device state @@ -527,8 +526,6 @@ struct iio_dev { int currentmode; struct device dev; - struct iio_event_interface *event_interface; - struct iio_buffer *buffer; int scan_bytes; struct mutex mlock; -- cgit v1.2.3 From 3970ed49a46bd0b062870edcc0894b2bd820371d Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 7 Jul 2020 03:49:35 +0200 Subject: net: phy: Properly define genphy_c45_driver Avoid the W=1 warning that symbol 'genphy_c45_driver' was not declared. Should it be static? Declare it on the phy header file. Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 101a48fa6750..1592c3d0e12f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1385,6 +1385,9 @@ int genphy_c45_pma_read_abilities(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); +/* Generic C45 PHY driver */ +extern struct phy_driver genphy_c45_driver; + /* The gen10g_* functions are the old Clause 45 stub */ int gen10g_config_aneg(struct phy_device *phydev); -- cgit v1.2.3 From ad0f75e5f57ccbceec13274e1e242f2b5a6397ed Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 2 Jul 2020 11:52:56 -0700 Subject: cgroup: fix cgroup_sk_alloc() for sk_clone_lock() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When we clone a socket in sk_clone_lock(), its sk_cgrp_data is copied, so the cgroup refcnt must be taken too. And, unlike the sk_alloc() path, sock_update_netprioidx() is not called here. Therefore, it is safe and necessary to grab the cgroup refcnt even when cgroup_sk_alloc is disabled. sk_clone_lock() is in BH context anyway, the in_interrupt() would terminate this function if called there. And for sk_alloc() skcd->val is always zero. So it's safe to factor out the code to make it more readable. The global variable 'cgroup_sk_alloc_disabled' is used to determine whether to take these reference counts. It is impossible to make the reference counting correct unless we save this bit of information in skcd->val. So, add a new bit there to record whether the socket has already taken the reference counts. This obviously relies on kmalloc() to align cgroup pointers to at least 4 bytes, ARCH_KMALLOC_MINALIGN is certainly larger than that. This bug seems to be introduced since the beginning, commit d979a39d7242 ("cgroup: duplicate cgroup reference when cloning sockets") tried to fix it but not compeletely. It seems not easy to trigger until the recent commit 090e28b229af ("netprio_cgroup: Fix unlimited memory leak of v2 cgroups") was merged. Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup") Reported-by: Cameron Berkenpas Reported-by: Peter Geis Reported-by: Lu Fengqi Reported-by: Daniël Sonck Reported-by: Zhang Qiang Tested-by: Cameron Berkenpas Tested-by: Peter Geis Tested-by: Thomas Lamprecht Cc: Daniel Borkmann Cc: Zefan Li Cc: Tejun Heo Cc: Roman Gushchin Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/cgroup-defs.h | 6 ++++-- include/linux/cgroup.h | 4 +++- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 52661155f85f..4f1cd0edc57d 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -790,7 +790,8 @@ struct sock_cgroup_data { union { #ifdef __LITTLE_ENDIAN struct { - u8 is_data; + u8 is_data : 1; + u8 no_refcnt : 1; u8 padding; u16 prioidx; u32 classid; @@ -800,7 +801,8 @@ struct sock_cgroup_data { u32 classid; u16 prioidx; u8 padding; - u8 is_data; + u8 no_refcnt : 1; + u8 is_data : 1; } __packed; #endif u64 val; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4598e4da6b1b..618838c48313 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -822,6 +822,7 @@ extern spinlock_t cgroup_sk_update_lock; void cgroup_sk_alloc_disable(void); void cgroup_sk_alloc(struct sock_cgroup_data *skcd); +void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) @@ -835,7 +836,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) */ v = READ_ONCE(skcd->val); - if (v & 1) + if (v & 3) return &cgrp_dfl_root.cgrp; return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp; @@ -847,6 +848,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) #else /* CONFIG_CGROUP_DATA */ static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {} +static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ -- cgit v1.2.3 From 41da51bce36f44eefc1e3d0f47d18841cbd065ba Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 21 Nov 2019 23:25:07 +0000 Subject: fs: Add IOCB_NOIO flag for generic_file_read_iter Add an IOCB_NOIO flag that indicates to generic_file_read_iter that it shouldn't trigger any filesystem I/O for the actual request or for readahead. This allows to do tentative reads out of the page cache as some filesystems allow, and to take the appropriate locks and retry the reads only if the requested pages are not cached. Signed-off-by: Andreas Gruenbacher --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3f881a892ea7..4b7cb76e5837 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -315,6 +315,7 @@ enum rw_hint { #define IOCB_SYNC (1 << 5) #define IOCB_WRITE (1 << 6) #define IOCB_NOWAIT (1 << 7) +#define IOCB_NOIO (1 << 9) struct kiocb { struct file *ki_filp; -- cgit v1.2.3 From 16d79cd4e23b1964d36c041ab027505ceacbbeeb Mon Sep 17 00:00:00 2001 From: Luc Van Oostenryck Date: Thu, 2 Jul 2020 18:26:49 +0200 Subject: PCI: Use 'pci_channel_state_t' instead of 'enum pci_channel_state' The method struct pci_error_handlers.error_detected() is defined and documented as taking an 'enum pci_channel_state' for the second argument, but most drivers use 'pci_channel_state_t' instead. This 'pci_channel_state_t' is not a typedef for the enum but a typedef for a bitwise type in order to have better/stricter typechecking. Consolidate everything by using 'pci_channel_state_t' in the method's definition, in the related helpers and in the drivers. Enforce use of 'pci_channel_state_t' by replacing 'enum pci_channel_state' with an anonymous 'enum'. Note: Currently, from a typechecking point of view this patch changes nothing because only the constants defined by the enum are bitwise, not the enum itself (sparse doesn't have the notion of 'bitwise enum'). This may change in some not too far future, hence the patch. [bhelgaas: squash in https://lore.kernel.org/r/20200702162651.49526-3-luc.vanoostenryck@gmail.com https://lore.kernel.org/r/20200702162651.49526-4-luc.vanoostenryck@gmail.com] Link: https://lore.kernel.org/r/20200702162651.49526-2-luc.vanoostenryck@gmail.com Signed-off-by: Luc Van Oostenryck Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c79d83304e52..adcee9e30bfa 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -179,7 +179,7 @@ static inline const char *pci_power_name(pci_power_t state) */ typedef unsigned int __bitwise pci_channel_state_t; -enum pci_channel_state { +enum { /* I/O channel is in normal state */ pci_channel_io_normal = (__force pci_channel_state_t) 1, @@ -785,7 +785,7 @@ enum pci_ers_result { struct pci_error_handlers { /* PCI bus error detected on this device */ pci_ers_result_t (*error_detected)(struct pci_dev *dev, - enum pci_channel_state error); + pci_channel_state_t error); /* MMIO has been re-enabled, but not DMA */ pci_ers_result_t (*mmio_enabled)(struct pci_dev *dev); -- cgit v1.2.3 From 4895d7808e7030c831f2ef83a3cc6ec0d46c30b1 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sun, 5 Jul 2020 21:27:56 -0700 Subject: net: ethtool: Introduce ethtool_phy_ops In order to decouple ethtool from its PHY library dependency, define an ethtool_phy_ops singleton which can be overriden by the PHY library when it loads with an appropriate set of function pointers. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/ethtool.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 48ad3b6a0150..0c139a93b67a 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -502,5 +502,30 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd, u32 *dev_speed, u8 *dev_duplex); +struct netlink_ext_ack; +struct phy_device; +struct phy_tdr_config; + +/** + * struct ethtool_phy_ops - Optional PHY device options + * @start_cable_test - Start a cable test + * @start_cable_test_tdr - Start a Time Domain Reflectometry cable test + * + * All operations are optional (i.e. the function pointer may be set to %NULL) + * and callers must take this into account. Callers must hold the RTNL lock. + */ +struct ethtool_phy_ops { + int (*start_cable_test)(struct phy_device *phydev, + struct netlink_ext_ack *extack); + int (*start_cable_test_tdr)(struct phy_device *phydev, + struct netlink_ext_ack *extack, + const struct phy_tdr_config *config); +}; + +/** + * ethtool_set_ethtool_phy_ops - Set the ethtool_phy_ops singleton + * @ops: Ethtool PHY operations to set + */ +void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops); #endif /* _LINUX_ETHTOOL_H */ -- cgit v1.2.3 From 469aceddfa3ed16e17ee30533fae45e90f62efd8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Tue, 7 Jul 2020 13:03:25 +0200 Subject: vlan: consolidate VLAN parsing code and limit max parsing depth MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Toshiaki pointed out that we now have two very similar functions to extract the L3 protocol number in the presence of VLAN tags. And Daniel pointed out that the unbounded parsing loop makes it possible for maliciously crafted packets to loop through potentially hundreds of tags. Fix both of these issues by consolidating the two parsing functions and limiting the VLAN tag parsing to a max depth of 8 tags. As part of this, switch over __vlan_get_protocol() to use skb_header_pointer() instead of pskb_may_pull(), to avoid the possible side effects of the latter and keep the skb pointer 'const' through all the parsing functions. v2: - Use limit of 8 tags instead of 32 (matching XMIT_RECURSION_LIMIT) Reported-by: Toshiaki Makita Reported-by: Daniel Borkmann Fixes: d7bf2ebebc2b ("sched: consistently handle layer3 header accesses in the presence of VLANs") Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 57 +++++++++++++++++++------------------------------ 1 file changed, 22 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 427a5b8597c2..41a518336673 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -25,6 +25,8 @@ #define VLAN_ETH_DATA_LEN 1500 /* Max. octets in payload */ #define VLAN_ETH_FRAME_LEN 1518 /* Max. octets in frame sans FCS */ +#define VLAN_MAX_DEPTH 8 /* Max. number of nested VLAN tags parsed */ + /* * struct vlan_hdr - vlan header * @h_vlan_TCI: priority and VLAN ID @@ -308,34 +310,6 @@ static inline bool eth_type_vlan(__be16 ethertype) } } -/* A getter for the SKB protocol field which will handle VLAN tags consistently - * whether VLAN acceleration is enabled or not. - */ -static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan) -{ - unsigned int offset = skb_mac_offset(skb) + sizeof(struct ethhdr); - __be16 proto = skb->protocol; - - if (!skip_vlan) - /* VLAN acceleration strips the VLAN header from the skb and - * moves it to skb->vlan_proto - */ - return skb_vlan_tag_present(skb) ? skb->vlan_proto : proto; - - while (eth_type_vlan(proto)) { - struct vlan_hdr vhdr, *vh; - - vh = skb_header_pointer(skb, offset, sizeof(vhdr), &vhdr); - if (!vh) - break; - - proto = vh->h_vlan_encapsulated_proto; - offset += sizeof(vhdr); - } - - return proto; -} - static inline bool vlan_hw_offload_capable(netdev_features_t features, __be16 proto) { @@ -605,10 +579,10 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ -static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type, +static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, int *depth) { - unsigned int vlan_depth = skb->mac_len; + unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; /* if type is 802.1Q/AD then the header should already be * present at mac_len - VLAN_HLEN (if mac_len > 0), or at @@ -623,13 +597,12 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type, vlan_depth = ETH_HLEN; } do { - struct vlan_hdr *vh; + struct vlan_hdr vhdr, *vh; - if (unlikely(!pskb_may_pull(skb, - vlan_depth + VLAN_HLEN))) + vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr); + if (unlikely(!vh || !--parse_depth)) return 0; - vh = (struct vlan_hdr *)(skb->data + vlan_depth); type = vh->h_vlan_encapsulated_proto; vlan_depth += VLAN_HLEN; } while (eth_type_vlan(type)); @@ -648,11 +621,25 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type, * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ -static inline __be16 vlan_get_protocol(struct sk_buff *skb) +static inline __be16 vlan_get_protocol(const struct sk_buff *skb) { return __vlan_get_protocol(skb, skb->protocol, NULL); } +/* A getter for the SKB protocol field which will handle VLAN tags consistently + * whether VLAN acceleration is enabled or not. + */ +static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan) +{ + if (!skip_vlan) + /* VLAN acceleration strips the VLAN header from the skb and + * moves it to skb->vlan_proto + */ + return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; + + return vlan_get_protocol(skb); +} + static inline void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr) { -- cgit v1.2.3 From f5836749c9c04a10decd2742845ad4870965fdef Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 6 Jul 2020 16:01:25 -0700 Subject: bpf: Add BPF_CGROUP_INET_SOCK_RELEASE hook Sometimes it's handy to know when the socket gets freed. In particular, we'd like to try to use a smarter allocation of ports for bpf_bind and explore the possibility of limiting the number of SOCK_DGRAM sockets the process can have. Implement BPF_CGROUP_INET_SOCK_RELEASE hook that triggers on inet socket release. It triggers only for userspace sockets (not in-kernel ones) and therefore has the same semantics as the existing BPF_CGROUP_INET_SOCK_CREATE. Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200706230128.4073544-2-sdf@google.com --- include/linux/bpf-cgroup.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index c66c545e161a..2c6f26670acc 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -210,6 +210,9 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_CREATE) +#define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) \ + BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_RELEASE) + #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET4_POST_BIND) @@ -401,6 +404,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) -- cgit v1.2.3 From 61a707c543e2afe3aa7e88f87267c5dafa4b5afa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 8 May 2020 08:54:16 +0200 Subject: fs: add a __kernel_read helper This is the counterpart to __kernel_write, and skip the rw_verify_area call compared to kernel_read. Signed-off-by: Christoph Hellwig --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3f881a892ea7..22cbe7b2e919 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3033,6 +3033,7 @@ extern int kernel_read_file_from_path_initns(const char *, void **, loff_t *, lo extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t, enum kernel_read_file_id); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); +ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); -- cgit v1.2.3 From 775802c0571fb438cd4f6548a323f9e4cb89f5aa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 8 May 2020 11:17:46 +0200 Subject: fs: remove __vfs_read Fold it into the two callers. Signed-off-by: Christoph Hellwig --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 22cbe7b2e919..0c0ec76b600b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1917,7 +1917,6 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, struct iovec *fast_pointer, struct iovec **ret_pointer); -extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, -- cgit v1.2.3 From 76c12881a38aaa83e1eb4ce2fada36c3a732bad4 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 6 Jul 2020 17:49:11 +0200 Subject: nsproxy: support CLONE_NEWTIME with setns() So far setns() was missing time namespace support. This was partially due to it simply not being implemented but also because vdso_join_timens() could still fail which made switching to multiple namespaces atomically problematic. This is now fixed so support CLONE_NEWTIME with setns() Signed-off-by: Christian Brauner Reviewed-by: Andrei Vagin Cc: Thomas Gleixner Cc: Michael Kerrisk Cc: Serge Hallyn Cc: Dmitry Safonov Link: https://lore.kernel.org/r/20200706154912.3248030-4-christian.brauner@ubuntu.com --- include/linux/time_namespace.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index 824d54e057eb..5b6031385db0 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -33,6 +33,7 @@ extern struct time_namespace init_time_ns; #ifdef CONFIG_TIME_NS extern int vdso_join_timens(struct task_struct *task, struct time_namespace *ns); +extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns); static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { @@ -96,6 +97,11 @@ static inline int vdso_join_timens(struct task_struct *task, return 0; } +static inline void timens_commit(struct task_struct *tsk, + struct time_namespace *ns) +{ +} + static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { return NULL; -- cgit v1.2.3 From dbfb089d360b1cc623c51a2c7cf9b99eff78e0e7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 3 Jul 2020 12:40:33 +0200 Subject: sched: Fix loadavg accounting race The recent commit: c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu") moved these lines in ttwu(): p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; up before: smp_cond_load_acquire(&p->on_cpu, !VAL); into the 'p->on_rq == 0' block, with the thinking that once we hit schedule() the current task cannot change it's ->state anymore. And while this is true, it is both incorrect and flawed. It is incorrect in that we need at least an ACQUIRE on 'p->on_rq == 0' to avoid weak hardware from re-ordering things for us. This can fairly easily be achieved by relying on the control-dependency already in place. The second problem, which makes the flaw in the original argument, is that while schedule() will not change prev->state, it will read it a number of times (arguably too many times since it's marked volatile). The previous condition 'p->on_cpu == 0' was sufficient because that indicates schedule() has completed, and will no longer read prev->state. So now the trick is to make this same true for the (much) earlier 'prev->on_rq == 0' case. Furthermore, in order to make the ordering stick, the 'prev->on_rq = 0' assignment needs to he a RELEASE, but adding additional ordering to schedule() is an unwelcome proposition at the best of times, doubly so for mere accounting. Luckily we can push the prev->state load up before rq->lock, with the only caveat that we then have to re-read the state after. However, we know that if it changed, we no longer have to worry about the blocking path. This gives us the required ordering, if we block, we did the prev->state load before an (effective) smp_mb() and the p->on_rq store needs not change. With this we end up with the effective ordering: LOAD p->state LOAD-ACQUIRE p->on_rq == 0 MB STORE p->on_rq, 0 STORE p->state, TASK_WAKING which ensures the TASK_WAKING store happens after the prev->state load, and all is well again. Fixes: c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu") Reported-by: Dave Jones Reported-by: Paul Gortmaker Signed-off-by: Peter Zijlstra (Intel) Tested-by: Dave Jones Tested-by: Paul Gortmaker Link: https://lkml.kernel.org/r/20200707102957.GN117543@hirez.programming.kicks-ass.net --- include/linux/sched.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 692e327d7455..683372943093 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -114,10 +114,6 @@ struct task_group; #define task_is_stopped_or_traced(task) ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) -#define task_contributes_to_load(task) ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ - (task->flags & PF_FROZEN) == 0 && \ - (task->state & TASK_NOLOAD) == 0) - #ifdef CONFIG_DEBUG_ATOMIC_SLEEP /* -- cgit v1.2.3 From 217c2a633ebb36f1cc6d249f4ef2e4a809d46818 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 3 Jul 2020 05:49:22 -0700 Subject: perf/core: Use kmem_cache to allocate the PMU specific data Currently, the PMU specific data task_ctx_data is allocated by the function kzalloc() in the perf generic code. When there is no specific alignment requirement for the task_ctx_data, the method works well for now. However, there will be a problem once a specific alignment requirement is introduced in future features, e.g., the Architecture LBR XSAVE feature requires 64-byte alignment. If the specific alignment requirement is not fulfilled, the XSAVE family of instructions will fail to save/restore the xstate to/from the task_ctx_data. The function kzalloc() itself only guarantees a natural alignment. A new method to allocate the task_ctx_data has to be introduced, which has to meet the requirements as below: - must be a generic method can be used by different architectures, because the allocation of the task_ctx_data is implemented in the perf generic code; - must be an alignment-guarantee method (The alignment requirement is not changed after the boot); - must be able to allocate/free a buffer (smaller than a page size) dynamically; - should not cause extra CPU overhead or space overhead. Several options were considered as below: - One option is to allocate a larger buffer for task_ctx_data. E.g., ptr = kmalloc(size + alignment, GFP_KERNEL); ptr &= ~(alignment - 1); This option causes space overhead. - Another option is to allocate the task_ctx_data in the PMU specific code. To do so, several function pointers have to be added. As a result, both the generic structure and the PMU specific structure will become bigger. Besides, extra function calls are added when allocating/freeing the buffer. This option will increase both the space overhead and CPU overhead. - The third option is to use a kmem_cache to allocate a buffer for the task_ctx_data. The kmem_cache can be created with a specific alignment requirement by the PMU at boot time. A new pointer for kmem_cache has to be added in the generic struct pmu, which would be used to dynamically allocate a buffer for the task_ctx_data at run time. Although the new pointer is added to the struct pmu, the existing variable task_ctx_size is not required anymore. The size of the generic structure is kept the same. The third option which meets all the aforementioned requirements is used to replace kzalloc() for the PMU specific data allocation. A later patch will remove the kzalloc() method and the related variables. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1593780569-62993-17-git-send-email-kan.liang@linux.intel.com --- include/linux/perf_event.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 46fe5cfb5163..09915ae06d28 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -424,6 +424,11 @@ struct pmu { */ size_t task_ctx_size; + /* + * Kmem cache of PMU specific data + */ + struct kmem_cache *task_ctx_cache; + /* * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) * can be synchronized using this function. See Intel LBR callstack support -- cgit v1.2.3 From 5a09928d339f3cf0973991ddc3a2798825c84c99 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 3 Jul 2020 05:49:24 -0700 Subject: perf/x86: Remove task_ctx_size A new kmem_cache method has replaced the kzalloc() to allocate the PMU specific data. The task_ctx_size is not required anymore. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1593780569-62993-19-git-send-email-kan.liang@linux.intel.com --- include/linux/perf_event.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 09915ae06d28..3b22db08b6fb 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -419,10 +419,6 @@ struct pmu { */ void (*sched_task) (struct perf_event_context *ctx, bool sched_in); - /* - * PMU specific data size - */ - size_t task_ctx_size; /* * Kmem cache of PMU specific data -- cgit v1.2.3 From 9d246053a69196c7c27068870e9b4b66ac536f68 Mon Sep 17 00:00:00 2001 From: Phil Auld Date: Mon, 29 Jun 2020 15:23:03 -0400 Subject: sched: Add a tracepoint to track rq->nr_running Add a bare tracepoint trace_sched_update_nr_running_tp which tracks ->nr_running CPU's rq. This is used to accurately trace this data and provide a visualization of scheduler imbalances in, for example, the form of a heat map. The tracepoint is accessed by loading an external kernel module. An example module (forked from Qais' module and including the pelt related tracepoints) can be found at: https://github.com/auldp/tracepoints-helpers.git A script to turn the trace-cmd report output into a heatmap plot can be found at: https://github.com/jirvoz/plot-nr-running The tracepoints are added to add_nr_running() and sub_nr_running() which are in kernel/sched/sched.h. In order to avoid CREATE_TRACE_POINTS in the header a wrapper call is used and the trace/events/sched.h include is moved before sched.h in kernel/sched/core. Signed-off-by: Phil Auld Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200629192303.GC120228@lorien.usersys.redhat.com --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 683372943093..12b10ce51a08 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2044,6 +2044,7 @@ const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq); const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq); int sched_trace_rq_cpu(struct rq *rq); +int sched_trace_rq_nr_running(struct rq *rq); const struct cpumask *sched_trace_rd_span(struct root_domain *rd); -- cgit v1.2.3 From 5cc2013bfeee756a1ee6da9bfbe42e52b4695035 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 6 Jul 2020 19:53:41 +0200 Subject: regmap-irq: use fwnode instead of device node in add_irq_chip() Convert the argument to the newer fwnode_handle instead a device tree node. Fortunately, there are no users for now. So this is an easy change. Signed-off-by: Michael Walle Link: https://lore.kernel.org/r/20200706175353.16404-2-michael@walle.cc Signed-off-by: Mark Brown --- include/linux/regmap.h | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index cb666b9c6b6a..e2c22c0f3b9a 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -18,6 +18,7 @@ #include #include #include +#include struct module; struct clk; @@ -1311,21 +1312,23 @@ struct regmap_irq_chip_data; int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, int irq_base, const struct regmap_irq_chip *chip, struct regmap_irq_chip_data **data); -int regmap_add_irq_chip_np(struct device_node *np, struct regmap *map, int irq, - int irq_flags, int irq_base, - const struct regmap_irq_chip *chip, - struct regmap_irq_chip_data **data); +int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, + struct regmap *map, int irq, + int irq_flags, int irq_base, + const struct regmap_irq_chip *chip, + struct regmap_irq_chip_data **data); void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *data); int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq, int irq_flags, int irq_base, const struct regmap_irq_chip *chip, struct regmap_irq_chip_data **data); -int devm_regmap_add_irq_chip_np(struct device *dev, struct device_node *np, - struct regmap *map, int irq, int irq_flags, - int irq_base, - const struct regmap_irq_chip *chip, - struct regmap_irq_chip_data **data); +int devm_regmap_add_irq_chip_fwnode(struct device *dev, + struct fwnode_handle *fwnode, + struct regmap *map, int irq, + int irq_flags, int irq_base, + const struct regmap_irq_chip *chip, + struct regmap_irq_chip_data **data); void devm_regmap_del_irq_chip(struct device *dev, int irq, struct regmap_irq_chip_data *data); -- cgit v1.2.3 From 71010c30945425203da8d069a10fa45a05a00f96 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Mon, 29 Jun 2020 12:06:39 -0700 Subject: nvme: implement multiple I/O Command Set support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implements support for multiple I/O Command Sets. NVMe TP 4056 introduces a method to enumerate multiple command sets per namespace. If the command set is exposed, this method for enumeration will be used instead of the traditional method that uses the CC.CSS register command set register for command set identification. For namespaces where the Command Set Identifier is not supported or recognized, the specific namespace will not be created. Reviewed-by: Javier González Reviewed-by: Martin K. Petersen Reviewed-by: Johannes Thumshirn Reviewed-by: Matias Bjørling Reviewed-by: Daniel Wagner Reviewed-by: Himanshu Madhani Reviewed-by: Hannes Reinecke Signed-off-by: Niklas Cassel Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 5ce51ab4c50e..81ffe5247505 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -132,6 +132,7 @@ enum { #define NVME_CAP_TIMEOUT(cap) (((cap) >> 24) & 0xff) #define NVME_CAP_STRIDE(cap) (((cap) >> 32) & 0xf) #define NVME_CAP_NSSRC(cap) (((cap) >> 36) & 0x1) +#define NVME_CAP_CSS(cap) (((cap) >> 37) & 0xff) #define NVME_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf) #define NVME_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf) @@ -162,7 +163,6 @@ enum { enum { NVME_CC_ENABLE = 1 << 0, - NVME_CC_CSS_NVM = 0 << 4, NVME_CC_EN_SHIFT = 0, NVME_CC_CSS_SHIFT = 4, NVME_CC_MPS_SHIFT = 7, @@ -170,6 +170,9 @@ enum { NVME_CC_SHN_SHIFT = 14, NVME_CC_IOSQES_SHIFT = 16, NVME_CC_IOCQES_SHIFT = 20, + NVME_CC_CSS_NVM = 0 << NVME_CC_CSS_SHIFT, + NVME_CC_CSS_CSI = 6 << NVME_CC_CSS_SHIFT, + NVME_CC_CSS_MASK = 7 << NVME_CC_CSS_SHIFT, NVME_CC_AMS_RR = 0 << NVME_CC_AMS_SHIFT, NVME_CC_AMS_WRRU = 1 << NVME_CC_AMS_SHIFT, NVME_CC_AMS_VS = 7 << NVME_CC_AMS_SHIFT, @@ -179,6 +182,8 @@ enum { NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, + NVME_CAP_CSS_NVM = 1 << 0, + NVME_CAP_CSS_CSI = 1 << 6, NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, @@ -374,6 +379,8 @@ enum { NVME_ID_CNS_CTRL = 0x01, NVME_ID_CNS_NS_ACTIVE_LIST = 0x02, NVME_ID_CNS_NS_DESC_LIST = 0x03, + NVME_ID_CNS_CS_NS = 0x05, + NVME_ID_CNS_CS_CTRL = 0x06, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, @@ -383,6 +390,10 @@ enum { NVME_ID_CNS_UUID_LIST = 0x17, }; +enum { + NVME_CSI_NVM = 0, +}; + enum { NVME_DIR_IDENTIFY = 0x00, NVME_DIR_STREAMS = 0x01, @@ -435,11 +446,13 @@ struct nvme_ns_id_desc { #define NVME_NIDT_EUI64_LEN 8 #define NVME_NIDT_NGUID_LEN 16 #define NVME_NIDT_UUID_LEN 16 +#define NVME_NIDT_CSI_LEN 1 enum { NVME_NIDT_EUI64 = 0x01, NVME_NIDT_NGUID = 0x02, NVME_NIDT_UUID = 0x03, + NVME_NIDT_CSI = 0x04, }; struct nvme_smart_log { @@ -972,7 +985,9 @@ struct nvme_identify { __u8 cns; __u8 rsvd3; __le16 ctrlid; - __u32 rsvd11[5]; + __u8 rsvd11[3]; + __u8 csi; + __u32 rsvd12[4]; }; #define NVME_IDENTIFY_DATA_SIZE 4096 -- cgit v1.2.3 From be93e87e780253780df9bb6ecc9bc1199b0d94c3 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 29 Jun 2020 12:06:40 -0700 Subject: nvme: support for multiple Command Sets Supported and Effects log pages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Commands Supported and Effects log page was extended with a CSI field that enables the host to query the log page for each command set supported. Retrieve this log page for each command set that an attached namespace supports, and save a pointer to that log in the namespace head. Reviewed-by: Matias Bjørling Reviewed-by: Javier González Reviewed-by: Himanshu Madhani Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Daniel Wagner Signed-off-by: Keith Busch Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 81ffe5247505..95cd03e240a1 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1101,7 +1101,9 @@ struct nvme_get_log_page_command { }; __le64 lpo; }; - __u32 rsvd14[2]; + __u8 rsvd14[3]; + __u8 csi; + __u32 rsvd15; }; struct nvme_directive_cmd { -- cgit v1.2.3 From 240e6ee272c07a2636dfc7d65f5bbb18377c49e5 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 29 Jun 2020 12:06:41 -0700 Subject: nvme: support for zoned namespaces MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for NVM Express Zoned Namespaces (ZNS) Command Set defined in NVM Express TP4053. Zoned namespaces are discovered based on their Command Set Identifier reported in the namespaces Namespace Identification Descriptor list. A successfully discovered Zoned Namespace will be registered with the block layer as a host managed zoned block device with Zone Append command support. A namespace that does not support append is not supported by the driver. Reviewed-by: Martin K. Petersen Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Reviewed-by: Sagi Grimberg Reviewed-by: Javier González Reviewed-by: Himanshu Madhani Signed-off-by: Hans Holmberg Signed-off-by: Dmitry Fomichev Signed-off-by: Ajay Joshi Signed-off-by: Aravind Ramesh Signed-off-by: Niklas Cassel Signed-off-by: Matias Bjørling Signed-off-by: Damien Le Moal Signed-off-by: Keith Busch Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 111 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 111 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 95cd03e240a1..1643005d21e3 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -374,6 +374,30 @@ struct nvme_id_ns { __u8 vs[3712]; }; +struct nvme_zns_lbafe { + __le64 zsze; + __u8 zdes; + __u8 rsvd9[7]; +}; + +struct nvme_id_ns_zns { + __le16 zoc; + __le16 ozcs; + __le32 mar; + __le32 mor; + __le32 rrl; + __le32 frl; + __u8 rsvd20[2796]; + struct nvme_zns_lbafe lbafe[16]; + __u8 rsvd3072[768]; + __u8 vs[256]; +}; + +struct nvme_id_ctrl_zns { + __u8 zasl; + __u8 rsvd1[4095]; +}; + enum { NVME_ID_CNS_NS = 0x00, NVME_ID_CNS_CTRL = 0x01, @@ -392,6 +416,7 @@ enum { enum { NVME_CSI_NVM = 0, + NVME_CSI_ZNS = 2, }; enum { @@ -532,6 +557,27 @@ struct nvme_ana_rsp_hdr { __le16 rsvd10[3]; }; +struct nvme_zone_descriptor { + __u8 zt; + __u8 zs; + __u8 za; + __u8 rsvd3[5]; + __le64 zcap; + __le64 zslba; + __le64 wp; + __u8 rsvd32[32]; +}; + +enum { + NVME_ZONE_TYPE_SEQWRITE_REQ = 0x2, +}; + +struct nvme_zone_report { + __le64 nr_zones; + __u8 resv8[56]; + struct nvme_zone_descriptor entries[]; +}; + enum { NVME_SMART_CRIT_SPARE = 1 << 0, NVME_SMART_CRIT_TEMPERATURE = 1 << 1, @@ -626,6 +672,9 @@ enum nvme_opcode { nvme_cmd_resv_report = 0x0e, nvme_cmd_resv_acquire = 0x11, nvme_cmd_resv_release = 0x15, + nvme_cmd_zone_mgmt_send = 0x79, + nvme_cmd_zone_mgmt_recv = 0x7a, + nvme_cmd_zone_append = 0x7d, }; #define nvme_opcode_name(opcode) { opcode, #opcode } @@ -764,6 +813,7 @@ struct nvme_rw_command { enum { NVME_RW_LR = 1 << 15, NVME_RW_FUA = 1 << 14, + NVME_RW_APPEND_PIREMAP = 1 << 9, NVME_RW_DSM_FREQ_UNSPEC = 0, NVME_RW_DSM_FREQ_TYPICAL = 1, NVME_RW_DSM_FREQ_RARE = 2, @@ -829,6 +879,53 @@ struct nvme_write_zeroes_cmd { __le16 appmask; }; +enum nvme_zone_mgmt_action { + NVME_ZONE_CLOSE = 0x1, + NVME_ZONE_FINISH = 0x2, + NVME_ZONE_OPEN = 0x3, + NVME_ZONE_RESET = 0x4, + NVME_ZONE_OFFLINE = 0x5, + NVME_ZONE_SET_DESC_EXT = 0x10, +}; + +struct nvme_zone_mgmt_send_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __le32 cdw2[2]; + __le64 metadata; + union nvme_data_ptr dptr; + __le64 slba; + __le32 cdw12; + __u8 zsa; + __u8 select_all; + __u8 rsvd13[2]; + __le32 cdw14[2]; +}; + +struct nvme_zone_mgmt_recv_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __le64 rsvd2[2]; + union nvme_data_ptr dptr; + __le64 slba; + __le32 numd; + __u8 zra; + __u8 zrasf; + __u8 pr; + __u8 rsvd13; + __le32 cdw14[2]; +}; + +enum { + NVME_ZRA_ZONE_REPORT = 0, + NVME_ZRASF_ZONE_REPORT_ALL = 0, + NVME_REPORT_ZONE_PARTIAL = 1, +}; + /* Features */ enum { @@ -1300,6 +1397,8 @@ struct nvme_command { struct nvme_format_cmd format; struct nvme_dsm_cmd dsm; struct nvme_write_zeroes_cmd write_zeroes; + struct nvme_zone_mgmt_send_cmd zms; + struct nvme_zone_mgmt_recv_cmd zmr; struct nvme_abort_cmd abort; struct nvme_get_log_page_command get_log_page; struct nvmf_common_command fabrics; @@ -1433,6 +1532,18 @@ enum { NVME_SC_DISCOVERY_RESTART = 0x190, NVME_SC_AUTH_REQUIRED = 0x191, + /* + * I/O Command Set Specific - Zoned commands: + */ + NVME_SC_ZONE_BOUNDARY_ERROR = 0x1b8, + NVME_SC_ZONE_FULL = 0x1b9, + NVME_SC_ZONE_READ_ONLY = 0x1ba, + NVME_SC_ZONE_OFFLINE = 0x1bb, + NVME_SC_ZONE_INVALID_WRITE = 0x1bc, + NVME_SC_ZONE_TOO_MANY_ACTIVE = 0x1bd, + NVME_SC_ZONE_TOO_MANY_OPEN = 0x1be, + NVME_SC_ZONE_INVALID_TRANSITION = 0x1bf, + /* * Media and Data Integrity Errors: */ -- cgit v1.2.3 From 457e7a135cbf0a0b5ed2717c192c0c57112c3b32 Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Thu, 2 Jul 2020 01:56:04 +0000 Subject: fs: introduce SB_INLINECRYPT Introduce SB_INLINECRYPT, which is set by filesystems that wish to use blk-crypto for file content en/decryption. This flag maps to the '-o inlinecrypt' mount option which multiple filesystems will implement, and code in fs/crypto/ needs to be able to check for this mount option in a filesystem-independent way. Signed-off-by: Satya Tangirala Reviewed-by: Jaegeuk Kim Reviewed-by: Eric Biggers Reviewed-by: Theodore Ts'o Link: https://lore.kernel.org/r/20200702015607.1215430-2-satyat@google.com Signed-off-by: Eric Biggers --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3f881a892ea7..b5e07fcdd11d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1380,6 +1380,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_NODIRATIME 2048 /* Do not update directory access times */ #define SB_SILENT 32768 #define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ +#define SB_INLINECRYPT (1<<17) /* Use blk-crypto for encrypted files */ #define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ #define SB_I_VERSION (1<<23) /* Update inode I_version field */ #define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ -- cgit v1.2.3 From 5fee36095cda45d34555aed3a2e8973b80cd6bf8 Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Thu, 2 Jul 2020 01:56:05 +0000 Subject: fscrypt: add inline encryption support Add support for inline encryption to fs/crypto/. With "inline encryption", the block layer handles the decryption/encryption as part of the bio, instead of the filesystem doing the crypto itself via Linux's crypto API. This model is needed in order to take advantage of the inline encryption hardware present on most modern mobile SoCs. To use inline encryption, the filesystem needs to be mounted with '-o inlinecrypt'. Blk-crypto will then be used instead of the traditional filesystem-layer crypto whenever possible to encrypt the contents of any encrypted files in that filesystem. Fscrypt still provides the key and IV to use, and the actual ciphertext on-disk is still the same; therefore it's testable using the existing fscrypt ciphertext verification tests. Note that since blk-crypto has a fallback to Linux's crypto API, and also supports all the encryption modes currently supported by fscrypt, this feature is usable and testable even without actual inline encryption hardware. Per-filesystem changes will be needed to set encryption contexts when submitting bios and to implement the 'inlinecrypt' mount option. This patch just adds the common code. Signed-off-by: Satya Tangirala Reviewed-by: Jaegeuk Kim Reviewed-by: Eric Biggers Reviewed-by: Theodore Ts'o Link: https://lore.kernel.org/r/20200702015607.1215430-3-satyat@google.com Co-developed-by: Eric Biggers Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 82 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 2862ca5fea33..bb257411365f 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -69,6 +69,9 @@ struct fscrypt_operations { bool (*has_stable_inodes)(struct super_block *sb); void (*get_ino_and_lblk_bits)(struct super_block *sb, int *ino_bits_ret, int *lblk_bits_ret); + int (*get_num_devices)(struct super_block *sb); + void (*get_devices)(struct super_block *sb, + struct request_queue **devs); }; static inline bool fscrypt_has_encryption_key(const struct inode *inode) @@ -537,6 +540,85 @@ static inline void fscrypt_set_ops(struct super_block *sb, #endif /* !CONFIG_FS_ENCRYPTION */ +/* inline_crypt.c */ +#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT + +bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode); + +void fscrypt_set_bio_crypt_ctx(struct bio *bio, + const struct inode *inode, u64 first_lblk, + gfp_t gfp_mask); + +void fscrypt_set_bio_crypt_ctx_bh(struct bio *bio, + const struct buffer_head *first_bh, + gfp_t gfp_mask); + +bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode, + u64 next_lblk); + +bool fscrypt_mergeable_bio_bh(struct bio *bio, + const struct buffer_head *next_bh); + +#else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ + +static inline bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode) +{ + return false; +} + +static inline void fscrypt_set_bio_crypt_ctx(struct bio *bio, + const struct inode *inode, + u64 first_lblk, gfp_t gfp_mask) { } + +static inline void fscrypt_set_bio_crypt_ctx_bh( + struct bio *bio, + const struct buffer_head *first_bh, + gfp_t gfp_mask) { } + +static inline bool fscrypt_mergeable_bio(struct bio *bio, + const struct inode *inode, + u64 next_lblk) +{ + return true; +} + +static inline bool fscrypt_mergeable_bio_bh(struct bio *bio, + const struct buffer_head *next_bh) +{ + return true; +} +#endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ + +/** + * fscrypt_inode_uses_inline_crypto() - test whether an inode uses inline + * encryption + * @inode: an inode. If encrypted, its key must be set up. + * + * Return: true if the inode requires file contents encryption and if the + * encryption should be done in the block layer via blk-crypto rather + * than in the filesystem layer. + */ +static inline bool fscrypt_inode_uses_inline_crypto(const struct inode *inode) +{ + return fscrypt_needs_contents_encryption(inode) && + __fscrypt_inode_uses_inline_crypto(inode); +} + +/** + * fscrypt_inode_uses_fs_layer_crypto() - test whether an inode uses fs-layer + * encryption + * @inode: an inode. If encrypted, its key must be set up. + * + * Return: true if the inode requires file contents encryption and if the + * encryption should be done in the filesystem layer rather than in the + * block layer via blk-crypto. + */ +static inline bool fscrypt_inode_uses_fs_layer_crypto(const struct inode *inode) +{ + return fscrypt_needs_contents_encryption(inode) && + !__fscrypt_inode_uses_inline_crypto(inode); +} + /** * fscrypt_require_key() - require an inode's encryption key * @inode: the inode we need the key for -- cgit v1.2.3 From 6ec4476ac82512f09c94aff5972654b70f3772b2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 8 Jul 2020 10:48:35 -0700 Subject: Raise gcc version requirement to 4.9 I realize that we fairly recently raised it to 4.8, but the fact is, 4.9 is a much better minimum version to target. We have a number of workarounds for actual bugs in pre-4.9 gcc versions (including things like internal compiler errors on ARM), but we also have some syntactic workarounds for lacking features. In particular, raising the minimum to 4.9 means that we can now just assume _Generic() exists, which is likely the much better replacement for a lot of very convoluted built-time magic with conditionals on sizeof and/or __builtin_choose_expr() with same_type() etc. Using _Generic also means that you will need to have a very recent version of 'sparse', but thats easy to build yourself, and much less of a hassle than some old gcc version can be. The latest (in a long string) of reasons for minimum compiler version upgrades was commit 5435f73d5c4a ("efi/x86: Fix build with gcc 4"). Ard points out that RHEL 7 uses gcc-4.8, but the people who stay back on old RHEL versions persumably also don't build their own kernels anyway. And maybe they should cross-built or just have a little side affair with a newer compiler? Acked-by: Ard Biesheuvel Acked-by: Peter Zijlstra Signed-off-by: Linus Torvalds --- include/linux/bits.h | 3 +-- include/linux/compiler-gcc.h | 2 +- include/linux/compiler_types.h | 27 +-------------------------- 3 files changed, 3 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bits.h b/include/linux/bits.h index 4671fbf28842..7f475d59a097 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -18,8 +18,7 @@ * position @h. For example * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ -#if !defined(__ASSEMBLY__) && \ - (!defined(CONFIG_CC_IS_GCC) || CONFIG_GCC_VERSION >= 49000) +#if !defined(__ASSEMBLY__) #include #define GENMASK_INPUT_CHECK(h, l) \ (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 1c74464c80c6..0b1dc61f3955 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -11,7 +11,7 @@ + __GNUC_PATCHLEVEL__) /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */ -#if GCC_VERSION < 40800 +#if GCC_VERSION < 40900 # error Sorry, your compiler is too old - please upgrade it. #endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index c3bf7710f69a..01dd58c74d80 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -252,32 +252,8 @@ struct ftrace_likely_data { * __unqual_scalar_typeof(x) - Declare an unqualified scalar type, leaving * non-scalar types unchanged. */ -#if (defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 40900) || defined(__CHECKER__) /* - * We build this out of a couple of helper macros in a vain attempt to - * help you keep your lunch down while reading it. - */ -#define __pick_scalar_type(x, type, otherwise) \ - __builtin_choose_expr(__same_type(x, type), (type)0, otherwise) - -/* - * 'char' is not type-compatible with either 'signed char' or 'unsigned char', - * so we include the naked type here as well as the signed/unsigned variants. - */ -#define __pick_integer_type(x, type, otherwise) \ - __pick_scalar_type(x, type, \ - __pick_scalar_type(x, unsigned type, \ - __pick_scalar_type(x, signed type, otherwise))) - -#define __unqual_scalar_typeof(x) typeof( \ - __pick_integer_type(x, char, \ - __pick_integer_type(x, short, \ - __pick_integer_type(x, int, \ - __pick_integer_type(x, long, \ - __pick_integer_type(x, long long, x)))))) -#else -/* - * If supported, prefer C11 _Generic for better compile-times. As above, 'char' + * Prefer C11 _Generic for better compile-times and simpler code. Note: 'char' * is not type-compatible with 'signed char', and we define a separate case. */ #define __scalar_type_to_expr_cases(type) \ @@ -293,7 +269,6 @@ struct ftrace_likely_data { __scalar_type_to_expr_cases(long), \ __scalar_type_to_expr_cases(long long), \ default: (x))) -#endif /* Is this type a native word size -- useful for atomic operations */ #define __native_word(t) \ -- cgit v1.2.3 From bd36ed1c935144a0e3b788bba659258f666e7b5b Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 8 Jul 2020 09:46:24 -0700 Subject: net: phy: Define PHY statistics ethtool_phy_ops Extend ethtool_phy_ops to include the 3 function pointers necessary for implementing PHY statistics. In a subsequent change we will uninline those functions. Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/ethtool.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 0c139a93b67a..969a80211df6 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -508,6 +508,9 @@ struct phy_tdr_config; /** * struct ethtool_phy_ops - Optional PHY device options + * @get_sset_count: Get number of strings that @get_strings will write. + * @get_strings: Return a set of strings that describe the requested objects + * @get_stats: Return extended statistics about the PHY device. * @start_cable_test - Start a cable test * @start_cable_test_tdr - Start a Time Domain Reflectometry cable test * @@ -515,6 +518,10 @@ struct phy_tdr_config; * and callers must take this into account. Callers must hold the RTNL lock. */ struct ethtool_phy_ops { + int (*get_sset_count)(struct phy_device *dev); + int (*get_strings)(struct phy_device *dev, u8 *data); + int (*get_stats)(struct phy_device *dev, + struct ethtool_stats *stats, u64 *data); int (*start_cable_test)(struct phy_device *phydev, struct netlink_ext_ack *extack); int (*start_cable_test_tdr)(struct phy_device *phydev, -- cgit v1.2.3 From 17809516a03a045565ad6a80e6241754615871ac Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 8 Jul 2020 09:46:25 -0700 Subject: net: phy: Uninline PHY ethtool statistics operations Now that we have moved the PHY ethtool statistics to be dynamically registered, we no longer need to inline those for ethtool. This used to be done to avoid cross symbol referencing and allow ethtool to be decoupled from PHYLIB entirely. Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 49 ++++--------------------------------------------- 1 file changed, 4 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 1592c3d0e12f..0403eb799913 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1474,51 +1474,10 @@ int __init mdio_bus_init(void); void mdio_bus_exit(void); #endif -/* Inline function for use within net/core/ethtool.c (built-in) */ -static inline int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data) -{ - if (!phydev->drv) - return -EIO; - - mutex_lock(&phydev->lock); - phydev->drv->get_strings(phydev, data); - mutex_unlock(&phydev->lock); - - return 0; -} - -static inline int phy_ethtool_get_sset_count(struct phy_device *phydev) -{ - int ret; - - if (!phydev->drv) - return -EIO; - - if (phydev->drv->get_sset_count && - phydev->drv->get_strings && - phydev->drv->get_stats) { - mutex_lock(&phydev->lock); - ret = phydev->drv->get_sset_count(phydev); - mutex_unlock(&phydev->lock); - - return ret; - } - - return -EOPNOTSUPP; -} - -static inline int phy_ethtool_get_stats(struct phy_device *phydev, - struct ethtool_stats *stats, u64 *data) -{ - if (!phydev->drv) - return -EIO; - - mutex_lock(&phydev->lock); - phydev->drv->get_stats(phydev, stats, data); - mutex_unlock(&phydev->lock); - - return 0; -} +int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); +int phy_ethtool_get_sset_count(struct phy_device *phydev); +int phy_ethtool_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data); static inline int phy_package_read(struct phy_device *phydev, u32 regnum) { -- cgit v1.2.3 From e8c22266e68f0db2a7e11b0a9f29fd88ec0cfd4a Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 15 Jun 2020 14:13:34 +0200 Subject: KVM: async_pf: change kvm_setup_async_pf()/kvm_arch_setup_async_pf() return type to bool Unlike normal 'int' functions returning '0' on success, kvm_setup_async_pf()/ kvm_arch_setup_async_pf() return '1' when a job to handle page fault asynchronously was scheduled and '0' otherwise. To avoid the confusion change return type to 'bool'. No functional change intended. Suggested-by: Sean Christopherson Signed-off-by: Vitaly Kuznetsov Message-Id: <20200615121334.91300-1-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 62ec926c78a0..9edc6fc71a89 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -211,8 +211,8 @@ struct kvm_async_pf { void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); -int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - unsigned long hva, struct kvm_arch_async_pf *arch); +bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + unsigned long hva, struct kvm_arch_async_pf *arch); int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif -- cgit v1.2.3 From ecd7274fb4cd2d6c035a52d59ca3d6ec936a07be Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 4 Jun 2020 18:11:15 +0100 Subject: iommu: Remove unused IOMMU_SYS_CACHE_ONLY flag The IOMMU_SYS_CACHE_ONLY flag was never exposed via the DMA API and has no in-tree users. Remove it. Cc: Robin Murphy Cc: "Isaac J. Manjarres" Cc: Joerg Roedel Cc: Rob Clark Reviewed-by: Christoph Hellwig Reviewed-by: Sai Prakash Ranjan Signed-off-by: Will Deacon --- include/linux/iommu.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 5f0b7859d2eb..bee1a8fa1fb1 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -31,12 +31,6 @@ * if the IOMMU page table format is equivalent. */ #define IOMMU_PRIV (1 << 5) -/* - * Non-coherent masters can use this page protection flag to set cacheable - * memory attributes for only a transparent outer level of cache, also known as - * the last-level or system cache. - */ -#define IOMMU_SYS_CACHE_ONLY (1 << 6) struct iommu_ops; struct iommu_group; -- cgit v1.2.3 From a564e23f0f99759f453dbefcb9160dec6d99df96 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Jul 2020 14:25:41 +0200 Subject: md: switch to ->check_events for media change notifications md is the last driver using the legacy media_changed method. Switch it over to (not so) new ->clear_events approach, which also removes the need for the ->revalidate_disk method. Signed-off-by: Christoph Hellwig [axboe: remove unused 'bdops' variable in disk_clear_events()] Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 408eb66a82fd..71173a1ffa8b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1781,8 +1781,6 @@ struct block_device_operations { int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); - /* ->media_changed() is DEPRECATED, use ->check_events() instead */ - int (*media_changed) (struct gendisk *); void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); -- cgit v1.2.3 From 8c22eb3a77373c616f141b56f44ef225ee15c96b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Jul 2020 14:25:42 +0200 Subject: cdrom: remove the unused cdrom_media_changed function As well as the ->media_changed method. All these are left over from before the drivers were switched over to the check_events scheme. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 8543fa59da72..f48d0a31deae 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -73,7 +73,6 @@ struct cdrom_device_ops { int (*drive_status) (struct cdrom_device_info *, int); unsigned int (*check_events) (struct cdrom_device_info *cdi, unsigned int clearing, int slot); - int (*media_changed) (struct cdrom_device_info *, int); int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); int (*select_speed) (struct cdrom_device_info *, int); @@ -107,7 +106,6 @@ extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi, unsigned int clearing); -extern int cdrom_media_changed(struct cdrom_device_info *); extern int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi); extern void unregister_cdrom(struct cdrom_device_info *cdi); -- cgit v1.2.3 From 12fdafb817c6cde87a4fa0e674e66b0226a0889d Mon Sep 17 00:00:00 2001 From: Meir Lichtinger Date: Mon, 6 Jul 2020 20:42:33 -0700 Subject: net/mlx5: Added support for 100Gbps per lane link modes This patch exposes new link modes using 100Gbps per lane, including 100G, 200G and 400G modes. Signed-off-by: Meir Lichtinger Reviewed-by: Aya Levin Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/port.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index de9a272c9f3d..2d45a6af52a4 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -104,8 +104,11 @@ enum mlx5e_ext_link_mode { MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR = 8, MLX5E_CAUI_4_100GBASE_CR4_KR4 = 9, MLX5E_100GAUI_2_100GBASE_CR2_KR2 = 10, + MLX5E_100GAUI_1_100GBASE_CR_KR = 11, MLX5E_200GAUI_4_200GBASE_CR4_KR4 = 12, + MLX5E_200GAUI_2_200GBASE_CR2_KR2 = 13, MLX5E_400GAUI_8 = 15, + MLX5E_400GAUI_4_400GBASE_CR4_KR4 = 16, MLX5E_EXT_LINK_MODES_NUMBER, }; -- cgit v1.2.3 From 160251842cd35a75edfb0a1d76afa3eb674ff40a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 2 Jul 2020 11:49:23 -0700 Subject: kallsyms: Refactor kallsyms_show_value() to take cred In order to perform future tests against the cred saved during open(), switch kallsyms_show_value() to operate on a cred, and have all current callers pass current_cred(). This makes it very obvious where callers are checking the wrong credential in their "read" contexts. These will be fixed in the coming patches. Additionally switch return value to bool, since it is always used as a direct permission check, not a 0-on-success, negative-on-error style function return. Cc: stable@vger.kernel.org Signed-off-by: Kees Cook --- include/linux/filter.h | 2 +- include/linux/kallsyms.h | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 259377723603..55104f6c78e8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -889,7 +889,7 @@ static inline bool bpf_dump_raw_ok(void) /* Reconstruction of call-sites is dependent on kallsyms, * thus make dump the same restriction. */ - return kallsyms_show_value() == 1; + return kallsyms_show_value(current_cred()); } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 98338dc6b5d2..481273f0c72d 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -18,6 +18,7 @@ #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \ 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1) +struct cred; struct module; static inline int is_kernel_inittext(unsigned long addr) @@ -98,7 +99,7 @@ int lookup_symbol_name(unsigned long addr, char *symname); int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); /* How and when do we show kallsyms values? */ -extern int kallsyms_show_value(void); +extern bool kallsyms_show_value(const struct cred *cred); #else /* !CONFIG_KALLSYMS */ @@ -158,7 +159,7 @@ static inline int lookup_symbol_attrs(unsigned long addr, unsigned long *size, u return -ERANGE; } -static inline int kallsyms_show_value(void) +static inline bool kallsyms_show_value(const struct cred *cred) { return false; } -- cgit v1.2.3 From 63960260457a02af2a6cb35d75e6bdb17299c882 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 2 Jul 2020 15:45:23 -0700 Subject: bpf: Check correct cred for CAP_SYSLOG in bpf_dump_raw_ok() When evaluating access control over kallsyms visibility, credentials at open() time need to be used, not the "current" creds (though in BPF's case, this has likely always been the same). Plumb access to associated file->f_cred down through bpf_dump_raw_ok() and its callers now that kallsysm_show_value() has been refactored to take struct cred. Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: bpf@vger.kernel.org Cc: stable@vger.kernel.org Fixes: 7105e828c087 ("bpf: allow for correlation of maps and helpers in dump") Signed-off-by: Kees Cook --- include/linux/filter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 55104f6c78e8..0b0144752d78 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -884,12 +884,12 @@ void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); bool bpf_helper_changes_pkt_data(void *func); -static inline bool bpf_dump_raw_ok(void) +static inline bool bpf_dump_raw_ok(const struct cred *cred) { /* Reconstruction of call-sites is dependent on kallsyms, * thus make dump the same restriction. */ - return kallsyms_show_value(current_cred()); + return kallsyms_show_value(cred); } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, -- cgit v1.2.3 From d7481b24b816b8c3955a9eaf01b97e2bd7f61a37 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Fri, 3 Jul 2020 12:56:19 -0400 Subject: audit: issue CWD record to accompany LSM_AUDIT_DATA_* records The LSM_AUDIT_DATA_* records for PATH, FILE, IOCTL_OP, DENTRY and INODE are incomplete without the task context of the AUDIT Current Working Directory record. Add it. This record addition can't use audit_dummy_context to determine whether or not to store the record information since the LSM_AUDIT_DATA_* records are initiated by various LSMs independent of any audit rules. context->in_syscall is used to determine if it was called in user context like audit_getname. Please see the upstream issue https://github.com/linux-audit/audit-kernel/issues/96 Adapted from Vladis Dronov's v2 patch. Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index b5478c64bc69..523f77494847 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -292,7 +292,7 @@ extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, extern void __audit_syscall_exit(int ret_success, long ret_value); extern struct filename *__audit_reusename(const __user char *uptr); extern void __audit_getname(struct filename *name); - +extern void __audit_getcwd(void); extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); extern void __audit_file(const struct file *); @@ -351,6 +351,11 @@ static inline void audit_getname(struct filename *name) if (unlikely(!audit_dummy_context())) __audit_getname(name); } +static inline void audit_getcwd(void) +{ + if (unlikely(audit_context())) + __audit_getcwd(); +} static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { @@ -579,6 +584,8 @@ static inline struct filename *audit_reusename(const __user char *name) } static inline void audit_getname(struct filename *name) { } +static inline void audit_getcwd(void) +{ } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) -- cgit v1.2.3 From 492d76b215660be833f12c3fa7cf2faf39434841 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 11:06:20 +0200 Subject: writeback: remove {set,clear}_wb_congested Just merge them into their only callers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 90a7e844a098..cc5aa1f32b91 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -232,18 +232,8 @@ enum { BLK_RW_SYNC = 1, }; -void clear_wb_congested(struct bdi_writeback_congested *congested, int sync); -void set_wb_congested(struct bdi_writeback_congested *congested, int sync); - -static inline void clear_bdi_congested(struct backing_dev_info *bdi, int sync) -{ - clear_wb_congested(bdi->wb.congested, sync); -} - -static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync) -{ - set_wb_congested(bdi->wb.congested, sync); -} +void clear_bdi_congested(struct backing_dev_info *bdi, int sync); +void set_bdi_congested(struct backing_dev_info *bdi, int sync); struct wb_lock_cookie { bool locked; -- cgit v1.2.3 From 8c911f3d4c074a17955a1757c9d1d5a9a5209ca5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 11:06:21 +0200 Subject: writeback: remove struct bdi_writeback_congested We never set any congested bits in the group writeback instances of it. And for the simpler bdi-wide case a simple scalar field is all that that is needed. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 25 +------------------------ include/linux/backing-dev.h | 18 +----------------- include/linux/blk-cgroup.h | 6 ------ 3 files changed, 2 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index cc5aa1f32b91..1cec4521e1fb 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -87,26 +87,6 @@ struct wb_completion { #define DEFINE_WB_COMPLETION(cmpl, bdi) \ struct wb_completion cmpl = WB_COMPLETION_INIT(bdi) -/* - * For cgroup writeback, multiple wb's may map to the same blkcg. Those - * wb's can operate mostly independently but should share the congested - * state. To facilitate such sharing, the congested state is tracked using - * the following struct which is created on demand, indexed by blkcg ID on - * its bdi, and refcounted. - */ -struct bdi_writeback_congested { - unsigned long state; /* WB_[a]sync_congested flags */ - refcount_t refcnt; /* nr of attached wb's and blkg */ - -#ifdef CONFIG_CGROUP_WRITEBACK - struct backing_dev_info *__bdi; /* the associated bdi, set to NULL - * on bdi unregistration. For memcg-wb - * internal use only! */ - int blkcg_id; /* ID of the associated blkcg */ - struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */ -#endif -}; - /* * Each wb (bdi_writeback) can perform writeback operations, is measured * and throttled, independently. Without cgroup writeback, each bdi @@ -140,7 +120,7 @@ struct bdi_writeback { struct percpu_counter stat[NR_WB_STAT_ITEMS]; - struct bdi_writeback_congested *congested; + unsigned long congested; /* WB_[a]sync_congested flags */ unsigned long bw_time_stamp; /* last time write bw is updated */ unsigned long dirtied_stamp; @@ -208,11 +188,8 @@ struct backing_dev_info { struct list_head wb_list; /* list of all wbs */ #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ - struct rb_root cgwb_congested_tree; /* their congested states */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ -#else - struct bdi_writeback_congested *wb_congested; #endif wait_queue_head_t wb_waitq; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 6b3504bf7a42..9173d2c22b4a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -173,7 +173,7 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) if (bdi->congested_fn) return bdi->congested_fn(bdi->congested_data, cong_bits); - return wb->congested->state & cong_bits; + return wb->congested & cong_bits; } long congestion_wait(int sync, long timeout); @@ -224,9 +224,6 @@ static inline int bdi_sched_wait(void *word) #ifdef CONFIG_CGROUP_WRITEBACK -struct bdi_writeback_congested * -wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp); -void wb_congested_put(struct bdi_writeback_congested *congested); struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css); struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, @@ -404,19 +401,6 @@ static inline bool inode_cgwb_enabled(struct inode *inode) return false; } -static inline struct bdi_writeback_congested * -wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) -{ - refcount_inc(&bdi->wb_congested->refcnt); - return bdi->wb_congested; -} - -static inline void wb_congested_put(struct bdi_writeback_congested *congested) -{ - if (refcount_dec_and_test(&congested->refcnt)) - kfree(congested); -} - static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { return &bdi->wb; diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 431b2d18bf40..c8fc9792ac77 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -109,12 +109,6 @@ struct blkcg_gq { struct hlist_node blkcg_node; struct blkcg *blkcg; - /* - * Each blkg gets congested separately and the congestion state is - * propagated to the matching bdi_writeback_congested. - */ - struct bdi_writeback_congested *wb_congested; - /* all non-root blkcg_gq's are guaranteed to have access to parent */ struct blkcg_gq *parent; -- cgit v1.2.3 From 21cf866145047f8bfecb38ec8d2fed64464c074f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 11:06:22 +0200 Subject: writeback: remove bdi->congested_fn Except for pktdvd, the only places setting congested bits are file systems that allocate their own backing_dev_info structures. And pktdvd is a deprecated driver that isn't useful in stack setup either. So remove the dead congested_fn stacking infrastructure. Signed-off-by: Christoph Hellwig Acked-by: Song Liu Acked-by: David Sterba [axboe: fixup unused variables in bcache/request.c] Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 4 ---- include/linux/backing-dev.h | 4 ---- include/linux/device-mapper.h | 11 ----------- 3 files changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 1cec4521e1fb..fff9367a6348 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -33,8 +33,6 @@ enum wb_congested_state { WB_sync_congested, /* The sync queue is getting full */ }; -typedef int (congested_fn)(void *, int); - enum wb_stat_item { WB_RECLAIMABLE, WB_WRITEBACK, @@ -170,8 +168,6 @@ struct backing_dev_info { struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned long io_pages; /* max allowed IO size */ - congested_fn *congested_fn; /* Function pointer if device is md/dm */ - void *congested_data; /* Pointer to aux data for congested func */ struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 9173d2c22b4a..0b06b2d26c9a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -169,10 +169,6 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) { - struct backing_dev_info *bdi = wb->bdi; - - if (bdi->congested_fn) - return bdi->congested_fn(bdi->congested_data, cong_bits); return wb->congested & cong_bits; } diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 8750f2dc5613..d5306d9c29c4 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -322,12 +322,6 @@ struct dm_target { bool discards_supported:1; }; -/* Each target can link one of these into the table */ -struct dm_target_callbacks { - struct list_head list; - int (*congested_fn) (struct dm_target_callbacks *, int); -}; - void *dm_per_bio_data(struct bio *bio, size_t data_size); struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size); unsigned dm_bio_get_target_bio_nr(const struct bio *bio); @@ -477,11 +471,6 @@ int dm_table_create(struct dm_table **result, fmode_t mode, int dm_table_add_target(struct dm_table *t, const char *type, sector_t start, sector_t len, char *params); -/* - * Target_ctr should call this if it needs to add any callbacks. - */ -void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb); - /* * Target can use this to set the table's type. * Can only ever be called from a target's ctr. -- cgit v1.2.3 From 5abfe5cf0b8358b8ad0da99e4188c2519839d67c Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Tue, 23 Jun 2020 19:23:27 -0700 Subject: remoteproc: qcom: Add per subsystem SSR notification Currently there is a single notification chain which is called whenever any remoteproc shuts down. This leads to all the listeners being notified, and is not an optimal design as kernel drivers might only be interested in listening to notifications from a particular remoteproc. Create a global list of remoteproc notification info data structures. This will hold the name and notifier_list information for a particular remoteproc. The API to register for notifications will use name argument to retrieve the notification info data structure and the notifier block will be added to that data structure's notification chain. Also move from blocking notifier to srcu notifer based implementation to support dynamic notifier head creation. Reviewed-by: Alex Elder Co-developed-by: Siddharth Gupta Signed-off-by: Siddharth Gupta Signed-off-by: Rishabh Bhatnagar Link: https://lore.kernel.org/r/1592965408-16908-2-git-send-email-rishabhb@codeaurora.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc/qcom_rproc.h | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc/qcom_rproc.h b/include/linux/remoteproc/qcom_rproc.h index fa8e38681b4b..2a1d6d0249d9 100644 --- a/include/linux/remoteproc/qcom_rproc.h +++ b/include/linux/remoteproc/qcom_rproc.h @@ -5,17 +5,27 @@ struct notifier_block; #if IS_ENABLED(CONFIG_QCOM_RPROC_COMMON) -int qcom_register_ssr_notifier(struct notifier_block *nb); -void qcom_unregister_ssr_notifier(struct notifier_block *nb); +struct qcom_ssr_notify_data { + const char *name; + bool crashed; +}; + +void *qcom_register_ssr_notifier(const char *name, struct notifier_block *nb); +int qcom_unregister_ssr_notifier(void *notify, struct notifier_block *nb); #else -static inline int qcom_register_ssr_notifier(struct notifier_block *nb) +static inline void *qcom_register_ssr_notifier(const char *name, + struct notifier_block *nb) { - return 0; + return NULL; } -static inline void qcom_unregister_ssr_notifier(struct notifier_block *nb) {} +static inline int qcom_unregister_ssr_notifier(void *notify, + struct notifier_block *nb) +{ + return 0; +} #endif -- cgit v1.2.3 From 62495d778439a4e47571293511a785cba754874c Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Tue, 23 Jun 2020 19:23:28 -0700 Subject: remoteproc: qcom: Add notification types to SSR The SSR subdevice only adds callback for the unprepare event. Add callbacks for prepare, start and prepare events. The client driver for a particular remoteproc might be interested in knowing the status of the remoteproc while undergoing SSR, not just when the remoteproc has finished shutting down. Reviewed-by: Alex Elder Signed-off-by: Siddharth Gupta Signed-off-by: Rishabh Bhatnagar Link: https://lore.kernel.org/r/1592965408-16908-3-git-send-email-rishabhb@codeaurora.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc/qcom_rproc.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc/qcom_rproc.h b/include/linux/remoteproc/qcom_rproc.h index 2a1d6d0249d9..647051662174 100644 --- a/include/linux/remoteproc/qcom_rproc.h +++ b/include/linux/remoteproc/qcom_rproc.h @@ -5,6 +5,22 @@ struct notifier_block; #if IS_ENABLED(CONFIG_QCOM_RPROC_COMMON) +/** + * enum qcom_ssr_notify_type - Startup/Shutdown events related to a remoteproc + * processor. + * + * @QCOM_SSR_BEFORE_POWERUP: Remoteproc about to start (prepare stage) + * @QCOM_SSR_AFTER_POWERUP: Remoteproc is running (start stage) + * @QCOM_SSR_BEFORE_SHUTDOWN: Remoteproc crashed or shutting down (stop stage) + * @QCOM_SSR_AFTER_SHUTDOWN: Remoteproc is down (unprepare stage) + */ +enum qcom_ssr_notify_type { + QCOM_SSR_BEFORE_POWERUP, + QCOM_SSR_AFTER_POWERUP, + QCOM_SSR_BEFORE_SHUTDOWN, + QCOM_SSR_AFTER_SHUTDOWN, +}; + struct qcom_ssr_notify_data { const char *name; bool crashed; -- cgit v1.2.3 From f88814cc2578c121e6edef686365036db72af0ed Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 8 Jul 2020 13:01:57 +0300 Subject: efi/efivars: Expose RT service availability via efivars abstraction Commit bf67fad19e493b ("efi: Use more granular check for availability for variable services") introduced a check into the efivarfs, efi-pstore and other drivers that aborts loading of the module if not all three variable runtime services (GetVariable, SetVariable and GetNextVariable) are supported. However, this results in efivarfs being unavailable entirely if only SetVariable support is missing, which is only needed if you want to make any modifications. Also, efi-pstore and the sysfs EFI variable interface could be backed by another implementation of the 'efivars' abstraction, in which case it is completely irrelevant which services are supported by the EFI firmware. So make the generic 'efivars' abstraction dependent on the availibility of the GetVariable and GetNextVariable EFI runtime services, and add a helper 'efivar_supports_writes()' to find out whether the currently active efivars abstraction supports writes (and wire it up to the availability of SetVariable for the generic one). Then, use the efivar_supports_writes() helper to decide whether to permit efivarfs to be mounted read-write, and whether to enable efi-pstore or the sysfs EFI variable interface altogether. Fixes: bf67fad19e493b ("efi: Use more granular check for availability for variable services") Reported-by: Heinrich Schuchardt Acked-by: Ilias Apalodimas Tested-by: Ilias Apalodimas Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index bb35f3305e55..05c47f857383 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -994,6 +994,7 @@ int efivars_register(struct efivars *efivars, int efivars_unregister(struct efivars *efivars); struct kobject *efivars_kobject(void); +int efivar_supports_writes(void); int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), void *data, bool duplicates, struct list_head *head); -- cgit v1.2.3 From 4fbfbdb5726ff15bdce1c371efa1281b28322f64 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 Jul 2020 14:49:56 +0200 Subject: USB: serial: inline sysrq dummy function Inline the dummy sysrq character handling when either console support or magic-sysrq support isn't enabled to allow the compiler to eliminate unused code. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold --- include/linux/usb/serial.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 14cac4a1ae8f..be73646706a9 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -365,8 +365,17 @@ extern int usb_serial_generic_submit_read_urbs(struct usb_serial_port *port, extern void usb_serial_generic_process_read_urb(struct urb *urb); extern int usb_serial_generic_prepare_write_buffer(struct usb_serial_port *port, void *dest, size_t size); + +#if defined(CONFIG_USB_SERIAL_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ) extern int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch); +#else +static inline int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch) +{ + return 0; +} +#endif + extern int usb_serial_handle_break(struct usb_serial_port *port); extern void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, struct tty_struct *tty, -- cgit v1.2.3 From 4b5cf2b8f90faf32bbb735b545510edefce094be Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 Jul 2020 14:49:57 +0200 Subject: USB: serial: add sysrq break-handler dummy Add inline sysrq break-handler dummy to allow the compiler to eliminate further code when either console or sysrq support isn't enabled and to clearly mark the two sysrq functions as belonging together. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold --- include/linux/usb/serial.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index be73646706a9..c4ed4404335e 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -369,14 +369,18 @@ extern int usb_serial_generic_prepare_write_buffer(struct usb_serial_port *port, #if defined(CONFIG_USB_SERIAL_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ) extern int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch); +extern int usb_serial_handle_break(struct usb_serial_port *port); #else static inline int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch) { return 0; } +static inline int usb_serial_handle_break(struct usb_serial_port *port) +{ + return 0; +} #endif -extern int usb_serial_handle_break(struct usb_serial_port *port); extern void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, struct tty_struct *tty, unsigned int status); -- cgit v1.2.3 From 1cafb03d5d88631c218a072e4116ac92e9782dd0 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 Jul 2020 14:49:58 +0200 Subject: USB: serial: drop unnecessary sysrq include There's no need to include sysrq.h in the subsystem header. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold --- include/linux/usb/serial.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index c4ed4404335e..4becca7ae264 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -17,7 +17,6 @@ #include #include #include -#include #include /* The maximum number of ports one device can grab at once */ -- cgit v1.2.3 From 7aab96d6e3c54128f9e335fa8b11a0bd8815e118 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 Jul 2020 14:49:59 +0200 Subject: USB: serial: drop extern keyword from function declarations Drop the redundant extern keyword from function declarations in the subsystem header file to improve readability (and make it easier to spot the global variables). Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold --- include/linux/usb/serial.h | 81 +++++++++++++++++++++------------------------- 1 file changed, 36 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 4becca7ae264..6d756d03f46f 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -315,19 +315,19 @@ struct usb_serial_driver { #define to_usb_serial_driver(d) \ container_of(d, struct usb_serial_driver, driver) -extern int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[], +int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[], const char *name, const struct usb_device_id *id_table); -extern void usb_serial_deregister_drivers(struct usb_serial_driver *const serial_drivers[]); -extern void usb_serial_port_softint(struct usb_serial_port *port); +void usb_serial_deregister_drivers(struct usb_serial_driver *const serial_drivers[]); +void usb_serial_port_softint(struct usb_serial_port *port); -extern int usb_serial_suspend(struct usb_interface *intf, pm_message_t message); -extern int usb_serial_resume(struct usb_interface *intf); +int usb_serial_suspend(struct usb_interface *intf, pm_message_t message); +int usb_serial_resume(struct usb_interface *intf); /* USB Serial console functions */ #ifdef CONFIG_USB_SERIAL_CONSOLE -extern void usb_serial_console_init(int minor); -extern void usb_serial_console_exit(void); -extern void usb_serial_console_disconnect(struct usb_serial *serial); +void usb_serial_console_init(int minor); +void usb_serial_console_exit(void); +void usb_serial_console_disconnect(struct usb_serial *serial); #else static inline void usb_serial_console_init(int minor) { } static inline void usb_serial_console_exit(void) { } @@ -335,40 +335,32 @@ static inline void usb_serial_console_disconnect(struct usb_serial *serial) {} #endif /* Functions needed by other parts of the usbserial core */ -extern struct usb_serial_port *usb_serial_port_get_by_minor(unsigned int minor); -extern void usb_serial_put(struct usb_serial *serial); -extern int usb_serial_generic_open(struct tty_struct *tty, - struct usb_serial_port *port); -extern int usb_serial_generic_write_start(struct usb_serial_port *port, - gfp_t mem_flags); -extern int usb_serial_generic_write(struct tty_struct *tty, - struct usb_serial_port *port, const unsigned char *buf, int count); -extern void usb_serial_generic_close(struct usb_serial_port *port); -extern int usb_serial_generic_resume(struct usb_serial *serial); -extern int usb_serial_generic_write_room(struct tty_struct *tty); -extern int usb_serial_generic_chars_in_buffer(struct tty_struct *tty); -extern void usb_serial_generic_wait_until_sent(struct tty_struct *tty, - long timeout); -extern void usb_serial_generic_read_bulk_callback(struct urb *urb); -extern void usb_serial_generic_write_bulk_callback(struct urb *urb); -extern void usb_serial_generic_throttle(struct tty_struct *tty); -extern void usb_serial_generic_unthrottle(struct tty_struct *tty); -extern int usb_serial_generic_tiocmiwait(struct tty_struct *tty, - unsigned long arg); -extern int usb_serial_generic_get_icount(struct tty_struct *tty, - struct serial_icounter_struct *icount); -extern int usb_serial_generic_register(void); -extern void usb_serial_generic_deregister(void); -extern int usb_serial_generic_submit_read_urbs(struct usb_serial_port *port, - gfp_t mem_flags); -extern void usb_serial_generic_process_read_urb(struct urb *urb); -extern int usb_serial_generic_prepare_write_buffer(struct usb_serial_port *port, - void *dest, size_t size); +struct usb_serial_port *usb_serial_port_get_by_minor(unsigned int minor); +void usb_serial_put(struct usb_serial *serial); +int usb_serial_generic_open(struct tty_struct *tty, struct usb_serial_port *port); +int usb_serial_generic_write_start(struct usb_serial_port *port, gfp_t mem_flags); +int usb_serial_generic_write(struct tty_struct *tty, struct usb_serial_port *port, + const unsigned char *buf, int count); +void usb_serial_generic_close(struct usb_serial_port *port); +int usb_serial_generic_resume(struct usb_serial *serial); +int usb_serial_generic_write_room(struct tty_struct *tty); +int usb_serial_generic_chars_in_buffer(struct tty_struct *tty); +void usb_serial_generic_wait_until_sent(struct tty_struct *tty, long timeout); +void usb_serial_generic_read_bulk_callback(struct urb *urb); +void usb_serial_generic_write_bulk_callback(struct urb *urb); +void usb_serial_generic_throttle(struct tty_struct *tty); +void usb_serial_generic_unthrottle(struct tty_struct *tty); +int usb_serial_generic_tiocmiwait(struct tty_struct *tty, unsigned long arg); +int usb_serial_generic_get_icount(struct tty_struct *tty, struct serial_icounter_struct *icount); +int usb_serial_generic_register(void); +void usb_serial_generic_deregister(void); +int usb_serial_generic_submit_read_urbs(struct usb_serial_port *port, gfp_t mem_flags); +void usb_serial_generic_process_read_urb(struct urb *urb); +int usb_serial_generic_prepare_write_buffer(struct usb_serial_port *port, void *dest, size_t size); #if defined(CONFIG_USB_SERIAL_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ) -extern int usb_serial_handle_sysrq_char(struct usb_serial_port *port, - unsigned int ch); -extern int usb_serial_handle_break(struct usb_serial_port *port); +int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch); +int usb_serial_handle_break(struct usb_serial_port *port); #else static inline int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch) { @@ -380,13 +372,12 @@ static inline int usb_serial_handle_break(struct usb_serial_port *port) } #endif -extern void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, - struct tty_struct *tty, - unsigned int status); +void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, + struct tty_struct *tty, unsigned int status); -extern int usb_serial_bus_register(struct usb_serial_driver *device); -extern void usb_serial_bus_deregister(struct usb_serial_driver *device); +int usb_serial_bus_register(struct usb_serial_driver *device); +void usb_serial_bus_deregister(struct usb_serial_driver *device); extern struct bus_type usb_serial_bus_type; extern struct tty_driver *usb_serial_tty_driver; -- cgit v1.2.3 From f7f611f2b1dc69547d425de0daeac548add2c761 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 8 Jul 2020 09:11:49 +0200 Subject: ARM: s3c24xx: leds: Convert to use GPIO descriptors This converts the s3c24xx LED driver to use GPIO descriptors and also modify all board files to account for these changes by registering the appropriate GPIO tables for each board. The driver was using a custom flag to indicate open drain (tristate) but this can be handled by standard descriptor machine tables. The driver was setting non-pull-up for the pin using the custom S3C24xx GPIO API, but this is a custom pin control system used by the S3C24xx and no generic GPIO function, so this has simply been pushed back into the respective board files. Signed-off-by: Linus Walleij Acked-by: Jacek Anaszewski Signed-off-by: Krzysztof Kozlowski --- include/linux/platform_data/leds-s3c24xx.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/leds-s3c24xx.h b/include/linux/platform_data/leds-s3c24xx.h index 5bbae85811e2..64f8d14876e0 100644 --- a/include/linux/platform_data/leds-s3c24xx.h +++ b/include/linux/platform_data/leds-s3c24xx.h @@ -10,13 +10,7 @@ #ifndef __LEDS_S3C24XX_H #define __LEDS_S3C24XX_H -#define S3C24XX_LEDF_ACTLOW (1<<0) /* LED is on when GPIO low */ -#define S3C24XX_LEDF_TRISTATE (1<<1) /* tristate to turn off */ - struct s3c24xx_led_platdata { - unsigned int gpio; - unsigned int flags; - char *name; char *def_trigger; }; -- cgit v1.2.3 From 7bc13b5b60e9412a7ddef300ce2c661eecd1fd5d Mon Sep 17 00:00:00 2001 From: Barry Song Date: Sun, 5 Jul 2020 21:18:58 +1200 Subject: crypto: api - permit users to specify numa node of acomp hardware For a Linux server with NUMA, there are possibly multiple (de)compressors which are either local or remote to some NUMA node. Some drivers will automatically use the (de)compressor near the CPU calling acomp_alloc(). However, it is not necessarily correct because users who send acomp_req could be from different NUMA node with the CPU which allocates acomp. Just like kernel has kmalloc() and kmalloc_node(), here crypto can have same support. Cc: Seth Jennings Cc: Dan Streetman Cc: Vitaly Wool Cc: Andrew Morton Cc: Jonathan Cameron Signed-off-by: Barry Song Signed-off-by: Herbert Xu --- include/linux/crypto.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index bc5d2d4bfc3d..7cd2d00f0a05 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -594,6 +594,8 @@ int crypto_has_alg(const char *name, u32 type, u32 mask); struct crypto_tfm { u32 crt_flags; + + int node; void (*exit)(struct crypto_tfm *tfm); -- cgit v1.2.3 From 995decb6c43e1d6e9d6a7d590471f2eea74600f4 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 8 Jul 2020 16:00:23 +0200 Subject: KVM: x86: take as_id into account when checking PGD OVMF booted guest running on shadow pages crashes on TRIPLE FAULT after enabling paging from SMM. The crash is triggered from mmu_check_root() and is caused by kvm_is_visible_gfn() searching through memslots with as_id = 0 while vCPU may be in a different context (address space). Introduce kvm_vcpu_is_visible_gfn() and use it from mmu_check_root(). Signed-off-by: Vitaly Kuznetsov Message-Id: <20200708140023.1476020-1-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9edc6fc71a89..87140e79648b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -774,6 +774,7 @@ int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); +bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); -- cgit v1.2.3 From 8d87ae48ced2dffd5e7247d19eb4c88be6f1c6f1 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 8 Jul 2020 16:32:13 -0700 Subject: PM: domains: Fix up terminology with parent/child The genpd infrastructure uses the terms master/slave, but such uses have no external exposures (not even in Documentation/driver-api/pm/*) and are not mandated by nor associated with any external specifications. Change the language used through-out to parent/child. There was one possible exception in the debugfs node "pm_genpd/pm_genpd_summary" but its path has no hits outside of the kernel itself when performing a code search[1], and it seems even this single usage has been non-functional since it was introduced due to a typo in the Python ("apend" instead of correct "append"). Fix the typo while we're at it. Link: https://codesearch.debian.net/ # [1] Signed-off-by: Kees Cook Reviewed-by: Greg Kroah-Hartman Reviewed-by: Kieran Bingham Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 9ec78ee53652..574a1fadb1e5 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -95,8 +95,8 @@ struct generic_pm_domain { struct device dev; struct dev_pm_domain domain; /* PM domain operations */ struct list_head gpd_list_node; /* Node in the global PM domains list */ - struct list_head master_links; /* Links with PM domain as a master */ - struct list_head slave_links; /* Links with PM domain as a slave */ + struct list_head parent_links; /* Links with PM domain as a parent */ + struct list_head child_links;/* Links with PM domain as a child */ struct list_head dev_list; /* List of devices */ struct dev_power_governor *gov; struct work_struct power_off_work; @@ -151,10 +151,10 @@ static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd) } struct gpd_link { - struct generic_pm_domain *master; - struct list_head master_node; - struct generic_pm_domain *slave; - struct list_head slave_node; + struct generic_pm_domain *parent; + struct list_head parent_node; + struct generic_pm_domain *child; + struct list_head child_node; /* Sub-domain's per-master domain performance state */ unsigned int performance_state; -- cgit v1.2.3 From 2aa9c199cf8151c190c7e7ca3ddfcfbb2d85ac36 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 2 Jul 2020 19:35:38 -0700 Subject: KVM: Move x86's version of struct kvm_mmu_memory_cache to common code Move x86's 'struct kvm_mmu_memory_cache' to common code in anticipation of moving the entire x86 implementation code to common KVM and reusing it for arm64 and MIPS. Add a new architecture specific asm/kvm_types.h to control the existence and parameters of the struct. The new header is needed to avoid a chicken-and-egg problem with asm/kvm_host.h as all architectures define instances of the struct in their vCPU structs. Add an asm-generic version of kvm_types.h to avoid having empty files on PPC and s390 in the long term, and for arm64 and mips in the short term. Suggested-by: Christoffer Dall Reviewed-by: Ben Gardon Signed-off-by: Sean Christopherson Message-Id: <20200703023545.8771-15-sean.j.christopherson@intel.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_types.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 68e84cf42a3f..a7580f69dda0 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -20,6 +20,8 @@ enum kvm_mr_change; #include +#include + /* * Address types: * @@ -58,4 +60,21 @@ struct gfn_to_pfn_cache { bool dirty; }; +#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE +/* + * Memory caches are used to preallocate memory ahead of various MMU flows, + * e.g. page fault handlers. Gracefully handling allocation failures deep in + * MMU flows is problematic, as is triggering reclaim, I/O, etc... while + * holding MMU locks. Note, these caches act more like prefetch buffers than + * classical caches, i.e. objects are not returned to the cache on being freed. + */ +struct kvm_mmu_memory_cache { + int nobjs; + gfp_t gfp_zero; + struct kmem_cache *kmem_cache; + void *objects[KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE]; +}; +#endif + + #endif /* __KVM_TYPES_H__ */ -- cgit v1.2.3 From 6926f95accee3f8ceb5f69dbecd880687028ae70 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 2 Jul 2020 19:35:39 -0700 Subject: KVM: Move x86's MMU memory cache helpers to common KVM code Move x86's memory cache helpers to common KVM code so that they can be reused by arm64 and MIPS in future patches. Suggested-by: Christoffer Dall Reviewed-by: Ben Gardon Signed-off-by: Sean Christopherson Message-Id: <20200703023545.8771-16-sean.j.christopherson@intel.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 87140e79648b..989afcbe642f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -817,6 +817,13 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); +#ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE +int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min); +int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc); +void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc); +void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); +#endif + bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, struct kvm_vcpu *except, unsigned long *vcpu_bitmap, cpumask_var_t tmp); -- cgit v1.2.3 From 60a883d119ab9ef63f830c85bbd2f0e2e2314f4f Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 9 Jul 2020 08:50:07 +0200 Subject: spi: use kthread_create_worker() helper Use kthread_create_worker() helper to simplify the code. It uses the kthread worker API the right way. It will eventually allow to remove the FIXME in kthread_worker_fn() and add more consistency checks in the future. Signed-off-by: Marek Szyprowski Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20200709065007.26896-1-m.szyprowski@samsung.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 0e67a9a3a1d3..5fcf5da13fdb 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -358,8 +358,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @cleanup: frees controller-specific state * @can_dma: determine whether this controller supports DMA * @queued: whether this controller is providing an internal message queue - * @kworker: thread struct for message pump - * @kworker_task: pointer to task for message pump kworker thread + * @kworker: pointer to thread struct for message pump * @pump_messages: work struct for scheduling work to the message pump * @queue_lock: spinlock to syncronise access to message queue * @queue: message queue @@ -593,8 +592,7 @@ struct spi_controller { * Over time we expect SPI drivers to be phased over to this API. */ bool queued; - struct kthread_worker kworker; - struct task_struct *kworker_task; + struct kthread_worker *kworker; struct kthread_work pump_messages; spinlock_t queue_lock; struct list_head queue; -- cgit v1.2.3 From 2575b2f3ee711f4638e772e07a5146afcc704f30 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 8 Jul 2020 15:59:30 +0800 Subject: PCI: Move PCI_VENDOR_ID_REDHAT definition to pci_ids.h Instead of duplicating the PCI_VENDOR_ID_REDHAT definition everywhere, move it to include/linux/pci_ids.h. [bhelgaas: also update MDPY_PCI_VENDOR_ID] Link: https://lore.kernel.org/r/1594195170-11119-1-git-send-email-chenhc@lemote.com Signed-off-by: Huacai Chen Signed-off-by: Bjorn Helgaas Acked-by: Gerd Hoffmann --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 0ad57693f392..5c709a1450b1 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2585,6 +2585,8 @@ #define PCI_VENDOR_ID_ASMEDIA 0x1b21 +#define PCI_VENDOR_ID_REDHAT 0x1b36 + #define PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS 0x1c36 #define PCI_VENDOR_ID_CIRCUITCO 0x1cc8 -- cgit v1.2.3 From 14b032b8f8fce03a546dcf365454bec8c4a58d7d Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 9 Jul 2020 16:28:44 -0700 Subject: cgroup: Fix sock_cgroup_data on big-endian. In order for no_refcnt and is_data to be the lowest order two bits in the 'val' we have to pad out the bitfield of the u8. Fixes: ad0f75e5f57c ("cgroup: fix cgroup_sk_alloc() for sk_clone_lock()") Reported-by: Guenter Roeck Signed-off-by: David S. Miller --- include/linux/cgroup-defs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4f1cd0edc57d..fee0b5547cd0 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -792,6 +792,7 @@ struct sock_cgroup_data { struct { u8 is_data : 1; u8 no_refcnt : 1; + u8 unused : 6; u8 padding; u16 prioidx; u32 classid; @@ -801,6 +802,7 @@ struct sock_cgroup_data { u32 classid; u16 prioidx; u8 padding; + u8 unused : 6; u8 no_refcnt : 1; u8 is_data : 1; } __packed; -- cgit v1.2.3 From 88b3d5c90e9685be54dd5bc441970044020eca76 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 22 Jun 2020 09:03:31 +0300 Subject: net/mlx5e: Fix port buffers cell size value Device unit for port buffers size, xoff_threshold and xon_threshold is cells. Fix a bug in driver where cell unit size was hard-coded to 128 bytes. This hard-coded value is buggy, as it is wrong for some hardware versions. Driver to read cell size from SBCAM register and translate bytes to cell units accordingly. In order to fix the bug, this patch exposes SBCAM (Shared buffer capabilities mask) layout and defines. If SBCAM.cap_cell_size is valid, use it for all bytes to cells calculations. If not valid, fallback to 128. Cell size do not change on the fly per device. Instead of issuing SBCAM access reg command every time such translation is needed, cache it in mlx5e_dcbx as part of mlx5e_dcbnl_initialize(). Pass dcbx.port_buff_cell_sz as a param to every function that needs bytes to cells translation. While fixing the bug, move MLX5E_BUFFER_CELL_SHIFT macro to en_dcbnl.c, as it is only used by that file. Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration") Signed-off-by: Eran Ben Elisha Reviewed-by: Huy Nguyen Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 13c0e4556eda..1e6ca716635a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -147,6 +147,7 @@ enum { MLX5_REG_MCDA = 0x9063, MLX5_REG_MCAM = 0x907f, MLX5_REG_MIRC = 0x9162, + MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ca1887dd0423..073b79eacc99 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9960,6 +9960,34 @@ struct mlx5_ifc_pptb_reg_bits { u8 untagged_buff[0x4]; }; +struct mlx5_ifc_sbcam_reg_bits { + u8 reserved_at_0[0x8]; + u8 feature_group[0x8]; + u8 reserved_at_10[0x8]; + u8 access_reg_group[0x8]; + + u8 reserved_at_20[0x20]; + + u8 sb_access_reg_cap_mask[4][0x20]; + + u8 reserved_at_c0[0x80]; + + u8 sb_feature_cap_mask[4][0x20]; + + u8 reserved_at_1c0[0x40]; + + u8 cap_total_buffer_size[0x20]; + + u8 cap_cell_size[0x10]; + u8 cap_max_pg_buffers[0x8]; + u8 cap_num_pool_supported[0x8]; + + u8 reserved_at_240[0x8]; + u8 cap_sbsr_stat_size[0x8]; + u8 cap_max_tclass_data[0x8]; + u8 cap_max_cpu_ingress_tclass_sb[0x8]; +}; + struct mlx5_ifc_pbmc_reg_bits { u8 reserved_at_0[0x8]; u8 local_port[0x8]; -- cgit v1.2.3 From 8c080d3a974ad471d8324825851044284f1886c9 Mon Sep 17 00:00:00 2001 From: Vincent Chen Date: Tue, 23 Jun 2020 13:36:42 +0800 Subject: kgdb: enable arch to support XML packet. The XML packet could be supported by required architecture if the architecture defines CONFIG_HAVE_ARCH_KGDB_QXFER_PKT and implement its own kgdb_arch_handle_qxfer_pkt(). Except for the kgdb_arch_handle_qxfer_pkt(), the architecture also needs to record the feature supported by gdb stub into the kgdb_arch_gdb_stub_feature, and these features will be reported to host gdb when gdb stub receives the qSupported packet. Signed-off-by: Vincent Chen Acked-by: Daniel Thompson Signed-off-by: Palmer Dabbelt --- include/linux/kgdb.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 529116b0cabe..0e4e3a80d58c 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -176,6 +176,17 @@ kgdb_arch_handle_exception(int vector, int signo, int err_code, char *remcom_out_buffer, struct pt_regs *regs); +/** + * kgdb_arch_handle_qxfer_pkt - Handle architecture specific GDB XML + * packets. + * @remcom_in_buffer: The buffer of the packet we have read. + * @remcom_out_buffer: The buffer of %BUFMAX bytes to write a packet into. + */ + +extern void +kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer, + char *remcom_out_buffer); + /** * kgdb_call_nmi_hook - Call kgdb_nmicallback() on the current CPU * @ignored: This parameter is only here to match the prototype. -- cgit v1.2.3 From def0aa218e6d42231540329e6f5741fdec9e7da4 Mon Sep 17 00:00:00 2001 From: Vincent Chen Date: Tue, 23 Jun 2020 13:37:25 +0800 Subject: kgdb: Move the extern declaration kgdb_has_hit_break() to generic kgdb.h Currently, only riscv kgdb.c uses the kgdb_has_hit_break() to identify the kgdb breakpoint. It causes other architectures will encounter the "no previous prototype" warnings if the compile option has W=1. Moving the declaration of extern kgdb_has_hit_break() from risc-v kgdb.h to generic kgdb.h to avoid generating these warnings. Signed-off-by: Vincent Chen Acked-by: Daniel Thompson Signed-off-by: Palmer Dabbelt --- include/linux/kgdb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 0e4e3a80d58c..477b8b7c908f 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -325,6 +325,7 @@ extern int kgdb_hex2mem(char *buf, char *mem, int count); extern int kgdb_isremovedbreak(unsigned long addr); extern void kgdb_schedule_breakpoint(void); +extern int kgdb_has_hit_break(unsigned long addr); extern int kgdb_handle_exception(int ex_vector, int signo, int err_code, -- cgit v1.2.3 From ba1f2b2eaa2a529dba722507c55ff3d761d325dd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 27 May 2020 15:50:29 +0200 Subject: x86/entry: Fix NMI vs IRQ state tracking While the nmi_enter() users did trace_hardirqs_{off_prepare,on_finish}() there was no matching lockdep_hardirqs_*() calls to complete the picture. Introduce idtentry_{enter,exit}_nmi() to enable proper IRQ state tracking across the NMIs. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ingo Molnar Link: https://lkml.kernel.org/r/20200623083721.216740948@infradead.org --- include/linux/hardirq.h | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 03c9fece7d43..754f67ac4326 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -111,32 +111,42 @@ extern void rcu_nmi_exit(void); /* * nmi_enter() can nest up to 15 times; see NMI_BITS. */ -#define nmi_enter() \ +#define __nmi_enter() \ do { \ + lockdep_off(); \ arch_nmi_enter(); \ printk_nmi_enter(); \ - lockdep_off(); \ BUG_ON(in_nmi() == NMI_MASK); \ __preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ - rcu_nmi_enter(); \ + } while (0) + +#define nmi_enter() \ + do { \ + __nmi_enter(); \ lockdep_hardirq_enter(); \ + rcu_nmi_enter(); \ instrumentation_begin(); \ ftrace_nmi_enter(); \ instrumentation_end(); \ } while (0) +#define __nmi_exit() \ + do { \ + BUG_ON(!in_nmi()); \ + __preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ + printk_nmi_exit(); \ + arch_nmi_exit(); \ + lockdep_on(); \ + } while (0) + #define nmi_exit() \ do { \ instrumentation_begin(); \ ftrace_nmi_exit(); \ instrumentation_end(); \ - lockdep_hardirq_exit(); \ rcu_nmi_exit(); \ - BUG_ON(!in_nmi()); \ - __preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ - lockdep_on(); \ - printk_nmi_exit(); \ - arch_nmi_exit(); \ + lockdep_hardirq_exit(); \ + __nmi_exit(); \ } while (0) #endif /* LINUX_HARDIRQ_H */ -- cgit v1.2.3 From a21ee6055c30ce68c4e201c6496f0ed2a1936230 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 25 May 2020 12:22:41 +0200 Subject: lockdep: Change hardirq{s_enabled,_context} to per-cpu variables Currently all IRQ-tracking state is in task_struct, this means that task_struct needs to be defined before we use it. Especially for lockdep_assert_irq*() this can lead to header-hell. Move the hardirq state into per-cpu variables to avoid the task_struct dependency. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ingo Molnar Link: https://lkml.kernel.org/r/20200623083721.512673481@infradead.org --- include/linux/irqflags.h | 19 ++++++++++++------- include/linux/lockdep.h | 34 ++++++++++++++++++---------------- include/linux/sched.h | 2 -- 3 files changed, 30 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 6384d2813ded..255444fe4609 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -14,6 +14,7 @@ #include #include +#include /* Currently lockdep_softirqs_on/off is used only by lockdep */ #ifdef CONFIG_PROVE_LOCKING @@ -31,18 +32,22 @@ #endif #ifdef CONFIG_TRACE_IRQFLAGS + +DECLARE_PER_CPU(int, hardirqs_enabled); +DECLARE_PER_CPU(int, hardirq_context); + extern void trace_hardirqs_on_prepare(void); extern void trace_hardirqs_off_finish(void); extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); -# define lockdep_hardirq_context(p) ((p)->hardirq_context) +# define lockdep_hardirq_context(p) (this_cpu_read(hardirq_context)) # define lockdep_softirq_context(p) ((p)->softirq_context) -# define lockdep_hardirqs_enabled(p) ((p)->hardirqs_enabled) +# define lockdep_hardirqs_enabled(p) (this_cpu_read(hardirqs_enabled)) # define lockdep_softirqs_enabled(p) ((p)->softirqs_enabled) -# define lockdep_hardirq_enter() \ -do { \ - if (!current->hardirq_context++) \ - current->hardirq_threaded = 0; \ +# define lockdep_hardirq_enter() \ +do { \ + if (this_cpu_inc_return(hardirq_context) == 1) \ + current->hardirq_threaded = 0; \ } while (0) # define lockdep_hardirq_threaded() \ do { \ @@ -50,7 +55,7 @@ do { \ } while (0) # define lockdep_hardirq_exit() \ do { \ - current->hardirq_context--; \ + this_cpu_dec(hardirq_context); \ } while (0) # define lockdep_softirq_enter() \ do { \ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 3b73cf84f77d..be6cb17a8879 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -11,6 +11,7 @@ #define __LINUX_LOCKDEP_H #include +#include struct task_struct; @@ -529,28 +530,29 @@ do { \ lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) -#define lockdep_assert_irqs_enabled() do { \ - WARN_ONCE(debug_locks && !current->lockdep_recursion && \ - !current->hardirqs_enabled, \ - "IRQs not enabled as expected\n"); \ - } while (0) +DECLARE_PER_CPU(int, hardirqs_enabled); +DECLARE_PER_CPU(int, hardirq_context); -#define lockdep_assert_irqs_disabled() do { \ - WARN_ONCE(debug_locks && !current->lockdep_recursion && \ - current->hardirqs_enabled, \ - "IRQs not disabled as expected\n"); \ - } while (0) +#define lockdep_assert_irqs_enabled() \ +do { \ + WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirqs_enabled)); \ +} while (0) -#define lockdep_assert_in_irq() do { \ - WARN_ONCE(debug_locks && !current->lockdep_recursion && \ - !current->hardirq_context, \ - "Not in hardirq as expected\n"); \ - } while (0) +#define lockdep_assert_irqs_disabled() \ +do { \ + WARN_ON_ONCE(debug_locks && this_cpu_read(hardirqs_enabled)); \ +} while (0) + +#define lockdep_assert_in_irq() \ +do { \ + WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirq_context)); \ +} while (0) #else # define might_lock(lock) do { } while (0) # define might_lock_read(lock) do { } while (0) # define might_lock_nested(lock, subclass) do { } while (0) + # define lockdep_assert_irqs_enabled() do { } while (0) # define lockdep_assert_irqs_disabled() do { } while (0) # define lockdep_assert_in_irq() do { } while (0) @@ -560,7 +562,7 @@ do { \ # define lockdep_assert_RT_in_threaded_ctx() do { \ WARN_ONCE(debug_locks && !current->lockdep_recursion && \ - current->hardirq_context && \ + lockdep_hardirq_context(current) && \ !(current->hardirq_threaded || current->irq_config), \ "Not in threaded context on PREEMPT_RT as expected\n"); \ } while (0) diff --git a/include/linux/sched.h b/include/linux/sched.h index 692e327d7455..3903a9500926 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -990,8 +990,6 @@ struct task_struct { unsigned long hardirq_disable_ip; unsigned int hardirq_enable_event; unsigned int hardirq_disable_event; - int hardirqs_enabled; - int hardirq_context; u64 hardirq_chain_key; unsigned long softirq_disable_ip; unsigned long softirq_enable_ip; -- cgit v1.2.3 From f9ad4a5f3f20bee022b1bdde94e5ece6dc0b0edc Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 27 May 2020 13:03:26 +0200 Subject: lockdep: Remove lockdep_hardirq{s_enabled,_context}() argument Now that the macros use per-cpu data, we no longer need the argument. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ingo Molnar Link: https://lkml.kernel.org/r/20200623083721.571835311@infradead.org --- include/linux/irqflags.h | 8 ++++---- include/linux/lockdep.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 255444fe4609..5811ee8a5cd8 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -40,9 +40,9 @@ DECLARE_PER_CPU(int, hardirq_context); extern void trace_hardirqs_off_finish(void); extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); -# define lockdep_hardirq_context(p) (this_cpu_read(hardirq_context)) +# define lockdep_hardirq_context() (this_cpu_read(hardirq_context)) # define lockdep_softirq_context(p) ((p)->softirq_context) -# define lockdep_hardirqs_enabled(p) (this_cpu_read(hardirqs_enabled)) +# define lockdep_hardirqs_enabled() (this_cpu_read(hardirqs_enabled)) # define lockdep_softirqs_enabled(p) ((p)->softirqs_enabled) # define lockdep_hardirq_enter() \ do { \ @@ -109,9 +109,9 @@ do { \ # define trace_hardirqs_off_finish() do { } while (0) # define trace_hardirqs_on() do { } while (0) # define trace_hardirqs_off() do { } while (0) -# define lockdep_hardirq_context(p) 0 +# define lockdep_hardirq_context() 0 # define lockdep_softirq_context(p) 0 -# define lockdep_hardirqs_enabled(p) 0 +# define lockdep_hardirqs_enabled() 0 # define lockdep_softirqs_enabled(p) 0 # define lockdep_hardirq_enter() do { } while (0) # define lockdep_hardirq_threaded() do { } while (0) diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index be6cb17a8879..fd04b9e96091 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -562,7 +562,7 @@ do { \ # define lockdep_assert_RT_in_threaded_ctx() do { \ WARN_ONCE(debug_locks && !current->lockdep_recursion && \ - lockdep_hardirq_context(current) && \ + lockdep_hardirq_context() && \ !(current->hardirq_threaded || current->irq_config), \ "Not in threaded context on PREEMPT_RT as expected\n"); \ } while (0) -- cgit v1.2.3 From 6348dd291e3653534a9e28e6917569bc9967b35b Mon Sep 17 00:00:00 2001 From: Charan Teja Kalla Date: Fri, 19 Jun 2020 17:27:19 +0530 Subject: dmabuf: use spinlock to access dmabuf->name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There exists a sleep-while-atomic bug while accessing the dmabuf->name under mutex in the dmabuffs_dname(). This is caused from the SELinux permissions checks on a process where it tries to validate the inherited files from fork() by traversing them through iterate_fd() (which traverse files under spin_lock) and call match_file(security/selinux/hooks.c) where the permission checks happen. This audit information is logged using dump_common_audit_data() where it calls d_path() to get the file path name. If the file check happen on the dmabuf's fd, then it ends up in ->dmabuffs_dname() and use mutex to access dmabuf->name. The flow will be like below: flush_unauthorized_files() iterate_fd() spin_lock() --> Start of the atomic section. match_file() file_has_perm() avc_has_perm() avc_audit() slow_avc_audit() common_lsm_audit() dump_common_audit_data() audit_log_d_path() d_path() dmabuffs_dname() mutex_lock()--> Sleep while atomic. Call trace captured (on 4.19 kernels) is below: ___might_sleep+0x204/0x208 __might_sleep+0x50/0x88 __mutex_lock_common+0x5c/0x1068 __mutex_lock_common+0x5c/0x1068 mutex_lock_nested+0x40/0x50 dmabuffs_dname+0xa0/0x170 d_path+0x84/0x290 audit_log_d_path+0x74/0x130 common_lsm_audit+0x334/0x6e8 slow_avc_audit+0xb8/0xf8 avc_has_perm+0x154/0x218 file_has_perm+0x70/0x180 match_file+0x60/0x78 iterate_fd+0x128/0x168 selinux_bprm_committing_creds+0x178/0x248 security_bprm_committing_creds+0x30/0x48 install_exec_creds+0x1c/0x68 load_elf_binary+0x3a4/0x14e0 search_binary_handler+0xb0/0x1e0 So, use spinlock to access dmabuf->name to avoid sleep-while-atomic. Cc: [5.3+] Signed-off-by: Charan Teja Kalla Reviewed-by: Michael J. Ruhl Acked-by: Christian König [sumits: added comment to spinlock_t definition to avoid warning] Signed-off-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/a83e7f0d-4e54-9848-4b58-e1acdbe06735@codeaurora.org --- include/linux/dma-buf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index ab0c156abee6..a2ca294eaebe 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -311,6 +311,7 @@ struct dma_buf { void *vmap_ptr; const char *exp_name; const char *name; + spinlock_t name_lock; /* spinlock to protect name access */ struct module *owner; struct list_head list_node; void *priv; -- cgit v1.2.3 From 5bc117a27fd044bd5ddeb8ab22c58976bf01b50d Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 9 Jul 2020 14:08:57 +0200 Subject: virt: vbox: Log unknown ioctl requests as error Every now and then upstream adds new ioctls without notifying us, log unknown ioctl requests as an error to catch these. Acked-by: Arnd Bergmann Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20200709120858.63928-8-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman --- include/linux/vbox_utils.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vbox_utils.h b/include/linux/vbox_utils.h index ff56c443180c..db8a7d118093 100644 --- a/include/linux/vbox_utils.h +++ b/include/linux/vbox_utils.h @@ -16,6 +16,7 @@ struct vbg_dev; __printf(1, 2) void vbg_info(const char *fmt, ...); __printf(1, 2) void vbg_warn(const char *fmt, ...); __printf(1, 2) void vbg_err(const char *fmt, ...); +__printf(1, 2) void vbg_err_ratelimited(const char *fmt, ...); /* Only use backdoor logging for non-dynamic debug builds */ #if defined(DEBUG) && !defined(CONFIG_DYNAMIC_DEBUG) -- cgit v1.2.3 From a9f91cebbeb8ea1355e852cce6d40efbcddbfe2b Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 8 Jul 2020 13:57:09 +0100 Subject: misc: vmw_vmci_defs: Mark 'struct vmci_handle VMCI_ANON_SRC_HANDLE' as __maybe_unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit vmw_vmci_defs.h is included by multiple source files. Some of which do not make use of 'struct vmci_handle VMCI_ANON_SRC_HANDLE' rendering it unused. Ensure the compiler knows that this is in fact intentional by marking it as __maybe_unused. This fixes the following W=1 warnings: In file included from drivers/misc/vmw_vmci/vmci_context.c:8: include/linux/vmw_vmci_defs.h:162:33: warning: ‘VMCI_ANON_SRC_HANDLE’ defined but not used [-Wunused-const-variable=] 162 | static const struct vmci_handle VMCI_ANON_SRC_HANDLE = { | ^~~~~~~~~~~~~~~~~~~~ In file included from drivers/misc/vmw_vmci/vmci_datagram.c:8: include/linux/vmw_vmci_defs.h:162:33: warning: ‘VMCI_ANON_SRC_HANDLE’ defined but not used [-Wunused-const-variable=] 162 | static const struct vmci_handle VMCI_ANON_SRC_HANDLE = { | ^~~~~~~~~~~~~~~~~~~~ Cc: George Zhang Signed-off-by: Lee Jones Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200708125711.3443569-2-lee.jones@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/vmw_vmci_defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index fefb5292403b..be0afe6f379b 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -159,7 +159,7 @@ static inline bool vmci_handle_is_invalid(struct vmci_handle h) */ #define VMCI_ANON_SRC_CONTEXT_ID VMCI_INVALID_ID #define VMCI_ANON_SRC_RESOURCE_ID VMCI_INVALID_ID -static const struct vmci_handle VMCI_ANON_SRC_HANDLE = { +static const struct vmci_handle __maybe_unused VMCI_ANON_SRC_HANDLE = { .context = VMCI_ANON_SRC_CONTEXT_ID, .resource = VMCI_ANON_SRC_RESOURCE_ID }; -- cgit v1.2.3 From 849a9366cba92cb5dc9dc1161ef49416a290aae9 Mon Sep 17 00:00:00 2001 From: Ricky Wu Date: Mon, 6 Jul 2020 15:02:59 +0800 Subject: misc: rtsx: Add support new chip rts5228 mmc: rtsx: Add support MMC_CAP2_NO_MMC In order to support new chip rts5228, the definitions of some internal registers and workflow have to be modified. Added rts5228.c rts5228.h for independent functions of the new chip rts5228 Signed-off-by: Ricky Wu Link: https://lore.kernel.org/r/20200706070259.32565-1-ricky_wu@realtek.com Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index e8780d4e4636..27a6ea82aeea 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -305,6 +305,8 @@ #define SD30_CLK_STOP_CFG0 0x01 #define REG_PRE_RW_MODE 0xFD70 #define EN_INFINITE_MODE 0x01 +#define REG_CRC_DUMMY_0 0xFD71 +#define CFG_SD_POW_AUTO_PD (1<<0) #define SRCTL 0xFC13 @@ -599,6 +601,7 @@ #define ASPM_FORCE_CTL 0xFE57 #define FORCE_ASPM_CTL0 0x10 +#define FORCE_ASPM_CTL1 0x20 #define FORCE_ASPM_VAL_MASK 0x03 #define FORCE_ASPM_L1_EN 0x02 #define FORCE_ASPM_L0_EN 0x01 @@ -667,6 +670,11 @@ #define PM_WAKE_EN 0x01 #define PM_CTRL4 0xFF47 +#define REG_CFG_OOBS_OFF_TIMER 0xFEA6 +#define REG_CFG_OOBS_ON_TIMER 0xFEA7 +#define REG_CFG_VCM_ON_TIMER 0xFEA8 +#define REG_CFG_OOBS_POLLING 0xFEA9 + /* Memory mapping */ #define SRAM_BASE 0xE600 #define RBUF_BASE 0xF400 @@ -1204,6 +1212,7 @@ struct rtsx_pcr { #define EXTRA_CAPS_MMC_HSDDR (1 << 3) #define EXTRA_CAPS_MMC_HS200 (1 << 4) #define EXTRA_CAPS_MMC_8BIT (1 << 5) +#define EXTRA_CAPS_NO_MMC (1 << 7) u32 extra_caps; #define IC_VER_A 0 @@ -1242,6 +1251,7 @@ struct rtsx_pcr { u8 dma_error_count; u8 ocp_stat; u8 ocp_stat2; + u8 rtd3_en; }; #define PID_524A 0x524A @@ -1250,6 +1260,7 @@ struct rtsx_pcr { #define PID_525A 0x525A #define PID_5260 0x5260 #define PID_5261 0x5261 +#define PID_5228 0x5228 #define CHK_PCI_PID(pcr, pid) ((pcr)->pci->device == (pid)) #define PCI_VID(pcr) ((pcr)->pci->vendor) -- cgit v1.2.3 From 776499058167d9f41c8eb468e21fe2d241c0b8e6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 1 Jul 2020 16:18:29 +0200 Subject: mm/memblock: expose only miminal interface to add/walk physmem "physmem" in the memblock allocator is somewhat weird: it's not actually used for allocation, it's simply information collected during boot, which describes the unmodified physical memory map at boot time, without any standby/hotplugged memory. It's only used on s390 and is currently the only reason s390 keeps using CONFIG_ARCH_KEEP_MEMBLOCK. Physmem isn't numa aware and current users don't specify any flags. Let's hide it from the user, exposing only for_each_physmem(), and simplify. The interface for physmem is now really minimalistic: - memblock_physmem_add() to add ranges - for_each_physmem() / __next_physmem_range() to walk physmem ranges Don't place it into an __init section and don't discard it without CONFIG_ARCH_KEEP_MEMBLOCK. As we're reusing __next_mem_range(), remove the __meminit notifier to avoid section mismatch warnings once CONFIG_ARCH_KEEP_MEMBLOCK is no longer used with CONFIG_HAVE_MEMBLOCK_PHYS_MAP. While fixing up the documentation, sneak in some related cleanups. We can stop setting CONFIG_ARCH_KEEP_MEMBLOCK for s390 next. Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Mike Rapoport Cc: Andrew Morton Signed-off-by: David Hildenbrand Reviewed-by: Mike Rapoport Message-Id: <20200701141830.18749-2-david@redhat.com> Signed-off-by: Heiko Carstens --- include/linux/memblock.h | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 017fae833d4a..9d925db0d355 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -77,16 +77,12 @@ struct memblock_type { * @current_limit: physical address of the current allocation limit * @memory: usable memory regions * @reserved: reserved memory regions - * @physmem: all physical memory */ struct memblock { bool bottom_up; /* is bottom up direction? */ phys_addr_t current_limit; struct memblock_type memory; struct memblock_type reserved; -#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP - struct memblock_type physmem; -#endif }; extern struct memblock memblock; @@ -145,6 +141,30 @@ void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, void __memblock_free_late(phys_addr_t base, phys_addr_t size); +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP +static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, + phys_addr_t *out_start, + phys_addr_t *out_end) +{ + extern struct memblock_type physmem; + + __next_mem_range(idx, NUMA_NO_NODE, MEMBLOCK_NONE, &physmem, type, + out_start, out_end, NULL); +} + +/** + * for_each_physmem_range - iterate through physmem areas not included in type. + * @i: u64 used as loop variable + * @type: ptr to memblock_type which excludes from the iteration, can be %NULL + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + */ +#define for_each_physmem_range(i, type, p_start, p_end) \ + for (i = 0, __next_physmem_range(&i, type, p_start, p_end); \ + i != (u64)ULLONG_MAX; \ + __next_physmem_range(&i, type, p_start, p_end)) +#endif /* CONFIG_HAVE_MEMBLOCK_PHYS_MAP */ + /** * for_each_mem_range - iterate through memblock areas from type_a and not * included in type_b. Or just type_a if type_b is NULL. -- cgit v1.2.3 From ec7bd78498f29680f536451fbdf9464e851273ed Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 1 Jul 2020 12:42:58 -0700 Subject: driver core: Rename dev_links_info.defer_sync to defer_hook The defer_sync field is used as a hook to add the device to the deferred_sync list. Rename it so that it's more meaningful for the next patch that'll also use this field as a hook to a deferred_fw_devlink list. Signed-off-by: Saravana Kannan Reviewed-by: Rafael J. Wysocki Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20200701194259.3337652-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 15460a5ac024..9bb2bc7bb8e3 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -433,7 +433,7 @@ enum dl_dev_state { * @suppliers: List of links to supplier devices. * @consumers: List of links to consumer devices. * @needs_suppliers: Hook to global list of devices waiting for suppliers. - * @defer_sync: Hook to global list of devices that have deferred sync_state. + * @defer_hook: Hook to global list of devices that have deferred sync_state. * @need_for_probe: If needs_suppliers is on a list, this indicates if the * suppliers are needed for probe or not. * @status: Driver status information. @@ -442,7 +442,7 @@ struct dev_links_info { struct list_head suppliers; struct list_head consumers; struct list_head needs_suppliers; - struct list_head defer_sync; + struct list_head defer_hook; bool need_for_probe; enum dl_dev_state status; }; -- cgit v1.2.3 From 2451e746478a6a6e981cfa66b62b791ca93b90c8 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 1 Jul 2020 12:42:59 -0700 Subject: driver core: Avoid deferred probe due to fw_devlink_pause/resume() With the earlier patch in this series, all devices that deferred probe due to fw_devlink_pause() will have their probes delayed till the deferred probe thread is kicked off during late_initcall. This will also affect all their consumers. This delayed probing in unnecessary. So this patch just keeps track of the devices that had their probe deferred due to fw_devlink_pause() and attempts to probe them once during fw_devlink_resume(). Fixes: 716a7a259690 ("driver core: fw_devlink: Add support for batching fwnode parsing") Signed-off-by: Saravana Kannan Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20200701194259.3337652-4-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 9bb2bc7bb8e3..5efed864b387 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -433,7 +433,8 @@ enum dl_dev_state { * @suppliers: List of links to supplier devices. * @consumers: List of links to consumer devices. * @needs_suppliers: Hook to global list of devices waiting for suppliers. - * @defer_hook: Hook to global list of devices that have deferred sync_state. + * @defer_hook: Hook to global list of devices that have deferred sync_state or + * deferred fw_devlink. * @need_for_probe: If needs_suppliers is on a list, this indicates if the * suppliers are needed for probe or not. * @status: Driver status information. -- cgit v1.2.3 From 287905e68dd29873bcb7986a8290cd1e4cfde600 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 21 May 2020 12:17:58 -0700 Subject: driver core: Expose device link details in sysfs It's helpful to be able to look at device link details from sysfs. So, expose it in sysfs. Say device-A is supplier of device-B. These are the additional files this patch would create: /sys/class/devlink/device-A:device-B/ auto_remove_on consumer/ -> .../device-B/ runtime_pm status supplier/ -> .../device-A/ sync_state_only /sys/devices/.../device-A/ consumer:device-B/ -> /sys/class/devlink/device-A:device-B/ /sys/devices/.../device-B/ supplier:device-A/ -> /sys/class/devlink/device-A:device-B/ That way: To get a list of all the device link in the system: ls /sys/class/devlink/ To get the consumer names and links of a device: ls -d /sys/devices/.../device-X/consumer:* To get the supplier names and links of a device: ls -d /sys/devices/.../device-X/supplier:* Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20200521191800.136035-2-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 58 ++++++++++++++++++++++++++------------------------ 1 file changed, 30 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 9a62f7f43d55..efad96ea17a0 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -386,34 +386,6 @@ enum device_link_state { #define DL_FLAG_MANAGED BIT(6) #define DL_FLAG_SYNC_STATE_ONLY BIT(7) -/** - * struct device_link - Device link representation. - * @supplier: The device on the supplier end of the link. - * @s_node: Hook to the supplier device's list of links to consumers. - * @consumer: The device on the consumer end of the link. - * @c_node: Hook to the consumer device's list of links to suppliers. - * @status: The state of the link (with respect to the presence of drivers). - * @flags: Link flags. - * @rpm_active: Whether or not the consumer device is runtime-PM-active. - * @kref: Count repeated addition of the same link. - * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks. - * @supplier_preactivated: Supplier has been made active before consumer probe. - */ -struct device_link { - struct device *supplier; - struct list_head s_node; - struct device *consumer; - struct list_head c_node; - enum device_link_state status; - u32 flags; - refcount_t rpm_active; - struct kref kref; -#ifdef CONFIG_SRCU - struct rcu_head rcu_head; -#endif - bool supplier_preactivated; /* Owned by consumer probe. */ -}; - /** * enum dl_dev_state - Device driver presence tracking information. * @DL_DEV_NO_DRIVER: There is no driver attached to the device. @@ -624,6 +596,36 @@ struct device { #endif }; +/** + * struct device_link - Device link representation. + * @supplier: The device on the supplier end of the link. + * @s_node: Hook to the supplier device's list of links to consumers. + * @consumer: The device on the consumer end of the link. + * @c_node: Hook to the consumer device's list of links to suppliers. + * @link_dev: device used to expose link details in sysfs + * @status: The state of the link (with respect to the presence of drivers). + * @flags: Link flags. + * @rpm_active: Whether or not the consumer device is runtime-PM-active. + * @kref: Count repeated addition of the same link. + * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks. + * @supplier_preactivated: Supplier has been made active before consumer probe. + */ +struct device_link { + struct device *supplier; + struct list_head s_node; + struct device *consumer; + struct list_head c_node; + struct device link_dev; + enum device_link_state status; + u32 flags; + refcount_t rpm_active; + struct kref kref; +#ifdef CONFIG_SRCU + struct rcu_head rcu_head; +#endif + bool supplier_preactivated; /* Owned by consumer probe. */ +}; + static inline struct device *kobj_to_dev(struct kobject *kobj) { return container_of(kobj, struct device, kobj); -- cgit v1.2.3 From 17d8dcf5330a97f6e5ae01d336eb1641782043f9 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 17 Jun 2020 12:56:47 -0500 Subject: fbdev/fb.h: Use struct_size() helper in kzalloc() Make use of the struct_size() helper instead of an open-coded version in order to avoid any potential type mistakes. This code was detected with the help of Coccinelle and, audited and fixed manually. Signed-off-by: Gustavo A. R. Silva Signed-off-by: Bartlomiej Zolnierkiewicz Link: https://patchwork.freedesktop.org/patch/msgid/20200617175647.GA26370@embeddedor --- include/linux/fb.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 3b4b2f0c6994..2b530e6d86e4 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -506,8 +506,9 @@ struct fb_info { }; static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { - struct apertures_struct *a = kzalloc(sizeof(struct apertures_struct) - + max_num * sizeof(struct aperture), GFP_KERNEL); + struct apertures_struct *a; + + a = kzalloc(struct_size(a, ranges, max_num), GFP_KERNEL); if (!a) return NULL; a->count = max_num; -- cgit v1.2.3 From 52fbf5bdeeef415b28b8e6cdade1e48927927f60 Mon Sep 17 00:00:00 2001 From: Rajat Jain Date: Tue, 7 Jul 2020 15:46:02 -0700 Subject: PCI: Cache ACS capability offset in device Currently the ACS capability is being looked up at a number of places. Read and store it once at enumeration so that it can be used by all later. No functional change intended. Link: https://lore.kernel.org/r/20200707224604.3737893-2-rajatja@google.com Signed-off-by: Rajat Jain Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c79d83304e52..a26be5332bba 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -486,6 +486,7 @@ struct pci_dev { #ifdef CONFIG_PCI_P2PDMA struct pci_p2pdma *p2pdma; #endif + u16 acs_cap; /* ACS Capability offset */ phys_addr_t rom; /* Physical address if not from BAR */ size_t romlen; /* Length if not from BAR */ char *driver_override; /* Driver name to force a match */ -- cgit v1.2.3 From 99b50be9d8ec9ef319cc7d5de07f4d405fac7764 Mon Sep 17 00:00:00 2001 From: Rajat Jain Date: Tue, 7 Jul 2020 15:46:03 -0700 Subject: PCI: Treat "external-facing" devices themselves as internal "External-facing" devices are internal devices that expose PCIe hierarchies such as Thunderbolt outside the platform [1]. Previously these internal devices were marked as "untrusted" the same as devices downstream from them. Use the ACPI or DT information to identify external-facing devices, but only mark the devices *downstream* from them as "untrusted" [2]. The external-facing device itself is no longer marked as untrusted. [1] https://docs.microsoft.com/en-us/windows-hardware/drivers/pci/dsd-for-pcie-root-ports#identifying-externally-exposed-pcie-root-ports [2] https://lore.kernel.org/linux-pci/20200610230906.GA1528594@bjorn-Precision-5520/ Link: https://lore.kernel.org/r/20200707224604.3737893-3-rajatja@google.com Signed-off-by: Rajat Jain Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index a26be5332bba..7a40cd5caed0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -432,6 +432,12 @@ struct pci_dev { * mappings to make sure they cannot access arbitrary memory. */ unsigned int untrusted:1; + /* + * Info from the platform, e.g., ACPI or device tree, may mark a + * device as "external-facing". An external-facing device is + * itself internal but devices downstream from it are external. + */ + unsigned int external_facing:1; unsigned int broken_intx_masking:1; /* INTx masking can't be used */ unsigned int io_window_1k:1; /* Intel bridge 1K I/O windows */ unsigned int irq_managed:1; -- cgit v1.2.3 From 3b50a6e536d2d843857ffe5f923eff7be4222afe Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Wed, 1 Jul 2020 15:53:49 -0700 Subject: mm/hmm: provide the page mapping order in hmm_range_fault() hmm_range_fault() returns an array of page frame numbers and flags for how the pages are mapped in the requested process' page tables. The PFN can be used to get the struct page with hmm_pfn_to_page() and the page size order can be determined with compound_order(page). However, if the page is larger than order 0 (PAGE_SIZE), there is no indication that a compound page is mapped by the CPU using a larger page size. Without this information, the caller can't safely use a large device PTE to map the compound page because the CPU might be using smaller PTEs with different read/write permissions. Add a new function hmm_pfn_to_map_order() to return the mapping size order so that callers know the pages are being mapped with consistent permissions and a large device page table mapping can be used if one is available. This will allow devices to optimize mapping the page into HW by avoiding or batching work for huge pages. For instance the dma_map can be done with a high order directly. Link: https://lore.kernel.org/r/20200701225352.9649-3-rcampbell@nvidia.com Signed-off-by: Ralph Campbell Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index f4a09ed223ac..866a0fa104c4 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -37,16 +37,17 @@ * will fail. Must be combined with HMM_PFN_REQ_FAULT. */ enum hmm_pfn_flags { - /* Output flags */ + /* Output fields and flags */ HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1), HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2), HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3), + HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 8), /* Input flags */ HMM_PFN_REQ_FAULT = HMM_PFN_VALID, HMM_PFN_REQ_WRITE = HMM_PFN_WRITE, - HMM_PFN_FLAGS = HMM_PFN_VALID | HMM_PFN_WRITE | HMM_PFN_ERROR, + HMM_PFN_FLAGS = 0xFFUL << HMM_PFN_ORDER_SHIFT, }; /* @@ -61,6 +62,25 @@ static inline struct page *hmm_pfn_to_page(unsigned long hmm_pfn) return pfn_to_page(hmm_pfn & ~HMM_PFN_FLAGS); } +/* + * hmm_pfn_to_map_order() - return the CPU mapping size order + * + * This is optionally useful to optimize processing of the pfn result + * array. It indicates that the page starts at the order aligned VA and is + * 1<> HMM_PFN_ORDER_SHIFT) & 0x1F; +} + /* * struct hmm_range - track invalidation lock on virtual address range * -- cgit v1.2.3 From a2b992c828f7651db369ba8f0eb0818d70232636 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 9 Jul 2020 17:42:44 -0700 Subject: debugfs: make sure we can remove u32_array files cleanly debugfs_create_u32_array() allocates a small structure to wrap the data and size information about the array. If users ever try to remove the file this leads to a leak since nothing ever frees this wrapper. That said there are no upstream users of debugfs_create_u32_array() that'd remove a u32 array file (we only have one u32 array user in CMA), so there is no real bug here. Make callers pass a wrapper they allocated. This way the lifetime management of the wrapper is on the caller, and we can avoid the potential leak in debugfs. CC: Chucheng Luo Signed-off-by: Jakub Kicinski Reviewed-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- include/linux/debugfs.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 63cb3606dea7..851dd1f9a8a5 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -38,6 +38,11 @@ struct debugfs_regset32 { struct device *dev; /* Optional device for Runtime PM */ }; +struct debugfs_u32_array { + u32 *array; + u32 n_elements; +}; + extern struct dentry *arch_debugfs_dir; #define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt) \ @@ -136,7 +141,8 @@ void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, int nregs, void __iomem *base, char *prefix); void debugfs_create_u32_array(const char *name, umode_t mode, - struct dentry *parent, u32 *array, u32 elements); + struct dentry *parent, + struct debugfs_u32_array *array); struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name, struct dentry *parent, @@ -316,8 +322,8 @@ static inline bool debugfs_initialized(void) } static inline void debugfs_create_u32_array(const char *name, umode_t mode, - struct dentry *parent, u32 *array, - u32 elements) + struct dentry *parent, + struct debugfs_u32_array *array) { } -- cgit v1.2.3 From cc4e3835eff474aa274d6e1d18f69d9d296d3b76 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 9 Jul 2020 17:42:46 -0700 Subject: udp_tunnel: add central NIC RX port offload infrastructure Cater to devices which: (a) may want to sleep in the callbacks; (b) only have IPv4 support; (c) need all the programming to happen while the netdev is up. Drivers attach UDP tunnel offload info struct to their netdevs, where they declare how many UDP ports of various tunnel types they support. Core takes care of tracking which ports to offload. Use a fixed-size array since this matches what almost all drivers do, and avoids a complexity and uncertainty around memory allocations in an atomic context. Make sure that tunnel drivers don't try to replay the ports when new NIC netdev is registered. Automatic replays would mess up reference counting, and will be removed completely once all drivers are converted. v4: - use a #define NULL to avoid build issues with CONFIG_INET=n. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 39e28e11863c..ac2cd3f49aba 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -65,6 +65,8 @@ struct wpan_dev; struct mpls_dev; /* UDP Tunnel offloads */ struct udp_tunnel_info; +struct udp_tunnel_nic_info; +struct udp_tunnel_nic; struct bpf_prog; struct xdp_buff; @@ -1836,6 +1838,10 @@ enum netdev_priv_flags { * * @macsec_ops: MACsec offloading ops * + * @udp_tunnel_nic_info: static structure describing the UDP tunnel + * offload capabilities of the device + * @udp_tunnel_nic: UDP tunnel offload state + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2134,6 +2140,8 @@ struct net_device { /* MACsec management functions */ const struct macsec_ops *macsec_ops; #endif + const struct udp_tunnel_nic_info *udp_tunnel_nic_info; + struct udp_tunnel_nic *udp_tunnel_nic; }; #define to_net_dev(d) container_of(d, struct net_device, dev) -- cgit v1.2.3 From c818c03b661cd769e035e41673d5543ba2ebda64 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 13 May 2020 14:11:26 -0700 Subject: seccomp: Report number of loaded filters in /proc/$pid/status A common question asked when debugging seccomp filters is "how many filters are attached to your process?" Provide a way to easily answer this question through /proc/$pid/status with a "Seccomp_filters" line. Signed-off-by: Kees Cook --- include/linux/seccomp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 4192369b8418..2ec2720f83cc 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -13,6 +13,7 @@ #ifdef CONFIG_SECCOMP #include +#include #include struct seccomp_filter; @@ -29,6 +30,7 @@ struct seccomp_filter; */ struct seccomp { int mode; + atomic_t filter_count; struct seccomp_filter *filter; }; -- cgit v1.2.3 From 3a15fb6ed92cb32b0a83f406aa4a96f28c9adbc3 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sun, 31 May 2020 13:50:29 +0200 Subject: seccomp: release filter after task is fully dead The seccomp filter used to be released in free_task() which is called asynchronously via call_rcu() and assorted mechanisms. Since we need to inform tasks waiting on the seccomp notifier when a filter goes empty we will notify them as soon as a task has been marked fully dead in release_task(). To not split seccomp cleanup into two parts, move filter release out of free_task() and into release_task() after we've unhashed struct task from struct pid, exited signals, and unlinked it from the threadgroups' thread list. We'll put the empty filter notification infrastructure into it in a follow up patch. This also renames put_seccomp_filter() to seccomp_filter_release() which is a more descriptive name of what we're doing here especially once we've added the empty filter notification mechanism in there. We're also NULL-ing the task's filter tree entrypoint which seems cleaner than leaving a dangling pointer in there. Note that this shouldn't need any memory barriers since we're calling this when the task is in release_task() which means it's EXIT_DEAD. So it can't modify its seccomp filters anymore. You can also see this from the point where we're calling seccomp_filter_release(). It's after __exit_signal() and at this point, tsk->sighand will already have been NULLed which is required for thread-sync and filter installation alike. Cc: Tycho Andersen Cc: Kees Cook Cc: Matt Denton Cc: Sargun Dhillon Cc: Jann Horn Cc: Chris Palmer Cc: Aleksa Sarai Cc: Robert Sesek Cc: Jeffrey Vander Stoep Cc: Linux Containers Signed-off-by: Christian Brauner Link: https://lore.kernel.org/r/20200531115031.391515-2-christian.brauner@ubuntu.com Signed-off-by: Kees Cook --- include/linux/seccomp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 2ec2720f83cc..babcd6c02d09 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -84,10 +84,10 @@ static inline int seccomp_mode(struct seccomp *s) #endif /* CONFIG_SECCOMP */ #ifdef CONFIG_SECCOMP_FILTER -extern void put_seccomp_filter(struct task_struct *tsk); +extern void seccomp_filter_release(struct task_struct *tsk); extern void get_seccomp_filter(struct task_struct *tsk); #else /* CONFIG_SECCOMP_FILTER */ -static inline void put_seccomp_filter(struct task_struct *tsk) +static inline void seccomp_filter_release(struct task_struct *tsk) { return; } -- cgit v1.2.3 From 943c8a80830b88b7b203fa3e2d755620d85129d1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 29 Jun 2020 09:43:52 -0700 Subject: : add stub for of_get_next_parent() to fix qcom build error Fix a (COMPILE_TEST) build error when CONFIG_OF is not set/enabled by adding a stub for of_get_next_parent(). ../drivers/soc/qcom/qcom-geni-se.c:819:11: error: implicit declaration of function 'of_get_next_parent'; did you mean 'of_get_parent'? [-Werror=implicit-function-declaration] ../drivers/soc/qcom/qcom-geni-se.c:819:9: warning: assignment makes pointer from integer without a cast [-Wint-conversion] Fixes: 048eb908a1f2 ("soc: qcom-geni-se: Add interconnect support to fix earlycon crash") Acked-by: Rob Herring Reviewed-by: Bjorn Andersson Signed-off-by: Randy Dunlap Cc: Rob Herring Cc: Frank Rowand Cc: devicetree@vger.kernel.org Cc: Andy Gross Cc: Bjorn Andersson Cc: linux-arm-msm@vger.kernel.org Link: https://lore.kernel.org/r/ce0d7561-ff93-d267-b57a-6505014c728c@infradead.org Signed-off-by: Bjorn Andersson --- include/linux/of.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index c669c0a4732f..c98ed245b815 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -630,6 +630,11 @@ static inline struct device_node *of_get_parent(const struct device_node *node) return NULL; } +static inline struct device_node *of_get_next_parent(struct device_node *node) +{ + return NULL; +} + static inline struct device_node *of_get_next_child( const struct device_node *node, struct device_node *prev) { -- cgit v1.2.3 From ac219bf3c9bdf9200767e8c98a56ad42c75e5cd5 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 27 Jun 2020 00:40:11 +0200 Subject: leds: lp55xx: Convert to use GPIO descriptors The LP55xx driver is already using the of_gpio() functions to pick a global GPIO number for "enable" from the device tree and request the line. Simplify it by just using a GPIO descriptor. Make sure to keep the enable GPIO line optional, change the naming from "lp5523_enable" to "LP55xx enable" to reflect that this is used on all LP55xx LED drivers. Cc: Milo Kim Signed-off-by: Linus Walleij Signed-off-by: Pavel Machek --- include/linux/platform_data/leds-lp55xx.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h index 96a787100fda..00492d6ff018 100644 --- a/include/linux/platform_data/leds-lp55xx.h +++ b/include/linux/platform_data/leds-lp55xx.h @@ -12,6 +12,8 @@ #ifndef _LEDS_LP55XX_H #define _LEDS_LP55XX_H +#include + /* Clock configuration */ #define LP55XX_CLOCK_AUTO 0 #define LP55XX_CLOCK_INT 1 @@ -49,7 +51,7 @@ enum lp8501_pwr_sel { * @clock_mode : Input clock mode. LP55XX_CLOCK_AUTO or _INT or _EXT * @setup_resources : Platform specific function before enabling the chip * @release_resources : Platform specific function after disabling the chip - * @enable : EN pin control by platform side + * @enable_gpiod : enable GPIO descriptor * @patterns : Predefined pattern data for RGB channels * @num_patterns : Number of patterns * @update_config : Value of CONFIG register @@ -65,7 +67,7 @@ struct lp55xx_platform_data { u8 clock_mode; /* optional enable GPIO */ - int enable_gpio; + struct gpio_desc *enable_gpiod; /* Predefined pattern data */ struct lp55xx_predef_pattern *patterns; -- cgit v1.2.3 From a24015fa8b89e4605a9c6581d56b48d991e2b66b Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Fri, 26 Jun 2020 05:14:07 +0800 Subject: firmware: imx: Move i.MX SCU soc driver into imx firmware folder The i.MX SCU soc driver depends on SCU firmware driver, so it has to use platform driver model for proper defer probe operation, since it has no device binding in DT file, a simple platform device is created together inside the platform driver. To make it more clean, we can just move the entire SCU soc driver into imx firmware folder and initialized by i.MX SCU firmware driver. Signed-off-by: Anson Huang Signed-off-by: Shawn Guo --- include/linux/firmware/imx/sci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h index 3c459f54a88f..22c76571a294 100644 --- a/include/linux/firmware/imx/sci.h +++ b/include/linux/firmware/imx/sci.h @@ -20,4 +20,5 @@ int imx_scu_enable_general_irq_channel(struct device *dev); int imx_scu_irq_register_notifier(struct notifier_block *nb); int imx_scu_irq_unregister_notifier(struct notifier_block *nb); int imx_scu_irq_group_enable(u8 group, u32 mask, u8 enable); +int imx_scu_soc_init(struct device *dev); #endif /* _SC_SCI_H */ -- cgit v1.2.3 From 02c003cc18dfb6db1001856fccb978a1179fe89a Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Fri, 10 Jul 2020 14:39:17 +0100 Subject: firmware: arm_scmi: Remove zero-length array in SCMI notifications Substitute zero-length array defined in scmi_base_error_report with a flexible length array definition. Link: https://lore.kernel.org/r/20200710133919.39792-1-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 46d98be92466..7d4348fb7330 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -421,7 +421,7 @@ struct scmi_base_error_report { u32 agent_id; bool fatal; u16 cmd_count; - u64 reports[0]; + u64 reports[]; }; #endif /* _LINUX_SCMI_PROTOCOL_H */ -- cgit v1.2.3 From 72a5eb9d9c319c99c11cfd9cfb486380dd136840 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Fri, 10 Jul 2020 14:39:19 +0100 Subject: firmware: arm_scmi: Remove fixed size fields from reports/scmi_event_header Event reports are used to convey information describing events to the registered user-callbacks: they are necessarily derived from the underlying raw SCMI events' messages but they are not meant to expose or directly mirror any of those messages data layout, which belong to the protocol layer. Using fixed size types for report fields, mirroring messages structure, is at odd with this: get rid of them using more generic, equivalent, typing. Substitute scmi_event_header fixed size fields with generic types too and shuffle around fields definitions to minimize implicit padding while adapting involved functions. Link: https://lore.kernel.org/r/20200710133919.39792-3-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 52 +++++++++++++++++++++---------------------- 1 file changed, 26 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 7d4348fb7330..7e5dd7d1e221 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -381,47 +381,47 @@ enum scmi_notification_events { }; struct scmi_power_state_changed_report { - u64 timestamp; - u32 agent_id; - u32 domain_id; - u32 power_state; + ktime_t timestamp; + unsigned int agent_id; + unsigned int domain_id; + unsigned int power_state; }; struct scmi_perf_limits_report { - u64 timestamp; - u32 agent_id; - u32 domain_id; - u32 range_max; - u32 range_min; + ktime_t timestamp; + unsigned int agent_id; + unsigned int domain_id; + unsigned int range_max; + unsigned int range_min; }; struct scmi_perf_level_report { - u64 timestamp; - u32 agent_id; - u32 domain_id; - u32 performance_level; + ktime_t timestamp; + unsigned int agent_id; + unsigned int domain_id; + unsigned int performance_level; }; struct scmi_sensor_trip_point_report { - u64 timestamp; - u32 agent_id; - u32 sensor_id; - u32 trip_point_desc; + ktime_t timestamp; + unsigned int agent_id; + unsigned int sensor_id; + unsigned int trip_point_desc; }; struct scmi_reset_issued_report { - u64 timestamp; - u32 agent_id; - u32 domain_id; - u32 reset_state; + ktime_t timestamp; + unsigned int agent_id; + unsigned int domain_id; + unsigned int reset_state; }; struct scmi_base_error_report { - u64 timestamp; - u32 agent_id; - bool fatal; - u16 cmd_count; - u64 reports[]; + ktime_t timestamp; + unsigned int agent_id; + bool fatal; + unsigned int cmd_count; + unsigned long long reports[]; }; #endif /* _LINUX_SCMI_PROTOCOL_H */ -- cgit v1.2.3 From b52fb259dff8d0da76d38005464edf4201b01d76 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 29 May 2020 12:23:41 +0200 Subject: mmc: core: Always allow the card detect uevent to be consumed The approach to allow userspace ~5s to consume the uevent, which is triggered when a new card is inserted/initialized, currently requires the mmc host to support system wakeup. This is unnecessary limiting, especially for an mmc host that relies on a GPIO IRQ for card detect. More precisely, the mmc host may not support system wakeup for its corresponding struct device, while the GPIO IRQ still could be configured as a wakeup IRQ via enable_irq_wake(). To support all various cases, let's simply drop the need for the wakeup support. Instead let's always register a wakeup source and activate it for all card detect IRQs by calling __pm_wakeup_event(). Signed-off-by: Ulf Hansson Link: https://lore.kernel.org/r/20200529102341.12529-1-ulf.hansson@linaro.org --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 7149bab555d7..1fa4fa1caef5 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -287,6 +287,7 @@ struct mmc_host { #ifdef CONFIG_PM_SLEEP struct notifier_block pm_notify; #endif + struct wakeup_source *ws; /* Enable consume of uevents */ u32 max_current_330; u32 max_current_300; u32 max_current_180; -- cgit v1.2.3 From 4f7872ae920fccf6a07ca64cc40792bd6be0d0d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Mon, 29 Jun 2020 09:21:44 +0200 Subject: mmc: sdio: Move SDIO IDs from rsi_sdio driver to common include file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define appropriate macro names for consistency with other macros. Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20200629072144.24351-1-pali@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 15ed8ce9d394..ab41801c5f51 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -118,6 +118,10 @@ #define SDIO_DEVICE_ID_SIANO_NOVA_A0 0x1100 #define SDIO_DEVICE_ID_SIANO_STELLAR 0x5347 +#define SDIO_VENDOR_ID_RSI 0x041b +#define SDIO_DEVICE_ID_RSI_9113 0x9330 +#define SDIO_DEVICE_ID_RSI_9116 0x9116 + #define SDIO_VENDOR_ID_TI_WL1251 0x104c #define SDIO_DEVICE_ID_TI_WL1251 0x9066 -- cgit v1.2.3 From 2f96126500991f356b9eacdc6611bec78e6253ed Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 1 Jul 2020 11:23:17 +0100 Subject: arch: arm: mach-omap2: mmc: Move omap_mmc_notify_cover_event() prototype MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When building the kernel with W=1 the build system complains of: drivers/mmc/host/omap.c:854:6: warning: no previous prototype for ‘omap_mmc_notify_cover_event’ [-Wmissing-prototypes] 854 | void omap_mmc_notify_cover_event(struct device *dev, int num, int is_closed) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~ If we move the prototype into a shared headerfile the build system will be satisfied. Rather than create a whole new headerfile just for this purpose, it makes sense to use the already existing mmc-omap.h. Cc: Ulf Hansson Cc: linux-mmc@vger.kernel.org Cc: Tony Lindgren Cc: linux-omap@vger.kernel.org Signed-off-by: Lee Jones Acked-by: Tony Lindgren Link: https://lore.kernel.org/r/20200701102317.235032-1-lee.jones@linaro.org Signed-off-by: Ulf Hansson --- include/linux/platform_data/mmc-omap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-omap.h b/include/linux/platform_data/mmc-omap.h index 9acf0e87aa9b..f0b8947e6b07 100644 --- a/include/linux/platform_data/mmc-omap.h +++ b/include/linux/platform_data/mmc-omap.h @@ -116,3 +116,6 @@ struct omap_mmc_platform_data { } slots[OMAP_MMC_MAX_SLOTS]; }; + +extern void omap_mmc_notify_cover_event(struct device *dev, int slot, + int is_closed); -- cgit v1.2.3 From ec02760b63c21c439d44956e9c66d0af24011f03 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Tue, 7 Jul 2020 20:58:42 +0900 Subject: mmc: core: Add MMC_CAP2_FULL_PWR_CYCLE_IN_SUSPEND The commit 5a36d6bcdf23 ("mmc: core: Add DT-bindings for MMC_CAP2_FULL_PWR_CYCLE") added the "full-pwr-cycle" property which is possible to perform a full power cycle of the card at any time. However, some environment (like r8a77951-salvator-xs) is possible to perform a full power cycle of the card in suspend via firmware (PSCI on arm-trusted-firmware). So, in worst case, since we are not doing a graceful shutdown of the eMMC device (just cut VCCQ while the eMMC is "sleeping") in suspend, it could lead to internal data corruptions. So, add MMC_CAP2_FULL_PWR_CYCLE_IN_SUSPEND to do a graceful shutdown which issues Power Off notification before entering system suspend. Signed-off-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/1594123122-13156-3-git-send-email-yoshihiro.shimoda.uh@renesas.com Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 1fa4fa1caef5..c5b6e97cb21a 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -352,6 +352,7 @@ struct mmc_host { #define MMC_CAP2_BOOTPART_NOACC (1 << 0) /* Boot partition no access */ #define MMC_CAP2_FULL_PWR_CYCLE (1 << 2) /* Can do full power cycle */ +#define MMC_CAP2_FULL_PWR_CYCLE_IN_SUSPEND (1 << 3) /* Can do full power cycle in suspend */ #define MMC_CAP2_HS200_1_8V_SDR (1 << 5) /* can support */ #define MMC_CAP2_HS200_1_2V_SDR (1 << 6) /* can support */ #define MMC_CAP2_HS200 (MMC_CAP2_HS200_1_8V_SDR | \ -- cgit v1.2.3 From f4bf09d5303ab3896604c58363fc705ba649ccb8 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Sun, 21 Jun 2020 15:33:39 +0300 Subject: iio: core: remove iio_priv_to_dev() helper All users of this helper have been updated to not use it. Remove it now, so that we don't need to move it when creating the iio_dev_opaque structure. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 30c9c9502478..e2df67a3b9ab 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -689,12 +689,6 @@ static inline void *iio_priv(const struct iio_dev *indio_dev) return indio_dev->priv; } -static inline struct iio_dev *iio_priv_to_dev(void *priv) -{ - return (struct iio_dev *)((char *)priv - - ALIGN(sizeof(struct iio_dev), IIO_ALIGN)); -} - void iio_device_free(struct iio_dev *indio_dev); struct iio_dev *devm_iio_device_alloc(struct device *parent, int sizeof_priv); struct iio_trigger *devm_iio_trigger_alloc(struct device *dev, -- cgit v1.2.3 From 8cdcd8aeee2819199ec7f68114b77b04c10611d3 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 25 Jun 2020 22:02:52 +0200 Subject: spi: imx/fsl-lpspi: Convert to GPIO descriptors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This converts the two Freescale i.MX SPI drivers Freescale i.MX (CONFIG_SPI_IMX) and Freescale i.MX LPSPI (CONFIG_SPI_FSL_LPSPI) to use GPIO descriptors handled in the SPI core for GPIO chip selects whether defined in the device tree or a board file. The reason why both are converted at the same time is that they were both using the same platform data and platform device population helpers when using board files intertwining the code so this gives a cleaner cut. The platform device creation was passing a platform data container from each boardfile down to the driver using struct spi_imx_master from , but this was only conveying the number of chipselects and an int * array of the chipselect GPIO numbers. The imx27 and imx31 platforms had code passing the now-unused platform data when creating the platform devices, this has been repurposed to pass around GPIO descriptor tables. The platform data struct that was just passing an array of integers and number of chip selects for the GPIO lines has been removed. The number of chipselects used to be passed from the board file, because this number also limits the number of native chipselects that the platform can use. To deal with this we just augment the i.MX (CONFIG_SPI_IMX) driver to support 3 chipselects if the platform does not define "num-cs" as a device property (such as from the device tree). This covers all the legacy boards as these use <= 3 native chip selects (or GPIO lines, and in that case the number of chip selects is determined by the core from the number of available GPIO lines). Any new boards should use device tree, so this is a reasonable simplification to cover all old boards. The LPSPI driver never assigned the number of chipselects and thus always fall back to the core default of 1 chip select if no GPIOs are defined in the device tree. The Freescale i.MX driver was already partly utilizing the SPI core to obtain the GPIO numbers from the device tree, so this completes the transtion to let the core handle all of it. All board files and the core i.MX boardfile registration code is augmented to account for these changes. This has been compile-tested with the imx_v4_v5_defconfig and the imx_v6_v7_defconfig. Signed-off-by: Linus Walleij Acked-by: Shawn Guo Cc: Uwe Kleine-König Cc: Robin Gong Cc: Trent Piepho Cc: Clark Wang Cc: Shawn Guo Cc: Sascha Hauer Cc: Pengutronix Kernel Team Cc: Fabio Estevam Cc: NXP Linux Team Link: https://lore.kernel.org/r/20200625200252.207614-1-linus.walleij@linaro.org Signed-off-by: Mark Brown --- include/linux/platform_data/spi-imx.h | 33 --------------------------------- 1 file changed, 33 deletions(-) delete mode 100644 include/linux/platform_data/spi-imx.h (limited to 'include/linux') diff --git a/include/linux/platform_data/spi-imx.h b/include/linux/platform_data/spi-imx.h deleted file mode 100644 index 328f670d10bd..000000000000 --- a/include/linux/platform_data/spi-imx.h +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#ifndef __MACH_SPI_H_ -#define __MACH_SPI_H_ - -/* - * struct spi_imx_master - device.platform_data for SPI controller devices. - * @chipselect: Array of chipselects for this master or NULL. Numbers >= 0 - * mean GPIO pins, -ENOENT means internal CSPI chipselect - * matching the position in the array. E.g., if chipselect[1] = - * -ENOENT then a SPI slave using chip select 1 will use the - * native SS1 line of the CSPI. Omitting the array will use - * all native chip selects. - - * Normally you want to use gpio based chip selects as the CSPI - * module tries to be intelligent about when to assert the - * chipselect: The CSPI module deasserts the chipselect once it - * runs out of input data. The other problem is that it is not - * possible to mix between high active and low active chipselects - * on one single bus using the internal chipselects. - * Unfortunately, on some SoCs, Freescale decided to put some - * chipselects on dedicated pins which are not usable as gpios, - * so we have to support the internal chipselects. - * - * @num_chipselect: If @chipselect is specified, ARRAY_SIZE(chipselect), - * otherwise the number of native chip selects. - */ -struct spi_imx_master { - int *chipselect; - int num_chipselect; -}; - -#endif /* __MACH_SPI_H_*/ -- cgit v1.2.3 From 5a2798ab32ba2952cfe25701ee460bccbd434c75 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sat, 11 Jul 2020 23:53:23 +0200 Subject: bpf: Add BTF_ID_LIST/BTF_ID/BTF_ID_UNUSED macros Adding support to generate .BTF_ids section that will hold BTF ID lists for verifier. Adding macros that will help to define lists of BTF ID values placed in .BTF_ids section. They are initially filled with zeros (during compilation) and resolved later during the linking phase by resolve_btfids tool. Following defines list of one BTF ID value: BTF_ID_LIST(bpf_skb_output_btf_ids) BTF_ID(struct, sk_buff) It also defines following variable to access the list: extern u32 bpf_skb_output_btf_ids[]; The BTF_ID_UNUSED macro defines 4 zero bytes. It's used when we want to define 'unused' entry in BTF_ID_LIST, like: BTF_ID_LIST(bpf_skb_output_btf_ids) BTF_ID(struct, sk_buff) BTF_ID_UNUSED BTF_ID(struct, task_struct) Suggested-by: Andrii Nakryiko Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Tested-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200711215329.41165-4-jolsa@kernel.org --- include/linux/btf_ids.h | 87 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 87 insertions(+) create mode 100644 include/linux/btf_ids.h (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h new file mode 100644 index 000000000000..fe019774f8a7 --- /dev/null +++ b/include/linux/btf_ids.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_BTF_IDS_H +#define _LINUX_BTF_IDS_H + +#include /* for __PASTE */ + +/* + * Following macros help to define lists of BTF IDs placed + * in .BTF_ids section. They are initially filled with zeros + * (during compilation) and resolved later during the + * linking phase by resolve_btfids tool. + * + * Any change in list layout must be reflected in resolve_btfids + * tool logic. + */ + +#define BTF_IDS_SECTION ".BTF_ids" + +#define ____BTF_ID(symbol) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".local " #symbol " ; \n" \ +".type " #symbol ", @object; \n" \ +".size " #symbol ", 4; \n" \ +#symbol ": \n" \ +".zero 4 \n" \ +".popsection; \n"); + +#define __BTF_ID(symbol) \ + ____BTF_ID(symbol) + +#define __ID(prefix) \ + __PASTE(prefix, __COUNTER__) + +/* + * The BTF_ID defines unique symbol for each ID pointing + * to 4 zero bytes. + */ +#define BTF_ID(prefix, name) \ + __BTF_ID(__ID(__BTF_ID__##prefix##__##name##__)) + +/* + * The BTF_ID_LIST macro defines pure (unsorted) list + * of BTF IDs, with following layout: + * + * BTF_ID_LIST(list1) + * BTF_ID(type1, name1) + * BTF_ID(type2, name2) + * + * list1: + * __BTF_ID__type1__name1__1: + * .zero 4 + * __BTF_ID__type2__name2__2: + * .zero 4 + * + */ +#define __BTF_ID_LIST(name) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".local " #name "; \n" \ +#name ":; \n" \ +".popsection; \n"); \ + +#define BTF_ID_LIST(name) \ +__BTF_ID_LIST(name) \ +extern u32 name[]; + +/* + * The BTF_ID_UNUSED macro defines 4 zero bytes. + * It's used when we want to define 'unused' entry + * in BTF_ID_LIST, like: + * + * BTF_ID_LIST(bpf_skb_output_btf_ids) + * BTF_ID(struct, sk_buff) + * BTF_ID_UNUSED + * BTF_ID(struct, task_struct) + */ + +#define BTF_ID_UNUSED \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".zero 4 \n" \ +".popsection; \n"); + + +#endif -- cgit v1.2.3 From 6659061045cc93f609e100b128f30581e5f012e9 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 10 Jun 2020 08:20:05 -0700 Subject: fs: Move __scm_install_fd() to __receive_fd() In preparation for users of the "install a received file" logic outside of net/ (pidfd and seccomp), relocate and rename __scm_install_fd() from net/core/scm.c to __receive_fd() in fs/file.c, and provide a wrapper named receive_fd_user(), as future patches will change the interface to __receive_fd(). Additionally add a comment to fd_install() as a counterpoint to how __receive_fd() interacts with fput(). Cc: Alexander Viro Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Dmitry Kadashev Cc: Jens Axboe Cc: Arnd Bergmann Cc: Sargun Dhillon Cc: Ido Schimmel Cc: Ioana Ciornei Cc: linux-fsdevel@vger.kernel.org Cc: netdev@vger.kernel.org Reviewed-by: Sargun Dhillon Acked-by: Christian Brauner Signed-off-by: Kees Cook --- include/linux/file.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 122f80084a3e..b14ff2ffd0bd 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -91,6 +91,14 @@ extern void put_unused_fd(unsigned int fd); extern void fd_install(unsigned int fd, struct file *file); +extern int __receive_fd(struct file *file, int __user *ufd, + unsigned int o_flags); +static inline int receive_fd_user(struct file *file, int __user *ufd, + unsigned int o_flags) +{ + return __receive_fd(file, ufd, o_flags); +} + extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); -- cgit v1.2.3 From deefa7f3505ae2fb6a7cb75f50134b65a1dd1494 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 10 Jun 2020 20:47:45 -0700 Subject: fs: Add receive_fd() wrapper for __receive_fd() For both pidfd and seccomp, the __user pointer is not used. Update __receive_fd() to make writing to ufd optional via a NULL check. However, for the receive_fd_user() wrapper, ufd is NULL checked so an -EFAULT can be returned to avoid changing the SCM_RIGHTS interface behavior. Add new wrapper receive_fd() for pidfd and seccomp that does not use the ufd argument. For the new helper, the allocated fd needs to be returned on success. Update the existing callers to handle it. Cc: Alexander Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Sargun Dhillon Acked-by: Christian Brauner Signed-off-by: Kees Cook --- include/linux/file.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index b14ff2ffd0bd..d9fee9f5c8da 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -9,6 +9,7 @@ #include #include #include +#include struct file; @@ -96,8 +97,14 @@ extern int __receive_fd(struct file *file, int __user *ufd, static inline int receive_fd_user(struct file *file, int __user *ufd, unsigned int o_flags) { + if (ufd == NULL) + return -EFAULT; return __receive_fd(file, ufd, o_flags); } +static inline int receive_fd(struct file *file, unsigned int o_flags) +{ + return __receive_fd(file, NULL, o_flags); +} extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); -- cgit v1.2.3 From 173817151b15d5a72a9bef1d2df7e6e7f6750f2e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 10 Jun 2020 08:46:58 -0700 Subject: fs: Expand __receive_fd() to accept existing fd Expand __receive_fd() with support for replace_fd() for the coming seccomp "addfd" ioctl(). Add new wrapper receive_fd_replace() for the new behavior and update existing wrappers to retain old behavior. Thanks to Colin Ian King for pointing out an uninitialized variable exposure in an earlier version of this patch. Cc: Alexander Viro Cc: Dmitry Kadashev Cc: Jens Axboe Cc: Arnd Bergmann Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Sargun Dhillon Acked-by: Christian Brauner Signed-off-by: Kees Cook --- include/linux/file.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index d9fee9f5c8da..225982792fa2 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -92,18 +92,22 @@ extern void put_unused_fd(unsigned int fd); extern void fd_install(unsigned int fd, struct file *file); -extern int __receive_fd(struct file *file, int __user *ufd, +extern int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags); static inline int receive_fd_user(struct file *file, int __user *ufd, unsigned int o_flags) { if (ufd == NULL) return -EFAULT; - return __receive_fd(file, ufd, o_flags); + return __receive_fd(-1, file, ufd, o_flags); } static inline int receive_fd(struct file *file, unsigned int o_flags) { - return __receive_fd(file, NULL, o_flags); + return __receive_fd(-1, file, NULL, o_flags); +} +static inline int receive_fd_replace(int fd, struct file *file, unsigned int o_flags) +{ + return __receive_fd(fd, file, NULL, o_flags); } extern void flush_delayed_fput(void); -- cgit v1.2.3 From c1326210477ecc06c53221f0005c64419aba30d6 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:39:20 +0000 Subject: nfs,nfsd: NFSv4.2 extended attribute protocol definitions Add definitions for the new operations, errors and flags as defined in RFC 8276 (File System Extended Attributes in NFSv4). Signed-off-by: Frank van der Linden Signed-off-by: Chuck Lever --- include/linux/nfs4.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 4dba3c948932..e6ca9d1d2e76 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -150,6 +150,12 @@ enum nfs_opnum4 { OP_WRITE_SAME = 70, OP_CLONE = 71, + /* xattr support (RFC8726) */ + OP_GETXATTR = 72, + OP_SETXATTR = 73, + OP_LISTXATTRS = 74, + OP_REMOVEXATTR = 75, + OP_ILLEGAL = 10044, }; @@ -280,6 +286,10 @@ enum nfsstat4 { NFS4ERR_WRONG_LFS = 10092, NFS4ERR_BADLABEL = 10093, NFS4ERR_OFFLOAD_NO_REQS = 10094, + + /* xattr (RFC8276) */ + NFS4ERR_NOXATTR = 10095, + NFS4ERR_XATTR2BIG = 10096, }; static inline bool seqid_mutating_err(u32 err) @@ -452,6 +462,7 @@ enum change_attr_type4 { #define FATTR4_WORD2_CHANGE_ATTR_TYPE (1UL << 15) #define FATTR4_WORD2_SECURITY_LABEL (1UL << 16) #define FATTR4_WORD2_MODE_UMASK (1UL << 17) +#define FATTR4_WORD2_XATTR_SUPPORT (1UL << 18) /* MDS threshold bitmap bits */ #define THRESHOLD_RD (1UL << 0) @@ -700,4 +711,13 @@ struct nl4_server { struct nfs42_netaddr nl4_addr; /* NL4_NETADDR */ } u; }; + +/* + * Options for setxattr. These match the flags for setxattr(2). + */ +enum nfs4_setxattr_options { + SETXATTR4_EITHER = 0, + SETXATTR4_CREATE = 1, + SETXATTR4_REPLACE = 2, +}; #endif -- cgit v1.2.3 From 08b5d5014a27e717826999ad20e394a8811aae92 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:39:18 +0000 Subject: xattr: break delegations in {set,remove}xattr set/removexattr on an exported filesystem should break NFS delegations. This is true in general, but also for the upcoming support for RFC 8726 (NFSv4 extended attribute support). Make sure that they do. Additionally, they need to grow a _locked variant, since callers might call this with i_rwsem held (like the NFS server code). Cc: stable@vger.kernel.org # v4.9+ Cc: linux-fsdevel@vger.kernel.org Cc: Al Viro Signed-off-by: Frank van der Linden Signed-off-by: Chuck Lever --- include/linux/xattr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 47eaa34f8761..a2f3cd02653c 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -51,8 +51,10 @@ ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int); int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int); +int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **); int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int); int __vfs_removexattr(struct dentry *, const char *); +int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **); int vfs_removexattr(struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); -- cgit v1.2.3 From cab8d289c5ad541a5351a651d95c4086b7f84d7c Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:39:19 +0000 Subject: xattr: add a function to check if a namespace is supported Add a function that checks is an extended attribute namespace is supported for an inode, meaning that a handler must be present for either the whole namespace, or at least one synthetic xattr in the namespace. To be used by the nfs server code when being queried for extended attributes support. Cc: linux-fsdevel@vger.kernel.org Cc: Al Viro Signed-off-by: Frank van der Linden Signed-off-by: Chuck Lever --- include/linux/xattr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index a2f3cd02653c..fac75810d9d3 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -61,6 +61,8 @@ ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_siz ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); +int xattr_supported_namespace(struct inode *inode, const char *prefix); + static inline const char *xattr_prefix(const struct xattr_handler *handler) { return handler->prefix ?: handler->name; -- cgit v1.2.3 From 23e50fe3a5e6045a573c69d4b0e3d78aa6183323 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:39:26 +0000 Subject: nfsd: implement the xattr functions and en/decode logic Implement the main entry points for the *XATTR operations. Add functions to calculate the reply size for the user extended attribute operations, and implement the XDR encode / decode logic for these operations. Add the user extended attributes operations to nfsd4_ops. Signed-off-by: Frank van der Linden Signed-off-by: Chuck Lever --- include/linux/nfs4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index e6ca9d1d2e76..33ebe476428e 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -165,7 +165,7 @@ Needs to be updated if more operations are defined in future.*/ #define FIRST_NFS4_OP OP_ACCESS #define LAST_NFS40_OP OP_RELEASE_LOCKOWNER #define LAST_NFS41_OP OP_RECLAIM_COMPLETE -#define LAST_NFS42_OP OP_CLONE +#define LAST_NFS42_OP OP_REMOVEXATTR #define LAST_NFS4_OP LAST_NFS42_OP enum nfsstat4 { -- cgit v1.2.3 From c65b326b1eb983bca35ed43d0e453d1b15705f10 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 25 Mar 2020 14:41:46 -0400 Subject: svcrdma: Make svc_rdma_send_error_msg() a global function Prepare for svc_rdma_send_error_msg() to be invoked from another source file. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 7ed82625dc0b..1579f7a14ab4 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -195,6 +195,10 @@ extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *sctxt, const struct svc_rdma_recv_ctxt *rctxt, struct xdr_buf *xdr); +extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma, + struct svc_rdma_send_ctxt *sctxt, + struct svc_rdma_recv_ctxt *rctxt, + int status); extern int svc_rdma_sendto(struct svc_rqst *); extern int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset, unsigned int length); -- cgit v1.2.3 From 0b8dc1b69995cbd81c2c9a2f1730c46cce085f62 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 18 May 2020 11:34:47 -0400 Subject: svcrdma: Remove declarations for functions long removed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Pavane pour une infante défunte. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 1579f7a14ab4..d28ca1b6f2eb 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -204,10 +204,6 @@ extern int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset, unsigned int length); /* svc_rdma_transport.c */ -extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); -extern void svc_sq_reap(struct svcxprt_rdma *); -extern void svc_rq_reap(struct svcxprt_rdma *); - extern struct svc_xprt_class svc_rdma_class; #ifdef CONFIG_SUNRPC_BACKCHANNEL extern struct svc_xprt_class svc_rdma_bc_class; -- cgit v1.2.3 From 07e9a6325a35fb9655f7b52e2b9dc632da6eef51 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 28 Mar 2020 13:43:22 -0400 Subject: SUNRPC: Add helpers for decoding list discriminators symbolically Use these helpers in a few spots to demonstrate their use. The remaining open-coded discriminator checks in rpcrdma will be addressed in subsequent patches. Signed-off-by: Chuck Lever --- include/linux/sunrpc/xdr.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 22c207b2425f..5a6a81b7cd9f 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -474,6 +474,32 @@ xdr_stream_encode_uint32_array(struct xdr_stream *xdr, return ret; } +/** + * xdr_item_is_absent - symbolically handle XDR discriminators + * @p: pointer to undecoded discriminator + * + * Return values: + * %true if the following XDR item is absent + * %false if the following XDR item is present + */ +static inline bool xdr_item_is_absent(const __be32 *p) +{ + return *p == xdr_zero; +} + +/** + * xdr_item_is_present - symbolically handle XDR discriminators + * @p: pointer to undecoded discriminator + * + * Return values: + * %true if the following XDR item is present + * %false if the following XDR item is absent + */ +static inline bool xdr_item_is_present(const __be32 *p) +{ + return *p != xdr_zero; +} + /** * xdr_stream_decode_u32 - Decode a 32-bit integer * @xdr: pointer to xdr_stream -- cgit v1.2.3 From f60a08697d28b138c73b14c3204947bc8e637197 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 29 Mar 2020 16:44:13 -0400 Subject: svcrdma: Add common XDR decoders for RDMA and Read segments Clean up: De-duplicate some code. Signed-off-by: Chuck Lever --- include/linux/sunrpc/rpc_rdma.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index 320c672d84de..db50380f64f4 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -124,4 +124,41 @@ rpcrdma_decode_buffer_size(u8 val) return ((unsigned int)val + 1) << 10; } +/** + * xdr_decode_rdma_segment - Decode contents of an RDMA segment + * @p: Pointer to the undecoded RDMA segment + * @handle: Upon return, the RDMA handle + * @length: Upon return, the RDMA length + * @offset: Upon return, the RDMA offset + * + * Return value: + * Pointer to the XDR item that follows the RDMA segment + */ +static inline __be32 *xdr_decode_rdma_segment(__be32 *p, u32 *handle, + u32 *length, u64 *offset) +{ + *handle = be32_to_cpup(p++); + *length = be32_to_cpup(p++); + return xdr_decode_hyper(p, offset); +} + +/** + * xdr_decode_read_segment - Decode contents of a Read segment + * @p: Pointer to the undecoded Read segment + * @position: Upon return, the segment's position + * @handle: Upon return, the RDMA handle + * @length: Upon return, the RDMA length + * @offset: Upon return, the RDMA offset + * + * Return value: + * Pointer to the XDR item that follows the Read segment + */ +static inline __be32 *xdr_decode_read_segment(__be32 *p, u32 *position, + u32 *handle, u32 *length, + u64 *offset) +{ + *position = be32_to_cpup(p++); + return xdr_decode_rdma_segment(p, handle, length, offset); +} + #endif /* _LINUX_SUNRPC_RPC_RDMA_H */ -- cgit v1.2.3 From 379c3bc6b4eb989ee37c4ce8ab403719e06fe35f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 7 Apr 2020 15:32:14 -0400 Subject: svcrdma: Add common XDR encoders for RDMA and Read segments Clean up: De-duplicate some code. Signed-off-by: Chuck Lever --- include/linux/sunrpc/rpc_rdma.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index db50380f64f4..4af31bbc8802 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -124,6 +124,43 @@ rpcrdma_decode_buffer_size(u8 val) return ((unsigned int)val + 1) << 10; } +/** + * xdr_encode_rdma_segment - Encode contents of an RDMA segment + * @p: Pointer into a send buffer + * @handle: The RDMA handle to encode + * @length: The RDMA length to encode + * @offset: The RDMA offset to encode + * + * Return value: + * Pointer to the XDR position that follows the encoded RDMA segment + */ +static inline __be32 *xdr_encode_rdma_segment(__be32 *p, u32 handle, + u32 length, u64 offset) +{ + *p++ = cpu_to_be32(handle); + *p++ = cpu_to_be32(length); + return xdr_encode_hyper(p, offset); +} + +/** + * xdr_encode_read_segment - Encode contents of a Read segment + * @p: Pointer into a send buffer + * @position: The position to encode + * @handle: The RDMA handle to encode + * @length: The RDMA length to encode + * @offset: The RDMA offset to encode + * + * Return value: + * Pointer to the XDR position that follows the encoded Read segment + */ +static inline __be32 *xdr_encode_read_segment(__be32 *p, u32 position, + u32 handle, u32 length, + u64 offset) +{ + *p++ = cpu_to_be32(position); + return xdr_encode_rdma_segment(p, handle, length, offset); +} + /** * xdr_decode_rdma_segment - Decode contents of an RDMA segment * @p: Pointer to the undecoded RDMA segment -- cgit v1.2.3 From f7bd657b55e3484cadc37a6439de23d2fd703bd6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 19 May 2020 09:30:32 -0400 Subject: svcrdma: Introduce infrastructure to support completion IDs The goal is to replace CQE kernel memory addresses in completion- related tracepoints. Each completion ID matches an incoming Send or Receive completion to a Completion Queue and to a previous ib_post_*(). The ID can then be displayed in an error message or recorded in a trace record. Signed-off-by: Chuck Lever --- include/linux/sunrpc/rpc_rdma_cid.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100644 include/linux/sunrpc/rpc_rdma_cid.h (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma_cid.h b/include/linux/sunrpc/rpc_rdma_cid.h new file mode 100644 index 000000000000..be24ab2baa6a --- /dev/null +++ b/include/linux/sunrpc/rpc_rdma_cid.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * * Copyright (c) 2020, Oracle and/or its affiliates. + */ + +#ifndef RPC_RDMA_CID_H +#define RPC_RDMA_CID_H + +/* + * The rpc_rdma_cid struct records completion ID information. A + * completion ID matches an incoming Send or Receive completion + * to a Completion Queue and to a previous ib_post_*(). The ID + * can then be displayed in an error message or recorded in a + * trace record. + * + * This struct is shared between the server and client RPC/RDMA + * transport implementations. + */ +struct rpc_rdma_cid { + u32 ci_queue_id; + int ci_completion_id; +}; + +#endif /* RPC_RDMA_CID_H */ -- cgit v1.2.3 From 9b3bcf8c5c134038e30624db5b57992ae50b80a9 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Apr 2020 16:22:26 -0400 Subject: svcrdma: Introduce Receive completion IDs Set up a completion ID in each svc_rdma_recv_ctxt. The ID is used to match an incoming Receive completion to a transport and to a previous ib_post_recv(). Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index d28ca1b6f2eb..c3c1e46f510f 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -46,6 +46,7 @@ #include #include #include +#include #include #include @@ -109,6 +110,8 @@ struct svcxprt_rdma { struct work_struct sc_work; struct llist_head sc_recv_ctxts; + + atomic_t sc_completion_ids; }; /* sc_flags */ #define RDMAXPRT_CONN_PENDING 3 @@ -129,6 +132,7 @@ struct svc_rdma_recv_ctxt { struct list_head rc_list; struct ib_recv_wr rc_recv_wr; struct ib_cqe rc_cqe; + struct rpc_rdma_cid rc_cid; struct ib_sge rc_recv_sge; void *rc_recv_buf; struct xdr_buf rc_arg; -- cgit v1.2.3 From 3ac56c2fb166fea25974d8c48bb4a72ee298361b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 30 Apr 2020 13:47:07 -0400 Subject: svcrdma: Introduce Send completion IDs Set up a completion ID in each svc_rdma_send_ctxt. The ID is used to match an incoming Send completion to a transport and to a previous ib_post_send(). Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index c3c1e46f510f..c91e00bc937e 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -151,6 +151,8 @@ struct svc_rdma_recv_ctxt { struct svc_rdma_send_ctxt { struct list_head sc_list; + struct rpc_rdma_cid sc_cid; + struct ib_send_wr sc_send_wr; struct ib_cqe sc_cqe; struct xdr_buf sc_hdrbuf; -- cgit v1.2.3 From 17f70f8dd52be3723250d21093403bb3a9f2162f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Apr 2020 11:05:33 -0400 Subject: svcrdma: Record send_ctxt completion ID in trace_svcrdma_post_send() First, refactor: Dereference the svc_rdma_send_ctxt inside svc_rdma_send() instead of at every call site. Then, it can be passed into trace_svcrdma_post_send() to get the proper completion ID. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index c91e00bc937e..9dc3a3b88391 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -196,7 +196,8 @@ extern struct svc_rdma_send_ctxt * svc_rdma_send_ctxt_get(struct svcxprt_rdma *rdma); extern void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt); -extern int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr); +extern int svc_rdma_send(struct svcxprt_rdma *rdma, + struct svc_rdma_send_ctxt *ctxt); extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *sctxt, const struct svc_rdma_recv_ctxt *rctxt, -- cgit v1.2.3 From 9a67fcc8f3fd1e294922f28f20003c31d7f6cfeb Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:38:53 +0000 Subject: nfs: add client side only definitions for user xattrs Add client-side only definitions for user extended attributes (RFC8276). These are the access bits as used by the client code, and the CLNT procedure number definition. Signed-off-by: Frank van der Linden Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 5 +++++ include/linux/nfs_fs.h | 3 +++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index e6ca9d1d2e76..db13026ac7d1 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -553,6 +553,11 @@ enum { NFSPROC4_CLNT_LAYOUTERROR, NFSPROC4_CLNT_COPY_NOTIFY, + + NFSPROC4_CLNT_GETXATTR, + NFSPROC4_CLNT_SETXATTR, + NFSPROC4_CLNT_LISTXATTRS, + NFSPROC4_CLNT_REMOVEXATTR, }; /* nfs41 types */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 6ee9119acc5d..b743988fcbd0 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -212,6 +212,9 @@ struct nfs4_copy_state { #define NFS_ACCESS_EXTEND 0x0008 #define NFS_ACCESS_DELETE 0x0010 #define NFS_ACCESS_EXECUTE 0x0020 +#define NFS_ACCESS_XAREAD 0x0040 +#define NFS_ACCESS_XAWRITE 0x0080 +#define NFS_ACCESS_XALIST 0x0100 /* * Cache validity bit flags -- cgit v1.2.3 From 04a5da690e8f2da23c2ac940f2921e3aa622db82 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:38:54 +0000 Subject: NFSv4.2: define limits and sizes for user xattr handling Set limits for extended attributes (attribute value size and listxattr buffer size), based on the fs-independent limits (XATTR_*_MAX). Define the maximum XDR sizes for the RFC 8276 XATTR operations. In the case of operations that carry a larger payload (SETXATTR, GETXATTR, LISTXATTR), these exclude that payload, which is added as separate pages, like other operations do. Define, much like for read and write operations, the maximum overhead sizes for get/set/listxattr, and use them to limit the maximum payload size for those operations, in combination with the channel attributes. Signed-off-by: Frank van der Linden Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 465fa98258a3..128e01acb4ca 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -163,6 +163,11 @@ struct nfs_server { unsigned int dtsize; /* readdir size */ unsigned short port; /* "port=" setting */ unsigned int bsize; /* server block size */ +#ifdef CONFIG_NFS_V4_2 + unsigned int gxasize; /* getxattr size */ + unsigned int sxasize; /* setxattr size */ + unsigned int lxasize; /* listxattr size */ +#endif unsigned int acregmin; /* attr cache timeouts */ unsigned int acregmax; unsigned int acdirmin; -- cgit v1.2.3 From b78ef845c35dbae25e57b598901a65b13d940c81 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:38:55 +0000 Subject: NFSv4.2: query the server for extended attribute support Query the server for extended attribute support, and record it as the NFS_CAP_XATTR flag in the server capabilities. Signed-off-by: Frank van der Linden Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + include/linux/nfs_xdr.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 128e01acb4ca..7eae72a8762e 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -286,5 +286,6 @@ struct nfs_server { #define NFS_CAP_OFFLOAD_CANCEL (1U << 25) #define NFS_CAP_LAYOUTERROR (1U << 26) #define NFS_CAP_COPY_NOTIFY (1U << 27) +#define NFS_CAP_XATTR (1U << 28) #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5fd0a9ef425f..dee9b1cfa972 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -150,6 +150,7 @@ struct nfs_fsinfo { __u32 layouttype[NFS_MAX_LAYOUT_TYPES]; /* supported pnfs layout driver */ __u32 blksize; /* preferred pnfs io block size */ __u32 clone_blksize; /* granularity of a CLONE operation */ + __u32 xattr_support; /* User xattrs supported */ }; struct nfs_fsstat { -- cgit v1.2.3 From 3e1f02123fba086d32dfd5729e6f4e2b54654acc Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:38:56 +0000 Subject: NFSv4.2: add client side XDR handling for extended attributes Define the argument and response structures that will be used for RFC 8276 extended attribute RPC calls, and implement the necessary functions to encode/decode the extended attribute operations. Signed-off-by: Frank van der Linden Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 58 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index dee9b1cfa972..9408f3252c8e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1498,7 +1498,64 @@ struct nfs42_seek_res { u32 sr_eof; u64 sr_offset; }; -#endif + +struct nfs42_setxattrargs { + struct nfs4_sequence_args seq_args; + struct nfs_fh *fh; + const char *xattr_name; + u32 xattr_flags; + size_t xattr_len; + struct page **xattr_pages; +}; + +struct nfs42_setxattrres { + struct nfs4_sequence_res seq_res; + struct nfs4_change_info cinfo; +}; + +struct nfs42_getxattrargs { + struct nfs4_sequence_args seq_args; + struct nfs_fh *fh; + const char *xattr_name; + size_t xattr_len; + struct page **xattr_pages; +}; + +struct nfs42_getxattrres { + struct nfs4_sequence_res seq_res; + size_t xattr_len; +}; + +struct nfs42_listxattrsargs { + struct nfs4_sequence_args seq_args; + struct nfs_fh *fh; + u32 count; + u64 cookie; + struct page **xattr_pages; +}; + +struct nfs42_listxattrsres { + struct nfs4_sequence_res seq_res; + struct page *scratch; + void *xattr_buf; + size_t xattr_len; + u64 cookie; + bool eof; + size_t copied; +}; + +struct nfs42_removexattrargs { + struct nfs4_sequence_args seq_args; + struct nfs_fh *fh; + const char *xattr_name; +}; + +struct nfs42_removexattrres { + struct nfs4_sequence_res seq_res; + struct nfs4_change_info cinfo; +}; + +#endif /* CONFIG_NFS_V4_2 */ struct nfs_page; -- cgit v1.2.3 From d2ae4f8b21c111bb795c557588d89dccd005828d Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:38:57 +0000 Subject: nfs: define nfs_access_get_cached function The only consumer of nfs_access_get_cached_rcu and nfs_access_cached calls these static functions in order to first try RCU access, and then locked access. Combine them in to a single function, and call that. Make this function available to the rest of the NFS code. Signed-off-by: Frank van der Linden Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b743988fcbd0..714b577dce19 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -493,6 +493,8 @@ extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); +extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, + bool may_block); /* * linux/fs/nfs/symlink.c -- cgit v1.2.3 From 0f44da51aeef9c974ea744c0d9e24d54eec4e94c Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:39:00 +0000 Subject: nfs: define and use the NFS_INO_INVALID_XATTR flag Define the NFS_INO_INVALID_XATTR flag, to be used for the NFSv4.2 xattr cache, and use it where appropriate. No functional change as yet. Signed-off-by: Frank van der Linden Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 714b577dce19..943ee750d68c 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -234,6 +234,7 @@ struct nfs4_copy_state { #define NFS_INO_DATA_INVAL_DEFER \ BIT(13) /* Deferred cache invalidation */ #define NFS_INO_INVALID_BLOCKS BIT(14) /* cached blocks are invalid */ +#define NFS_INO_INVALID_XATTR BIT(15) /* xattrs are invalid */ #define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \ | NFS_INO_INVALID_CTIME \ -- cgit v1.2.3 From 95ad37f90c338e3fd4abf61cecfe02b6f3e080f0 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:39:04 +0000 Subject: NFSv4.2: add client side xattr caching. Implement client side caching for NFSv4.2 extended attributes. The cache is a per-inode hashtable, with name/value entries. There is one special entry for the listxattr cache. NFS inodes have a pointer to a cache structure. The cache structure is allocated on demand, freed when the cache is invalidated. Memory shrinkers keep the size in check. Large entries (> PAGE_SIZE) are collected by a separate shrinker, and freed more aggressively than others. Signed-off-by: Frank van der Linden Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 943ee750d68c..a2c6455ea3fa 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -102,6 +102,8 @@ struct nfs_delegation; struct posix_acl; +struct nfs4_xattr_cache; + /* * nfs fs inode data in memory */ @@ -188,6 +190,10 @@ struct nfs_inode { struct fscache_cookie *fscache; #endif struct inode vfs_inode; + +#ifdef CONFIG_NFS_V4_2 + struct nfs4_xattr_cache *xattr_cache; +#endif }; struct nfs4_copy_state { -- cgit v1.2.3 From 4a3107f61f1ce2c8ccd4dde8ae655ae3f2996f35 Mon Sep 17 00:00:00 2001 From: Rajendra Nayak Date: Tue, 14 Jul 2020 11:01:49 +0530 Subject: tty: serial: qcom-geni-serial: Drop the icc bw votes in suspend for console When using the geni-serial as console, its important to be able to hit the lowest possible power state in suspend, even with no_console_suspend. The only thing that prevents it today on platforms like the sc7180 is the interconnect BW votes, which we certainly don't need when the system is in suspend. So in the suspend handler mark them as ACTIVE_ONLY (0x3) and on resume switch them back to the ALWAYS tag (0x7) Signed-off-by: Rajendra Nayak Reviewed-by: Akash Asthana Tested-by: Matthias Kaehlcke Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/1594704709-26072-1-git-send-email-rnayak@codeaurora.org Signed-off-by: Bjorn Andersson --- include/linux/qcom-geni-se.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index afa511ef1457..8f385fbe5a0e 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -454,6 +454,7 @@ void geni_se_rx_dma_unprep(struct geni_se *se, dma_addr_t iova, size_t len); int geni_icc_get(struct geni_se *se, const char *icc_ddr); int geni_icc_set_bw(struct geni_se *se); +void geni_icc_set_tag(struct geni_se *se, u32 tag); int geni_icc_enable(struct geni_se *se); -- cgit v1.2.3 From b330966f79fb4fdc49183f58db113303695a750f Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 14 Jul 2020 14:45:41 +0200 Subject: fuse: reject options on reconfigure via fsconfig(2) Previous patch changed handling of remount/reconfigure to ignore all options, including those that are unknown to the fuse kernel fs. This was done for backward compatibility, but this likely only affects the old mount(2) API. The new fsconfig(2) based reconfiguration could possibly be improved. This would make the new API less of a drop in replacement for the old, OTOH this is a good chance to get rid of some weirdnesses in the old API. Several other behaviors might make sense: 1) unknown options are rejected, known options are ignored 2) unknown options are rejected, known options are rejected if the value is changed, allowed otherwise 3) all options are rejected Prior to the backward compatibility fix to ignore all options all known options were accepted (1), even if they change the value of a mount parameter; fuse_reconfigure() does not look at the config values set by fuse_parse_param(). To fix that we'd need to verify that the value provided is the same as set in the initial configuration (2). The major drawback is that this is much more complex than just rejecting all attempts at changing options (3); i.e. all options signify initial configuration values and don't make sense on reconfigure. This patch opts for (3) with the rationale that no mount options are reconfigurable in fuse. Signed-off-by: Miklos Szeredi --- include/linux/fs_context.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 5f24fcbfbfb4..37e1e8f7f08d 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -109,6 +109,7 @@ struct fs_context { enum fs_context_phase phase:8; /* The phase the context is in */ bool need_free:1; /* Need to call ops->free() */ bool global:1; /* Goes into &init_user_ns */ + bool oldapi:1; /* Coming from mount(2) */ }; struct fs_context_operations { -- cgit v1.2.3 From afb0367a80553e795e7ad055299096544454f3f6 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 14 Jul 2020 14:56:25 +0200 Subject: PM: domains: Restore comment indentation for generic_pm_domain.child_links The rename of generic_pm_domain.slave_links to generic_pm_domain.child_links accidentally dropped the TAB to align the member's comment. Re-add the lost TAB to restore indentation. Fixes: 8d87ae48ced2dffd ("PM: domains: Fix up terminology with parent/child") Signed-off-by: Geert Uytterhoeven [ rjw: Minor subject edit ] Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 574a1fadb1e5..ee11502a575b 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -96,7 +96,7 @@ struct generic_pm_domain { struct dev_pm_domain domain; /* PM domain operations */ struct list_head gpd_list_node; /* Node in the global PM domains list */ struct list_head parent_links; /* Links with PM domain as a parent */ - struct list_head child_links;/* Links with PM domain as a child */ + struct list_head child_links; /* Links with PM domain as a child */ struct list_head dev_list; /* List of devices */ struct dev_power_governor *gov; struct work_struct power_off_work; -- cgit v1.2.3 From 567f6a6eba0c09e5f502e0290e57651befa8aacb Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Tue, 14 Jul 2020 14:39:25 +0200 Subject: dma-direct: provide function to check physical memory area validity dma_coherent_ok() checks if a physical memory area fits a device's DMA constraints. Signed-off-by: Nicolas Saenz Julienne Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 5184735a0fe8..ab2e20cba951 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -69,6 +69,7 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, u64 dma_direct_get_required_mask(struct device *dev); gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, u64 *phys_mask); +bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size); void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, -- cgit v1.2.3 From 4c5e2bba30e49b970a0fd07b43e0b7a3b5fd5ea7 Mon Sep 17 00:00:00 2001 From: Pratyush Yadav Date: Wed, 24 Jun 2020 00:00:14 +0530 Subject: spi: spi-mem: allow specifying whether an op is DTR or not Each phase is given a separate 'dtr' field so mixed protocols like 4S-4D-4D can be supported. Signed-off-by: Pratyush Yadav Reviewed-by: Tudor Ambarus Link: https://lore.kernel.org/r/20200623183030.26591-2-p.yadav@ti.com Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index af9ff2f0f1b2..e3dcb956bf61 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -71,9 +71,11 @@ enum spi_mem_data_dir { * struct spi_mem_op - describes a SPI memory operation * @cmd.buswidth: number of IO lines used to transmit the command * @cmd.opcode: operation opcode + * @cmd.dtr: whether the command opcode should be sent in DTR mode or not * @addr.nbytes: number of address bytes to send. Can be zero if the operation * does not need to send an address * @addr.buswidth: number of IO lines used to transmit the address cycles + * @addr.dtr: whether the address should be sent in DTR mode or not * @addr.val: address value. This value is always sent MSB first on the bus. * Note that only @addr.nbytes are taken into account in this * address value, so users should make sure the value fits in the @@ -81,7 +83,9 @@ enum spi_mem_data_dir { * @dummy.nbytes: number of dummy bytes to send after an opcode or address. Can * be zero if the operation does not require dummy bytes * @dummy.buswidth: number of IO lanes used to transmit the dummy bytes + * @dummy.dtr: whether the dummy bytes should be sent in DTR mode or not * @data.buswidth: number of IO lanes used to send/receive the data + * @data.dtr: whether the data should be sent in DTR mode or not * @data.dir: direction of the transfer * @data.nbytes: number of data bytes to send/receive. Can be zero if the * operation does not involve transferring data @@ -91,22 +95,26 @@ enum spi_mem_data_dir { struct spi_mem_op { struct { u8 buswidth; + u8 dtr : 1; u8 opcode; } cmd; struct { u8 nbytes; u8 buswidth; + u8 dtr : 1; u64 val; } addr; struct { u8 nbytes; u8 buswidth; + u8 dtr : 1; } dummy; struct { u8 buswidth; + u8 dtr : 1; enum spi_mem_data_dir dir; unsigned int nbytes; union { -- cgit v1.2.3 From caf72df48be32c39f74287976ae843501ae06949 Mon Sep 17 00:00:00 2001 From: Pratyush Yadav Date: Wed, 24 Jun 2020 00:00:15 +0530 Subject: spi: spi-mem: allow specifying a command's extension In xSPI mode, flashes expect 2-byte opcodes. The second byte is called the "command extension". There can be 3 types of extensions in xSPI: repeat, invert, and hex. When the extension type is "repeat", the same opcode is sent twice. When it is "invert", the second byte is the inverse of the opcode. When it is "hex" an additional opcode byte based is sent with the command whose value can be anything. So, make opcode a 16-bit value and add a 'nbytes', similar to how multiple address widths are handled. Some places use sizeof(op->cmd.opcode). Replace them with op->cmd.nbytes The spi-mxic and spi-zynq-qspi drivers directly use op->cmd.opcode as a buffer. Now that opcode is a 2-byte field, this can result in different behaviour depending on if the machine is little endian or big endian. Extract the opcode in a local 1-byte variable and use that as the buffer instead. Both these drivers would reject multi-byte opcodes in their supports_op() hook anyway, so we only need to worry about single-byte opcodes for now. The above two changes are put in this commit to keep the series bisectable. Signed-off-by: Pratyush Yadav Reviewed-by: Tudor Ambarus Link: https://lore.kernel.org/r/20200623183030.26591-3-p.yadav@ti.com Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index e3dcb956bf61..159463cc659c 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -17,6 +17,7 @@ { \ .buswidth = __buswidth, \ .opcode = __opcode, \ + .nbytes = 1, \ } #define SPI_MEM_OP_ADDR(__nbytes, __val, __buswidth) \ @@ -69,6 +70,8 @@ enum spi_mem_data_dir { /** * struct spi_mem_op - describes a SPI memory operation + * @cmd.nbytes: number of opcode bytes (only 1 or 2 are valid). The opcode is + * sent MSB-first. * @cmd.buswidth: number of IO lines used to transmit the command * @cmd.opcode: operation opcode * @cmd.dtr: whether the command opcode should be sent in DTR mode or not @@ -94,9 +97,10 @@ enum spi_mem_data_dir { */ struct spi_mem_op { struct { + u8 nbytes; u8 buswidth; u8 dtr : 1; - u8 opcode; + u16 opcode; } cmd; struct { -- cgit v1.2.3 From 079ef53673f2e3b3ee1728800311f20f28eed4f7 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 14 Jul 2020 12:25:33 +0200 Subject: bpf: Fix build for disabled CONFIG_DEBUG_INFO_BTF option Stephen reported following linker warnings on powerpc build: ld: warning: orphan section `.BTF_ids' from `kernel/trace/bpf_trace.o' being placed in section `.BTF_ids' ld: warning: orphan section `.BTF_ids' from `kernel/bpf/btf.o' being placed in section `.BTF_ids' ld: warning: orphan section `.BTF_ids' from `kernel/bpf/stackmap.o' being placed in section `.BTF_ids' ld: warning: orphan section `.BTF_ids' from `net/core/filter.o' being placed in section `.BTF_ids' ld: warning: orphan section `.BTF_ids' from `kernel/trace/bpf_trace.o' being placed in section `.BTF_ids' It's because we generated .BTF_ids section even when CONFIG_DEBUG_INFO_BTF is not enabled. Fixing this by generating empty btf_id arrays for this case. Reported-by: Stephen Rothwell Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/bpf/20200714102534.299280-1-jolsa@kernel.org --- include/linux/btf_ids.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index fe019774f8a7..b3c73db9587c 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -3,6 +3,8 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +#ifdef CONFIG_DEBUG_INFO_BTF + #include /* for __PASTE */ /* @@ -83,5 +85,12 @@ asm( \ ".zero 4 \n" \ ".popsection; \n"); +#else + +#define BTF_ID_LIST(name) static u32 name[5]; +#define BTF_ID(prefix, name) +#define BTF_ID_UNUSED + +#endif /* CONFIG_DEBUG_INFO_BTF */ #endif -- cgit v1.2.3 From 11bb2f7a45909f4f64afe471875672ae1b84a380 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 14 Jul 2020 12:25:34 +0200 Subject: bpf: Fix cross build for CONFIG_DEBUG_INFO_BTF option Stephen and 0-DAY CI Kernel Test Service reported broken cross build for arm (arm-linux-gnueabi-gcc (GCC) 9.3.0), with following output: /tmp/ccMS5uth.s: Assembler messages: /tmp/ccMS5uth.s:69: Error: unrecognized symbol type "" /tmp/ccMS5uth.s:82: Error: unrecognized symbol type "" Having '@object' for .type diretive is wrong because '@' is comment character for some architectures. Using STT_OBJECT instead that should work everywhere. Also using HOST* variables to build resolve_btfids so it's properly build in crossbuilds (stolen from objtool's Makefile). Reported-by: kernel test robot Reported-by: Stephen Rothwell Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/bpf/20200714102534.299280-2-jolsa@kernel.org --- include/linux/btf_ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index b3c73db9587c..1cdb56950ffe 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -23,7 +23,7 @@ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ ".local " #symbol " ; \n" \ -".type " #symbol ", @object; \n" \ +".type " #symbol ", STT_OBJECT; \n" \ ".size " #symbol ", 4; \n" \ #symbol ": \n" \ ".zero 4 \n" \ -- cgit v1.2.3 From 59679d9933ab897d197297eaf37e5b3788c052a5 Mon Sep 17 00:00:00 2001 From: He Zhe Date: Mon, 6 Jul 2020 17:52:24 +0800 Subject: freezer: Add unsafe version of freezable_schedule_timeout_interruptible() for NFS commit 0688e64bc600 ("NFS: Allow signal interruption of NFS4ERR_DELAYed operations") introduces nfs4_delay_interruptible which also needs an _unsafe version to avoid the following call trace for the same reason explained in commit 416ad3c9c006 ("freezer: add unsafe versions of freezable helpers for NFS") CPU: 4 PID: 3968 Comm: rm Tainted: G W 5.8.0-rc4 #1 Hardware name: Marvell OcteonTX CN96XX board (DT) Call trace: dump_backtrace+0x0/0x1dc show_stack+0x20/0x30 dump_stack+0xdc/0x150 debug_check_no_locks_held+0x98/0xa0 nfs4_delay_interruptible+0xd8/0x120 nfs4_handle_exception+0x130/0x170 nfs4_proc_rmdir+0x8c/0x220 nfs_rmdir+0xa4/0x360 vfs_rmdir.part.0+0x6c/0x1b0 do_rmdir+0x18c/0x210 __arm64_sys_unlinkat+0x64/0x7c el0_svc_common.constprop.0+0x7c/0x110 do_el0_svc+0x24/0xa0 el0_sync_handler+0x13c/0x1b8 el0_sync+0x158/0x180 Signed-off-by: He Zhe Signed-off-by: Rafael J. Wysocki --- include/linux/freezer.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 21f5aa0b217f..27828145ca09 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -207,6 +207,17 @@ static inline long freezable_schedule_timeout_interruptible(long timeout) return __retval; } +/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ +static inline long freezable_schedule_timeout_interruptible_unsafe(long timeout) +{ + long __retval; + + freezer_do_not_count(); + __retval = schedule_timeout_interruptible(timeout); + freezer_count_unsafe(); + return __retval; +} + /* Like schedule_timeout_killable(), but should not block the freezer. */ static inline long freezable_schedule_timeout_killable(long timeout) { @@ -285,6 +296,9 @@ static inline void set_freezable(void) {} #define freezable_schedule_timeout_interruptible(timeout) \ schedule_timeout_interruptible(timeout) +#define freezable_schedule_timeout_interruptible_unsafe(timeout) \ + schedule_timeout_interruptible(timeout) + #define freezable_schedule_timeout_killable(timeout) \ schedule_timeout_killable(timeout) -- cgit v1.2.3 From 43364ef1a12a4236b7956b076649ddd080764cd1 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 14 Jul 2020 09:34:49 +0200 Subject: bridge: mrp: Extend bridge interface This patch adds a new flag(BR_MRP_LOST_IN_CONT) to the net bridge ports. This bit will be set when the port lost the continuity of MRP_InTest frames. Signed-off-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index b3a8d3054af0..6479a38e52fa 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -49,6 +49,7 @@ struct br_ip_list { #define BR_ISOLATED BIT(16) #define BR_MRP_AWARE BIT(17) #define BR_MRP_LOST_CONT BIT(18) +#define BR_MRP_LOST_IN_CONT BIT(19) #define BR_DEFAULT_AGEING_TIME (300 * HZ) -- cgit v1.2.3 From 7cf97b12545503992020796c74bd84078eb39299 Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Tue, 2 Jun 2020 18:10:43 -0700 Subject: seccomp: Introduce addfd ioctl to seccomp user notifier The current SECCOMP_RET_USER_NOTIF API allows for syscall supervision over an fd. It is often used in settings where a supervising task emulates syscalls on behalf of a supervised task in userspace, either to further restrict the supervisee's syscall abilities or to circumvent kernel enforced restrictions the supervisor deems safe to lift (e.g. actually performing a mount(2) for an unprivileged container). While SECCOMP_RET_USER_NOTIF allows for the interception of any syscall, only a certain subset of syscalls could be correctly emulated. Over the last few development cycles, the set of syscalls which can't be emulated has been reduced due to the addition of pidfd_getfd(2). With this we are now able to, for example, intercept syscalls that require the supervisor to operate on file descriptors of the supervisee such as connect(2). However, syscalls that cause new file descriptors to be installed can not currently be correctly emulated since there is no way for the supervisor to inject file descriptors into the supervisee. This patch adds a new addfd ioctl to remove this restriction by allowing the supervisor to install file descriptors into the intercepted task. By implementing this feature via seccomp the supervisor effectively instructs the supervisee to install a set of file descriptors into its own file descriptor table during the intercepted syscall. This way it is possible to intercept syscalls such as open() or accept(), and install (or replace, like dup2(2)) the supervisor's resulting fd into the supervisee. One replacement use-case would be to redirect the stdout and stderr of a supervisee into log file descriptors opened by the supervisor. The ioctl handling is based on the discussions[1] of how Extensible Arguments should interact with ioctls. Instead of building size into the addfd structure, make it a function of the ioctl command (which is how sizes are normally passed to ioctls). To support forward and backward compatibility, just mask out the direction and size, and match everything. The size (and any future direction) checks are done along with copy_struct_from_user() logic. As a note, the seccomp_notif_addfd structure is laid out based on 8-byte alignment without requiring packing as there have been packing issues with uapi highlighted before[2][3]. Although we could overload the newfd field and use -1 to indicate that it is not to be used, doing so requires changing the size of the fd field, and introduces struct packing complexity. [1]: https://lore.kernel.org/lkml/87o8w9bcaf.fsf@mid.deneb.enyo.de/ [2]: https://lore.kernel.org/lkml/a328b91d-fd8f-4f27-b3c2-91a9c45f18c0@rasmusvillemoes.dk/ [3]: https://lore.kernel.org/lkml/20200612104629.GA15814@ircssh-2.c.rugged-nimbus-611.internal Cc: Christoph Hellwig Cc: Christian Brauner Cc: Tycho Andersen Cc: Jann Horn Cc: Robert Sesek Cc: Chris Palmer Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-api@vger.kernel.org Suggested-by: Matt Denton Link: https://lore.kernel.org/r/20200603011044.7972-4-sargun@sargun.me Signed-off-by: Sargun Dhillon Reviewed-by: Will Drewry Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/seccomp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index babcd6c02d09..881c90b6aa25 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -10,6 +10,10 @@ SECCOMP_FILTER_FLAG_NEW_LISTENER | \ SECCOMP_FILTER_FLAG_TSYNC_ESRCH) +/* sizeof() the first published struct seccomp_notif_addfd */ +#define SECCOMP_NOTIFY_ADDFD_SIZE_VER0 24 +#define SECCOMP_NOTIFY_ADDFD_SIZE_LATEST SECCOMP_NOTIFY_ADDFD_SIZE_VER0 + #ifdef CONFIG_SECCOMP #include -- cgit v1.2.3 From 4550569bd779f25398503ad5556f8dc7c1f216c2 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 Jul 2020 02:43:53 +0800 Subject: soundwire: stream: add helper to startup/shutdown streams To handle streams at the dailink level, expose two helpers that will be called from machine drivers. Reviewed-by: Ranjani Sridharan Reviewed-by: Guennadi Liakhovetski Reviewed-by: Kai Vehmanen Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20200630184356.24939-3-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 64c9314cb903..4057adf7f049 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -955,10 +955,12 @@ int sdw_stream_remove_master(struct sdw_bus *bus, struct sdw_stream_runtime *stream); int sdw_stream_remove_slave(struct sdw_slave *slave, struct sdw_stream_runtime *stream); +int sdw_startup_stream(void *sdw_substream); int sdw_prepare_stream(struct sdw_stream_runtime *stream); int sdw_enable_stream(struct sdw_stream_runtime *stream); int sdw_disable_stream(struct sdw_stream_runtime *stream); int sdw_deprepare_stream(struct sdw_stream_runtime *stream); +void sdw_shutdown_stream(void *sdw_substream); int sdw_bus_prep_clk_stop(struct sdw_bus *bus); int sdw_bus_clk_stop(struct sdw_bus *bus); int sdw_bus_exit_clk_stop(struct sdw_bus *bus); -- cgit v1.2.3 From 58eeba0bdb52afe5c18ce2a760ca9fe2901943e9 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Tue, 14 Jul 2020 15:01:53 +0300 Subject: lib/string_helpers: Introduce string_upper() and string_lower() helpers Provide the helpers for string conversions to upper and lower cases. Signed-off-by: Vadim Pasternak Signed-off-by: Andy Shevchenko --- include/linux/string_helpers.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index c28955132234..86f150c2a6b6 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -2,6 +2,7 @@ #ifndef _LINUX_STRING_HELPERS_H_ #define _LINUX_STRING_HELPERS_H_ +#include #include struct file; @@ -75,6 +76,20 @@ static inline int string_escape_str_any_np(const char *src, char *dst, return string_escape_str(src, dst, sz, ESCAPE_ANY_NP, only); } +static inline void string_upper(char *dst, const char *src) +{ + do { + *dst++ = toupper(*src); + } while (*src++); +} + +static inline void string_lower(char *dst, const char *src) +{ + do { + *dst++ = tolower(*src); + } while (*src++); +} + char *kstrdup_quotable(const char *src, gfp_t gfp); char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp); char *kstrdup_quotable_file(struct file *file, gfp_t gfp); -- cgit v1.2.3 From 13e52e63a4462e2bd0ef249fb535a599ea158725 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Tue, 14 Jul 2020 15:01:58 +0300 Subject: platform_data/mlxreg: Add support for complex attributes Add new field 'regnum' to the structure 'mlxreg_core_data' to specify the number of registers occupied by multi-register attribute. Signed-off-by: Vadim Pasternak Signed-off-by: Andy Shevchenko --- include/linux/platform_data/mlxreg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index b8da8aef2446..a2adc3ad45f2 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -80,6 +80,7 @@ struct mlxreg_hotplug_device { * @hpdev - hotplug device data; * @health_cntr: dynamic device health indication counter; * @attached: true if device has been attached after good health indication; + * @regnum: number of registers occupied by multi-register attribute; */ struct mlxreg_core_data { char label[MLXREG_CORE_LABEL_MAX_SIZE]; @@ -92,6 +93,7 @@ struct mlxreg_core_data { struct mlxreg_hotplug_device hpdev; u8 health_cntr; bool attached; + u8 regnum; }; /** -- cgit v1.2.3 From 17727a3b4879324818ea6f2ebc3f68432173ce24 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Tue, 14 Jul 2020 15:02:02 +0300 Subject: platform_data/mlxreg: Add presence register field for FAN devices Add new field 'reg_prsnt' to the structure 'mlxreg_core_data' to provide the number FAN drawers equpped within the system. The purpose is to allow mapping between FAN drawers and FAN rotors (tachometer), since FAN drawer can be eqipped with a few rotors. Signed-off-by: Vadim Pasternak Signed-off-by: Andy Shevchenko --- include/linux/platform_data/mlxreg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index a2adc3ad45f2..9cffa9a64ab3 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -75,6 +75,7 @@ struct mlxreg_hotplug_device { * @mask: attribute access mask; * @bit: attribute effective bit; * @capability: attribute capability register; + * @reg_prsnt: attribute presence register; * @mode: access mode; * @np - pointer to node platform associated with attribute; * @hpdev - hotplug device data; @@ -88,6 +89,7 @@ struct mlxreg_core_data { u32 mask; u32 bit; u32 capability; + u32 reg_prsnt; umode_t mode; struct device_node *np; struct mlxreg_hotplug_device hpdev; -- cgit v1.2.3 From a8209dd42a60dca0fd15bc73d19fc4009e704c17 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 15 Jul 2020 05:37:43 +0800 Subject: soundwire: sdw.h: fix PRBS/Static_1 swapped definitions Table 110 "Port Data Modes" of the SoundWire 1.2 specification lists PRBS as b01 and Static_1 as b11. The existing headers swapped the two values, fix. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Guennadi Liakhovetski Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20200714213744.24674-2-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 4057adf7f049..6452bac957b3 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -152,19 +152,19 @@ enum sdw_data_direction { * * @SDW_PORT_DATA_MODE_NORMAL: Normal data mode where audio data is received * and transmitted. + * @SDW_PORT_DATA_MODE_PRBS: Test mode which uses a PRBS generator to produce + * a pseudo random data pattern that is transferred + * @SDW_PORT_DATA_MODE_STATIC_0: Simple test mode which uses static value of + * logic 0. The encoding will result in no signal transitions * @SDW_PORT_DATA_MODE_STATIC_1: Simple test mode which uses static value of * logic 1. The encoding will result in signal transitions at every bitslot * owned by this Port - * @SDW_PORT_DATA_MODE_STATIC_0: Simple test mode which uses static value of - * logic 0. The encoding will result in no signal transitions - * @SDW_PORT_DATA_MODE_PRBS: Test mode which uses a PRBS generator to produce - * a pseudo random data pattern that is transferred */ enum sdw_port_data_mode { SDW_PORT_DATA_MODE_NORMAL = 0, - SDW_PORT_DATA_MODE_STATIC_1 = 1, + SDW_PORT_DATA_MODE_PRBS = 1, SDW_PORT_DATA_MODE_STATIC_0 = 2, - SDW_PORT_DATA_MODE_PRBS = 3, + SDW_PORT_DATA_MODE_STATIC_1 = 3, }; /* -- cgit v1.2.3 From 9256686898881b0694fe6af2c3283b69677838de Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 15 Jul 2020 05:37:44 +0800 Subject: soundwire: sdw.h: fix indentation Not sure how this went undetected for years. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Guennadi Liakhovetski Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20200714213744.24674-3-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 6452bac957b3..76052f12c9f7 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -88,10 +88,10 @@ enum sdw_slave_status { * @SDW_CLK_POST_DEPREPARE: post clock stop de-prepare */ enum sdw_clk_stop_type { - SDW_CLK_PRE_PREPARE = 0, - SDW_CLK_POST_PREPARE, - SDW_CLK_PRE_DEPREPARE, - SDW_CLK_POST_DEPREPARE, + SDW_CLK_PRE_PREPARE = 0, + SDW_CLK_POST_PREPARE, + SDW_CLK_PRE_DEPREPARE, + SDW_CLK_POST_DEPREPARE, }; /** -- cgit v1.2.3 From 71d734103edfa2b4c6657578a3082ee0e51d767e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 8 Jul 2020 14:11:36 +0300 Subject: fsnotify: Rearrange fast path to minimise overhead when there is no watcher The fsnotify paths are trivial to hit even when there are no watchers and they are surprisingly expensive. For example, every successful vfs_write() hits fsnotify_modify which calls both fsnotify_parent and fsnotify unless FMODE_NONOTIFY is set which is an internal flag invisible to userspace. As it stands, fsnotify_parent is a guaranteed functional call even if there are no watchers and fsnotify() does a substantial amount of unnecessary work before it checks if there are any watchers. A perf profile showed that applying mnt->mnt_fsnotify_mask in fnotify() was almost half of the total samples taken in that function during a test. This patch rearranges the fast paths to reduce the amount of work done when there are no watchers. The test motivating this was "perf bench sched messaging --pipe". Despite the fact the pipes are anonymous, fsnotify is still called a lot and the overhead is noticeable even though it's completely pointless. It's likely the overhead is negligible for real IO so this is an extreme example. This is a comparison of hackbench using processes and pipes on a 1-socket machine with 8 CPU threads without fanotify watchers. 5.7.0 5.7.0 vanilla fastfsnotify-v1r1 Amean 1 0.4837 ( 0.00%) 0.4630 * 4.27%* Amean 3 1.5447 ( 0.00%) 1.4557 ( 5.76%) Amean 5 2.6037 ( 0.00%) 2.4363 ( 6.43%) Amean 7 3.5987 ( 0.00%) 3.4757 ( 3.42%) Amean 12 5.8267 ( 0.00%) 5.6983 ( 2.20%) Amean 18 8.4400 ( 0.00%) 8.1327 ( 3.64%) Amean 24 11.0187 ( 0.00%) 10.0290 * 8.98%* Amean 30 13.1013 ( 0.00%) 12.8510 ( 1.91%) Amean 32 13.9190 ( 0.00%) 13.2410 ( 4.87%) 5.7.0 5.7.0 vanilla fastfsnotify-v1r1 Duration User 157.05 152.79 Duration System 1279.98 1219.32 Duration Elapsed 182.81 174.52 This is showing that the latencies are improved by roughly 2-9%. The variability is not shown but some of these results are within the noise as this workload heavily overloads the machine. That said, the system CPU usage is reduced by quite a bit so it makes sense to avoid the overhead even if it is a bit tricky to detect at times. A perf profile of just 1 group of tasks showed that 5.14% of samples taken were in either fsnotify() or fsnotify_parent(). With the patch, 2.8% of samples were in fsnotify, mostly function entry and the initial check for watchers. The check for watchers is complicated enough that inlining it may be controversial. [Amir] Slightly simplify with mnt_or_sb_mask => marks_mask Link: https://lore.kernel.org/r/20200708111156.24659-1-amir73il@gmail.com Signed-off-by: Mel Gorman Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 10 ++++++++++ include/linux/fsnotify_backend.h | 4 ++-- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 5ab28f6c7d26..508f6bb0b06b 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -44,6 +44,16 @@ static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0); } +/* Notify this dentry's parent about a child's events. */ +static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, + const void *data, int data_type) +{ + if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) + return 0; + + return __fsnotify_parent(dentry, mask, data, data_type); +} + /* * Simple wrappers to consolidate calls fsnotify_parent()/fsnotify() when * an event is on a file/dentry. diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index f0c506405b54..1626fa7d10ff 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -379,7 +379,7 @@ struct fsnotify_mark { /* main fsnotify call to send events */ extern int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_type, const struct qstr *name, u32 cookie); -extern int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, +extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); @@ -541,7 +541,7 @@ static inline int fsnotify(struct inode *to_tell, __u32 mask, const void *data, return 0; } -static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, +static inline int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { return 0; -- cgit v1.2.3 From 8635764bcf0f109933b593d79ac2247b1e863d0a Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 15 Jul 2020 10:52:03 +0800 Subject: netpoll: Remove unused inline function netpoll_netdev_init() commit d565b0a1a9b6 ("net: Add Generic Receive Offload infrastructure") left behind this, remove it. Signed-off-by: YueHaibing Signed-off-by: David S. Miller --- include/linux/netpoll.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index f47af135bd56..e6a2d72e0dc7 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -102,9 +102,6 @@ static inline void *netpoll_poll_lock(struct napi_struct *napi) static inline void netpoll_poll_unlock(void *have) { } -static inline void netpoll_netdev_init(struct net_device *dev) -{ -} static inline bool netpoll_tx_running(struct net_device *dev) { return false; -- cgit v1.2.3 From f7d7ad42a9dc2d63cab6a79fe31e6732a30dacf5 Mon Sep 17 00:00:00 2001 From: Sumit Semwal Date: Mon, 22 Jun 2020 18:11:07 +0530 Subject: regulator: Allow regulators to verify enabled during enable() Some regulators might need to verify that they have indeed been enabled after the enable() call is made and enable_time delay has passed. This is implemented by repeatedly checking is_enabled() upto poll_enabled_time, waiting for the already calculated enable delay in each iteration. Signed-off-by: Sumit Semwal Link: https://lore.kernel.org/r/20200622124110.20971-2-sumit.semwal@linaro.org Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 7eb9fea8e482..436df3ba0b2a 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -305,6 +305,9 @@ enum regulator_type { * @enable_time: Time taken for initial enable of regulator (in uS). * @off_on_delay: guard time (in uS), before re-enabling a regulator * + * @poll_enabled_time: The polling interval (in uS) to use while checking that + * the regulator was actually enabled. Max upto enable_time. + * * @of_map_mode: Maps a hardware mode defined in a DeviceTree to a standard mode */ struct regulator_desc { @@ -372,6 +375,8 @@ struct regulator_desc { unsigned int off_on_delay; + unsigned int poll_enabled_time; + unsigned int (*of_map_mode)(unsigned int mode); }; -- cgit v1.2.3 From ded071f475cb5b67fda412f88fd5fd4d9c27916c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 14 Jul 2020 21:56:58 -0700 Subject: usb: linux/usb.h: drop duplicated word in comment Drop the doubled word "the" in a comment. Signed-off-by: Randy Dunlap Cc: Greg Kroah-Hartman Cc: linux-usb@vger.kernel.org Link: https://lore.kernel.org/r/20200715045701.22949-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index c28fc391444a..20c555db4621 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -341,7 +341,7 @@ struct usb_interface_cache { * @interface: array of pointers to usb_interface structures, one for each * interface in the configuration. The number of interfaces is stored * in desc.bNumInterfaces. These pointers are valid only while the - * the configuration is active. + * configuration is active. * @intf_cache: array of pointers to usb_interface_cache structures, one * for each interface in the configuration. These structures exist * for the entire life of the device. -- cgit v1.2.3 From c76ae34b5af22497b660f6baeed182869c24e411 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 14 Jul 2020 21:57:00 -0700 Subject: usb: linux/usb/pd_vdo.h: drop duplicated word in comment Drop the doubled word "all" in a comment. Signed-off-by: Randy Dunlap Cc: Greg Kroah-Hartman Cc: linux-usb@vger.kernel.org Link: https://lore.kernel.org/r/20200715045701.22949-3-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd_vdo.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/pd_vdo.h b/include/linux/usb/pd_vdo.h index 35b8e15efaa0..68bdc4e2f5a9 100644 --- a/include/linux/usb/pd_vdo.h +++ b/include/linux/usb/pd_vdo.h @@ -249,7 +249,7 @@ * SVDM Discover SVIDs request -> response * * Request is properly formatted VDM Header with discover SVIDs command. - * Response is a set of SVIDs of all all supported SVIDs with all zero's to + * Response is a set of SVIDs of all supported SVIDs with all zero's to * mark the end of SVIDs. If more than 12 SVIDs are supported command SHOULD be * repeated. */ -- cgit v1.2.3 From 4e28335f2b442662148f9803f3e7e053e6074815 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 14 Jul 2020 21:57:01 -0700 Subject: usb: linux/usb/serial.h: drop duplicated word in comment Drop the doubled word "set" in a comment. Signed-off-by: Randy Dunlap Cc: Greg Kroah-Hartman Cc: linux-usb@vger.kernel.org Link: https://lore.kernel.org/r/20200715045701.22949-4-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/serial.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 14cac4a1ae8f..315cfc6f99a9 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -213,7 +213,7 @@ struct usb_serial_endpoints { * Return 0 to continue on with the initialization sequence. Anything * else will abort it. * @attach: pointer to the driver's attach function. - * This will be called when the struct usb_serial structure is fully set + * This will be called when the struct usb_serial structure is fully * set up. Do any local initialization of the device, or any private * memory structure allocation at this point in time. * @disconnect: pointer to the driver's disconnect function. This will be -- cgit v1.2.3 From e4dfa8029925f6200f6ab2db5a25d86fd082e9cf Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 14 Jul 2020 21:56:59 -0700 Subject: usb: linux/usb/gadget.h: fix duplicated word in comment Change the doubled word "in" to "be in" in a comment. Signed-off-by: Randy Dunlap Cc: Greg Kroah-Hartman Cc: linux-usb@vger.kernel.org Link: https://lore.kernel.org/r/20200715045701.22949-2-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 298b334e2951..52ce1f6b8f83 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -731,7 +731,7 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver); * it will first disconnect(). The driver is also requested * to unbind() and clean up any device state, before this procedure * finally returns. It's expected that the unbind() functions - * will in in exit sections, so may not be linked in some kernels. + * will be in exit sections, so may not be linked in some kernels. */ int usb_gadget_unregister_driver(struct usb_gadget_driver *driver); -- cgit v1.2.3 From c738fbabb0ff62d0f9a9572e56e65d05a1b34c6a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 8 Jul 2020 14:11:37 +0300 Subject: fsnotify: fold fsnotify() call into fsnotify_parent() All (two) callers of fsnotify_parent() also call fsnotify() to notify the child inode. Move the second fsnotify() call into fsnotify_parent(). This will allow more flexibility in making decisions about which of the two event falvors should be sent. Using 'goto notify_child' in the inline helper seems a bit strange, but it mimics the code in __fsnotify_parent() for clarity and the goto pattern will become less strage after following patches are applied. Link: https://lore.kernel.org/r/20200708111156.24659-2-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 33 +++++++++++++-------------------- 1 file changed, 13 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 508f6bb0b06b..316c9b820517 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -48,44 +48,37 @@ static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { + struct inode *inode = d_inode(dentry); + + if (S_ISDIR(inode->i_mode)) + mask |= FS_ISDIR; + if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) - return 0; + goto notify_child; return __fsnotify_parent(dentry, mask, data, data_type); + +notify_child: + return fsnotify(inode, mask, data, data_type, NULL, 0); } /* - * Simple wrappers to consolidate calls fsnotify_parent()/fsnotify() when - * an event is on a file/dentry. + * Simple wrappers to consolidate calls to fsnotify_parent() when an event + * is on a file/dentry. */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { - struct inode *inode = d_inode(dentry); - - if (S_ISDIR(inode->i_mode)) - mask |= FS_ISDIR; - - fsnotify_parent(dentry, mask, inode, FSNOTIFY_EVENT_INODE); - fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); + fsnotify_parent(dentry, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE); } static inline int fsnotify_file(struct file *file, __u32 mask) { const struct path *path = &file->f_path; - struct inode *inode = file_inode(file); - int ret; if (file->f_mode & FMODE_NONOTIFY) return 0; - if (S_ISDIR(inode->i_mode)) - mask |= FS_ISDIR; - - ret = fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); - if (ret) - return ret; - - return fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } /* Simple call site for access decisions */ -- cgit v1.2.3 From cbcf47adc8aadbcaa741391ccfd96f764b50be7e Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 8 Jul 2020 14:11:38 +0300 Subject: fsnotify: return non const from fsnotify_data_inode() Return non const inode pointer from fsnotify_data_inode(). None of the fsnotify hooks pass const inode pointer as data and callers often need to cast to a non const pointer. Link: https://lore.kernel.org/r/20200708111156.24659-3-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 1626fa7d10ff..97300f3b8ff0 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -220,12 +220,11 @@ enum fsnotify_data_type { FSNOTIFY_EVENT_INODE, }; -static inline const struct inode *fsnotify_data_inode(const void *data, - int data_type) +static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: - return data; + return (struct inode *)data; case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); default: -- cgit v1.2.3 From e15864f8ea05b24071b07300459ae7e511d0b938 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Tue, 14 Jul 2020 23:18:23 +0200 Subject: block: add max_open_zones to blk-sysfs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a new max_open_zones definition in the sysfs documentation. This definition will be common for all devices utilizing the zoned block device support in the kernel. Export max open zones according to this new definition for NVMe Zoned Namespace devices, ZAC ATA devices (which are treated as SCSI devices by the kernel), and ZBC SCSI devices. Add the new max_open_zones member to struct request_queue, rather than as a queue limit, since this property cannot be split across stacking drivers. Signed-off-by: Niklas Cassel Reviewed-by: Javier González Reviewed-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index de7adc59b993..c8beb8bbdb08 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -513,6 +513,7 @@ struct request_queue { unsigned int nr_zones; unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; + unsigned int max_open_zones; #endif /* CONFIG_BLK_DEV_ZONED */ /* @@ -722,6 +723,17 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q, return true; return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap); } + +static inline void blk_queue_max_open_zones(struct request_queue *q, + unsigned int max_open_zones) +{ + q->max_open_zones = max_open_zones; +} + +static inline unsigned int queue_max_open_zones(const struct request_queue *q) +{ + return q->max_open_zones; +} #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { @@ -737,6 +749,10 @@ static inline unsigned int blk_queue_zone_no(struct request_queue *q, { return 0; } +static inline unsigned int queue_max_open_zones(const struct request_queue *q) +{ + return 0; +} #endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) @@ -1519,6 +1535,15 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev) return 0; } +static inline unsigned int bdev_max_open_zones(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q) + return queue_max_open_zones(q); + return 0; +} + static inline int queue_dma_alignment(const struct request_queue *q) { return q ? q->dma_alignment : 511; -- cgit v1.2.3 From 659bf827ba8f1183b714341d8a1d4b1e446178d9 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Tue, 14 Jul 2020 23:18:24 +0200 Subject: block: add max_active_zones to blk-sysfs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a new max_active zones definition in the sysfs documentation. This definition will be common for all devices utilizing the zoned block device support in the kernel. Export max_active_zones according to this new definition for NVMe Zoned Namespace devices, ZAC ATA devices (which are treated as SCSI devices by the kernel), and ZBC SCSI devices. Add the new max_active_zones member to struct request_queue, rather than as a queue limit, since this property cannot be split across stacking drivers. For SCSI devices, even though max active zones is not part of the ZBC/ZAC spec, export max_active_zones as 0, signifying "no limit". Signed-off-by: Niklas Cassel Reviewed-by: Javier González Reviewed-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c8beb8bbdb08..285b59cfc064 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -514,6 +514,7 @@ struct request_queue { unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; unsigned int max_open_zones; + unsigned int max_active_zones; #endif /* CONFIG_BLK_DEV_ZONED */ /* @@ -734,6 +735,17 @@ static inline unsigned int queue_max_open_zones(const struct request_queue *q) { return q->max_open_zones; } + +static inline void blk_queue_max_active_zones(struct request_queue *q, + unsigned int max_active_zones) +{ + q->max_active_zones = max_active_zones; +} + +static inline unsigned int queue_max_active_zones(const struct request_queue *q) +{ + return q->max_active_zones; +} #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { @@ -753,6 +765,10 @@ static inline unsigned int queue_max_open_zones(const struct request_queue *q) { return 0; } +static inline unsigned int queue_max_active_zones(const struct request_queue *q) +{ + return 0; +} #endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) @@ -1544,6 +1560,15 @@ static inline unsigned int bdev_max_open_zones(struct block_device *bdev) return 0; } +static inline unsigned int bdev_max_active_zones(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q) + return queue_max_active_zones(q); + return 0; +} + static inline int queue_dma_alignment(const struct request_queue *q) { return q ? q->dma_alignment : 511; -- cgit v1.2.3 From 1a8f0886a6008c98a926bdeca49f2ef33015a491 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Thu, 9 Jul 2020 10:48:35 +0530 Subject: powerpc/perf/hv-24x7: Add cpu hotplug support Patch here adds cpu hotplug functions to hv_24x7 pmu. A new cpuhp_state "CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE" enum is added. The online callback function updates the cpumask only if its empty. As the primary intention of adding hotplug support is to designate a CPU to make HCALL to collect the counter data. The offline function test and clear corresponding cpu in a cpumask and update cpumask to any other active cpu. Signed-off-by: Kajol Jain Reviewed-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200709051836.723765-2-kjain@linux.ibm.com --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 191772d4a4d7..a2710e654b64 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -181,6 +181,7 @@ enum cpuhp_state { CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE, + CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE, CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, -- cgit v1.2.3 From 0d80b76184ac9f2dfb939e39ad1f961fc006b99d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 09:42:38 -0700 Subject: net: qed: drop duplicate words in comments Drop doubled word "the" in two comments. Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Jakub Kicinski --- include/linux/qed/qed_chain.h | 2 +- include/linux/qed/qed_if.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 92cdc79e5019..7071dc92b4e2 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -130,7 +130,7 @@ struct qed_chain { } pbl_sp; /* Address of first page of the chain - the address is required - * for fastpath operation [consume/produce] but only for the the SINGLE + * for fastpath operation [consume/produce] but only for the SINGLE * flavour which isn't considered fastpath [== SPQ]. */ void *p_virt_addr; diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 90e1060da02b..8a6e3ad436d1 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -498,7 +498,7 @@ struct qed_fcoe_pf_params { u8 bdq_pbl_num_entries[2]; }; -/* Most of the the parameters below are described in the FW iSCSI / TCP HSI */ +/* Most of the parameters below are described in the FW iSCSI / TCP HSI */ struct qed_iscsi_pf_params { u64 glbl_q_params_addr; u64 bdq_pbl_base_addr[3]; -- cgit v1.2.3 From 2ff17117e60572d6974c766d6b1a225ec7d68795 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 09:42:39 -0700 Subject: net: skbuff.h: drop duplicate words in comments Drop doubled words in several comments. Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0c0377fc00c2..6a82d4a8229e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1328,7 +1328,7 @@ void skb_flow_dissect_meta(const struct sk_buff *skb, void *target_container); /* Gets a skb connection tracking info, ctinfo map should be a - * a map of mapsize to translate enum ip_conntrack_info states + * map of mapsize to translate enum ip_conntrack_info states * to user states. */ void @@ -3812,7 +3812,7 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) * must call this function to return the skb back to the stack with a * timestamp. * - * @skb: clone of the the original outgoing packet + * @skb: clone of the original outgoing packet * @hwtstamps: hardware time stamps * */ -- cgit v1.2.3 From 158e89639166461e225a855bce6e3ee6cd8bb1c0 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 09:42:40 -0700 Subject: net: wimax: fix duplicate words in comments Drop doubled words in two comments. Fix a spello/typo. Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Jakub Kicinski --- include/linux/wimax/debug.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wimax/debug.h b/include/linux/wimax/debug.h index 4dd2c1cea6a9..cdae052bcdcd 100644 --- a/include/linux/wimax/debug.h +++ b/include/linux/wimax/debug.h @@ -184,8 +184,8 @@ do { \ /* - * CPP sintatic sugar to generate A_B like symbol names when one of - * the arguments is a a preprocessor #define. + * CPP syntactic sugar to generate A_B like symbol names when one of + * the arguments is a preprocessor #define. */ #define __D_PASTE__(varname, modulename) varname##_##modulename #define __D_PASTE(varname, modulename) (__D_PASTE__(varname, modulename)) -- cgit v1.2.3 From 59632b220f2d61df274ed3a14a204e941051fdad Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 09:42:46 -0700 Subject: net: ipv6: drop duplicate word in comment Drop the doubled word "by" in a comment. Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Jakub Kicinski --- include/linux/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 2cb445a8fc9e..8d8f877e7f81 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -223,7 +223,7 @@ struct ipv6_pinfo { /* * Packed in 16bits. - * Omit one shift by by putting the signed field at MSB. + * Omit one shift by putting the signed field at MSB. */ #if defined(__BIG_ENDIAN_BITFIELD) __s16 hop_limit:9; -- cgit v1.2.3 From 1dcb6c36a5ebac46099b6363ccf8f4e7563d51e2 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 14 Jul 2020 21:28:32 -0700 Subject: net/mlx5: Support setting access rights of dma addresses mlx5_fill_page_frag_array() is used to populate dma addresses to resources that require it, such as QPs, RQs etc. When the resource is used, PA list permissions are ignored. For resources that use MTT list, the user is required to provide the access rights. Subsequent patches use resources that require MTT lists, so modify API and implementation to support that. Signed-off-by: Eli Cohen Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 13c0e4556eda..f2557d7e1355 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -971,6 +971,7 @@ void mlx5_register_debugfs(void); void mlx5_unregister_debugfs(void); void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas); +void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm); void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, unsigned int *irqn); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3786888cb1ba..5890e5c9da77 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10653,4 +10653,10 @@ struct mlx5_ifc_tls_progress_params_bits { u8 hw_offset_record_number[0x18]; }; +enum { + MLX5_MTT_PERM_READ = 1 << 0, + MLX5_MTT_PERM_WRITE = 1 << 1, + MLX5_MTT_PERM_RW = MLX5_MTT_PERM_READ | MLX5_MTT_PERM_WRITE, +}; + #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From 2a913f23447ce7ef2a4dcaaa230ff43116cf5249 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 14 Jul 2020 21:28:33 -0700 Subject: net/mlx5: Add VDPA interface type to supported enumerations VDPA is a new interface that will be added in subsequent patches. It uses mlx5 core devices and resources. Add an interface type for it. Signed-off-by: Eli Cohen Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f2557d7e1355..5ecc48831ae8 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1054,6 +1054,7 @@ enum { enum { MLX5_INTERFACE_PROTOCOL_IB = 0, MLX5_INTERFACE_PROTOCOL_ETH = 1, + MLX5_INTERFACE_PROTOCOL_VDPA = 2, }; struct mlx5_interface { -- cgit v1.2.3 From 8a06a79b0aa811eee6d56b3cfc738c5d08b0dc74 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 14 Jul 2020 21:28:34 -0700 Subject: net/mlx5: Add interface changes required for VDPA Rename mlx5_ifc_device_virtio_emulation_cap_bits to mlx5_ifc_virtio_emulation_cap_bits to match names produced by the tools producing these auto generated files. In addition missing capabilities that will be required by VDPA implementation. Signed-off-by: Eli Cohen Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 4 +- include/linux/mlx5/mlx5_ifc.h | 112 ++++++++++++++++++++++++++++++++++++------ 2 files changed, 100 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 57db125e5802..2aacf9a8ee4d 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1361,11 +1361,11 @@ enum mlx5_qcam_feature_groups { MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca_cur[MLX5_CAP_DEV_EVENT], cap) #define MLX5_CAP_DEV_VDPA_EMULATION(mdev, cap)\ - MLX5_GET(device_virtio_emulation_cap, \ + MLX5_GET(virtio_emulation_cap, \ (mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap) #define MLX5_CAP64_DEV_VDPA_EMULATION(mdev, cap)\ - MLX5_GET64(device_virtio_emulation_cap, \ + MLX5_GET64(virtio_emulation_cap, \ (mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap) #define MLX5_CAP_IPSEC(mdev, cap)\ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5890e5c9da77..435ab47d5362 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -93,6 +93,7 @@ enum { enum { MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b, + MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d, MLX5_OBJ_TYPE_MKEY = 0xff01, MLX5_OBJ_TYPE_QP = 0xff02, MLX5_OBJ_TYPE_PSV = 0xff03, @@ -981,17 +982,40 @@ struct mlx5_ifc_device_event_cap_bits { u8 user_unaffiliated_events[4][0x40]; }; -struct mlx5_ifc_device_virtio_emulation_cap_bits { - u8 reserved_at_0[0x20]; +struct mlx5_ifc_virtio_emulation_cap_bits { + u8 desc_tunnel_offload_type[0x1]; + u8 eth_frame_offload_type[0x1]; + u8 virtio_version_1_0[0x1]; + u8 device_features_bits_mask[0xd]; + u8 event_mode[0x8]; + u8 virtio_queue_type[0x8]; - u8 reserved_at_20[0x13]; + u8 max_tunnel_desc[0x10]; + u8 reserved_at_30[0x3]; u8 log_doorbell_stride[0x5]; u8 reserved_at_38[0x3]; u8 log_doorbell_bar_size[0x5]; u8 doorbell_bar_offset[0x40]; - u8 reserved_at_80[0x780]; + u8 max_emulated_devices[0x8]; + u8 max_num_virtio_queues[0x18]; + + u8 reserved_at_a0[0x60]; + + u8 umem_1_buffer_param_a[0x20]; + + u8 umem_1_buffer_param_b[0x20]; + + u8 umem_2_buffer_param_a[0x20]; + + u8 umem_2_buffer_param_b[0x20]; + + u8 umem_3_buffer_param_a[0x20]; + + u8 umem_3_buffer_param_b[0x20]; + + u8 reserved_at_1c0[0x640]; }; enum { @@ -1216,7 +1240,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_sgl_for_optimized_performance[0x8]; u8 log_max_cq_sz[0x8]; - u8 reserved_at_d0[0xb]; + u8 reserved_at_d0[0x9]; + u8 virtio_net_device_emualtion_manager[0x1]; + u8 virtio_blk_device_emualtion_manager[0x1]; u8 log_max_cq[0x5]; u8 log_max_eq_sz[0x8]; @@ -2952,7 +2978,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_fpga_cap_bits fpga_cap; struct mlx5_ifc_tls_cap_bits tls_cap; struct mlx5_ifc_device_mem_cap_bits device_mem_cap; - struct mlx5_ifc_device_virtio_emulation_cap_bits virtio_emulation_cap; + struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap; u8 reserved_at_0[0x8000]; }; @@ -3298,15 +3324,18 @@ struct mlx5_ifc_scheduling_context_bits { }; struct mlx5_ifc_rqtc_bits { - u8 reserved_at_0[0xa0]; + u8 reserved_at_0[0xa0]; - u8 reserved_at_a0[0x10]; - u8 rqt_max_size[0x10]; + u8 reserved_at_a0[0x5]; + u8 list_q_type[0x3]; + u8 reserved_at_a8[0x8]; + u8 rqt_max_size[0x10]; - u8 reserved_at_c0[0x10]; - u8 rqt_actual_size[0x10]; + u8 rq_vhca_id_format[0x1]; + u8 reserved_at_c1[0xf]; + u8 rqt_actual_size[0x10]; - u8 reserved_at_e0[0x6a0]; + u8 reserved_at_e0[0x6a0]; struct mlx5_ifc_rq_num_bits rq_num[]; }; @@ -7084,7 +7113,7 @@ struct mlx5_ifc_destroy_mkey_out_bits { struct mlx5_ifc_destroy_mkey_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7782,7 +7811,7 @@ struct mlx5_ifc_create_mkey_out_bits { struct mlx5_ifc_create_mkey_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -10312,6 +10341,40 @@ struct mlx5_ifc_create_umem_in_bits { struct mlx5_ifc_umem_bits umem; }; +struct mlx5_ifc_create_umem_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x8]; + u8 umem_id[0x18]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_destroy_umem_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x8]; + u8 umem_id[0x18]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_destroy_umem_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_create_uctx_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; @@ -10324,6 +10387,18 @@ struct mlx5_ifc_create_uctx_in_bits { struct mlx5_ifc_uctx_bits uctx; }; +struct mlx5_ifc_create_uctx_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x10]; + u8 uid[0x10]; + + u8 reserved_at_60[0x20]; +}; + struct mlx5_ifc_destroy_uctx_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; @@ -10337,6 +10412,15 @@ struct mlx5_ifc_destroy_uctx_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_destroy_uctx_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_create_sw_icm_in_bits { struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; struct mlx5_ifc_sw_icm_bits sw_icm; -- cgit v1.2.3 From a5e6f964bb2c613933de58a35ddfa306128ba004 Mon Sep 17 00:00:00 2001 From: Misono Tomohiro Date: Fri, 10 Jul 2020 17:00:03 +0900 Subject: rtc: cleanup obsolete comment about struct rtc_class_ops Commit ea369ea6d828 ("rtc: remove .open() and .release()") removes open/release callback from struct rtc_class_ops. Also commit 80d4bb515b78 ("RTC: Cleanup rtc_class_ops->irq_set_state") and commit 696160fec162 ("RTC: Cleanup rtc_class_ops->irq_set_freq()") removes irq callbacks. So, just remove related comments so that readers will not be confused. Signed-off-by: Misono Tomohiro Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20200710080003.7986-1-misono.tomohiro@jp.fujitsu.com --- include/linux/rtc.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index bba3db3f7efa..22d1575e4991 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -55,10 +55,6 @@ extern struct class *rtc_class; * * The (current) exceptions are mostly filesystem hooks: * - the proc() hook for procfs - * - non-ioctl() chardev hooks: open(), release() - * - * REVISIT those periodic irq calls *do* have ops_lock when they're - * issued through ioctl() ... */ struct rtc_class_ops { int (*ioctl)(struct device *, unsigned int, unsigned long); -- cgit v1.2.3 From 2eb27c11937ee9984c04b75d213a737291c5f58c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 9 Jul 2020 23:20:39 -0700 Subject: crypto: algapi - add NEED_FALLBACK to INHERITED_FLAGS CRYPTO_ALG_NEED_FALLBACK is handled inconsistently. When it's requested to be clear, some templates propagate that request to child algorithms, while others don't. It's apparently desired for NEED_FALLBACK to be propagated, to avoid deadlocks where a module tries to load itself while it's being initialized, and to avoid unnecessarily complex fallback chains where we have e.g. cbc-aes-$driver falling back to cbc(aes-$driver) where aes-$driver itself falls back to aes-generic, instead of cbc-aes-$driver simply falling back to cbc(aes-generic). There have been a number of fixes to this effect: commit 89027579bc6c ("crypto: xts - Propagate NEED_FALLBACK bit") commit d2c2a85cfe82 ("crypto: ctr - Propagate NEED_FALLBACK bit") commit e6c2e65c70a6 ("crypto: cbc - Propagate NEED_FALLBACK bit") But it seems that other templates can have the same problems too. To avoid this whack-a-mole, just add NEED_FALLBACK to INHERITED_FLAGS so that it's always inherited. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/crypto.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 7cd2d00f0a05..f73f0b51e1cd 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -60,8 +60,8 @@ #define CRYPTO_ALG_ASYNC 0x00000080 /* - * Set this bit if and only if the algorithm requires another algorithm of - * the same type to handle corner cases. + * Set if the algorithm (or an algorithm which it uses) requires another + * algorithm of the same type to handle corner cases. */ #define CRYPTO_ALG_NEED_FALLBACK 0x00000100 -- cgit v1.2.3 From fbb6cda44190d72aa5199d728797aabc6d2ed816 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 9 Jul 2020 23:20:40 -0700 Subject: crypto: algapi - introduce the flag CRYPTO_ALG_ALLOCATES_MEMORY Introduce a new algorithm flag CRYPTO_ALG_ALLOCATES_MEMORY. If this flag is set, then the driver allocates memory in its request routine. Such drivers are not suitable for disk encryption because GFP_ATOMIC allocation can fail anytime (causing random I/O errors) and GFP_KERNEL allocation can recurse into the block layer, causing a deadlock. For now, this flag is only implemented for some algorithm types. We also assume some usage constraints for it to be meaningful, since there are lots of edge cases the crypto API allows (e.g., misaligned or fragmented scatterlists) that mean that nearly any crypto algorithm can allocate memory in some case. See the comment for details. Also add this flag to CRYPTO_ALG_INHERITED_FLAGS so that when a template is instantiated, this flag is set on the template instance if it is set on any algorithm the instance uses. Based on a patch by Mikulas Patocka (https://lore.kernel.org/r/alpine.LRH.2.02.2006301414580.30526@file01.intranet.prod.int.rdu2.redhat.com). Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/crypto.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index f73f0b51e1cd..ef90e07c9635 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -100,6 +100,38 @@ */ #define CRYPTO_NOLOAD 0x00008000 +/* + * The algorithm may allocate memory during request processing, i.e. during + * encryption, decryption, or hashing. Users can request an algorithm with this + * flag unset if they can't handle memory allocation failures. + * + * This flag is currently only implemented for algorithms of type "skcipher", + * "aead", "ahash", "shash", and "cipher". Algorithms of other types might not + * have this flag set even if they allocate memory. + * + * In some edge cases, algorithms can allocate memory regardless of this flag. + * To avoid these cases, users must obey the following usage constraints: + * skcipher: + * - The IV buffer and all scatterlist elements must be aligned to the + * algorithm's alignmask. + * - If the data were to be divided into chunks of size + * crypto_skcipher_walksize() (with any remainder going at the end), no + * chunk can cross a page boundary or a scatterlist element boundary. + * aead: + * - The IV buffer and all scatterlist elements must be aligned to the + * algorithm's alignmask. + * - The first scatterlist element must contain all the associated data, + * and its pages must be !PageHighMem. + * - If the plaintext/ciphertext were to be divided into chunks of size + * crypto_aead_walksize() (with the remainder going at the end), no chunk + * can cross a page boundary or a scatterlist element boundary. + * ahash: + * - The result buffer must be aligned to the algorithm's alignmask. + * - crypto_ahash_finup() must not be used unless the algorithm implements + * ->finup() natively. + */ +#define CRYPTO_ALG_ALLOCATES_MEMORY 0x00010000 + /* * Transform masks and values (for crt_flags). */ -- cgit v1.2.3 From c04011fe8cbd80af1be6e12b53193bf3846750d7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Jul 2020 08:47:43 +0200 Subject: fs: add a vfs_fchown helper Add a helper for struct file based chown operations. To be used by the initramfs code soon. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f5abba86107d..0ddd64ca0b45 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1744,6 +1744,8 @@ int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); +int vfs_fchown(struct file *file, uid_t user, gid_t group); + extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT -- cgit v1.2.3 From 9e96c8c0e94eea2f69a9705f5d0f51928ea26c17 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Jul 2020 08:55:05 +0200 Subject: fs: add a vfs_fchmod helper Add a helper for struct file based chmode operations. To be used by the initramfs code soon. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 0ddd64ca0b45..635086726f20 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1745,6 +1745,7 @@ int vfs_mkobj(struct dentry *, umode_t, void *); int vfs_fchown(struct file *file, uid_t user, gid_t group); +int vfs_fchmod(struct file *file, umode_t mode); extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); -- cgit v1.2.3 From 4f5b246b37e024955c0fcca0c7f5952089052d1d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 7 Jun 2020 16:18:59 +0200 Subject: md: move the early init autodetect code to drivers/md/ Just like the NFS and CIFS root code this better lives with the driver it is tightly integrated with. Signed-off-by: Christoph Hellwig Acked-by: Song Liu Acked-by: Linus Torvalds --- include/linux/raid/detect.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/detect.h b/include/linux/raid/detect.h index 37dd3f40cd31..1f029a71c3ef 100644 --- a/include/linux/raid/detect.h +++ b/include/linux/raid/detect.h @@ -1,3 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ void md_autodetect_dev(dev_t dev); + +#ifdef CONFIG_BLK_DEV_MD +void md_run_setup(void); +#else +static inline void md_run_setup(void) +{ +} +#endif -- cgit v1.2.3 From 1a6a050620e496abf42749a2e1d3882645cc053f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 7 Jun 2020 16:33:01 +0200 Subject: md: remove the kernel version of md_u.h mdp_major can just move to drivers/md/md.h. Signed-off-by: Christoph Hellwig Acked-by: Song Liu Acked-by: Linus Torvalds --- include/linux/raid/md_u.h | 13 ------------- 1 file changed, 13 deletions(-) delete mode 100644 include/linux/raid/md_u.h (limited to 'include/linux') diff --git a/include/linux/raid/md_u.h b/include/linux/raid/md_u.h deleted file mode 100644 index 8dfec085a20e..000000000000 --- a/include/linux/raid/md_u.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - md_u.h : user <=> kernel API between Linux raidtools and RAID drivers - Copyright (C) 1998 Ingo Molnar - -*/ -#ifndef _MD_U_H -#define _MD_U_H - -#include - -extern int mdp_major; -#endif -- cgit v1.2.3 From d3fa60d7bfdc9a0ff1a524bdef96b3db1fd62022 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Jul 2020 09:45:11 +0200 Subject: dma-mapping: move the remaining DMA API calls out of line For a long time the DMA API has been implemented inline in dma-mapping.h, but the function bodies can be quite large. Move them all out of line. This also removes all the dma_direct_* exports as those are just implementation details and should never be used by drivers directly. Signed-off-by: Christoph Hellwig Tested-by: Alexey Kardashevskiy Reviewed-by: Alexey Kardashevskiy --- include/linux/dma-direct.h | 58 +++++++++++ include/linux/dma-mapping.h | 247 ++++---------------------------------------- 2 files changed, 80 insertions(+), 225 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index ab2e20cba951..2b045c509146 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -87,4 +87,62 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long attrs); int dma_direct_supported(struct device *dev, u64 mask); bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr); +dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs); +int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, + enum dma_data_direction dir, unsigned long attrs); +dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir, unsigned long attrs); + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir); +void dma_direct_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); +#else +static inline void dma_direct_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_direct_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ +} +#endif + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ + defined(CONFIG_SWIOTLB) +void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs); +void dma_direct_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir); +void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); +#else +static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ +} +static inline void dma_direct_unmap_sg(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir, + unsigned long attrs) +{ +} +static inline void dma_direct_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ +} +#endif + +size_t dma_direct_max_mapping_size(struct device *dev); + #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index a33ed3954ed4..bd0a6f5ee445 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -188,73 +188,6 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, } #endif /* CONFIG_DMA_DECLARE_COHERENT */ -static inline bool dma_is_direct(const struct dma_map_ops *ops) -{ - return likely(!ops); -} - -/* - * All the dma_direct_* declarations are here just for the indirect call bypass, - * and must not be used directly drivers! - */ -dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs); -int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, - enum dma_data_direction dir, unsigned long attrs); -dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir, unsigned long attrs); - -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ - defined(CONFIG_SWIOTLB) -void dma_direct_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir); -void dma_direct_sync_sg_for_device(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir); -#else -static inline void dma_direct_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir) -{ -} -static inline void dma_direct_sync_sg_for_device(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir) -{ -} -#endif - -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ - defined(CONFIG_SWIOTLB) -void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir, unsigned long attrs); -void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, - int nents, enum dma_data_direction dir, unsigned long attrs); -void dma_direct_sync_single_for_cpu(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir); -void dma_direct_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir); -#else -static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ -} -static inline void dma_direct_unmap_sg(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir, - unsigned long attrs) -{ -} -static inline void dma_direct_sync_single_for_cpu(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir) -{ -} -static inline void dma_direct_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir) -{ -} -#endif - -size_t dma_direct_max_mapping_size(struct device *dev); - #ifdef CONFIG_HAS_DMA #include @@ -271,164 +204,6 @@ static inline void set_dma_ops(struct device *dev, dev->dma_ops = dma_ops; } -static inline dma_addr_t dma_map_page_attrs(struct device *dev, - struct page *page, size_t offset, size_t size, - enum dma_data_direction dir, unsigned long attrs) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - dma_addr_t addr; - - BUG_ON(!valid_dma_direction(dir)); - if (dma_is_direct(ops)) - addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); - else - addr = ops->map_page(dev, page, offset, size, dir, attrs); - debug_dma_map_page(dev, page, offset, size, dir, addr); - - return addr; -} - -static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - - BUG_ON(!valid_dma_direction(dir)); - if (dma_is_direct(ops)) - dma_direct_unmap_page(dev, addr, size, dir, attrs); - else if (ops->unmap_page) - ops->unmap_page(dev, addr, size, dir, attrs); - debug_dma_unmap_page(dev, addr, size, dir); -} - -/* - * dma_maps_sg_attrs returns 0 on error and > 0 on success. - * It should never return a value < 0. - */ -static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - unsigned long attrs) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - int ents; - - BUG_ON(!valid_dma_direction(dir)); - if (dma_is_direct(ops)) - ents = dma_direct_map_sg(dev, sg, nents, dir, attrs); - else - ents = ops->map_sg(dev, sg, nents, dir, attrs); - BUG_ON(ents < 0); - debug_dma_map_sg(dev, sg, nents, ents, dir); - - return ents; -} - -static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - unsigned long attrs) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - - BUG_ON(!valid_dma_direction(dir)); - debug_dma_unmap_sg(dev, sg, nents, dir); - if (dma_is_direct(ops)) - dma_direct_unmap_sg(dev, sg, nents, dir, attrs); - else if (ops->unmap_sg) - ops->unmap_sg(dev, sg, nents, dir, attrs); -} - -static inline dma_addr_t dma_map_resource(struct device *dev, - phys_addr_t phys_addr, - size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - dma_addr_t addr = DMA_MAPPING_ERROR; - - BUG_ON(!valid_dma_direction(dir)); - - /* Don't allow RAM to be mapped */ - if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr)))) - return DMA_MAPPING_ERROR; - - if (dma_is_direct(ops)) - addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs); - else if (ops->map_resource) - addr = ops->map_resource(dev, phys_addr, size, dir, attrs); - - debug_dma_map_resource(dev, phys_addr, size, dir, addr); - return addr; -} - -static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - - BUG_ON(!valid_dma_direction(dir)); - if (!dma_is_direct(ops) && ops->unmap_resource) - ops->unmap_resource(dev, addr, size, dir, attrs); - debug_dma_unmap_resource(dev, addr, size, dir); -} - -static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, - size_t size, - enum dma_data_direction dir) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - - BUG_ON(!valid_dma_direction(dir)); - if (dma_is_direct(ops)) - dma_direct_sync_single_for_cpu(dev, addr, size, dir); - else if (ops->sync_single_for_cpu) - ops->sync_single_for_cpu(dev, addr, size, dir); - debug_dma_sync_single_for_cpu(dev, addr, size, dir); -} - -static inline void dma_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, - enum dma_data_direction dir) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - - BUG_ON(!valid_dma_direction(dir)); - if (dma_is_direct(ops)) - dma_direct_sync_single_for_device(dev, addr, size, dir); - else if (ops->sync_single_for_device) - ops->sync_single_for_device(dev, addr, size, dir); - debug_dma_sync_single_for_device(dev, addr, size, dir); -} - -static inline void -dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - - BUG_ON(!valid_dma_direction(dir)); - if (dma_is_direct(ops)) - dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir); - else if (ops->sync_sg_for_cpu) - ops->sync_sg_for_cpu(dev, sg, nelems, dir); - debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir); -} - -static inline void -dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - - BUG_ON(!valid_dma_direction(dir)); - if (dma_is_direct(ops)) - dma_direct_sync_sg_for_device(dev, sg, nelems, dir); - else if (ops->sync_sg_for_device) - ops->sync_sg_for_device(dev, sg, nelems, dir); - debug_dma_sync_sg_for_device(dev, sg, nelems, dir); - -} static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { @@ -439,6 +214,28 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) return 0; } +dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, + size_t offset, size_t size, enum dma_data_direction dir, + unsigned long attrs); +void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir, unsigned long attrs); +int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, unsigned long attrs); +void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, + unsigned long attrs); +dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, + size_t size, enum dma_data_direction dir, unsigned long attrs); +void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir, unsigned long attrs); +void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir); +void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir); +void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir); +void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir); void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs); void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, -- cgit v1.2.3 From b4174173005972f8f6497883d08d87e0aba1b604 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Jul 2020 09:47:08 +0200 Subject: dma-mapping: inline the fast path dma-direct calls Inline the single page map/unmap/sync dma-direct calls into the now out of line generic wrappers. This restores the behavior of a single function call that we had before moving the generic calls out of line. Besides the dma-mapping callers there are just a few callers in IOMMU drivers that have a bypass mode, and more of those are going to be switched to the generic bypass soon. Signed-off-by: Christoph Hellwig Tested-by: Alexey Kardashevskiy Reviewed-by: Alexey Kardashevskiy --- include/linux/dma-direct.h | 92 ++++++++++++++++++++++++++++++++++------------ 1 file changed, 69 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 2b045c509146..5a3ce2a24794 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -1,10 +1,16 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Internals of the DMA direct mapping implementation. Only for use by the + * DMA mapping code and IOMMU drivers. + */ #ifndef _LINUX_DMA_DIRECT_H #define _LINUX_DMA_DIRECT_H 1 #include +#include #include /* for min_low_pfn */ #include +#include extern unsigned int zone_dma_bits; @@ -87,25 +93,17 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long attrs); int dma_direct_supported(struct device *dev, u64 mask); bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr); -dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs); int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs); dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir, unsigned long attrs); +size_t dma_direct_max_mapping_size(struct device *dev); #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_SWIOTLB) -void dma_direct_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir); -void dma_direct_sync_sg_for_device(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir); +void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir); #else -static inline void dma_direct_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir) -{ -} static inline void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { @@ -115,34 +113,82 @@ static inline void dma_direct_sync_sg_for_device(struct device *dev, #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ defined(CONFIG_SWIOTLB) -void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir, unsigned long attrs); void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs); -void dma_direct_sync_single_for_cpu(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir); void dma_direct_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir); #else -static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ -} static inline void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs) { } +static inline void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ +} +#endif + +static inline void dma_direct_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + phys_addr_t paddr = dma_to_phys(dev, addr); + + if (unlikely(is_swiotlb_buffer(paddr))) + swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE); + + if (!dev_is_dma_coherent(dev)) + arch_sync_dma_for_device(paddr, size, dir); +} + static inline void dma_direct_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { + phys_addr_t paddr = dma_to_phys(dev, addr); + + if (!dev_is_dma_coherent(dev)) { + arch_sync_dma_for_cpu(paddr, size, dir); + arch_sync_dma_for_cpu_all(); + } + + if (unlikely(is_swiotlb_buffer(paddr))) + swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); } -static inline void dma_direct_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir) + +static inline dma_addr_t dma_direct_map_page(struct device *dev, + struct page *page, unsigned long offset, size_t size, + enum dma_data_direction dir, unsigned long attrs) { + phys_addr_t phys = page_to_phys(page) + offset; + dma_addr_t dma_addr = phys_to_dma(dev, phys); + + if (unlikely(swiotlb_force == SWIOTLB_FORCE)) + return swiotlb_map(dev, phys, size, dir, attrs); + + if (unlikely(!dma_capable(dev, dma_addr, size, true))) { + if (swiotlb_force != SWIOTLB_NO_FORCE) + return swiotlb_map(dev, phys, size, dir, attrs); + + dev_WARN_ONCE(dev, 1, + "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); + return DMA_MAPPING_ERROR; + } + + if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(phys, size, dir); + return dma_addr; } -#endif -size_t dma_direct_max_mapping_size(struct device *dev); +static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + phys_addr_t phys = dma_to_phys(dev, addr); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_direct_sync_single_for_cpu(dev, addr, size, dir); + + if (unlikely(is_swiotlb_buffer(phys))) + swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs); +} #endif /* _LINUX_DMA_DIRECT_H */ -- cgit v1.2.3 From 9216477449f33cdbc9c9a99d49f500b7fbb81702 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 14 Jul 2020 15:56:38 +0200 Subject: bpf: cpumap: Add the possibility to attach an eBPF program to cpumap Introduce the capability to attach an eBPF program to cpumap entries. The idea behind this feature is to add the possibility to define on which CPU run the eBPF program if the underlying hw does not support RSS. Current supported verdicts are XDP_DROP and XDP_PASS. This patch has been tested on Marvell ESPRESSObin using xdp_redirect_cpu sample available in the kernel tree to identify possible performance regressions. Results show there are no observable differences in packet-per-second: $./xdp_redirect_cpu --progname xdp_cpu_map0 --dev eth0 --cpu 1 rx: 354.8 Kpps rx: 356.0 Kpps rx: 356.8 Kpps rx: 356.3 Kpps rx: 356.6 Kpps rx: 356.6 Kpps rx: 356.7 Kpps rx: 355.8 Kpps rx: 356.8 Kpps rx: 356.8 Kpps Co-developed-by: Jesper Dangaard Brouer Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/5c9febdf903d810b3415732e5cd98491d7d9067a.1594734381.git.lorenzo@kernel.org --- include/linux/bpf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c67c88ad35f8..54ad426dbea1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1272,6 +1272,7 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); void __cpu_map_flush(void); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); +bool cpu_map_prog_allowed(struct bpf_map *map); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) @@ -1432,6 +1433,11 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, return 0; } +static inline bool cpu_map_prog_allowed(struct bpf_map *map) +{ + return false; +} + static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { -- cgit v1.2.3 From ecbe6bc0003bfd5bf8581cb679cae0eb944432cb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Jul 2020 16:33:09 +0200 Subject: block: use bd_prepare_to_claim directly in the loop driver The arcane magic in bd_start_claiming is only needed to be able to claim a block_device that hasn't been fully set up. Switch the loop driver that claims from the ioctl path with a fully set up struct block_device to just use the much simpler bd_prepare_to_claim directly. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 71173a1ffa8b..06995b96e946 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1919,7 +1919,8 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); -struct block_device *bd_start_claiming(struct block_device *bdev, void *holder); +int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole, + void *holder); void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void *holder); void blkdev_put(struct block_device *bdev, fmode_t mode); -- cgit v1.2.3 From aecfd220b223043475fa515aa563249f683fcd04 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 3 Jun 2020 13:28:45 -0700 Subject: x86/mm/numa: Remove uninitialized_var() usage Using uninitialized_var() is dangerous as it papers over real bugs[1] (or can in the future), and suppresses unrelated compiler warnings (e.g. "unused variable"). If the compiler thinks it is uninitialized, either simply initialize the variable or make compiler changes. As a precursor to removing[2] this[3] macro[4], refactor code to avoid its need. The original reason for its use here was to work around the #ifdef being the only place the variable was used. This is better expressed using IS_ENABLED() and a new code block where the variable can be used unconditionally. [1] https://lore.kernel.org/lkml/20200603174714.192027-1-glider@google.com/ [2] https://lore.kernel.org/lkml/CA+55aFw+Vbj0i=1TGqCR5vQkCzWJ0QxK6CernOU6eedsudAixw@mail.gmail.com/ [3] https://lore.kernel.org/lkml/CA+55aFwgbgqhbp1fkxvRKEpzyR5J8n1vKT1VZdz9knmPuXhOeg@mail.gmail.com/ [4] https://lore.kernel.org/lkml/CA+55aFz2500WfbKXAx8s67wrm9=yVJu65TpLgN_ybYNv0VEOKA@mail.gmail.com/ Fixes: 1e01979c8f50 ("x86, numa: Implement pfn -> nid mapping granularity check") Signed-off-by: Kees Cook --- include/linux/page-flags-layout.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index 71283739ffd2..e200eef6a7fd 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -98,9 +98,11 @@ /* * We are going to use the flags for the page to node mapping if its in * there. This includes the case where there is no node, so it is implicit. + * Note that this #define MUST have a value so that it can be tested with + * the IS_ENABLED() macro. */ #if !(NODES_WIDTH > 0 || NODES_SHIFT == 0) -#define NODE_NOT_IN_PAGE_FLAGS +#define NODE_NOT_IN_PAGE_FLAGS 1 #endif #if defined(CONFIG_NUMA_BALANCING) && LAST_CPUPID_WIDTH == 0 -- cgit v1.2.3 From 63a0895d960aa3d3653ef0ecad5bd8579388f14b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 3 Jun 2020 13:09:38 -0700 Subject: compiler: Remove uninitialized_var() macro Using uninitialized_var() is dangerous as it papers over real bugs[1] (or can in the future), and suppresses unrelated compiler warnings (e.g. "unused variable"). If the compiler thinks it is uninitialized, either simply initialize the variable or make compiler changes. As recommended[2] by[3] Linus[4], remove the macro. With the recent change to disable -Wmaybe-uninitialized in v5.7 in commit 78a5255ffb6a ("Stop the ad-hoc games with -Wno-maybe-initialized"), this is likely the best time to make this treewide change. [1] https://lore.kernel.org/lkml/20200603174714.192027-1-glider@google.com/ [2] https://lore.kernel.org/lkml/CA+55aFw+Vbj0i=1TGqCR5vQkCzWJ0QxK6CernOU6eedsudAixw@mail.gmail.com/ [3] https://lore.kernel.org/lkml/CA+55aFwgbgqhbp1fkxvRKEpzyR5J8n1vKT1VZdz9knmPuXhOeg@mail.gmail.com/ [4] https://lore.kernel.org/lkml/CA+55aFz2500WfbKXAx8s67wrm9=yVJu65TpLgN_ybYNv0VEOKA@mail.gmail.com/ Suggested-by: Linus Torvalds Reviewed-by: Bart van Assche Reviewed-by: Miguel Ojeda Tested-by: Nathan Chancellor Tested-by: Sedat Dilek Signed-off-by: Kees Cook --- include/linux/compiler-clang.h | 2 -- include/linux/compiler-gcc.h | 6 ------ 2 files changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 5e55302e3bf6..8a072d00e688 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -5,8 +5,6 @@ /* Compiler specific definitions for Clang compiler */ -#define uninitialized_var(x) x = *(&(x)) - /* same as gcc, this was present in clang-2.6 so we can assume it works * with any version that can compile the kernel */ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 1c74464c80c6..4099ac8b7f10 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -59,12 +59,6 @@ (typeof(ptr)) (__ptr + (off)); \ }) -/* - * A trick to suppress uninitialized variable warning without generating any - * code - */ -#define uninitialized_var(x) x = x - #ifdef CONFIG_RETPOLINE #define __noretpoline __attribute__((__indirect_branch__("keep"))) #endif -- cgit v1.2.3 From 5be542e945cb39a2457aa2cfe8b84aac95ef0f2d Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 16 Jul 2020 16:36:50 +1000 Subject: lockdep: Move list.h inclusion into lockdep.h Currently lockdep_types.h includes list.h without actually using any of its macros or functions. All it needs are the type definitions which were moved into types.h long ago. This potentially causes inclusion loops because both are included by many core header files. This patch moves the list.h inclusion into lockdep.h. Note that we could probably remove it completely but that could potentially result in compile failures should any end users not include list.h directly and also be unlucky enough to not get list.h via some other header file. Reported-by: Petr Mladek Signed-off-by: Herbert Xu Signed-off-by: Peter Zijlstra (Intel) Tested-by: Petr Mladek Link: https://lkml.kernel.org/r/20200716063649.GA23065@gondor.apana.org.au --- include/linux/lockdep.h | 1 + include/linux/lockdep_types.h | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index fd04b9e96091..7aafba0ddcf9 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -22,6 +22,7 @@ extern int lock_stat; #ifdef CONFIG_LOCKDEP #include +#include #include #include diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index 7b9350624577..bb35b449f533 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -32,8 +32,6 @@ enum lockdep_wait_type { #ifdef CONFIG_LOCKDEP -#include - /* * We'd rather not expose kernel/lockdep_states.h this wide, but we do need * the total number of states... :-( -- cgit v1.2.3 From a9232dc5607dbada801f2fe83ea307cda762969a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sat, 11 Jul 2020 17:59:54 +0300 Subject: rwsem: fix commas in initialisation Leading comma prevents arbitrary reordering of initialisation clauses. The whole point of C99 initialisation is to allow any such reordering. Signed-off-by: Alexey Dobriyan Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200711145954.GA1178171@localhost.localdomain --- include/linux/rwsem.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 7e5b2a4eb560..25e3fde85617 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -60,39 +60,39 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem) } #define RWSEM_UNLOCKED_VALUE 0L -#define __RWSEM_INIT_COUNT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) +#define __RWSEM_COUNT_INIT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) /* Common initializer macros and functions */ #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __RWSEM_DEP_MAP_INIT(lockname) \ - , .dep_map = { \ + .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_SLEEP, \ - } + }, #else # define __RWSEM_DEP_MAP_INIT(lockname) #endif #ifdef CONFIG_DEBUG_RWSEMS -# define __DEBUG_RWSEM_INITIALIZER(lockname) , .magic = &lockname +# define __RWSEM_DEBUG_INIT(lockname) .magic = &lockname, #else -# define __DEBUG_RWSEM_INITIALIZER(lockname) +# define __RWSEM_DEBUG_INIT(lockname) #endif #ifdef CONFIG_RWSEM_SPIN_ON_OWNER -#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED +#define __RWSEM_OPT_INIT(lockname) .osq = OSQ_LOCK_UNLOCKED, #else #define __RWSEM_OPT_INIT(lockname) #endif #define __RWSEM_INITIALIZER(name) \ - { __RWSEM_INIT_COUNT(name), \ + { __RWSEM_COUNT_INIT(name), \ .owner = ATOMIC_LONG_INIT(0), \ - .wait_list = LIST_HEAD_INIT((name).wait_list), \ - .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock) \ __RWSEM_OPT_INIT(name) \ - __DEBUG_RWSEM_INITIALIZER(name) \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),\ + .wait_list = LIST_HEAD_INIT((name).wait_list), \ + __RWSEM_DEBUG_INIT(name) \ __RWSEM_DEP_MAP_INIT(name) } #define DECLARE_RWSEM(name) \ -- cgit v1.2.3 From 6611561a7a7ef925294353a4c2124bdb66eb831c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 18:30:12 -0700 Subject: regmap: fix duplicated word in Change doubled word "be" to "to be". Signed-off-by: Randy Dunlap Cc: Mark Brown Link: https://lore.kernel.org/r/7ef41bfc-de3e-073a-8746-0b3fdf7628c0@infradead.org Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index e3817c097791..1970ed59d49f 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -275,7 +275,7 @@ typedef void (*regmap_unlock)(void *); * readable if it belongs to one of the ranges specified * by rd_noinc_table). * @disable_locking: This regmap is either protected by external means or - * is guaranteed not be be accessed from multiple threads. + * is guaranteed not to be accessed from multiple threads. * Don't use any locking mechanisms. * @lock: Optional lock callback (overrides regmap's default lock * function, based on spinlock or mutex). -- cgit v1.2.3 From a98bcaa92d3d7a7753e23b3363d90ffdb82e8edb Mon Sep 17 00:00:00 2001 From: Colton Lewis Date: Wed, 15 Jul 2020 19:15:00 +0000 Subject: regulator: Correct kernel-doc inconsistency Silence documentation build warning by correcting kernel-doc comments. ./include/linux/regulator/machine.h:196: warning: Function parameter or member 'max_uV_step' not described in 'regulation_constraints' ./include/linux/regulator/driver.h:206: warning: Function parameter or member 'resume' not described in 'regulator_ops' Signed-off-by: Colton Lewis Link: https://lore.kernel.org/r/20200715191438.29312-1-colton.w.lewis@protonmail.com Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 +- include/linux/regulator/machine.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 436df3ba0b2a..8539f34ae42b 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -117,7 +117,7 @@ enum regulator_status { * suspended. * @set_suspend_mode: Set the operating mode for the regulator when the * system is suspended. - * + * @resume: Resume operation of suspended regulator. * @set_pull_down: Configure the regulator to pull down when the regulator * is disabled. * diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index a84cc8879c3e..8a56f033b6cd 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -101,6 +101,7 @@ struct regulator_state { * @system_load: Load that isn't captured by any consumer requests. * * @max_spread: Max possible spread between coupled regulators + * @max_uV_step: Max possible step change in voltage * @valid_modes_mask: Mask of modes which may be configured by consumers. * @valid_ops_mask: Operations which may be performed by consumers. * -- cgit v1.2.3 From 9a6ad1ad71fbc5a52617e016a3608d71b91f62e8 Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Mon, 18 Nov 2019 14:30:20 +0200 Subject: net/mlx5: Accel, Add core IPsec support for the Connect-X family This to set the base for downstream patches to support the new IPsec implementation of the Connect-X family. Following modifications made: - Remove accel layer dependency from MLX5_FPGA_IPSEC. - Introduce accel_ipsec_ops, each IPsec device will have to support these ops. Signed-off-by: Raed Salem Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/accel.h | 6 +++--- include/linux/mlx5/driver.h | 3 +++ 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 96ebaa94a92e..dacf69516002 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -126,7 +126,7 @@ enum mlx5_accel_ipsec_cap { MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN = 1 << 7, }; -#ifdef CONFIG_MLX5_FPGA_IPSEC +#ifdef CONFIG_MLX5_ACCEL u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev); @@ -152,5 +152,5 @@ static inline int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, const struct mlx5_accel_esp_xfrm_attrs *attrs) { return -EOPNOTSUPP; } -#endif -#endif +#endif /* CONFIG_MLX5_ACCEL */ +#endif /* __MLX5_ACCEL_H__ */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1e6ca716635a..6a97ad601991 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -707,6 +707,9 @@ struct mlx5_core_dev { } roce; #ifdef CONFIG_MLX5_FPGA struct mlx5_fpga_device *fpga; +#endif +#ifdef CONFIG_MLX5_ACCEL + const struct mlx5_accel_ipsec_ops *ipsec_ops; #endif struct mlx5_clock clock; struct mlx5_ib_clock_info *clock_info; -- cgit v1.2.3 From 78fb6122fa2b6b55fafee1b32cd94913ad72f8a4 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Wed, 8 Apr 2020 20:09:05 -0500 Subject: net/mlx5: Add IPsec related Flow steering entry's fields Add FTE actions IPsec ENCRYPT/DECRYPT Add ipsec_obj_id field in FTE Add new action field MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME Signed-off-by: Huy Nguyen Reviewed-by: Raed Salem Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 5 ++++- include/linux/mlx5/mlx5_ifc.h | 12 ++++++++++-- 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 6c5aa0a21425..92d991d93757 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -207,7 +207,10 @@ struct mlx5_flow_act { u32 action; struct mlx5_modify_hdr *modify_hdr; struct mlx5_pkt_reformat *pkt_reformat; - uintptr_t esp_id; + union { + u32 ipsec_obj_id; + uintptr_t esp_id; + }; u32 flags; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 791766e15d5c..9e64710bc54f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -416,7 +416,11 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 table_miss_action_domain[0x1]; u8 termination_table[0x1]; u8 reformat_and_fwd_to_table[0x1]; - u8 reserved_at_1a[0x6]; + u8 reserved_at_1a[0x2]; + u8 ipsec_encrypt[0x1]; + u8 ipsec_decrypt[0x1]; + u8 reserved_at_1e[0x2]; + u8 termination_table_raw_traffic[0x1]; u8 reserved_at_21[0x1]; u8 log_max_ft_size[0x6]; @@ -2965,6 +2969,8 @@ enum { MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH = 0x100, MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2 = 0x400, MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800, + MLX5_FLOW_CONTEXT_ACTION_IPSEC_DECRYPT = 0x1000, + MLX5_FLOW_CONTEXT_ACTION_IPSEC_ENCRYPT = 0x2000, }; enum { @@ -3006,7 +3012,8 @@ struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_vlan_bits push_vlan_2; - u8 reserved_at_120[0xe0]; + u8 ipsec_obj_id[0x20]; + u8 reserved_at_140[0xc0]; struct mlx5_ifc_fte_match_param_bits match_value; @@ -5752,6 +5759,7 @@ enum { MLX5_ACTION_IN_FIELD_METADATA_REG_C_7 = 0x58, MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM = 0x59, MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM = 0x5B, + MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME = 0x5D, }; struct mlx5_ifc_alloc_modify_header_context_out_bits { -- cgit v1.2.3 From 2ae3de10abfe0be40c9d93ebc2f429b969abf008 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 18:30:48 -0700 Subject: spi: fix duplicated word in Change doubled word "as" to "as a". Change "Return: Return:" in kernel-doc notation to have only one "Return:". Signed-off-by: Randy Dunlap Cc: Mark Brown Cc: linux-spi@vger.kernel.org Link: https://lore.kernel.org/r/40354d64-be71-3952-a980-63a76a278145@infradead.org Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 5fcf5da13fdb..f8b721fcd5c6 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -971,7 +971,7 @@ struct spi_transfer { * each represented by a struct spi_transfer. The sequence is "atomic" * in the sense that no other spi_message may use that SPI bus until that * sequence completes. On some systems, many such sequences can execute as - * as single programmed DMA transfer. On all systems, these messages are + * a single programmed DMA transfer. On all systems, these messages are * queued, and might complete after transactions to other devices. Messages * sent to a given spi_device are always executed in FIFO order. * @@ -1234,7 +1234,7 @@ extern int spi_bus_unlock(struct spi_controller *ctlr); * * For more specific semantics see spi_sync(). * - * Return: Return: zero on success, else a negative error code. + * Return: zero on success, else a negative error code. */ static inline int spi_sync_transfer(struct spi_device *spi, struct spi_transfer *xfers, -- cgit v1.2.3 From e2e5c55eed8023ecfbf4c9b623ef7dec343d1845 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 13:50:27 -0600 Subject: remoteproc: Add new RPROC_DETACHED state Add a new RPROC_DETACHED state to take into account scenarios where the remoteproc core needs to attach to a remote processor that is booted by another entity. Signed-off-by: Mathieu Poirier Reviewed-by: Bjorn Andersson Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714195035.1426873-2-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index e7b7bab8b235..21182ad2d059 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -400,6 +400,8 @@ struct rproc_ops { * @RPROC_RUNNING: device is up and running * @RPROC_CRASHED: device has crashed; need to start recovery * @RPROC_DELETED: device is deleted + * @RPROC_DETACHED: device has been booted by another entity and waiting + * for the core to attach to it * @RPROC_LAST: just keep this one at the end * * Please note that the values of these states are used as indices @@ -414,7 +416,8 @@ enum rproc_state { RPROC_RUNNING = 2, RPROC_CRASHED = 3, RPROC_DELETED = 4, - RPROC_LAST = 5, + RPROC_DETACHED = 5, + RPROC_LAST = 6, }; /** -- cgit v1.2.3 From a6a4f2857524007848f7957af432cddb4d43b593 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 13:50:28 -0600 Subject: remoteproc: Add new attach() remoteproc operation Add an new attach() operation in order to properly deal with scenarios where the remoteproc core needs to attach to a remote processor that has been booted by another entity. Signed-off-by: Mathieu Poirier Reviewed-by: Bjorn Andersson Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714195035.1426873-3-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 21182ad2d059..bf6a310ba870 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -359,6 +359,7 @@ enum rsc_handling_status { * @unprepare: unprepare device after stop * @start: power on the device and boot it * @stop: power off the device + * @attach: attach to a device that his already powered up * @kick: kick a virtqueue (virtqueue id given as a parameter) * @da_to_va: optional platform hook to perform address translations * @parse_fw: parse firmware to extract information (e.g. resource table) @@ -379,6 +380,7 @@ struct rproc_ops { int (*unprepare)(struct rproc *rproc); int (*start)(struct rproc *rproc); int (*stop)(struct rproc *rproc); + int (*attach)(struct rproc *rproc); void (*kick)(struct rproc *rproc, int vqid); void * (*da_to_va)(struct rproc *rproc, u64 da, size_t len); int (*parse_fw)(struct rproc *rproc, const struct firmware *fw); -- cgit v1.2.3 From 4a4dca1941fedc1b02635ff0b4ed51b9857d0382 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 13:50:35 -0600 Subject: remoteproc: Properly handle firmware name when attaching This patch prevents the firmware image name from being displayed when the remoteproc core is attaching to a remote processor. This is needed needed since there is no guarantee about the nature of the firmware image that is loaded by the external entity. Signed-off-by: Mathieu Poirier Reviewed-by: Arnaud Pouliquen Reviewed-by: Bjorn Andersson Tested-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20200714195035.1426873-10-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index bf6a310ba870..cf5e31556780 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -491,6 +491,7 @@ struct rproc_dump_segment { * @table_sz: size of @cached_table * @has_iommu: flag to indicate if remote processor is behind an MMU * @auto_boot: flag to indicate if remote processor should be auto-started + * @autonomous: true if an external entity has booted the remote processor * @dump_segments: list of segments in the firmware * @nb_vdev: number of vdev currently handled by rproc */ @@ -524,6 +525,7 @@ struct rproc { size_t table_sz; bool has_iommu; bool auto_boot; + bool autonomous; struct list_head dump_segments; int nb_vdev; u8 elf_class; -- cgit v1.2.3 From 9c8ebd8b82da89c2484594b61d66288d24983348 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 17 Jul 2020 04:33:34 +0300 Subject: dmaengine: Add support for repeating transactions DMA engines used with displays perform 2D interleaved transfers to read framebuffers from memory and feed the data to the display engine. As the same framebuffer can be displayed for multiple frames, the DMA transactions need to be repeated until a new framebuffer replaces the current one. This feature is implemented natively by some DMA engines that have the ability to repeat transactions and switch to a new transaction at the end of a transfer without any race condition or frame loss. This patch implements support for this feature in the DMA engine API. A new DMA_PREP_REPEAT transaction flag allows DMA clients to instruct the DMA channel to repeat the transaction automatically until one or more new transactions are issued on the channel (or until all active DMA transfers are explicitly terminated with the dmaengine_terminate_*() functions). A new DMA_REPEAT transaction type is also added for DMA engine drivers to report their support of the DMA_PREP_REPEAT flag. A new DMA_PREP_LOAD_EOT transaction flag is also introduced (with a corresponding DMA_LOAD_EOT capability bit), as requested during the review of v4. The flag instructs the DMA channel that the transaction being queued should replace the active repeated transaction when the latter terminates (at End Of Transaction). Not setting the flag will result in the active repeated transaction to continue being repeated, and the new transaction being silently ignored. The DMA_PREP_REPEAT flag is currently supported for interleaved transactions only. Its usage can easily be extended to cover more transaction types simply by adding an appropriate check in the corresponding dmaengine_prep_*() function. Signed-off-by: Laurent Pinchart Reviewed-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20200717013337.24122-3-laurent.pinchart@ideasonboard.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index e1c03339918f..328e3aca7f51 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -61,6 +61,8 @@ enum dma_transaction_type { DMA_SLAVE, DMA_CYCLIC, DMA_INTERLEAVE, + DMA_REPEAT, + DMA_LOAD_EOT, /* last transaction type for creation of the capabilities mask */ DMA_TX_TYPE_END, }; @@ -176,6 +178,16 @@ struct dma_interleaved_template { * @DMA_PREP_CMD: tell the driver that the data passed to DMA API is command * data and the descriptor should be in different format from normal * data descriptors. + * @DMA_PREP_REPEAT: tell the driver that the transaction shall be automatically + * repeated when it ends until a transaction is issued on the same channel + * with the DMA_PREP_LOAD_EOT flag set. This flag is only applicable to + * interleaved transactions and is ignored for all other transaction types. + * @DMA_PREP_LOAD_EOT: tell the driver that the transaction shall replace any + * active repeated (as indicated by DMA_PREP_REPEAT) transaction when the + * repeated transaction ends. Not setting this flag when the previously queued + * transaction is marked with DMA_PREP_REPEAT will cause the new transaction + * to never be processed and stay in the issued queue forever. The flag is + * ignored if the previous transaction is not a repeated transaction. */ enum dma_ctrl_flags { DMA_PREP_INTERRUPT = (1 << 0), @@ -186,6 +198,8 @@ enum dma_ctrl_flags { DMA_PREP_FENCE = (1 << 5), DMA_CTRL_REUSE = (1 << 6), DMA_PREP_CMD = (1 << 7), + DMA_PREP_REPEAT = (1 << 8), + DMA_PREP_LOAD_EOT = (1 << 9), }; /** @@ -980,6 +994,9 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma( { if (!chan || !chan->device || !chan->device->device_prep_interleaved_dma) return NULL; + if (flags & DMA_PREP_REPEAT && + !test_bit(DMA_REPEAT, chan->device->cap_mask.bits)) + return NULL; return chan->device->device_prep_interleaved_dma(chan, xt, flags); } -- cgit v1.2.3 From ecdef9f459ad24bf987267df6c25967819016707 Mon Sep 17 00:00:00 2001 From: Coly Li Date: Fri, 17 Jul 2020 10:42:29 +0800 Subject: block: change REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL to be odd numbers Currently REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL are defined as even numbers 6 and 8, such zone reset bios are treated as READ bios by bio_data_dir(), which is obviously misleading. The macro bio_data_dir() is defined in include/linux/bio.h as, 55 #define bio_data_dir(bio) \ 56 (op_is_write(bio_op(bio)) ? WRITE : READ) And op_is_write() is defined in include/linux/blk_types.h as, 397 static inline bool op_is_write(unsigned int op) 398 { 399 return (op & 1); 400 } The convention of op_is_write() is when there is data transfer then the op code should be odd number, and treat as a write op. bio_data_dir() treats all bio direction as READ if op_is_write() reports false, and WRITE if op_is_write() reports true. Because REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL are even numbers, although they don't transfer data but reporting them as READ bio by bio_data_dir() is misleading and might be wrong. Because these two commands will reset the writer pointers of the resetting zones, and all content after the reset write pointer will be invalid and unaccessible, obviously they are not READ bios in any means. This patch changes REQ_OP_ZONE_RESET from 6 to 15, and changes REQ_OP_ZONE_RESET_ALL from 8 to 17. Now bios with these two op code can be treated as WRITE by bio_data_dir(). Although they don't transfer data, now we keep them consistent with REQ_OP_DISCARD and REQ_OP_WRITE_ZEROES with the ituition that they change on-media content and should be WRITE request. Signed-off-by: Coly Li Reviewed-by: Damien Le Moal Reviewed-by: Chaitanya Kulkarni Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Jens Axboe Cc: Johannes Thumshirn Cc: Keith Busch Cc: Shaun Tancheff Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 07facaf62b72..4ecf4fed171f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -327,12 +327,8 @@ enum req_opf { REQ_OP_DISCARD = 3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, - /* reset a zone write pointer */ - REQ_OP_ZONE_RESET = 6, /* write the same sector many times */ REQ_OP_WRITE_SAME = 7, - /* reset all the zone present on the device */ - REQ_OP_ZONE_RESET_ALL = 8, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = 9, /* Open a zone */ @@ -343,6 +339,10 @@ enum req_opf { REQ_OP_ZONE_FINISH = 12, /* write data at the current zone write pointer */ REQ_OP_ZONE_APPEND = 13, + /* reset a zone write pointer */ + REQ_OP_ZONE_RESET = 15, + /* reset all the zone present on the device */ + REQ_OP_ZONE_RESET_ALL = 17, /* SCSI passthrough using struct scsi_request */ REQ_OP_SCSI_IN = 32, -- cgit v1.2.3 From 767598d447aa46411289c5808b0e45e20a1823b4 Mon Sep 17 00:00:00 2001 From: Sowjanya Komatineni Date: Tue, 14 Jul 2020 21:20:51 -0700 Subject: gpu: host1x: mipi: Update tegra_mipi_request() to be node based Tegra CSI driver need a separate MIPI device for each channel as calibration of corresponding MIPI pads for each channel should happen independently. So, this patch updates tegra_mipi_request() API to add a device_node pointer argument to allow creating mipi device for specific device node rather than a device. Signed-off-by: Sowjanya Komatineni Signed-off-by: Thierry Reding --- include/linux/host1x.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index a3a568bf9686..9e678412778c 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -328,7 +328,8 @@ int host1x_client_resume(struct host1x_client *client); struct tegra_mipi_device; -struct tegra_mipi_device *tegra_mipi_request(struct device *device); +struct tegra_mipi_device *tegra_mipi_request(struct device *device, + struct device_node *np); void tegra_mipi_free(struct tegra_mipi_device *device); int tegra_mipi_enable(struct tegra_mipi_device *device); int tegra_mipi_disable(struct tegra_mipi_device *device); -- cgit v1.2.3 From b3f1b760710f2acfc04abefc09358c26a75e7e89 Mon Sep 17 00:00:00 2001 From: Sowjanya Komatineni Date: Tue, 14 Jul 2020 21:20:53 -0700 Subject: gpu: host1x: mipi: Split tegra_mipi_calibrate() and tegra_mipi_wait() SW can trigger MIPI pads calibration any time after power on but calibration results will be latched and applied to the pads by MIPI CAL unit only when the link is in LP-11 state and then status register will be updated. For CSI, trigger of pads calibration happen during CSI stream enable where CSI receiver is kept ready prior to sensor or CSI transmitter stream start. So, pads may not be in LP-11 at this time and waiting for the calibration to be done immediate after calibration start will result in timeout. This patch splits tegra_mipi_calibrate() and tegra_mipi_wait() so triggering for calibration and waiting for it to complete can happen at different stages. Signed-off-by: Sowjanya Komatineni Signed-off-by: Thierry Reding --- include/linux/host1x.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 9e678412778c..20c885d0bddc 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -334,5 +334,6 @@ void tegra_mipi_free(struct tegra_mipi_device *device); int tegra_mipi_enable(struct tegra_mipi_device *device); int tegra_mipi_disable(struct tegra_mipi_device *device); int tegra_mipi_calibrate(struct tegra_mipi_device *device); +int tegra_mipi_wait(struct tegra_mipi_device *device); #endif -- cgit v1.2.3 From ab91e7a6da7eeb8aa54843748652c186daee43eb Mon Sep 17 00:00:00 2001 From: He Zhe Date: Mon, 6 Jul 2020 17:52:24 +0800 Subject: freezer: Add unsafe versions of freezable_schedule_timeout_interruptible for NFS commit 0688e64bc600 ("NFS: Allow signal interruption of NFS4ERR_DELAYed operations") introduces nfs4_delay_interruptible which also needs an _unsafe version to avoid the following call trace for the same reason explained in commit 416ad3c9c006 ("freezer: add unsafe versions of freezable helpers for NFS") CPU: 4 PID: 3968 Comm: rm Tainted: G W 5.8.0-rc4 #1 Hardware name: Marvell OcteonTX CN96XX board (DT) Call trace: dump_backtrace+0x0/0x1dc show_stack+0x20/0x30 dump_stack+0xdc/0x150 debug_check_no_locks_held+0x98/0xa0 nfs4_delay_interruptible+0xd8/0x120 nfs4_handle_exception+0x130/0x170 nfs4_proc_rmdir+0x8c/0x220 nfs_rmdir+0xa4/0x360 vfs_rmdir.part.0+0x6c/0x1b0 do_rmdir+0x18c/0x210 __arm64_sys_unlinkat+0x64/0x7c el0_svc_common.constprop.0+0x7c/0x110 do_el0_svc+0x24/0xa0 el0_sync_handler+0x13c/0x1b8 el0_sync+0x158/0x180 Signed-off-by: He Zhe Signed-off-by: Trond Myklebust --- include/linux/freezer.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 21f5aa0b217f..27828145ca09 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -207,6 +207,17 @@ static inline long freezable_schedule_timeout_interruptible(long timeout) return __retval; } +/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ +static inline long freezable_schedule_timeout_interruptible_unsafe(long timeout) +{ + long __retval; + + freezer_do_not_count(); + __retval = schedule_timeout_interruptible(timeout); + freezer_count_unsafe(); + return __retval; +} + /* Like schedule_timeout_killable(), but should not block the freezer. */ static inline long freezable_schedule_timeout_killable(long timeout) { @@ -285,6 +296,9 @@ static inline void set_freezable(void) {} #define freezable_schedule_timeout_interruptible(timeout) \ schedule_timeout_interruptible(timeout) +#define freezable_schedule_timeout_interruptible_unsafe(timeout) \ + schedule_timeout_interruptible(timeout) + #define freezable_schedule_timeout_killable(timeout) \ schedule_timeout_killable(timeout) -- cgit v1.2.3 From e506addeff844237d60545ef4f6141de21471caf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Miguel=20Rodr=C3=ADguez=20P=C3=A9rez?= Date: Wed, 15 Jul 2020 20:40:57 +0200 Subject: net: cdc_ether: export usbnet_cdc_update_filter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This makes the function available to other drivers, like cdc_ncm. Signed-off-by: Miguel Rodríguez Pérez Acked-by: Oliver Neukum Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index b0bff3083278..3a856963a363 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -207,6 +207,7 @@ struct cdc_state { struct usb_interface *data; }; +extern void usbnet_cdc_update_filter(struct usbnet *dev); extern int usbnet_generic_cdc_bind(struct usbnet *, struct usb_interface *); extern int usbnet_ether_cdc_bind(struct usbnet *dev, struct usb_interface *intf); extern int usbnet_cdc_bind(struct usbnet *, struct usb_interface *); -- cgit v1.2.3 From 1ea2b748b5eb4f9b6c8f66d098f1277afb724336 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Wed, 15 Jul 2020 20:40:58 +0200 Subject: net: usbnet: export usbnet_set_rx_mode() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function can be reused by other usbnet minidrivers. Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 3a856963a363..2e4f7721fc4e 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -274,6 +274,7 @@ extern int usbnet_set_link_ksettings(struct net_device *net, extern u32 usbnet_get_link(struct net_device *net); extern u32 usbnet_get_msglevel(struct net_device *); extern void usbnet_set_msglevel(struct net_device *, u32); +extern void usbnet_set_rx_mode(struct net_device *net); extern void usbnet_get_drvinfo(struct net_device *, struct ethtool_drvinfo *); extern int usbnet_nway_reset(struct net_device *net); -- cgit v1.2.3 From d9473cbfb0c5cbb279dfdeaec780934729537d27 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Tue, 14 Jul 2020 14:04:41 -0600 Subject: remoteproc: Make function rproc_resource_cleanup() public Make function rproc_resource_cleanup() public so that it can be used by platform drivers when allocating resources to be used by a detached remote processor. Acked-by: Arnaud Pouliquen Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200714200445.1427257-8-mathieu.poirier@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index cf5e31556780..7c0567029f7c 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -610,6 +610,7 @@ void rproc_put(struct rproc *rproc); int rproc_add(struct rproc *rproc); int rproc_del(struct rproc *rproc); void rproc_free(struct rproc *rproc); +void rproc_resource_cleanup(struct rproc *rproc); struct rproc *devm_rproc_alloc(struct device *dev, const char *name, const struct rproc_ops *ops, -- cgit v1.2.3 From 7f5f81406e2b36785f1e25fe5209edd9dd3610d7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 17 Jul 2020 16:37:25 -0700 Subject: rhashtable: drop duplicated word in Drop the doubled word "be" in a comment. Signed-off-by: Randy Dunlap Cc: Thomas Graf Cc: Herbert Xu Cc: netdev@vger.kernel.org Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 70ebef866cc8..d3432ee65de7 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -33,7 +33,7 @@ * of two or more hash tables when the rhashtable is being resized. * The end of the chain is marked with a special nulls marks which has * the least significant bit set but otherwise stores the address of - * the hash bucket. This allows us to be be sure we've found the end + * the hash bucket. This allows us to be sure we've found the end * of the right list. * The value stored in the hash bucket has BIT(0) used as a lock bit. * This bit must be atomically set before any changes are made to -- cgit v1.2.3 From ef45fe470e1e5410db4af87abc5d5055427945ac Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Mon, 1 Jun 2020 13:12:05 -0700 Subject: blk-cgroup: show global disk stats in root cgroup io.stat In order to improve consistency and usability in cgroup stat accounting, we would like to support the root cgroup's io.stat. Since the root cgroup has processes doing io even if the system has no explicitly created cgroups, we need to be careful to avoid overhead in that case. For that reason, the rstat algorithms don't handle the root cgroup, so just turning the file on wouldn't give correct statistics. To get around this, we simulate flushing the iostat struct by filling it out directly from global disk stats. The result is a root cgroup io.stat file consistent with both /proc/diskstats and io.stat. Note that in order to collect the disk stats, we needed to iterate over devices. To facilitate that, we had to change the linkage of a disk_type to external so that it can be used from blk-cgroup.c to iterate over disks. Suggested-by: Tejun Heo Signed-off-by: Boris Burkov Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 31a54072ffd6..4ab853461dff 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -24,6 +24,7 @@ #define disk_to_dev(disk) (&(disk)->part0.__dev) #define part_to_dev(part) (&((part)->__dev)) +extern const struct device_type disk_type; extern struct device_type part_type; extern struct class block_class; -- cgit v1.2.3 From ce3aa9cc5109363099b7c4ac82e2c9768afcaf31 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 17 Jul 2020 12:35:22 +0200 Subject: bpf, netns: Handle multiple link attachments Extend the BPF netns link callbacks to rebuild (grow/shrink) or update the prog_array at given position when link gets attached/updated/released. This let's us lift the limit of having just one link attached for the new attach type introduced by subsequent patch. No functional changes intended. Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200717103536.397595-2-jakub@cloudflare.com --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 54ad426dbea1..c8c9eabcd106 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -928,6 +928,9 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, void bpf_prog_array_delete_safe(struct bpf_prog_array *progs, struct bpf_prog *old_prog); +int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index); +int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, + struct bpf_prog *prog); int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt); -- cgit v1.2.3 From e9ddbb7707ff5891616240026062b8c1e29864ca Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 17 Jul 2020 12:35:23 +0200 Subject: bpf: Introduce SK_LOOKUP program type with a dedicated attach point Add a new program type BPF_PROG_TYPE_SK_LOOKUP with a dedicated attach type BPF_SK_LOOKUP. The new program kind is to be invoked by the transport layer when looking up a listening socket for a new connection request for connection oriented protocols, or when looking up an unconnected socket for a packet for connection-less protocols. When called, SK_LOOKUP BPF program can select a socket that will receive the packet. This serves as a mechanism to overcome the limits of what bind() API allows to express. Two use-cases driving this work are: (1) steer packets destined to an IP range, on fixed port to a socket 192.0.2.0/24, port 80 -> NGINX socket (2) steer packets destined to an IP address, on any port to a socket 198.51.100.1, any port -> L7 proxy socket In its run-time context program receives information about the packet that triggered the socket lookup. Namely IP version, L4 protocol identifier, and address 4-tuple. Context can be further extended to include ingress interface identifier. To select a socket BPF program fetches it from a map holding socket references, like SOCKMAP or SOCKHASH, and calls bpf_sk_assign(ctx, sk, ...) helper to record the selection. Transport layer then uses the selected socket as a result of socket lookup. In its basic form, SK_LOOKUP acts as a filter and hence must return either SK_PASS or SK_DROP. If the program returns with SK_PASS, transport should look for a socket to receive the packet, or use the one selected by the program if available, while SK_DROP informs the transport layer that the lookup should fail. This patch only enables the user to attach an SK_LOOKUP program to a network namespace. Subsequent patches hook it up to run on local delivery path in ipv4 and ipv6 stacks. Suggested-by: Marek Majkowski Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200717103536.397595-3-jakub@cloudflare.com --- include/linux/bpf-netns.h | 3 +++ include/linux/bpf.h | 1 + include/linux/bpf_types.h | 2 ++ include/linux/filter.h | 17 +++++++++++++++++ 4 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h index 47d5b0c708c9..722f799c1a2e 100644 --- a/include/linux/bpf-netns.h +++ b/include/linux/bpf-netns.h @@ -8,6 +8,7 @@ enum netns_bpf_attach_type { NETNS_BPF_INVALID = -1, NETNS_BPF_FLOW_DISSECTOR = 0, + NETNS_BPF_SK_LOOKUP, MAX_NETNS_BPF_ATTACH_TYPE }; @@ -17,6 +18,8 @@ to_netns_bpf_attach_type(enum bpf_attach_type attach_type) switch (attach_type) { case BPF_FLOW_DISSECTOR: return NETNS_BPF_FLOW_DISSECTOR; + case BPF_SK_LOOKUP: + return NETNS_BPF_SK_LOOKUP; default: return NETNS_BPF_INVALID; } diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c8c9eabcd106..adb16bdc5f0a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -249,6 +249,7 @@ enum bpf_arg_type { ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ + ARG_PTR_TO_SOCKET_OR_NULL, /* pointer to bpf_sock (fullsock) or NULL */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index a18ae82a298a..a52a5688418e 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -64,6 +64,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2, #ifdef CONFIG_INET BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport, struct sk_reuseport_md, struct sk_reuseport_kern) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_LOOKUP, sk_lookup, + struct bpf_sk_lookup, struct bpf_sk_lookup_kern) #endif #if defined(CONFIG_BPF_JIT) BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops, diff --git a/include/linux/filter.h b/include/linux/filter.h index 0b0144752d78..fa1ea12ad2cd 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1278,4 +1278,21 @@ struct bpf_sockopt_kern { s32 retval; }; +struct bpf_sk_lookup_kern { + u16 family; + u16 protocol; + struct { + __be32 saddr; + __be32 daddr; + } v4; + struct { + const struct in6_addr *saddr; + const struct in6_addr *daddr; + } v6; + __be16 sport; + u16 dport; + struct sock *selected_sk; + bool no_reuseport; +}; + #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From 1559b4aa1db443096af493c7d621dc156054babe Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 17 Jul 2020 12:35:25 +0200 Subject: inet: Run SK_LOOKUP BPF program on socket lookup Run a BPF program before looking up a listening socket on the receive path. Program selects a listening socket to yield as result of socket lookup by calling bpf_sk_assign() helper and returning SK_PASS code. Program can revert its decision by assigning a NULL socket with bpf_sk_assign(). Alternatively, BPF program can also fail the lookup by returning with SK_DROP, or let the lookup continue as usual with SK_PASS on return, when no socket has been selected with bpf_sk_assign(). This lets the user match packets with listening sockets freely at the last possible point on the receive path, where we know that packets are destined for local delivery after undergoing policing, filtering, and routing. With BPF code selecting the socket, directing packets destined to an IP range or to a port range to a single socket becomes possible. In case multiple programs are attached, they are run in series in the order in which they were attached. The end result is determined from return codes of all the programs according to following rules: 1. If any program returned SK_PASS and selected a valid socket, the socket is used as result of socket lookup. 2. If more than one program returned SK_PASS and selected a socket, last selection takes effect. 3. If any program returned SK_DROP, and no program returned SK_PASS and selected a socket, socket lookup fails with -ECONNREFUSED. 4. If all programs returned SK_PASS and none of them selected a socket, socket lookup continues to htable-based lookup. Suggested-by: Marek Majkowski Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200717103536.397595-5-jakub@cloudflare.com --- include/linux/filter.h | 91 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 91 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index fa1ea12ad2cd..c4f54c216347 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1295,4 +1295,95 @@ struct bpf_sk_lookup_kern { bool no_reuseport; }; +extern struct static_key_false bpf_sk_lookup_enabled; + +/* Runners for BPF_SK_LOOKUP programs to invoke on socket lookup. + * + * Allowed return values for a BPF SK_LOOKUP program are SK_PASS and + * SK_DROP. Their meaning is as follows: + * + * SK_PASS && ctx.selected_sk != NULL: use selected_sk as lookup result + * SK_PASS && ctx.selected_sk == NULL: continue to htable-based socket lookup + * SK_DROP : terminate lookup with -ECONNREFUSED + * + * This macro aggregates return values and selected sockets from + * multiple BPF programs according to following rules in order: + * + * 1. If any program returned SK_PASS and a non-NULL ctx.selected_sk, + * macro result is SK_PASS and last ctx.selected_sk is used. + * 2. If any program returned SK_DROP return value, + * macro result is SK_DROP. + * 3. Otherwise result is SK_PASS and ctx.selected_sk is NULL. + * + * Caller must ensure that the prog array is non-NULL, and that the + * array as well as the programs it contains remain valid. + */ +#define BPF_PROG_SK_LOOKUP_RUN_ARRAY(array, ctx, func) \ + ({ \ + struct bpf_sk_lookup_kern *_ctx = &(ctx); \ + struct bpf_prog_array_item *_item; \ + struct sock *_selected_sk = NULL; \ + bool _no_reuseport = false; \ + struct bpf_prog *_prog; \ + bool _all_pass = true; \ + u32 _ret; \ + \ + migrate_disable(); \ + _item = &(array)->items[0]; \ + while ((_prog = READ_ONCE(_item->prog))) { \ + /* restore most recent selection */ \ + _ctx->selected_sk = _selected_sk; \ + _ctx->no_reuseport = _no_reuseport; \ + \ + _ret = func(_prog, _ctx); \ + if (_ret == SK_PASS && _ctx->selected_sk) { \ + /* remember last non-NULL socket */ \ + _selected_sk = _ctx->selected_sk; \ + _no_reuseport = _ctx->no_reuseport; \ + } else if (_ret == SK_DROP && _all_pass) { \ + _all_pass = false; \ + } \ + _item++; \ + } \ + _ctx->selected_sk = _selected_sk; \ + _ctx->no_reuseport = _no_reuseport; \ + migrate_enable(); \ + _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ + }) + +static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, + const __be32 saddr, const __be16 sport, + const __be32 daddr, const u16 dport, + struct sock **psk) +{ + struct bpf_prog_array *run_array; + struct sock *selected_sk = NULL; + bool no_reuseport = false; + + rcu_read_lock(); + run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); + if (run_array) { + struct bpf_sk_lookup_kern ctx = { + .family = AF_INET, + .protocol = protocol, + .v4.saddr = saddr, + .v4.daddr = daddr, + .sport = sport, + .dport = dport, + }; + u32 act; + + act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN); + if (act == SK_PASS) { + selected_sk = ctx.selected_sk; + no_reuseport = ctx.no_reuseport; + } else { + selected_sk = ERR_PTR(-ECONNREFUSED); + } + } + rcu_read_unlock(); + *psk = selected_sk; + return no_reuseport; +} + #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From 1122702f02678597c4f1c7d316365ef502aafe08 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 17 Jul 2020 12:35:27 +0200 Subject: inet6: Run SK_LOOKUP BPF program on socket lookup Following ipv4 stack changes, run a BPF program attached to netns before looking up a listening socket. Program can return a listening socket to use as result of socket lookup, fail the lookup, or take no action. Suggested-by: Marek Majkowski Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200717103536.397595-7-jakub@cloudflare.com --- include/linux/filter.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index c4f54c216347..8252572db918 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1386,4 +1386,43 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, return no_reuseport; } +#if IS_ENABLED(CONFIG_IPV6) +static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, + const struct in6_addr *saddr, + const __be16 sport, + const struct in6_addr *daddr, + const u16 dport, + struct sock **psk) +{ + struct bpf_prog_array *run_array; + struct sock *selected_sk = NULL; + bool no_reuseport = false; + + rcu_read_lock(); + run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); + if (run_array) { + struct bpf_sk_lookup_kern ctx = { + .family = AF_INET6, + .protocol = protocol, + .v6.saddr = saddr, + .v6.daddr = daddr, + .sport = sport, + .dport = dport, + }; + u32 act; + + act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN); + if (act == SK_PASS) { + selected_sk = ctx.selected_sk; + no_reuseport = ctx.no_reuseport; + } else { + selected_sk = ERR_PTR(-ECONNREFUSED); + } + } + rcu_read_unlock(); + *psk = selected_sk; + return no_reuseport; +} +#endif /* IS_ENABLED(CONFIG_IPV6) */ + #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From 2be90e914c12bdea70b0bd297d5715ee66eb46d0 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 17 Jul 2020 19:51:18 -0700 Subject: dmaengine: linux/dmaengine.h: drop duplicated word in a comment Drop the doubled word "has" in a comment. Signed-off-by: Randy Dunlap Cc: Vinod Koul Cc: dmaengine@vger.kernel.org Link: https://lore.kernel.org/r/06e64046-ebf1-15db-dbaf-73698de3b493@infradead.org Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 9f9a13a2c01f..883e1e087de5 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -164,7 +164,7 @@ struct dma_interleaved_template { * @DMA_PREP_INTERRUPT - trigger an interrupt (callback) upon completion of * this transaction * @DMA_CTRL_ACK - if clear, the descriptor cannot be reused until the client - * acknowledges receipt, i.e. has has a chance to establish any dependency + * acknowledges receipt, i.e. has a chance to establish any dependency * chains * @DMA_PREP_PQ_DISABLE_P - prevent generation of P while generating Q * @DMA_PREP_PQ_DISABLE_Q - prevent generation of Q while generating P -- cgit v1.2.3 From 2f9237d4f6df49b74c51cdac555b0a9979d0c237 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Jul 2020 09:30:00 +0200 Subject: dma-mapping: make support for dma ops optional Avoid the overhead of the dma ops support for tiny builds that only use the direct mapping. Signed-off-by: Christoph Hellwig Tested-by: Alexey Kardashevskiy Reviewed-by: Alexey Kardashevskiy --- include/linux/device.h | 3 ++- include/linux/dma-mapping.h | 12 +++++++++++- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 15460a5ac024..4c4af98321eb 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -568,8 +568,9 @@ struct device { #ifdef CONFIG_GENERIC_MSI_IRQ struct list_head msi_list; #endif - +#ifdef CONFIG_DMA_OPS const struct dma_map_ops *dma_ops; +#endif u64 *dma_mask; /* dma mask (if dma'able device) */ u64 coherent_dma_mask;/* Like dma_mask, but for alloc_coherent mappings as diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index bd0a6f5ee445..39da883c8619 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -191,6 +191,7 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, #ifdef CONFIG_HAS_DMA #include +#ifdef CONFIG_DMA_OPS static inline const struct dma_map_ops *get_dma_ops(struct device *dev) { if (dev->dma_ops) @@ -203,7 +204,16 @@ static inline void set_dma_ops(struct device *dev, { dev->dma_ops = dma_ops; } - +#else /* CONFIG_DMA_OPS */ +static inline const struct dma_map_ops *get_dma_ops(struct device *dev) +{ + return NULL; +} +static inline void set_dma_ops(struct device *dev, + const struct dma_map_ops *dma_ops) +{ +} +#endif /* CONFIG_DMA_OPS */ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { -- cgit v1.2.3 From d35834c64820c7ef397f8a244061d4450720540e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 23 Mar 2020 18:19:30 +0100 Subject: dma-mapping: add a dma_ops_bypass flag to struct device Several IOMMU drivers have a bypass mode where they can use a direct mapping if the devices DMA mask is large enough. Add generic support to the core dma-mapping code to do that to switch those drivers to a common solution. Signed-off-by: Christoph Hellwig Tested-by: Alexey Kardashevskiy Reviewed-by: Alexey Kardashevskiy --- include/linux/device.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 4c4af98321eb..1f71acf37f78 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -523,6 +523,11 @@ struct dev_links_info { * sync_state() callback. * @dma_coherent: this particular device is dma coherent, even if the * architecture supports non-coherent devices. + * @dma_ops_bypass: If set to %true then the dma_ops are bypassed for the + * streaming DMA operations (->map_* / ->unmap_* / ->sync_*), + * and optionall (if the coherent mask is large enough) also + * for dma allocations. This flag is managed by the dma ops + * instance from ->dma_supported. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -623,6 +628,9 @@ struct device { defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) bool dma_coherent:1; #endif +#ifdef CONFIG_DMA_OPS_BYPASS + bool dma_ops_bypass : 1; +#endif }; static inline struct device *kobj_to_dev(struct kobject *kobj) -- cgit v1.2.3 From 35694afc92646ac24d7f3ef34a7387876d998fe7 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 1 Jul 2020 08:21:37 +0200 Subject: media: device property: Add a function to test is a fwnode is a graph endpoint MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drivers may need to test if a fwnode is a graph endpoint. To avoid hand-written solutions that wouldn't work for all fwnode types, add a new fwnode_graph_is_endpoint() function for this purpose. We don't need to wire it up to different backends for OF and ACPI for now, as the implementation can simply be based on checkout the presence of a remote-endpoint property. Signed-off-by: Laurent Pinchart Reviewed-by: Niklas Söderlund Reviewed-by: Lad Prabhakar Reviewed-by: Kieran Bingham Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/linux/property.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 10d03572f52e..9f805c442819 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -389,6 +389,11 @@ struct fwnode_handle * fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port, u32 endpoint); +static inline bool fwnode_graph_is_endpoint(struct fwnode_handle *fwnode) +{ + return fwnode_property_present(fwnode, "remote-endpoint"); +} + /* * Fwnode lookup flags * -- cgit v1.2.3 From 124ea650d3072b005457faed69909221c2905a1f Mon Sep 17 00:00:00 2001 From: Adrian Reber Date: Sun, 19 Jul 2020 12:04:11 +0200 Subject: capabilities: Introduce CAP_CHECKPOINT_RESTORE This patch introduces CAP_CHECKPOINT_RESTORE, a new capability facilitating checkpoint/restore for non-root users. Over the last years, The CRIU (Checkpoint/Restore In Userspace) team has been asked numerous times if it is possible to checkpoint/restore a process as non-root. The answer usually was: 'almost'. The main blocker to restore a process as non-root was to control the PID of the restored process. This feature available via the clone3 system call, or via /proc/sys/kernel/ns_last_pid is unfortunately guarded by CAP_SYS_ADMIN. In the past two years, requests for non-root checkpoint/restore have increased due to the following use cases: * Checkpoint/Restore in an HPC environment in combination with a resource manager distributing jobs where users are always running as non-root. There is a desire to provide a way to checkpoint and restore long running jobs. * Container migration as non-root * We have been in contact with JVM developers who are integrating CRIU into a Java VM to decrease the startup time. These checkpoint/restore applications are not meant to be running with CAP_SYS_ADMIN. We have seen the following workarounds: * Use a setuid wrapper around CRIU: See https://github.com/FredHutch/slurm-examples/blob/master/checkpointer/lib/checkpointer/checkpointer-suid.c * Use a setuid helper that writes to ns_last_pid. Unfortunately, this helper delegation technique is impossible to use with clone3, and is thus prone to races. See https://github.com/twosigma/set_ns_last_pid * Cycle through PIDs with fork() until the desired PID is reached: This has been demonstrated to work with cycling rates of 100,000 PIDs/s See https://github.com/twosigma/set_ns_last_pid * Patch out the CAP_SYS_ADMIN check from the kernel * Run the desired application in a new user and PID namespace to provide a local CAP_SYS_ADMIN for controlling PIDs. This technique has limited use in typical container environments (e.g., Kubernetes) as /proc is typically protected with read-only layers (e.g., /proc/sys) for hardening purposes. Read-only layers prevent additional /proc mounts (due to proc's SB_I_USERNS_VISIBLE property), making the use of new PID namespaces limited as certain applications need access to /proc matching their PID namespace. The introduced capability allows to: * Control PIDs when the current user is CAP_CHECKPOINT_RESTORE capable for the corresponding PID namespace via ns_last_pid/clone3. * Open files in /proc/pid/map_files when the current user is CAP_CHECKPOINT_RESTORE capable in the root namespace, useful for recovering files that are unreachable via the file system such as deleted files, or memfd files. See corresponding selftest for an example with clone3(). Signed-off-by: Adrian Reber Signed-off-by: Nicolas Viennot Reviewed-by: Serge Hallyn Acked-by: Christian Brauner Link: https://lore.kernel.org/r/20200719100418.2112740-2-areber@redhat.com Signed-off-by: Christian Brauner --- include/linux/capability.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index b4345b38a6be..1e7fe311cabe 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -261,6 +261,12 @@ static inline bool bpf_capable(void) return capable(CAP_BPF) || capable(CAP_SYS_ADMIN); } +static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns) +{ + return ns_capable(ns, CAP_CHECKPOINT_RESTORE) || + ns_capable(ns, CAP_SYS_ADMIN); +} + /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); -- cgit v1.2.3 From a4872f7a4bc16d6ed831833b4f1ec16df642c367 Mon Sep 17 00:00:00 2001 From: Tim Harvey Date: Tue, 9 Jun 2020 07:57:20 -0700 Subject: hwmon: (gsc) add 16bit pre-scaled voltage mode add a 16-bit pre-scaled voltage mode to adc and clarify that existing pre-scaled mode is 24bit. Signed-off-by: Tim Harvey Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/1591714640-10332-3-git-send-email-tharvey@gateworks.com Signed-off-by: Guenter Roeck --- include/linux/platform_data/gsc_hwmon.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gsc_hwmon.h b/include/linux/platform_data/gsc_hwmon.h index ec1611aff863..37a8f554da00 100644 --- a/include/linux/platform_data/gsc_hwmon.h +++ b/include/linux/platform_data/gsc_hwmon.h @@ -4,8 +4,9 @@ enum gsc_hwmon_mode { mode_temperature, - mode_voltage, + mode_voltage_24bit, mode_voltage_raw, + mode_voltage_16bit, mode_max, }; -- cgit v1.2.3 From a06d30ae7af492497ffbca6abf1621d508b8fcaa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:10 +0200 Subject: net/atm: remove the atmdev_ops {get, set}sockopt methods All implementations of these two methods are dummies that always return -EINVAL. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/atmdev.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 8124815eb121..5d5ff2203fa2 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -176,11 +176,6 @@ struct atm_dev { #define ATM_OF_IMMED 1 /* Attempt immediate delivery */ #define ATM_OF_INRATE 2 /* Attempt in-rate delivery */ - -/* - * ioctl, getsockopt, and setsockopt are optional and can be set to NULL. - */ - struct atmdev_ops { /* only send is required */ void (*dev_close)(struct atm_dev *dev); int (*open)(struct atm_vcc *vcc); @@ -190,10 +185,6 @@ struct atmdev_ops { /* only send is required */ int (*compat_ioctl)(struct atm_dev *dev,unsigned int cmd, void __user *arg); #endif - int (*getsockopt)(struct atm_vcc *vcc,int level,int optname, - void __user *optval,int optlen); - int (*setsockopt)(struct atm_vcc *vcc,int level,int optname, - void __user *optval,unsigned int optlen); int (*send)(struct atm_vcc *vcc,struct sk_buff *skb); int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags); void (*phy_put)(struct atm_dev *dev,unsigned char value, -- cgit v1.2.3 From 4d295e54611509854a12c26f95a6f4430731d614 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:13 +0200 Subject: net: simplify cBPF setsockopt compat handling Add a helper that copies either a native or compat bpf_fprog from userspace after verifying the length, and remove the compat setsockopt handlers that now aren't required. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/filter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 0b0144752d78..4d049c8e1fbe 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -502,13 +502,11 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) offsetof(TYPE, MEMBER); \ }) -#ifdef CONFIG_COMPAT /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { u16 len; compat_uptr_t filter; /* struct sock_filter * */ }; -#endif struct sock_fprog_kern { u16 len; @@ -1278,4 +1276,6 @@ struct bpf_sockopt_kern { s32 retval; }; +int copy_bpf_fprog_from_user(struct sock_fprog *dst, void __user *src, int len); + #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From 8c918ffbbad49454ed26c53eb1b90bf98bb5e394 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:14 +0200 Subject: net: remove compat_sock_common_{get,set}sockopt Add the compat handling to sock_common_{get,set}sockopt instead, keyed of in_compat_syscall(). This allow to remove the now unused ->compat_{get,set}sockopt methods from struct proto_ops. Signed-off-by: Christoph Hellwig Acked-by: Matthieu Baerts Acked-by: Stefan Schmidt Signed-off-by: David S. Miller --- include/linux/net.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 016a9c5faa34..858ff1d98154 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -165,12 +165,6 @@ struct proto_ops { int optname, char __user *optval, unsigned int optlen); int (*getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); -#ifdef CONFIG_COMPAT - int (*compat_setsockopt)(struct socket *sock, int level, - int optname, char __user *optval, unsigned int optlen); - int (*compat_getsockopt)(struct socket *sock, int level, - int optname, char __user *optval, int __user *optlen); -#endif void (*show_fdinfo)(struct seq_file *m, struct socket *sock); int (*sendmsg) (struct socket *sock, struct msghdr *m, size_t total_len); -- cgit v1.2.3 From 55db9c0e853421fa71cac5e6855898601f78a1f5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:15 +0200 Subject: net: remove compat_sys_{get,set}sockopt Now that the ->compat_{get,set}sockopt proto_ops methods are gone there is no good reason left to keep the compat syscalls separate. This fixes the odd use of unsigned int for the compat_setsockopt optlen and the missing sock_use_custom_sol_socket. It would also easily allow running the eBPF hooks for the compat syscalls, but such a large change in behavior does not belong into a consolidation patch like this one. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/compat.h | 4 ---- include/linux/syscalls.h | 4 ++++ 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index e90100c0de72..c4255d8a4a8a 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -737,10 +737,6 @@ asmlinkage long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg); asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, compat_size_t len, unsigned flags, struct sockaddr __user *addr, int __user *addrlen); -asmlinkage long compat_sys_setsockopt(int fd, int level, int optname, - char __user *optval, unsigned int optlen); -asmlinkage long compat_sys_getsockopt(int fd, int level, int optname, - char __user *optval, int __user *optlen); asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags); asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b951a87da987..aa46825c6f9d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1424,4 +1424,8 @@ long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems, unsigned int nsops, const struct old_timespec32 __user *timeout); +int __sys_getsockopt(int fd, int level, int optname, char __user *optval, + int __user *optlen); +int __sys_setsockopt(int fd, int level, int optname, char __user *optval, + int optlen); #endif -- cgit v1.2.3 From 77d4df41d53e5c2af14db26f20fe50da52e382ba Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:20 +0200 Subject: netfilter: remove the compat_{get,set} methods All instances handle compat sockopts via in_compat_syscall() now, so remove the compat_{get,set} methods as well as the compat_nf_{get,set}sockopt wrappers. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/netfilter.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index eb312e7ca36e..711b4d4486f0 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -164,17 +164,9 @@ struct nf_sockopt_ops { int set_optmin; int set_optmax; int (*set)(struct sock *sk, int optval, void __user *user, unsigned int len); -#ifdef CONFIG_COMPAT - int (*compat_set)(struct sock *sk, int optval, - void __user *user, unsigned int len); -#endif int get_optmin; int get_optmax; int (*get)(struct sock *sk, int optval, void __user *user, int *len); -#ifdef CONFIG_COMPAT - int (*compat_get)(struct sock *sk, int optval, - void __user *user, int *len); -#endif /* Use the module struct to lock set/get code in place */ struct module *owner; }; @@ -350,12 +342,6 @@ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, unsigned int len); int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); -#ifdef CONFIG_COMPAT -int compat_nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, - char __user *opt, unsigned int len); -int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, - char __user *opt, int *len); -#endif struct flowi; struct nf_queue_entry; -- cgit v1.2.3 From c34bc10d2535719ddf77d44ee849f6c7589583ba Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:21 +0200 Subject: netfilter: remove the compat argument to xt_copy_counters_from_user Lift the in_compat_syscall() from the callers instead. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 5da88451853b..b8b943ee7b8b 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -302,7 +302,7 @@ int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size); void *xt_copy_counters_from_user(const void __user *user, unsigned int len, - struct xt_counters_info *info, bool compat); + struct xt_counters_info *info); struct xt_counters *xt_counters_alloc(unsigned int counters); struct xt_table *xt_register_table(struct net *net, -- cgit v1.2.3 From eba75c587e811d3249c8bd50d22bb2266ccd3c0f Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 10 Jul 2020 09:29:02 -0400 Subject: icmp: support rfc 4884 Add setsockopt SOL_IP/IP_RECVERR_4884 to return the offset to an extension struct if present. ICMP messages may include an extension structure after the original datagram. RFC 4884 standardized this behavior. It stores the offset in words to the extension header in u8 icmphdr.un.reserved[1]. The field is valid only for ICMP types destination unreachable, time exceeded and parameter problem, if length is at least 128 bytes and entire packet does not exceed 576 bytes. Return the offset to the start of the extension struct when reading an ICMP error from the error queue, if it matches the above constraints. Do not return the raw u8 field. Return the offset from the start of the user buffer, in bytes. The kernel does not return the network and transport headers, so subtract those. Also validate the headers. Return the offset regardless of validation, as an invalid extension must still not be misinterpreted as part of the original datagram. Note that !invalid does not imply valid. If the extension version does not match, no validation can take place, for instance. For backward compatibility, make this optional, set by setsockopt SOL_IP/IP_RECVERR_RFC4884. For API example and feature test, see github.com/wdebruij/kerneltools/blob/master/tests/recv_icmp_v2.c For forward compatibility, reserve only setsockopt value 1, leaving other bits for additional icmp extensions. Changes v1->v2: - convert word offset to byte offset from start of user buffer - return in ee_data as u8 may be insufficient - define extension struct and object header structs - return len only if constraints met - if returning len, also validate Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/icmp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/icmp.h b/include/linux/icmp.h index 81ca84ce3119..8fc38a34cb20 100644 --- a/include/linux/icmp.h +++ b/include/linux/icmp.h @@ -15,6 +15,7 @@ #include #include +#include static inline struct icmphdr *icmp_hdr(const struct sk_buff *skb) { @@ -35,4 +36,7 @@ static inline bool icmp_is_err(int type) return false; } +void ip_icmp_error_rfc4884(const struct sk_buff *skb, + struct sock_ee_data_rfc4884 *out); + #endif /* _LINUX_ICMP_H */ -- cgit v1.2.3 From c6a8b84da4c28bda61b842a089651c3ec9d89a48 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 17 Jul 2020 16:36:50 -0700 Subject: modules: linux/moduleparam.h: drop duplicated word in a comment Drop the doubled word "the" in a comment. Signed-off-by: Randy Dunlap Cc: Jessica Yu Signed-off-by: Jessica Yu --- include/linux/moduleparam.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 3ef917ff0964..1ad5aa3b86d9 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -108,7 +108,7 @@ struct kparam_array * ".") the kernel commandline parameter. Note that - is changed to _, so * the user can use "foo-bar=1" even for variable "foo_bar". * - * @perm is 0 if the the variable is not to appear in sysfs, or 0444 + * @perm is 0 if the variable is not to appear in sysfs, or 0444 * for world-readable, 0644 for root-writable, etc. Note that if it * is writable, you may need to use kernel_param_lock() around * accesses (esp. charp, which can be kfreed when it changes). -- cgit v1.2.3 From 1c91b46555aa1dd86331025e62d55d92459e0faf Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:26 +0200 Subject: backlight: backlight: Add backlight_is_blank() The backlight support has three properties that express the state: - power - state - fb_blank It is un-documented and easy to get wrong. Add backlight_is_blank() helper to make it simpler for drivers to get the check of the state correct. A lot of drivers also includes checks for fb_blank. This check is redundant when the state is checked and thus not needed in this helper function. But added anyway to avoid introducing subtle bugs due to the creative use of fb_blank in some drivers. Introducing this helper will for some drivers results in added support for fb_blank. This will be a change in functionality, which will improve the backlight driver. Rolling out this helper to all relevant backlight drivers will eliminate almost all accesses to fb_blank. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Peter Ujfalusi Reviewed-by: Emil Velikov Reviewed-by: Daniel Vetter Signed-off-by: Lee Jones --- include/linux/backlight.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 56e4580d4f55..56e51ebab740 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -175,6 +175,25 @@ static inline void backlight_put(struct backlight_device *bd) put_device(&bd->dev); } +/** + * backlight_is_blank - Return true if display is expected to be blank + * @bd: the backlight device + * + * Display is expected to be blank if any of these is true:: + * + * 1) if power in not UNBLANK + * 2) if fb_blank is not UNBLANK + * 3) if state indicate BLANK or SUSPENDED + * + * Returns true if display is expected to be blank, false otherwise. + */ +static inline bool backlight_is_blank(const struct backlight_device *bd) +{ + return bd->props.power != FB_BLANK_UNBLANK || + bd->props.fb_blank != FB_BLANK_UNBLANK || + bd->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK); +} + extern struct backlight_device *backlight_device_register(const char *name, struct device *dev, void *devdata, const struct backlight_ops *ops, const struct backlight_properties *props); -- cgit v1.2.3 From ca7c20b2132d228ec76df3c96f5d0b5ae3d6f218 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:27 +0200 Subject: backlight: backlight: Improve backlight_ops documentation Improve the documentation for backlight_ops and adapt it to kernel-doc style. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- include/linux/backlight.h | 59 ++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 53 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 56e51ebab740..4ff60774ae22 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -55,19 +55,66 @@ enum backlight_scale { struct backlight_device; struct fb_info; +/** + * struct backlight_ops - backlight operations + * + * The backlight operations are specified when the backlight device is registered. + */ struct backlight_ops { + /** + * @options: Configure how operations are called from the core. + * + * The options parameter is used to adjust the behaviour of the core. + * Set BL_CORE_SUSPENDRESUME to get the update_status() operation called + * upon suspend and resume. + */ unsigned int options; #define BL_CORE_SUSPENDRESUME (1 << 0) - /* Notify the backlight driver some property has changed */ + /** + * @update_status: Operation called when properties have changed. + * + * Notify the backlight driver some property has changed. + * The update_status operation is protected by the update_lock. + * + * The backlight driver is expected to use backlight_is_blank() + * to check if the display is blanked and set brightness accordingly. + * update_status() is called when any of the properties has changed. + * + * RETURNS: + * + * 0 on success, negative error code if any failure occurred. + */ int (*update_status)(struct backlight_device *); - /* Return the current backlight brightness (accounting for power, - fb_blank etc.) */ + + /** + * @get_brightness: Return the current backlight brightness. + * + * The driver may implement this as a readback from the HW. + * This operation is optional and if not present then the current + * brightness property value is used. + * + * RETURNS: + * + * A brightness value which is 0 or a positive number. + * On failure a negative error code is returned. + */ int (*get_brightness)(struct backlight_device *); - /* Check if given framebuffer device is the one bound to this backlight; - return 0 if not, !=0 if it is. If NULL, backlight always matches the fb. */ - int (*check_fb)(struct backlight_device *, struct fb_info *); + + /** + * @check_fb: Check the framebuffer device. + * + * Check if given framebuffer device is the one bound to this backlight. + * This operation is optional and if not implemented it is assumed that the + * fbdev is always the one bound to the backlight. + * + * RETURNS: + * + * If info is NULL or the info matches the fbdev bound to the backlight return true. + * If info does not match the fbdev bound to the backlight return false. + */ + int (*check_fb)(struct backlight_device *bd, struct fb_info *info); }; /* This structure defines all the properties of a backlight */ -- cgit v1.2.3 From cabf161335ca9fe695bb87469ed99be881cd08f5 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:28 +0200 Subject: backlight: backlight: Improve backlight_properties documentation Improve the documentation for backlight_properties and adapt it to kernel-doc style. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- include/linux/backlight.h | 96 +++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 85 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 4ff60774ae22..3554aef008ea 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -117,28 +117,102 @@ struct backlight_ops { int (*check_fb)(struct backlight_device *bd, struct fb_info *info); }; -/* This structure defines all the properties of a backlight */ +/** + * struct backlight_properties - backlight properties + * + * This structure defines all the properties of a backlight. + */ struct backlight_properties { - /* Current User requested brightness (0 - max_brightness) */ + /** + * @brightness: The current brightness requested by the user. + * + * The backlight core makes sure the range is (0 to max_brightness) + * when the brightness is set via the sysfs attribute: + * /sys/class/backlight//brightness. + * + * This value can be set in the backlight_properties passed + * to devm_backlight_device_register() to set a default brightness + * value. + */ int brightness; - /* Maximal value for brightness (read-only) */ + + /** + * @max_brightness: The maximum brightness value. + * + * This value must be set in the backlight_properties passed to + * devm_backlight_device_register() and shall not be modified by the + * driver after registration. + */ int max_brightness; - /* Current FB Power mode (0: full on, 1..3: power saving - modes; 4: full off), see FB_BLANK_XXX */ + + /** + * @power: The current power mode. + * + * User space can configure the power mode using the sysfs + * attribute: /sys/class/backlight//bl_power + * When the power property is updated update_status() is called. + * + * The possible values are: (0: full on, 1 to 3: power saving + * modes; 4: full off), see FB_BLANK_XXX. + * + * When the backlight device is enabled @power is set + * to FB_BLANK_UNBLANK. When the backlight device is disabled + * @power is set to FB_BLANK_POWERDOWN. + */ int power; - /* FB Blanking active? (values as for power) */ - /* Due to be removed, please use (state & BL_CORE_FBBLANK) */ + + /** + * @fb_blank: The power state from the FBIOBLANK ioctl. + * + * When the FBIOBLANK ioctl is called @fb_blank is set to the + * blank parameter and the update_status() operation is called. + * + * When the backlight device is enabled @fb_blank is set + * to FB_BLANK_UNBLANK. When the backlight device is disabled + * @fb_blank is set to FB_BLANK_POWERDOWN. + * + * Backlight drivers should avoid using this property. It has been + * replaced by state & BL_CORE_FBLANK (although most drivers should + * use backlight_is_blank() as the preferred means to get the blank + * state). + * + * fb_blank is deprecated and will be removed. + */ int fb_blank; - /* Backlight type */ + + /** + * @type: The type of backlight supported. + * + * The backlight type allows userspace to make appropriate + * policy decisions based on the backlight type. + * + * This value must be set in the backlight_properties + * passed to devm_backlight_device_register(). + */ enum backlight_type type; - /* Flags used to signal drivers of state changes */ + + /** + * @state: The state of the backlight core. + * + * The state is a bitmask. BL_CORE_FBBLANK is set when the display + * is expected to be blank. BL_CORE_SUSPENDED is set when the + * driver is suspended. + * + * backlight drivers are expected to use backlight_is_blank() + * in their update_status() operation rather than reading the + * state property. + * + * The state is maintained by the core and drivers may not modify it. + */ unsigned int state; - /* Type of the brightness scale (linear, non-linear, ...) */ - enum backlight_scale scale; #define BL_CORE_SUSPENDED (1 << 0) /* backlight is suspended */ #define BL_CORE_FBBLANK (1 << 1) /* backlight is under an fb blank event */ + /** + * @scale: The type of the brightness scale. + */ + enum backlight_scale scale; }; struct backlight_device { -- cgit v1.2.3 From 6f10cd124c44eea018672d5852708ca5dca4d06d Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:29 +0200 Subject: backlight: backlight: Improve backlight_device documentation Improve the documentation for backlight_device and adapt it to kernel-doc style. The updated documentation is more strict on how locking is used. With the update neither update_lock nor ops_lock may be used outside the backlight core. This restriction was introduced to keep the locking simple by keeping it in the core. It was verified that this documents the current state by renaming update_lock => bl_update_lock and ops_lock => bl_ops_lock. The rename did not reveal any uses outside the backlight core. The rename is NOT part of this patch. Signed-off-by: Sam Ravnborg Reviewed-by: Emil Velikov Reviewed-by: Daniel Thompson Reviewed-by: Jingoo Han Signed-off-by: Lee Jones --- include/linux/backlight.h | 72 ++++++++++++++++++++++++++++++++--------------- 1 file changed, 49 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 3554aef008ea..cf9977169fe8 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -14,21 +14,6 @@ #include #include -/* Notes on locking: - * - * backlight_device->ops_lock is an internal backlight lock protecting the - * ops pointer and no code outside the core should need to touch it. - * - * Access to update_status() is serialised by the update_lock mutex since - * most drivers seem to need this and historically get it wrong. - * - * Most drivers don't need locking on their get_brightness() method. - * If yours does, you need to implement it in the driver. You can use the - * update_lock mutex if appropriate. - * - * Any other use of the locks below is probably wrong. - */ - enum backlight_update_reason { BACKLIGHT_UPDATE_HOTKEY, BACKLIGHT_UPDATE_SYSFS, @@ -215,30 +200,71 @@ struct backlight_properties { enum backlight_scale scale; }; +/** + * struct backlight_device - backlight device data + * + * This structure holds all data required by a backlight device. + */ struct backlight_device { - /* Backlight properties */ + /** + * @props: Backlight properties + */ struct backlight_properties props; - /* Serialise access to update_status method */ + /** + * @update_lock: The lock used when calling the update_status() operation. + * + * update_lock is an internal backlight lock that serialise access + * to the update_status() operation. The backlight core holds the update_lock + * when calling the update_status() operation. The update_lock shall not + * be used by backlight drivers. + */ struct mutex update_lock; - /* This protects the 'ops' field. If 'ops' is NULL, the driver that - registered this device has been unloaded, and if class_get_devdata() - points to something in the body of that driver, it is also invalid. */ + /** + * @ops_lock: The lock used around everything related to backlight_ops. + * + * ops_lock is an internal backlight lock that protects the ops pointer + * and is used around all accesses to ops and when the operations are + * invoked. The ops_lock shall not be used by backlight drivers. + */ struct mutex ops_lock; + + /** + * @ops: Pointer to the backlight operations. + * + * If ops is NULL, the driver that registered this device has been unloaded, + * and if class_get_devdata() points to something in the body of that driver, + * it is also invalid. + */ const struct backlight_ops *ops; - /* The framebuffer notifier block */ + /** + * @fb_notif: The framebuffer notifier block + */ struct notifier_block fb_notif; - /* list entry of all registered backlight devices */ + /** + * @entry: List entry of all registered backlight devices + */ struct list_head entry; + /** + * @dev: Parent device. + */ struct device dev; - /* Multiple framebuffers may share one backlight device */ + /** + * @fb_bl_on: The state of individual fbdev's. + * + * Multiple fbdev's may share one backlight device. The fb_bl_on + * records the state of the individual fbdev. + */ bool fb_bl_on[FB_MAX]; + /** + * @use_count: The number of uses of fb_bl_on. + */ int use_count; }; -- cgit v1.2.3 From d160fd4e918da33f5ffbcf005cd95888dbbe4f76 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:30 +0200 Subject: backlight: backlight: Document inline functions in backlight.h Add documentation for the inline functions in backlight.h Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- include/linux/backlight.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index cf9977169fe8..99381b5a289d 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -268,6 +268,10 @@ struct backlight_device { int use_count; }; +/** + * backlight_update_status - force an update of the backlight device status + * @bd: the backlight device + */ static inline int backlight_update_status(struct backlight_device *bd) { int ret = -ENOENT; @@ -361,6 +365,18 @@ extern int backlight_device_set_brightness(struct backlight_device *bd, unsigned #define to_backlight_device(obj) container_of(obj, struct backlight_device, dev) +/** + * bl_get_data - access devdata + * @bl_dev: pointer to backlight device + * + * When a backlight device is registered the driver has the possibility + * to supply a void * devdata. bl_get_data() return a pointer to the + * devdata. + * + * RETURNS: + * + * pointer to devdata stored while registering the backlight device. + */ static inline void * bl_get_data(struct backlight_device *bl_dev) { return dev_get_drvdata(&bl_dev->dev); -- cgit v1.2.3 From 2d15bb47f3331db979bd0a1987812ca1a3ff40c6 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:31 +0200 Subject: backlight: backlight: Document enums in backlight.h Add kernel-doc documentation for the backlight enums Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- include/linux/backlight.h | 72 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 99381b5a289d..1d56b34ff33c 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -14,26 +14,98 @@ #include #include +/** + * enum backlight_update_reason - what method was used to update backlight + * + * A driver indicates the method (reason) used for updating the backlight + * when calling backlight_force_update(). + */ enum backlight_update_reason { + /** + * @BACKLIGHT_UPDATE_HOTKEY: The backlight was updated using a hot-key. + */ BACKLIGHT_UPDATE_HOTKEY, + + /** + * @BACKLIGHT_UPDATE_SYSFS: The backlight was updated using sysfs. + */ BACKLIGHT_UPDATE_SYSFS, }; +/** + * enum backlight_type - the type of backlight control + * + * The type of interface used to control the backlight. + */ enum backlight_type { + /** + * @BACKLIGHT_RAW: + * + * The backlight is controlled using hardware registers. + */ BACKLIGHT_RAW = 1, + + /** + * @BACKLIGHT_PLATFORM: + * + * The backlight is controlled using a platform-specific interface. + */ BACKLIGHT_PLATFORM, + + /** + * @BACKLIGHT_FIRMWARE: + * + * The backlight is controlled using a standard firmware interface. + */ BACKLIGHT_FIRMWARE, + + /** + * @BACKLIGHT_TYPE_MAX: Number of entries. + */ BACKLIGHT_TYPE_MAX, }; +/** + * enum backlight_notification - the type of notification + * + * The notifications that is used for notification sent to the receiver + * that registered notifications using backlight_register_notifier(). + */ enum backlight_notification { + /** + * @BACKLIGHT_REGISTERED: The backlight device is registered. + */ BACKLIGHT_REGISTERED, + + /** + * @BACKLIGHT_UNREGISTERED: The backlight revice is unregistered. + */ BACKLIGHT_UNREGISTERED, }; +/** enum backlight_scale - the type of scale used for brightness values + * + * The type of scale used for brightness values. + */ enum backlight_scale { + /** + * @BACKLIGHT_SCALE_UNKNOWN: The scale is unknown. + */ BACKLIGHT_SCALE_UNKNOWN = 0, + + /** + * @BACKLIGHT_SCALE_LINEAR: The scale is linear. + * + * The linear scale will increase brightness the same for each step. + */ BACKLIGHT_SCALE_LINEAR, + + /** + * @BACKLIGHT_SCALE_NON_LINEAR: The scale is not linear. + * + * This is often used when the brightness values tries to adjust to + * the relative perception of the eye demanding a non-linear scale. + */ BACKLIGHT_SCALE_NON_LINEAR, }; -- cgit v1.2.3 From 7ecdea4a0226f6c5cd0e86859d1b38cf17bc8529 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:32 +0200 Subject: backlight: generic_bl: Remove this driver as it is unused The backlight_bl driver required initialization using struct generic_bl_info. As there are no more references to this struct there is no users left. So it is safe to delete the driver. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- include/linux/backlight.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 1d56b34ff33c..d0f01dc3b98d 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -454,15 +454,6 @@ static inline void * bl_get_data(struct backlight_device *bl_dev) return dev_get_drvdata(&bl_dev->dev); } -struct generic_bl_info { - const char *name; - int max_intensity; - int default_intensity; - int limit_mask; - void (*set_bl_intensity)(int intensity); - void (*kick_battery)(void); -}; - #ifdef CONFIG_OF struct backlight_device *of_find_backlight_by_node(struct device_node *node); #else -- cgit v1.2.3 From 9c4aa3118bab6f10904b7bc9bc34b501a083751b Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:33 +0200 Subject: backlight: backlight: Drop extern from prototypes No need to put "extern" in front of prototypes. While touching the prototypes adjust indent to follow the kernel style. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Reviewed-by: Emil Velikov Signed-off-by: Lee Jones --- include/linux/backlight.h | 35 +++++++++++++++++++---------------- 1 file changed, 19 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index d0f01dc3b98d..c1824426fc9e 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -417,23 +417,26 @@ static inline bool backlight_is_blank(const struct backlight_device *bd) bd->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK); } -extern struct backlight_device *backlight_device_register(const char *name, - struct device *dev, void *devdata, const struct backlight_ops *ops, - const struct backlight_properties *props); -extern struct backlight_device *devm_backlight_device_register( - struct device *dev, const char *name, struct device *parent, - void *devdata, const struct backlight_ops *ops, - const struct backlight_properties *props); -extern void backlight_device_unregister(struct backlight_device *bd); -extern void devm_backlight_device_unregister(struct device *dev, - struct backlight_device *bd); -extern void backlight_force_update(struct backlight_device *bd, - enum backlight_update_reason reason); -extern int backlight_register_notifier(struct notifier_block *nb); -extern int backlight_unregister_notifier(struct notifier_block *nb); -extern struct backlight_device *backlight_device_get_by_type(enum backlight_type type); +struct backlight_device * +backlight_device_register(const char *name, struct device *dev, void *devdata, + const struct backlight_ops *ops, + const struct backlight_properties *props); +struct backlight_device * +devm_backlight_device_register(struct device *dev, const char *name, + struct device *parent, void *devdata, + const struct backlight_ops *ops, + const struct backlight_properties *props); +void backlight_device_unregister(struct backlight_device *bd); +void devm_backlight_device_unregister(struct device *dev, + struct backlight_device *bd); +void backlight_force_update(struct backlight_device *bd, + enum backlight_update_reason reason); +int backlight_register_notifier(struct notifier_block *nb); +int backlight_unregister_notifier(struct notifier_block *nb); struct backlight_device *backlight_device_get_by_name(const char *name); -extern int backlight_device_set_brightness(struct backlight_device *bd, unsigned long brightness); +struct backlight_device *backlight_device_get_by_type(enum backlight_type type); +int backlight_device_set_brightness(struct backlight_device *bd, + unsigned long brightness); #define to_backlight_device(obj) container_of(obj, struct backlight_device, dev) -- cgit v1.2.3 From 2144d00ed0db28c764513080f95e4c49ea9133b0 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:36 +0200 Subject: backlight: backlight: Introduce backlight_get_brightness() Based on an idea from Emil Velikov, add a helper that checks backlight_is_blank() and return 0 as brightness if display is blank or the property value if not. This allows us to simplify the update_status() implementation in most of the backlight drivers. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- include/linux/backlight.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index c1824426fc9e..26e89a8033f5 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -417,6 +417,25 @@ static inline bool backlight_is_blank(const struct backlight_device *bd) bd->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK); } +/** + * backlight_get_brightness - Returns the current brightness value + * @bd: the backlight device + * + * Returns the current brightness value, taking in consideration the current + * state. If backlight_is_blank() returns true then return 0 as brightness + * otherwise return the current brightness property value. + * + * Backlight drivers are expected to use this function in their update_status() + * operation to get the brightness value. + */ +static inline int backlight_get_brightness(const struct backlight_device *bd) +{ + if (backlight_is_blank(bd)) + return 0; + else + return bd->props.brightness; +} + struct backlight_device * backlight_device_register(const char *name, struct device *dev, void *devdata, const struct backlight_ops *ops, -- cgit v1.2.3 From 0f6a3256fd810eeca9c56cccafee46359d995138 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:42 +0200 Subject: backlight: backlight: Drop backlight_put() There are no external users of backlight_put(). Drop it and open code the two users in backlight.c. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- include/linux/backlight.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 26e89a8033f5..64f91324c911 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -388,16 +388,6 @@ static inline int backlight_disable(struct backlight_device *bd) return backlight_update_status(bd); } -/** - * backlight_put - Drop backlight reference - * @bd: the backlight device to put - */ -static inline void backlight_put(struct backlight_device *bd) -{ - if (bd) - put_device(&bd->dev); -} - /** * backlight_is_blank - Return true if display is expected to be blank * @bd: the backlight device -- cgit v1.2.3 From b6539a11e807c531e51ff7ad9a25c3a1b6ff7340 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 19 Jul 2020 10:07:43 +0200 Subject: backlight: backlight: Make of_find_backlight static There are no external users of of_find_backlight, as they have all changed to use the managed version. Make of_find_backlight static to prevent new external users. Signed-off-by: Sam Ravnborg Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- include/linux/backlight.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 64f91324c911..614653e07e3a 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -477,14 +477,8 @@ of_find_backlight_by_node(struct device_node *node) #endif #if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE) -struct backlight_device *of_find_backlight(struct device *dev); struct backlight_device *devm_of_find_backlight(struct device *dev); #else -static inline struct backlight_device *of_find_backlight(struct device *dev) -{ - return NULL; -} - static inline struct backlight_device * devm_of_find_backlight(struct device *dev) { -- cgit v1.2.3 From 1b86abc1c645ad5c9c7bf70910cb3ce73939d2d7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 16 Jul 2020 13:11:24 +0800 Subject: sched_clock: Expose struct clock_read_data In order to support perf_event_mmap_page::cap_time features, an architecture needs, aside from a userspace readable counter register, to expose the exact clock data so that userspace can convert the counter register into a correct timestamp. Provide struct clock_read_data and two (seqcount) helpers so that architectures (arm64 in specific) can expose the numbers to userspace. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Leo Yan Link: https://lore.kernel.org/r/20200716051130.4359-2-leo.yan@linaro.org Signed-off-by: Will Deacon --- include/linux/sched_clock.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h index 0bb04a96a6d4..528718e4ed52 100644 --- a/include/linux/sched_clock.h +++ b/include/linux/sched_clock.h @@ -6,6 +6,34 @@ #define LINUX_SCHED_CLOCK #ifdef CONFIG_GENERIC_SCHED_CLOCK +/** + * struct clock_read_data - data required to read from sched_clock() + * + * @epoch_ns: sched_clock() value at last update + * @epoch_cyc: Clock cycle value at last update. + * @sched_clock_mask: Bitmask for two's complement subtraction of non 64bit + * clocks. + * @read_sched_clock: Current clock source (or dummy source when suspended). + * @mult: Multipler for scaled math conversion. + * @shift: Shift value for scaled math conversion. + * + * Care must be taken when updating this structure; it is read by + * some very hot code paths. It occupies <=40 bytes and, when combined + * with the seqcount used to synchronize access, comfortably fits into + * a 64 byte cache line. + */ +struct clock_read_data { + u64 epoch_ns; + u64 epoch_cyc; + u64 sched_clock_mask; + u64 (*read_sched_clock)(void); + u32 mult; + u32 shift; +}; + +extern struct clock_read_data *sched_clock_read_begin(unsigned int *seq); +extern int sched_clock_read_retry(unsigned int seq); + extern void generic_sched_clock_init(void); extern void sched_clock_register(u64 (*read)(void), int bits, -- cgit v1.2.3 From 3c8387d234f75887a2d78972ab0f764fe9f756e4 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 22 Jun 2020 10:53:55 +0300 Subject: uuid: remove unused uuid_le_to_bin() definition There is no more user, so remove it. Signed-off-by: Andy Shevchenko Signed-off-by: Christoph Hellwig --- include/linux/uuid.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uuid.h b/include/linux/uuid.h index d41b0d3e9474..8cdc0d3567cd 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -98,8 +98,6 @@ int guid_parse(const char *uuid, guid_t *u); int uuid_parse(const char *uuid, uuid_t *u); /* backwards compatibility, don't use in new code */ -#define uuid_le_to_bin(guid, u) guid_parse(guid, u) - static inline int uuid_le_cmp(const guid_t u1, const guid_t u2) { return memcmp(&u1, &u2, sizeof(guid_t)); -- cgit v1.2.3 From 4834177e633258fbf3c5754b1220f01c705b79eb Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Thu, 9 Jul 2020 01:19:11 -0500 Subject: ima: Support additional conditionals in the KEXEC_CMDLINE hook function Take the properties of the kexec kernel's inode and the current task ownership into consideration when matching a KEXEC_CMDLINE operation to the rules in the IMA policy. This allows for some uniformity when writing IMA policy rules for KEXEC_KERNEL_CHECK, KEXEC_INITRAMFS_CHECK, and KEXEC_CMDLINE operations. Prior to this patch, it was not possible to write a set of rules like this: dont_measure func=KEXEC_KERNEL_CHECK obj_type=foo_t dont_measure func=KEXEC_INITRAMFS_CHECK obj_type=foo_t dont_measure func=KEXEC_CMDLINE obj_type=foo_t measure func=KEXEC_KERNEL_CHECK measure func=KEXEC_INITRAMFS_CHECK measure func=KEXEC_CMDLINE The inode information associated with the kernel being loaded by a kexec_kernel_load(2) syscall can now be included in the decision to measure or not Additonally, the uid, euid, and subj_* conditionals can also now be used in KEXEC_CMDLINE rules. There was no technical reason as to why those conditionals weren't being considered previously other than ima_match_rules() didn't have a valid inode to use so it immediately bailed out for KEXEC_CMDLINE operations rather than going through the full list of conditional comparisons. Signed-off-by: Tyler Hicks Cc: Eric Biederman Cc: kexec@lists.infradead.org Reviewed-by: Lakshmi Ramasubramanian Signed-off-by: Mimi Zohar --- include/linux/ima.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 9164e1534ec9..d15100de6cdd 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -25,7 +25,7 @@ extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); extern void ima_post_path_mknod(struct dentry *dentry); extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); -extern void ima_kexec_cmdline(const void *buf, int size); +extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size); #ifdef CONFIG_IMA_KEXEC extern void ima_add_kexec_buffer(struct kimage *image); @@ -103,7 +103,7 @@ static inline int ima_file_hash(struct file *file, char *buf, size_t buf_size) return -EOPNOTSUPP; } -static inline void ima_kexec_cmdline(const void *buf, int size) {} +static inline void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) {} #endif /* CONFIG_IMA */ #ifndef CONFIG_IMA_KEXEC -- cgit v1.2.3 From 3093a479727be194996dbc40f803711af5877be4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2020 08:12:49 +0200 Subject: block: inherit the zoned characteristics in blk_stack_limits Lift the code from device mapper into blk_stack_limits to inherity the stacking limitations. This ensures we do the right thing for all stacked zoned block devices. Reviewed-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Tested-by: Damien Le Moal Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 63078944909c..9e331a1eb35f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -306,11 +306,14 @@ enum blk_queue_state { /* * Zoned block device models (zoned limit). + * + * Note: This needs to be ordered from the least to the most severe + * restrictions for the inheritance in blk_stack_limits() to work. */ enum blk_zoned_model { - BLK_ZONED_NONE, /* Regular block device */ - BLK_ZONED_HA, /* Host-aware zoned block device */ - BLK_ZONED_HM, /* Host-managed zoned block device */ + BLK_ZONED_NONE = 0, /* Regular block device */ + BLK_ZONED_HA, /* Host-aware zoned block device */ + BLK_ZONED_HM, /* Host-managed zoned block device */ }; struct queue_limits { -- cgit v1.2.3 From 9efa82ef2b15d1757dd6cc518988a4506554e893 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2020 08:12:50 +0200 Subject: block: remove bdev_stack_limits This function is just a tiny wrapper around blk_stack_limit and has two callers. Simplify the stack a bit by open coding it in the two callers. Reviewed-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Tested-by: Damien Le Moal Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9e331a1eb35f..54b963109e64 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1139,8 +1139,6 @@ extern void blk_set_default_limits(struct queue_limits *lim); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); -extern int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev, - sector_t offset); extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset); extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b); -- cgit v1.2.3 From b9b1a5d71533f2ccd54b810dffdcf0789b30ba9b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2020 08:12:51 +0200 Subject: block: remove blk_queue_stack_limits This function is just a tiny wrapper around blk_stack_limits. Open code it int the two callers. Reviewed-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Tested-by: Damien Le Moal Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 54b963109e64..bbdd3cf62038 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1141,7 +1141,6 @@ extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset); -extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b); extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); -- cgit v1.2.3 From 6c4411f14d1afa8ead90cd4cf18a308c43ac6908 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:28:30 -0700 Subject: clk: : drop a duplicated word Drop the repeated word "not" in a comment. Signed-off-by: Randy Dunlap Cc: Michael Turquette Cc: Stephen Boyd Cc: linux-clk@vger.kernel.org Link: https://lore.kernel.org/r/20200719002830.20319-1-rdunlap@infradead.org Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index bd1ee9039558..6f815be99b77 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -189,7 +189,7 @@ struct clk_duty { * and >= numerator) Return 0 on success, otherwise -EERROR. * * @init: Perform platform-specific initialization magic. - * This is not not used by any of the basic clock types. + * This is not used by any of the basic clock types. * This callback exist for HW which needs to perform some * initialisation magic for CCF to get an accurate view of the * clock. It may also be used dynamic resource allocation is -- cgit v1.2.3 From a8b7b2d0b3fc965d823e362840e5451e2eb4a71b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 20 Jul 2020 10:10:41 +0200 Subject: sched: sch_api: add missing rcu read lock to silence the warning In case the qdisc_match_from_root function() is called from non-rcu path with rtnl mutex held, a suspiciout rcu usage warning appears: [ 241.504354] ============================= [ 241.504358] WARNING: suspicious RCU usage [ 241.504366] 5.8.0-rc4-custom-01521-g72a7c7d549c3 #32 Not tainted [ 241.504370] ----------------------------- [ 241.504378] net/sched/sch_api.c:270 RCU-list traversed in non-reader section!! [ 241.504382] other info that might help us debug this: [ 241.504388] rcu_scheduler_active = 2, debug_locks = 1 [ 241.504394] 1 lock held by tc/1391: [ 241.504398] #0: ffffffff85a27850 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x49a/0xbd0 [ 241.504431] stack backtrace: [ 241.504440] CPU: 0 PID: 1391 Comm: tc Not tainted 5.8.0-rc4-custom-01521-g72a7c7d549c3 #32 [ 241.504446] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014 [ 241.504453] Call Trace: [ 241.504465] dump_stack+0x100/0x184 [ 241.504482] lockdep_rcu_suspicious+0x153/0x15d [ 241.504499] qdisc_match_from_root+0x293/0x350 Fix this by passing the rtnl held lockdep condition down to hlist_for_each_entry_rcu() Reported-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/hashtable.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hashtable.h b/include/linux/hashtable.h index 78b6ea5fa8ba..f6c666730b8c 100644 --- a/include/linux/hashtable.h +++ b/include/linux/hashtable.h @@ -173,9 +173,9 @@ static inline void hash_del_rcu(struct hlist_node *node) * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ -#define hash_for_each_possible_rcu(name, obj, member, key) \ +#define hash_for_each_possible_rcu(name, obj, member, key, cond...) \ hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))],\ - member) + member, ## cond) /** * hash_for_each_possible_rcu_notrace - iterate over all possible objects hashing -- cgit v1.2.3 From e812916d3278baf03aabf10044661fc3b2848823 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 20 Jul 2020 21:08:00 +0300 Subject: linkmode: introduce linkmode_intersects() Add a new helper to find intersections between Ethtool link modes, linkmode_intersects(), similar to the other linkmode helpers. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/linkmode.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index c664c27a29a0..f8397f300fcd 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -82,6 +82,12 @@ static inline int linkmode_equal(const unsigned long *src1, return bitmap_equal(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } +static inline int linkmode_intersects(const unsigned long *src1, + const unsigned long *src2) +{ + return bitmap_intersects(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + static inline int linkmode_subset(const unsigned long *src1, const unsigned long *src2) { -- cgit v1.2.3 From bdb5d8ec47611ca61e168349f233e1dd1ed063f4 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 20 Jul 2020 21:08:01 +0300 Subject: qed, qede, qedf: convert link mode from u32 to ETHTOOL_LINK_MODE Currently qed driver already ran out of 32 bits to store link modes, and this doesn't allow to add and support more speeds. Convert custom link mode to generic Ethtool bitmap and definitions (convenient Phylink shorthands are used for elegance and readability). This allowed us to drop all conversions/mappings between the driver and Ethtool. This involves changes in qede and qedf as well, as they used definitions from shared "qed_if.h". Suggested-by: Andrew Lunn Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 47 ++++++---------------------------------------- 1 file changed, 6 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8a6e3ad436d1..f82db1b92d45 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -661,42 +661,6 @@ enum qed_protocol { QED_PROTOCOL_FCOE, }; -enum qed_link_mode_bits { - QED_LM_FIBRE_BIT = BIT(0), - QED_LM_Autoneg_BIT = BIT(1), - QED_LM_Asym_Pause_BIT = BIT(2), - QED_LM_Pause_BIT = BIT(3), - QED_LM_1000baseT_Full_BIT = BIT(4), - QED_LM_10000baseT_Full_BIT = BIT(5), - QED_LM_10000baseKR_Full_BIT = BIT(6), - QED_LM_20000baseKR2_Full_BIT = BIT(7), - QED_LM_25000baseKR_Full_BIT = BIT(8), - QED_LM_40000baseLR4_Full_BIT = BIT(9), - QED_LM_50000baseKR2_Full_BIT = BIT(10), - QED_LM_100000baseKR4_Full_BIT = BIT(11), - QED_LM_TP_BIT = BIT(12), - QED_LM_Backplane_BIT = BIT(13), - QED_LM_1000baseKX_Full_BIT = BIT(14), - QED_LM_10000baseKX4_Full_BIT = BIT(15), - QED_LM_10000baseR_FEC_BIT = BIT(16), - QED_LM_40000baseKR4_Full_BIT = BIT(17), - QED_LM_40000baseCR4_Full_BIT = BIT(18), - QED_LM_40000baseSR4_Full_BIT = BIT(19), - QED_LM_25000baseCR_Full_BIT = BIT(20), - QED_LM_25000baseSR_Full_BIT = BIT(21), - QED_LM_50000baseCR2_Full_BIT = BIT(22), - QED_LM_100000baseSR4_Full_BIT = BIT(23), - QED_LM_100000baseCR4_Full_BIT = BIT(24), - QED_LM_100000baseLR4_ER4_Full_BIT = BIT(25), - QED_LM_50000baseSR2_Full_BIT = BIT(26), - QED_LM_1000baseX_Full_BIT = BIT(27), - QED_LM_10000baseCR_Full_BIT = BIT(28), - QED_LM_10000baseSR_Full_BIT = BIT(29), - QED_LM_10000baseLR_Full_BIT = BIT(30), - QED_LM_10000baseLRM_Full_BIT = BIT(31), - QED_LM_COUNT = 32 -}; - struct qed_link_params { bool link_up; @@ -708,7 +672,9 @@ struct qed_link_params { #define QED_LINK_OVERRIDE_EEE_CONFIG BIT(5) u32 override_flags; bool autoneg; - u32 adv_speeds; + + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_speeds); + u32 forced_speed; #define QED_LINK_PAUSE_AUTONEG_ENABLE BIT(0) #define QED_LINK_PAUSE_RX_ENABLE BIT(1) @@ -726,10 +692,9 @@ struct qed_link_params { struct qed_link_output { bool link_up; - /* In QED_LM_* defs */ - u32 supported_caps; - u32 advertised_caps; - u32 lp_caps; + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_caps); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertised_caps); + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_caps); u32 speed; /* In Mb/s */ u8 duplex; /* In DUPLEX defs */ -- cgit v1.2.3 From 37237b5b7104f91b519133d7862d1b5169a3ba8e Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 20 Jul 2020 21:08:06 +0300 Subject: qed: reformat several structures a bit Prior to adding new fields and bitfields, reformat the related structures according to the Linux style (spaces to tabs, lowercase hex, indentation etc.). Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 64 ++++++++++++++++++++++++---------------------- 1 file changed, 33 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index f82db1b92d45..dde48f206d0d 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -662,51 +662,53 @@ enum qed_protocol { }; struct qed_link_params { - bool link_up; + bool link_up; -#define QED_LINK_OVERRIDE_SPEED_AUTONEG BIT(0) -#define QED_LINK_OVERRIDE_SPEED_ADV_SPEEDS BIT(1) -#define QED_LINK_OVERRIDE_SPEED_FORCED_SPEED BIT(2) -#define QED_LINK_OVERRIDE_PAUSE_CONFIG BIT(3) -#define QED_LINK_OVERRIDE_LOOPBACK_MODE BIT(4) -#define QED_LINK_OVERRIDE_EEE_CONFIG BIT(5) - u32 override_flags; - bool autoneg; + u32 override_flags; +#define QED_LINK_OVERRIDE_SPEED_AUTONEG BIT(0) +#define QED_LINK_OVERRIDE_SPEED_ADV_SPEEDS BIT(1) +#define QED_LINK_OVERRIDE_SPEED_FORCED_SPEED BIT(2) +#define QED_LINK_OVERRIDE_PAUSE_CONFIG BIT(3) +#define QED_LINK_OVERRIDE_LOOPBACK_MODE BIT(4) +#define QED_LINK_OVERRIDE_EEE_CONFIG BIT(5) + bool autoneg; __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_speeds); + u32 forced_speed; - u32 forced_speed; -#define QED_LINK_PAUSE_AUTONEG_ENABLE BIT(0) -#define QED_LINK_PAUSE_RX_ENABLE BIT(1) -#define QED_LINK_PAUSE_TX_ENABLE BIT(2) - u32 pause_config; -#define QED_LINK_LOOPBACK_NONE BIT(0) -#define QED_LINK_LOOPBACK_INT_PHY BIT(1) -#define QED_LINK_LOOPBACK_EXT_PHY BIT(2) -#define QED_LINK_LOOPBACK_EXT BIT(3) -#define QED_LINK_LOOPBACK_MAC BIT(4) - u32 loopback_mode; - struct qed_link_eee_params eee; + u32 pause_config; +#define QED_LINK_PAUSE_AUTONEG_ENABLE BIT(0) +#define QED_LINK_PAUSE_RX_ENABLE BIT(1) +#define QED_LINK_PAUSE_TX_ENABLE BIT(2) + + u32 loopback_mode; +#define QED_LINK_LOOPBACK_NONE BIT(0) +#define QED_LINK_LOOPBACK_INT_PHY BIT(1) +#define QED_LINK_LOOPBACK_EXT_PHY BIT(2) +#define QED_LINK_LOOPBACK_EXT BIT(3) +#define QED_LINK_LOOPBACK_MAC BIT(4) + + struct qed_link_eee_params eee; }; struct qed_link_output { - bool link_up; + bool link_up; __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_caps); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertised_caps); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_caps); - u32 speed; /* In Mb/s */ - u8 duplex; /* In DUPLEX defs */ - u8 port; /* In PORT defs */ - bool autoneg; - u32 pause_config; + u32 speed; /* In Mb/s */ + u8 duplex; /* In DUPLEX defs */ + u8 port; /* In PORT defs */ + bool autoneg; + u32 pause_config; /* EEE - capability & param */ - bool eee_supported; - bool eee_active; - u8 sup_caps; - struct qed_link_eee_params eee; + bool eee_supported; + bool eee_active; + u8 sup_caps; + struct qed_link_eee_params eee; }; struct qed_probe_params { -- cgit v1.2.3 From ae7e69379fd5a87141fd8c7f2efab8e73f2a9f7e Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 20 Jul 2020 21:08:07 +0300 Subject: qed: add support for Forward Error Correction Add all necessary routines for reading supported FEC modes from NVM and querying FEC control to the MFW (if the running version supports it). Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index dde48f206d0d..f0b4cdc79299 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -661,6 +661,14 @@ enum qed_protocol { QED_PROTOCOL_FCOE, }; +enum qed_fec_mode { + QED_FEC_MODE_NONE = BIT(0), + QED_FEC_MODE_FIRECODE = BIT(1), + QED_FEC_MODE_RS = BIT(2), + QED_FEC_MODE_AUTO = BIT(3), + QED_FEC_MODE_UNSUPPORTED = BIT(4), +}; + struct qed_link_params { bool link_up; @@ -671,6 +679,7 @@ struct qed_link_params { #define QED_LINK_OVERRIDE_PAUSE_CONFIG BIT(3) #define QED_LINK_OVERRIDE_LOOPBACK_MODE BIT(4) #define QED_LINK_OVERRIDE_EEE_CONFIG BIT(5) +#define QED_LINK_OVERRIDE_FEC_CONFIG BIT(6) bool autoneg; __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_speeds); @@ -689,6 +698,7 @@ struct qed_link_params { #define QED_LINK_LOOPBACK_MAC BIT(4) struct qed_link_eee_params eee; + u32 fec; }; struct qed_link_output { @@ -709,6 +719,9 @@ struct qed_link_output { bool eee_active; u8 sup_caps; struct qed_link_eee_params eee; + + u32 sup_fec; + u32 active_fec; }; struct qed_probe_params { -- cgit v1.2.3 From 98e675ec5a92a15f6f8ade41eda883cd39df5712 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 20 Jul 2020 21:08:13 +0300 Subject: qed: add missing loopback modes These modes are relevant only for several boards, but may be reported by MFW as well as the others. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index f0b4cdc79299..2e780159a5fb 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -696,6 +696,11 @@ struct qed_link_params { #define QED_LINK_LOOPBACK_EXT_PHY BIT(2) #define QED_LINK_LOOPBACK_EXT BIT(3) #define QED_LINK_LOOPBACK_MAC BIT(4) +#define QED_LINK_LOOPBACK_CNIG_AH_ONLY_0123 BIT(5) +#define QED_LINK_LOOPBACK_CNIG_AH_ONLY_2301 BIT(6) +#define QED_LINK_LOOPBACK_PCS_AH_ONLY BIT(7) +#define QED_LINK_LOOPBACK_REVERSE_MAC_AH_ONLY BIT(8) +#define QED_LINK_LOOPBACK_INT_PHY_FEA_AH_ONLY BIT(9) struct qed_link_eee_params eee; u32 fec; -- cgit v1.2.3 From 99785a87fc7d27207c7dca0f0fe04386f1981690 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 20 Jul 2020 21:08:15 +0300 Subject: qed: add support for the extended speed and FEC modes Add all necessary code (NVM parsing, MFW and Ethtool reports etc.) to support extended speed and FEC modes. These new modes are supported by the new boards revisions and newer MFW versions. Misc: correct port type for MEDIA_KR. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 2e780159a5fb..a5c6854343e6 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -594,6 +594,7 @@ enum qed_hw_err_type { enum qed_dev_type { QED_DEV_TYPE_BB, QED_DEV_TYPE_AH, + QED_DEV_TYPE_E5, }; struct qed_dev_info { -- cgit v1.2.3 From 5fbff813a4a328b730cb117027c43a4ae9d8b6c0 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 7 Jul 2020 22:12:05 +0200 Subject: dma-fence: basic lockdep annotations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Design is similar to the lockdep annotations for workers, but with some twists: - We use a read-lock for the execution/worker/completion side, so that this explicit annotation can be more liberally sprinkled around. With read locks lockdep isn't going to complain if the read-side isn't nested the same way under all circumstances, so ABBA deadlocks are ok. Which they are, since this is an annotation only. - We're using non-recursive lockdep read lock mode, since in recursive read lock mode lockdep does not catch read side hazards. And we _very_ much want read side hazards to be caught. For full details of this limitation see commit e91498589746065e3ae95d9a00b068e525eec34f Author: Peter Zijlstra Date: Wed Aug 23 13:13:11 2017 +0200 locking/lockdep/selftests: Add mixed read-write ABBA tests - To allow nesting of the read-side explicit annotations we explicitly keep track of the nesting. lock_is_held() allows us to do that. - The wait-side annotation is a write lock, and entirely done within dma_fence_wait() for everyone by default. - To be able to freely annotate helper functions I want to make it ok to call dma_fence_begin/end_signalling from soft/hardirq context. First attempt was using the hardirq locking context for the write side in lockdep, but this forces all normal spinlocks nested within dma_fence_begin/end_signalling to be spinlocks. That bollocks. The approach now is to simple check in_atomic(), and for these cases entirely rely on the might_sleep() check in dma_fence_wait(). That will catch any wrong nesting against spinlocks from soft/hardirq contexts. The idea here is that every code path that's critical for eventually signalling a dma_fence should be annotated with dma_fence_begin/end_signalling. The annotation ideally starts right after a dma_fence is published (added to a dma_resv, exposed as a sync_file fd, attached to a drm_syncobj fd, or anything else that makes the dma_fence visible to other kernel threads), up to and including the dma_fence_wait(). Examples are irq handlers, the scheduler rt threads, the tail of execbuf (after the corresponding fences are visible), any workers that end up signalling dma_fences and really anything else. Not annotated should be code paths that only complete fences opportunistically as the gpu progresses, like e.g. shrinker/eviction code. The main class of deadlocks this is supposed to catch are: Thread A: mutex_lock(A); mutex_unlock(A); dma_fence_signal(); Thread B: mutex_lock(A); dma_fence_wait(); mutex_unlock(A); Thread B is blocked on A signalling the fence, but A never gets around to that because it cannot acquire the lock A. Note that dma_fence_wait() is allowed to be nested within dma_fence_begin/end_signalling sections. To allow this to happen the read lock needs to be upgraded to a write lock, which means that any other lock is acquired between the dma_fence_begin_signalling() call and the call to dma_fence_wait(), and still held, this will result in an immediate lockdep complaint. The only other option would be to not annotate such calls, defeating the point. Therefore these annotations cannot be sprinkled over the code entirely mindless to avoid false positives. Originally I hope that the cross-release lockdep extensions would alleviate the need for explicit annotations: https://lwn.net/Articles/709849/ But there's a few reasons why that's not an option: - It's not happening in upstream, since it got reverted due to too many false positives: commit e966eaeeb623f09975ef362c2866fae6f86844f9 Author: Ingo Molnar Date: Tue Dec 12 12:31:16 2017 +0100 locking/lockdep: Remove the cross-release locking checks This code (CONFIG_LOCKDEP_CROSSRELEASE=y and CONFIG_LOCKDEP_COMPLETIONS=y), while it found a number of old bugs initially, was also causing too many false positives that caused people to disable lockdep - which is arguably a worse overall outcome. - cross-release uses the complete() call to annotate the end of critical sections, for dma_fence that would be dma_fence_signal(). But we do not want all dma_fence_signal() calls to be treated as critical, since many are opportunistic cleanup of gpu requests. If these get stuck there's still the main completion interrupt and workers who can unblock everyone. Automatically annotating all dma_fence_signal() calls would hence cause false positives. - cross-release had some educated guesses for when a critical section starts, like fresh syscall or fresh work callback. This would again cause false positives without explicit annotations, since for dma_fence the critical sections only starts when we publish a fence. - Furthermore there can be cases where a thread never does a dma_fence_signal, but is still critical for reaching completion of fences. One example would be a scheduler kthread which picks up jobs and pushes them into hardware, where the interrupt handler or another completion thread calls dma_fence_signal(). But if the scheduler thread hangs, then all the fences hang, hence we need to manually annotate it. cross-release aimed to solve this by chaining cross-release dependencies, but the dependency from scheduler thread to the completion interrupt handler goes through hw where cross-release code can't observe it. In short, without manual annotations and careful review of the start and end of critical sections, cross-relese dependency tracking doesn't work. We need explicit annotations. v2: handle soft/hardirq ctx better against write side and dont forget EXPORT_SYMBOL, drivers can't use this otherwise. v3: Kerneldoc. v4: Some spelling fixes from Mika v5: Amend commit message to explain in detail why cross-release isn't the solution. v6: Pull out misplaced .rst hunk. Acked-by: Christian König Acked-by: Dave Airlie Cc: Felix Kuehling Reviewed-by: Thomas Hellström Reviewed-by: Maarten Lankhorst Cc: Mika Kuoppala Cc: Thomas Hellstrom Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Cc: linux-rdma@vger.kernel.org Cc: amd-gfx@lists.freedesktop.org Cc: intel-gfx@lists.freedesktop.org Cc: Chris Wilson Cc: Maarten Lankhorst Cc: Christian König Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20200707201229.472834-2-daniel.vetter@ffwll.ch --- include/linux/dma-fence.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 3347c54f3a87..3f288f7db2ef 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -357,6 +357,18 @@ dma_fence_get_rcu_safe(struct dma_fence __rcu **fencep) } while (1); } +#ifdef CONFIG_LOCKDEP +bool dma_fence_begin_signalling(void); +void dma_fence_end_signalling(bool cookie); +#else +static inline bool dma_fence_begin_signalling(void) +{ + return true; +} +static inline void dma_fence_end_signalling(bool cookie) {} +static inline void __dma_fence_might_wait(void) {} +#endif + int dma_fence_signal(struct dma_fence *fence); int dma_fence_signal_locked(struct dma_fence *fence); signed long dma_fence_default_wait(struct dma_fence *fence, -- cgit v1.2.3 From d0b9a9aef0a18e7ba473d0887e7ebd107ab84fe4 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 7 Jul 2020 22:12:06 +0200 Subject: dma-fence: prime lockdep annotations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Two in one go: - it is allowed to call dma_fence_wait() while holding a dma_resv_lock(). This is fundamental to how eviction works with ttm, so required. - it is allowed to call dma_fence_wait() from memory reclaim contexts, specifically from shrinker callbacks (which i915 does), and from mmu notifier callbacks (which amdgpu does, and which i915 sometimes also does, and probably always should, but that's kinda a debate). Also for stuff like HMM we really need to be able to do this, or things get real dicey. Consequence is that any critical path necessary to get to a dma_fence_signal for a fence must never a) call dma_resv_lock nor b) allocate memory with GFP_KERNEL. Also by implication of dma_resv_lock(), no userspace faulting allowed. That's some supremely obnoxious limitations, which is why we need to sprinkle the right annotations to all relevant paths. The one big locking context we're leaving out here is mmu notifiers, added in commit 23b68395c7c78a764e8963fc15a7cfd318bf187f Author: Daniel Vetter Date: Mon Aug 26 22:14:21 2019 +0200 mm/mmu_notifiers: add a lockdep map for invalidate_range_start/end that one covers a lot of other callsites, and it's also allowed to wait on dma-fences from mmu notifiers. But there's no ready-made functions exposed to prime this, so I've left it out for now. v2: Also track against mmu notifier context. v3: kerneldoc to spec the cross-driver contract. Note that currently i915 throws in a hard-coded 10s timeout on foreign fences (not sure why that was done, but it's there), which is why that rule is worded with SHOULD instead of MUST. Also some of the mmu_notifier/shrinker rules might surprise SoC drivers, I haven't fully audited them all. Which is infeasible anyway, we'll need to run them with lockdep and dma-fence annotations and see what goes boom. v4: A spelling fix from Mika v5: #ifdef for CONFIG_MMU_NOTIFIER. Reported by 0day. Unfortunately this means lockdep enforcement is slightly inconsistent, it won't spot GFP_NOIO and GFP_NOFS allocations in the wrong spot if CONFIG_MMU_NOTIFIER is disabled in the kernel config. Oh well. v5: Note that only drivers/gpu has a reasonable (or at least historical) excuse to use dma_fence_wait() from shrinker and mmu notifier callbacks. Everyone else should either have a better memory manager model, or better hardware. This reflects discussions with Jason Gunthorpe. Cc: Jason Gunthorpe Cc: Felix Kuehling Cc: kernel test robot Acked-by: Christian König Acked-by: Dave Airlie Reviewed-by: Maarten Lankhorst Reviewed-by: Thomas Hellström (v4) Cc: Mika Kuoppala Cc: Thomas Hellstrom Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Cc: linux-rdma@vger.kernel.org Cc: amd-gfx@lists.freedesktop.org Cc: intel-gfx@lists.freedesktop.org Cc: Chris Wilson Cc: Maarten Lankhorst Cc: Christian König Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20200707201229.472834-3-daniel.vetter@ffwll.ch --- include/linux/dma-fence.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 3f288f7db2ef..09e23adb351d 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -360,6 +360,7 @@ dma_fence_get_rcu_safe(struct dma_fence __rcu **fencep) #ifdef CONFIG_LOCKDEP bool dma_fence_begin_signalling(void); void dma_fence_end_signalling(bool cookie); +void __dma_fence_might_wait(void); #else static inline bool dma_fence_begin_signalling(void) { -- cgit v1.2.3 From af0e5f1f47d8b7139ee446bc2367f74e4f034202 Mon Sep 17 00:00:00 2001 From: Amit Kucheria Date: Wed, 1 Jul 2020 21:44:14 +0530 Subject: thermal/drivers/clock_cooling: Remove clock_cooling code clock_cooling has no in-kernel users. It has never found any use in drivers as far as I can tell. Remove the code. Signed-off-by: Amit Kucheria Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/aa5d5ac2589cf7b14ece882130731b4a916849a6.1593619943.git.amit.kucheria@linaro.org --- include/linux/clock_cooling.h | 57 ------------------------------------------- 1 file changed, 57 deletions(-) delete mode 100644 include/linux/clock_cooling.h (limited to 'include/linux') diff --git a/include/linux/clock_cooling.h b/include/linux/clock_cooling.h deleted file mode 100644 index 4b0a69863656..000000000000 --- a/include/linux/clock_cooling.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * linux/include/linux/clock_cooling.h - * - * Copyright (C) 2014 Eduardo Valentin - * - * Copyright (C) 2013 Texas Instruments Inc. - * Contact: Eduardo Valentin - * - * Highly based on cpufreq_cooling.c. - * Copyright (C) 2012 Samsung Electronics Co., Ltd(http://www.samsung.com) - * Copyright (C) 2012 Amit Daniel - */ - -#ifndef __CPU_COOLING_H__ -#define __CPU_COOLING_H__ - -#include -#include -#include - -#ifdef CONFIG_CLOCK_THERMAL -/** - * clock_cooling_register - function to create clock cooling device. - * @dev: struct device pointer to the device used as clock cooling device. - * @clock_name: string containing the clock used as cooling mechanism. - */ -struct thermal_cooling_device * -clock_cooling_register(struct device *dev, const char *clock_name); - -/** - * clock_cooling_unregister - function to remove clock cooling device. - * @cdev: thermal cooling device pointer. - */ -void clock_cooling_unregister(struct thermal_cooling_device *cdev); - -unsigned long clock_cooling_get_level(struct thermal_cooling_device *cdev, - unsigned long freq); -#else /* !CONFIG_CLOCK_THERMAL */ -static inline struct thermal_cooling_device * -clock_cooling_register(struct device *dev, const char *clock_name) -{ - return NULL; -} -static inline -void clock_cooling_unregister(struct thermal_cooling_device *cdev) -{ -} -static inline -unsigned long clock_cooling_get_level(struct thermal_cooling_device *cdev, - unsigned long freq) -{ - return THERMAL_CSTATE_INVALID; -} -#endif /* CONFIG_CLOCK_THERMAL */ - -#endif /* __CPU_COOLING_H__ */ -- cgit v1.2.3 From e506ea451254ab17e0bf918ca36232fec2a9b10c Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 15 Oct 2019 16:29:32 -0700 Subject: compiler.h: Split {READ,WRITE}_ONCE definitions out into rwonce.h In preparation for allowing architectures to define their own implementation of the READ_ONCE() macro, move the generic {READ,WRITE}_ONCE() definitions out of the unwieldy 'linux/compiler.h' file and into a new 'rwonce.h' header under 'asm-generic'. Acked-by: Peter Zijlstra (Intel) Acked-by: Paul E. McKenney Signed-off-by: Will Deacon --- include/linux/compiler.h | 93 ++---------------------------------------------- 1 file changed, 2 insertions(+), 91 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 204e76856435..f075a3df4fe2 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -230,28 +230,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__) #endif -/* - * Prevent the compiler from merging or refetching reads or writes. The - * compiler is also forbidden from reordering successive instances of - * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some - * particular ordering. One way to make the compiler aware of ordering is to - * put the two invocations of READ_ONCE or WRITE_ONCE in different C - * statements. - * - * These two macros will also work on aggregate data types like structs or - * unions. - * - * Their two major use cases are: (1) Mediating communication between - * process-level code and irq/NMI handlers, all running on the same CPU, - * and (2) Ensuring that the compiler does not fold, spindle, or otherwise - * mutilate accesses that either do not require ordering or that interact - * with an explicit memory barrier or atomic instruction that provides the - * required ordering. - */ -#include -#include -#include - /** * data_race - mark an expression as containing intentional data races * @@ -272,65 +250,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, __v; \ }) -/* - * Use __READ_ONCE() instead of READ_ONCE() if you do not require any - * atomicity or dependency ordering guarantees. Note that this may result - * in tears! - */ -#define __READ_ONCE(x) (*(const volatile __unqual_scalar_typeof(x) *)&(x)) - -#define __READ_ONCE_SCALAR(x) \ -({ \ - __unqual_scalar_typeof(x) __x = __READ_ONCE(x); \ - smp_read_barrier_depends(); \ - (typeof(x))__x; \ -}) - -#define READ_ONCE(x) \ -({ \ - compiletime_assert_rwonce_type(x); \ - __READ_ONCE_SCALAR(x); \ -}) - -#define __WRITE_ONCE(x, val) \ -do { \ - *(volatile typeof(x) *)&(x) = (val); \ -} while (0) - -#define WRITE_ONCE(x, val) \ -do { \ - compiletime_assert_rwonce_type(x); \ - __WRITE_ONCE(x, val); \ -} while (0) - -static __no_sanitize_or_inline -unsigned long __read_once_word_nocheck(const void *addr) -{ - return __READ_ONCE(*(unsigned long *)addr); -} - -/* - * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a - * word from memory atomically but without telling KASAN/KCSAN. This is - * usually used by unwinding code when walking the stack of a running process. - */ -#define READ_ONCE_NOCHECK(x) \ -({ \ - unsigned long __x; \ - compiletime_assert(sizeof(x) == sizeof(__x), \ - "Unsupported access size for READ_ONCE_NOCHECK()."); \ - __x = __read_once_word_nocheck(&(x)); \ - smp_read_barrier_depends(); \ - (typeof(x))__x; \ -}) - -static __no_kasan_or_inline -unsigned long read_word_at_a_time(const void *addr) -{ - kasan_check_read(addr, 1); - return *(unsigned long *)addr; -} - #endif /* __KERNEL__ */ /* @@ -395,16 +314,6 @@ static inline void *offset_to_ptr(const int *off) compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") -/* - * Yes, this permits 64-bit accesses on 32-bit architectures. These will - * actually be atomic in some cases (namely Armv7 + LPAE), but for others we - * rely on the access being split into 2x32-bit accesses for a 32-bit quantity - * (e.g. a virtual address) and a strong prevailing wind. - */ -#define compiletime_assert_rwonce_type(t) \ - compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ - "Unsupported access size for {READ,WRITE}_ONCE().") - /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) @@ -414,4 +323,6 @@ static inline void *offset_to_ptr(const int *off) */ #define prevent_tail_call_optimization() mb() +#include + #endif /* __LINUX_COMPILER_H */ -- cgit v1.2.3 From 002dff36acfba3476b685a09f78ffb7c452f5951 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 10 Jul 2020 14:49:40 +0100 Subject: asm/rwonce: Don't pull into 'asm-generic/rwonce.h' Now that 'smp_read_barrier_depends()' has gone the way of the Norwegian Blue, drop the inclusion of in 'asm-generic/rwonce.h'. This requires fixups to some architecture vdso headers which were previously relying on 'asm/barrier.h' coming in via 'linux/compiler.h'. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Will Deacon --- include/linux/nospec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nospec.h b/include/linux/nospec.h index 0c5ef54fd416..c1e79f72cd89 100644 --- a/include/linux/nospec.h +++ b/include/linux/nospec.h @@ -5,6 +5,8 @@ #ifndef _LINUX_NOSPEC_H #define _LINUX_NOSPEC_H + +#include #include struct task_struct; -- cgit v1.2.3 From c6cd2e011655aead2097273a04350f52429a1a8d Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 7 Nov 2019 14:46:59 +0000 Subject: include/linux: Remove smp_read_barrier_depends() from comments smp_read_barrier_depends() doesn't exist any more, so reword the two comments that mention it to refer to "dependency ordering" instead. Acked-by: Peter Zijlstra (Intel) Acked-by: Paul E. McKenney Signed-off-by: Will Deacon --- include/linux/percpu-refcount.h | 2 +- include/linux/ptr_ring.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 22d9d183950d..87d8a38bdea1 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -155,7 +155,7 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref, * between contaminating the pointer value, meaning that * READ_ONCE() is required when fetching it. * - * The smp_read_barrier_depends() implied by READ_ONCE() pairs + * The dependency ordering from the READ_ONCE() pairs * with smp_store_release() in __percpu_ref_switch_to_percpu(). */ percpu_ptr = READ_ONCE(ref->percpu_count_ptr); diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 417db0a79a62..808f9d3ee546 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -107,7 +107,7 @@ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) return -ENOSPC; /* Make sure the pointer we are storing points to a valid data. */ - /* Pairs with smp_read_barrier_depends in __ptr_ring_consume. */ + /* Pairs with the dependency ordering in __ptr_ring_consume. */ smp_wmb(); WRITE_ONCE(r->queue[r->producer++], ptr); -- cgit v1.2.3 From eb5c2d4b45e3d2d5d052ea6b8f1463976b1020d5 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 21 Jul 2020 09:54:15 +0100 Subject: compiler.h: Move compiletime_assert() macros into compiler_types.h The kernel test robot reports that moving READ_ONCE() out into its own header breaks a W=1 build for parisc, which is relying on the definition of compiletime_assert() being available: | In file included from ./arch/parisc/include/generated/asm/rwonce.h:1, | from ./include/asm-generic/barrier.h:16, | from ./arch/parisc/include/asm/barrier.h:29, | from ./arch/parisc/include/asm/atomic.h:11, | from ./include/linux/atomic.h:7, | from kernel/locking/percpu-rwsem.c:2: | ./arch/parisc/include/asm/atomic.h: In function 'atomic_read': | ./include/asm-generic/rwonce.h:36:2: error: implicit declaration of function 'compiletime_assert' [-Werror=implicit-function-declaration] | 36 | compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ | | ^~~~~~~~~~~~~~~~~~ | ./include/asm-generic/rwonce.h:49:2: note: in expansion of macro 'compiletime_assert_rwonce_type' | 49 | compiletime_assert_rwonce_type(x); \ | | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | ./arch/parisc/include/asm/atomic.h:73:9: note: in expansion of macro 'READ_ONCE' | 73 | return READ_ONCE((v)->counter); | | ^~~~~~~~~ Move these macros into compiler_types.h, so that they are available to READ_ONCE() and friends. Link: http://lists.infradead.org/pipermail/linux-arm-kernel/2020-July/587094.html Reported-by: kernel test robot Signed-off-by: Will Deacon --- include/linux/compiler.h | 41 ----------------------------------------- include/linux/compiler_types.h | 41 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index f075a3df4fe2..59f7194fdf08 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -273,47 +273,6 @@ static inline void *offset_to_ptr(const int *off) #endif /* __ASSEMBLY__ */ -/* Compile time object size, -1 for unknown */ -#ifndef __compiletime_object_size -# define __compiletime_object_size(obj) -1 -#endif -#ifndef __compiletime_warning -# define __compiletime_warning(message) -#endif -#ifndef __compiletime_error -# define __compiletime_error(message) -#endif - -#ifdef __OPTIMIZE__ -# define __compiletime_assert(condition, msg, prefix, suffix) \ - do { \ - extern void prefix ## suffix(void) __compiletime_error(msg); \ - if (!(condition)) \ - prefix ## suffix(); \ - } while (0) -#else -# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0) -#endif - -#define _compiletime_assert(condition, msg, prefix, suffix) \ - __compiletime_assert(condition, msg, prefix, suffix) - -/** - * compiletime_assert - break build and emit msg if condition is false - * @condition: a compile-time constant condition to check - * @msg: a message to emit if condition is false - * - * In tradition of POSIX assert, this macro will break the build if the - * supplied condition is *false*, emitting the supplied error message if the - * compiler has support to do so. - */ -#define compiletime_assert(condition, msg) \ - _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) - -#define compiletime_assert_atomic_type(t) \ - compiletime_assert(__native_word(t), \ - "Need native word sized stores/loads for atomicity.") - /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index c3bf7710f69a..d9bbb62a3e2a 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -300,6 +300,47 @@ struct ftrace_likely_data { (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) +/* Compile time object size, -1 for unknown */ +#ifndef __compiletime_object_size +# define __compiletime_object_size(obj) -1 +#endif +#ifndef __compiletime_warning +# define __compiletime_warning(message) +#endif +#ifndef __compiletime_error +# define __compiletime_error(message) +#endif + +#ifdef __OPTIMIZE__ +# define __compiletime_assert(condition, msg, prefix, suffix) \ + do { \ + extern void prefix ## suffix(void) __compiletime_error(msg); \ + if (!(condition)) \ + prefix ## suffix(); \ + } while (0) +#else +# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0) +#endif + +#define _compiletime_assert(condition, msg, prefix, suffix) \ + __compiletime_assert(condition, msg, prefix, suffix) + +/** + * compiletime_assert - break build and emit msg if condition is false + * @condition: a compile-time constant condition to check + * @msg: a message to emit if condition is false + * + * In tradition of POSIX assert, this macro will break the build if the + * supplied condition is *false*, emitting the supplied error message if the + * compiler has support to do so. + */ +#define compiletime_assert(condition, msg) \ + _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) + +#define compiletime_assert_atomic_type(t) \ + compiletime_assert(__native_word(t), \ + "Need native word sized stores/loads for atomicity.") + /* Helpers for emitting diagnostics in pragmas. */ #ifndef __diag #define __diag(string) -- cgit v1.2.3 From 4a17c441c7cb06ac1e5fd3409a64d8ce78151983 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 16 Jul 2020 23:09:40 +0800 Subject: soundwire: intel: revisit SHIM programming sequences. Somehow the existing code is not aligned with the steps described in the documentation, refactor code and make sure the register programming sequences are correct. Also add missing power-up, power-down and wake capabilities (the last two are used in follow-up patches but introduced here for consistency). Some of the SHIM registers exposed fields that are link specific, and in addition some of the power-related registers (SPA/CPA) take time to be updated. Uncontrolled access leads to timeouts or errors. Add a mutex, shared by all links, so that all accesses to such registers are serialized, and follow a pattern of read-modify-write. This includes making sure SHIM_SYNC is programmed only once, before the first master is powered on. We use a 'shim_mask' field, shared between all links and protected by a mutex, to deal with power-up and power-down sequences. Note that the SYNCPRD value is tied only to the XTAL value and not the current bus frequency or the frame rate. BugLink: https://github.com/thesofproject/linux/issues/1555 Signed-off-by: Rander Wang Signed-off-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20200716150947.22119-3-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_intel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 979b41b5dcb4..120ffddc03d2 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -115,6 +115,7 @@ struct sdw_intel_slave_id { * links * @link_list: list to handle interrupts across all links * @shim_lock: mutex to handle concurrent rmw access to shared SHIM registers. + * @shim_mask: flags to track initialization of SHIM shared registers */ struct sdw_intel_ctx { int count; @@ -126,6 +127,7 @@ struct sdw_intel_ctx { struct sdw_intel_slave_id *ids; struct list_head link_list; struct mutex shim_lock; /* lock for access to shared SHIM registers */ + u32 shim_mask; }; /** -- cgit v1.2.3 From b2dcfefc43f783c4462f30507f78b7bb093ee8df Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Wed, 15 Jul 2020 20:41:26 -0700 Subject: usb: typec: tcpm: Support bist test data mode for compliance TCPM supports BIST carried mode. PD compliance tests require BIST Test Data to be supported as well. Introducing set_bist_data callback to signal tcpc driver for configuring the port controller hardware to enable/disable BIST Test Data mode. Signed-off-by: Badhri Jagan Sridharan Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20200716034128.1251728-1-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tcpm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index e7979c01c351..89f58760cf48 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -79,6 +79,7 @@ enum tcpm_transmit_type { * @try_role: Optional; called to set a preferred role * @pd_transmit:Called to transmit PD message * @mux: Pointer to multiplexer data + * @set_bist_data: Turn on/off bist data mode for compliance testing */ struct tcpc_dev { struct fwnode_handle *fwnode; @@ -103,6 +104,7 @@ struct tcpc_dev { int (*try_role)(struct tcpc_dev *dev, int role); int (*pd_transmit)(struct tcpc_dev *dev, enum tcpm_transmit_type type, const struct pd_message *msg); + int (*set_bist_data)(struct tcpc_dev *dev, bool on); }; struct tcpm_port; -- cgit v1.2.3 From 6e1c2241f4cecfc21f26f44179d04217c8390338 Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Wed, 15 Jul 2020 20:41:28 -0700 Subject: usb: typec: tcpm: Stay in BIST mode till hardreset or unattached MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Port starts to toggle when transitioning to unattached state. This is incorrect while in BIST mode. 6.4.3.1 BIST Carrier Mode Upon receipt of a BIST Message, with a BIST Carrier Mode BIST Data Object, the UUT Shall send out a continuous string of BMC encoded alternating "1"s and “0”s. The UUT Shall exit the Continuous BIST Mode within tBISTContMode of this Continuous BIST Mode being enabled(see Section 6.6.7.2). 6.4.3.2 BIST Test Data Upon receipt of a BIST Message, with a BIST Test Data BIST Data Object, the UUT Shall return a GoodCRC Message and Shall enter a test mode in which it sends no further Messages except for GoodCRC Messages in response to received Messages. See Section 5.9.2 for the definition of the Test Data Frame. The test Shall be ended by sending Hard Reset Signaling to reset the UUT. Signed-off-by: Badhri Jagan Sridharan Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20200716034128.1251728-3-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index a665d7f21142..b6c233e79bd4 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -483,4 +483,5 @@ static inline unsigned int rdo_max_power(u32 rdo) #define PD_N_CAPS_COUNT (PD_T_NO_RESPONSE / PD_T_SEND_SOURCE_CAP) #define PD_N_HARD_RESET_COUNT 2 +#define PD_T_BIST_CONT_MODE 50 /* 30 - 60 ms */ #endif /* __LINUX_USB_PD_H */ -- cgit v1.2.3 From ffeb1e9e897b8d36b197275592d121c96d3bdb95 Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Sun, 19 Jul 2020 18:09:10 +0200 Subject: USB: Replace HTTP links with HTTPS ones Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. Signed-off-by: Alexander A. Klimov Link: https://lore.kernel.org/r/20200719160910.60018-1-grandmaster@al2klimov.de Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/phy_companion.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/phy_companion.h b/include/linux/usb/phy_companion.h index 407f530061cd..263196f05015 100644 --- a/include/linux/usb/phy_companion.h +++ b/include/linux/usb/phy_companion.h @@ -2,7 +2,7 @@ /* * phy-companion.h -- phy companion to indicate the comparator part of PHY * - * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or -- cgit v1.2.3 From 9746c9be0bb5860592e048468b37974be4c59d44 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 11 Jul 2020 06:45:36 -0500 Subject: exec: Remove unnecessary spaces from binfmts.h The general convention in the linux kernel is to define a pointer member as "type *name". The declaration of struct linux_binprm has several pointer defined as "type * name". Update them to the form of "type *name" for consistency. Suggested-by: Kees Cook Reviewed-by: Kees Cook Reviewed-by: Christoph Hellwig Link: https://lkml.kernel.org/r/87v9iq6x9x.fsf@x220.int.ebiederm.org Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 7c27d7b57871..eb5cb8df5485 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -45,15 +45,15 @@ struct linux_binprm { #ifdef __alpha__ unsigned int taso:1; #endif - struct file * executable; /* Executable to pass to the interpreter */ - struct file * interpreter; - struct file * file; + struct file *executable; /* Executable to pass to the interpreter */ + struct file *interpreter; + struct file *file; struct cred *cred; /* new credentials */ int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ unsigned int per_clear; /* bits to clear in current->personality */ int argc, envc; - const char * filename; /* Name of binary as seen by procps */ - const char * interp; /* Name of the binary really executed. Most + const char *filename; /* Name of binary as seen by procps */ + const char *interp; /* Name of the binary really executed. Most of the time same as filename, but could be different for binfmt_{misc,script} */ unsigned interp_flags; -- cgit v1.2.3 From 60d9ad1d1d7f15964d23f6e71a7adcf1bde0e18e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 11 Jul 2020 08:16:15 -0500 Subject: exec: Move initialization of bprm->filename into alloc_bprm Currently it is necessary for the usermode helper code and the code that launches init to use set_fs so that pages coming from the kernel look like they are coming from userspace. To allow that usage of set_fs to be removed cleanly the argument copying from userspace needs to happen earlier. Move the computation of bprm->filename and possible allocation of a name in the case of execveat into alloc_bprm to make that possible. The exectuable name, the arguments, and the environment are copied into the new usermode stack which is stored in bprm until exec passes the point of no return. As the executable name is copied first onto the usermode stack it needs to be known. As there are no dependencies to computing the executable name, compute it early in alloc_bprm. As an implementation detail if the filename needs to be generated because it embeds a file descriptor store that filename in a new field bprm->fdpath, and free it in free_bprm. Previously this was done in an independent variable pathbuf. I have renamed pathbuf fdpath because fdpath is more suggestive of what kind of path is in the variable. I moved fdpath into struct linux_binprm because it is tightly tied to the other variables in struct linux_binprm, and as such is needed to allow the call alloc_binprm to move. Reviewed-by: Kees Cook Reviewed-by: Christoph Hellwig Link: https://lkml.kernel.org/r/87k0z66x8f.fsf@x220.int.ebiederm.org Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index eb5cb8df5485..8e9e1b0c8eb8 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -56,6 +56,7 @@ struct linux_binprm { const char *interp; /* Name of the binary really executed. Most of the time same as filename, but could be different for binfmt_{misc,script} */ + const char *fdpath; /* generated filename for execveat */ unsigned interp_flags; int execfd; /* File descriptor of the executable */ unsigned long loader, exec; -- cgit v1.2.3 From be619f7f063a49c656f620a46af4f8ea3e759e91 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 13 Jul 2020 12:06:48 -0500 Subject: exec: Implement kernel_execve To allow the kernel not to play games with set_fs to call exec implement kernel_execve. The function kernel_execve takes pointers into kernel memory and copies the values pointed to onto the new userspace stack. The calls with arguments from kernel space of do_execve are replaced with calls to kernel_execve. The calls do_execve and do_execveat are made static as there are now no callers outside of exec. The comments that mention do_execve are updated to refer to kernel_execve or execve depending on the circumstances. In addition to correcting the comments, this makes it easy to grep for do_execve and verify it is not used. Inspired-by: https://lkml.kernel.org/r/20200627072704.2447163-1-hch@lst.de Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/87wo365ikj.fsf@x220.int.ebiederm.org Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 8e9e1b0c8eb8..0571701ab1c5 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -135,12 +135,7 @@ int copy_string_kernel(const char *arg, struct linux_binprm *bprm); extern void set_binfmt(struct linux_binfmt *new); extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t); -extern int do_execve(struct filename *, - const char __user * const __user *, - const char __user * const __user *); -extern int do_execveat(int, struct filename *, - const char __user * const __user *, - const char __user * const __user *, - int); +int kernel_execve(const char *filename, + const char *const *argv, const char *const *envp); #endif /* _LINUX_BINFMTS_H */ -- cgit v1.2.3 From d061cd734f1a59798574b50188b14b49e95a54d3 Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Thu, 16 Jul 2020 11:57:40 -0600 Subject: coresight: Fix comment in main header file Comment for an elemnt in the coresight_device structure appears to have been corrupted and makes no sense. Fix this before making further changes. Signed-off-by: Mike Leach Reviewed-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200716175746.3338735-12-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index e3e9f0e3a878..84dc695e87d4 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -179,7 +179,8 @@ struct coresight_sysfs_link { * @enable: 'true' if component is currently part of an active path. * @activated: 'true' only if a _sink_ has been activated. A sink can be * activated but not yet enabled. Enabling for a _sink_ - * appens when a source has been selected for that it. + * happens when a source has been selected and a path is enabled + * from source to that sink. * @ea: Device attribute for sink representation under PMU directory. * @ect_dev: Associated cross trigger device. Not part of the trace data * path or connections. -- cgit v1.2.3 From 0336bdfd7354edfa3db0e01675b5df224516e3e9 Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Thu, 16 Jul 2020 11:57:43 -0600 Subject: coresight: Add default sink selection to CoreSight base Adds a method to select a suitable sink connected to a given source. In cases where no sink is defined, the coresight_find_default_sink routine can search from a given source, through the child connections until a suitable sink is found. The suitability is defined in by the sink coresight_dev_subtype on the CoreSight device, and the distance from the source by counting connections. Higher value subtype is preferred - where these are equal, shorter distance from source is used as a tie-break. This allows for default sink to be discovered were none is specified (e.g. perf command line) Signed-off-by: Mike Leach Suggested-by: Suzuki K Poulose Reviewed-by: Leo Yan Reviewed-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20200716175746.3338735-15-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 84dc695e87d4..58fffdecdbfd 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -48,6 +48,7 @@ enum coresight_dev_subtype_sink { CORESIGHT_DEV_SUBTYPE_SINK_NONE, CORESIGHT_DEV_SUBTYPE_SINK_PORT, CORESIGHT_DEV_SUBTYPE_SINK_BUFFER, + CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM, }; enum coresight_dev_subtype_link { @@ -182,6 +183,7 @@ struct coresight_sysfs_link { * happens when a source has been selected and a path is enabled * from source to that sink. * @ea: Device attribute for sink representation under PMU directory. + * @def_sink: cached reference to default sink found for this device. * @ect_dev: Associated cross trigger device. Not part of the trace data * path or connections. * @nr_links: number of sysfs links created to other components from this @@ -200,6 +202,7 @@ struct coresight_device { /* sink specific fields */ bool activated; /* true only if a sink is part of a path */ struct dev_ext_attribute *ea; + struct coresight_device *def_sink; /* cross trigger handling */ struct coresight_device *ect_dev; /* sysfs links between components */ -- cgit v1.2.3 From 5c9fa16e8abd342ce04dc830c1ebb2a03abf6c05 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 3 Jul 2020 11:19:57 +1000 Subject: powerpc/64s: Remove PROT_SAO support ISA v3.1 does not support the SAO storage control attribute required to implement PROT_SAO. PROT_SAO was used by specialised system software (Lx86) that has been discontinued for about 7 years, and is not thought to be used elsewhere, so removal should not cause problems. We rather remove it than keep support for older processors, because live migrating guest partitions to newer processors may not be possible if SAO is in use (or worse allowed with silent races). - PROT_SAO stays in the uapi header so code using it would still build. - arch_validate_prot() is removed, the generic version rejects PROT_SAO so applications would get a failure at mmap() time. Signed-off-by: Nicholas Piggin [mpe: Drop KVM change for the time being] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200703011958.1166620-3-npiggin@gmail.com --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index dc7b87310c10..6c8333d6c991 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -317,8 +317,6 @@ extern unsigned int kobjsize(const void *objp); #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ -#elif defined(CONFIG_PPC) -# define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_IA64) -- cgit v1.2.3 From f1d9b23cabc61e58509164c3c3132556476491d2 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Mon, 13 Jul 2020 15:51:59 -0400 Subject: audit: purge audit_log_string from the intra-kernel audit API audit_log_string() was inteded to be an internal audit function and since there are only two internal uses, remove them. Purge all external uses of it by restructuring code to use an existing audit_log_format() or using audit_log_format(). Please see the upstream issue https://github.com/linux-audit/audit-kernel/issues/84 Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 523f77494847..b3d859831a31 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -694,9 +694,4 @@ static inline bool audit_loginuid_set(struct task_struct *tsk) return uid_valid(audit_get_loginuid(tsk)); } -static inline void audit_log_string(struct audit_buffer *ab, const char *buf) -{ - audit_log_n_string(ab, buf, strlen(buf)); -} - #endif -- cgit v1.2.3 From 98cc1b93724aa85bd828269855d48d884c702726 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Mon, 20 Jul 2020 15:43:57 -0500 Subject: power_supply: Add additional health properties to the header Add HEALTH_WARM, HEALTH_COOL and HEALTH_HOT to the health enum. HEALTH_WARM, HEALTH_COOL, and HEALTH_HOT properties are taken from JEITA specification JISC8712:2015 Acked-by: Andrew F. Davis Tested-by: Guru Das Srinagesh Signed-off-by: Dan Murphy Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index ac1345a48ad0..b5ee35d3c304 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -62,6 +62,9 @@ enum { POWER_SUPPLY_HEALTH_SAFETY_TIMER_EXPIRE, POWER_SUPPLY_HEALTH_OVERCURRENT, POWER_SUPPLY_HEALTH_CALIBRATION_REQUIRED, + POWER_SUPPLY_HEALTH_WARM, + POWER_SUPPLY_HEALTH_COOL, + POWER_SUPPLY_HEALTH_HOT, }; enum { -- cgit v1.2.3 From bc4f0548f683a3d53359cef15f088d2d5bb4bc39 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 20 Jul 2020 09:33:58 -0700 Subject: bpf: Compute bpf_skc_to_*() helper socket btf ids at build time Currently, socket types (struct tcp_sock, udp_sock, etc.) used by bpf_skc_to_*() helpers are computed when vmlinux_btf is first built in the kernel. Commit 5a2798ab32ba ("bpf: Add BTF_ID_LIST/BTF_ID/BTF_ID_UNUSED macros") implemented a mechanism to compute btf_ids at kernel build time which can simplify kernel implementation and reduce runtime overhead by removing in-kernel btf_id calculation. This patch did exactly this, removing in-kernel btf_id computation and utilizing build-time btf_id computation. If CONFIG_DEBUG_INFO_BTF is not defined, BTF_ID_LIST will define an array with size of 5, which is not enough for btf_sock_ids. So define its own static array if CONFIG_DEBUG_INFO_BTF is not defined. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200720163358.1393023-1-yhs@fb.com --- include/linux/bpf.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index adb16bdc5f0a..1df1c0fd3f28 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1541,7 +1541,6 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map) struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); -void init_btf_sock_ids(struct btf *btf); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -1567,9 +1566,6 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) static inline void bpf_map_offload_map_free(struct bpf_map *map) { } -static inline void init_btf_sock_ids(struct btf *btf) -{ -} #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_BPF_STREAM_PARSER) -- cgit v1.2.3 From 0f12e584b241285cf60a6227f3771fa444cfcf76 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 20 Jul 2020 09:34:01 -0700 Subject: bpf: Add BTF_ID_LIST_GLOBAL in btf_ids.h Existing BTF_ID_LIST used a local static variable to store btf_ids. This patch provided a new macro BTF_ID_LIST_GLOBAL to store btf_ids in a global variable which can be shared among multiple files. The existing BTF_ID_LIST is still retained. Two reasons. First, BTF_ID_LIST is also used to build btf_ids for helper arguments which typically is an array of 5. Since typically different helpers have different signature, it makes little sense to share them. Second, some current computed btf_ids are indeed local. If later those btf_ids are shared between different files, they can use BTF_ID_LIST_GLOBAL then. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20200720163401.1393159-1-yhs@fb.com --- include/linux/btf_ids.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 1cdb56950ffe..77ab45baa095 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -57,17 +57,20 @@ asm( \ * .zero 4 * */ -#define __BTF_ID_LIST(name) \ +#define __BTF_ID_LIST(name, scope) \ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ -".local " #name "; \n" \ +"." #scope " " #name "; \n" \ #name ":; \n" \ ".popsection; \n"); \ #define BTF_ID_LIST(name) \ -__BTF_ID_LIST(name) \ +__BTF_ID_LIST(name, local) \ extern u32 name[]; +#define BTF_ID_LIST_GLOBAL(name) \ +__BTF_ID_LIST(name, globl) + /* * The BTF_ID_UNUSED macro defines 4 zero bytes. * It's used when we want to define 'unused' entry @@ -90,6 +93,7 @@ asm( \ #define BTF_ID_LIST(name) static u32 name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED +#define BTF_ID_LIST_GLOBAL(name) u32 name[1]; #endif /* CONFIG_DEBUG_INFO_BTF */ -- cgit v1.2.3 From fce557bcef119a1bc5ab3cb02678cf454bcaf424 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 20 Jul 2020 09:34:02 -0700 Subject: bpf: Make btf_sock_ids global tcp and udp bpf_iter can reuse some socket ids in btf_sock_ids, so make it global. I put the extern definition in btf_ids.h as a central place so it can be easily discovered by developers. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200720163402.1393427-1-yhs@fb.com --- include/linux/btf_ids.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 77ab45baa095..4867d549e3c1 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -97,4 +97,34 @@ asm( \ #endif /* CONFIG_DEBUG_INFO_BTF */ +#ifdef CONFIG_NET +/* Define a list of socket types which can be the argument for + * skc_to_*_sock() helpers. All these sockets should have + * sock_common as the first argument in its memory layout. + */ +#define BTF_SOCK_TYPE_xxx \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, inet_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, inet_connection_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, inet_request_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, inet_timewait_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, request_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, sock_common) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, tcp_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, tcp_request_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) + +enum { +#define BTF_SOCK_TYPE(name, str) name, +BTF_SOCK_TYPE_xxx +#undef BTF_SOCK_TYPE +MAX_BTF_SOCK_TYPE, +}; + +extern u32 btf_sock_ids[]; +#endif + #endif -- cgit v1.2.3 From 951cf368bcb11d6f817709660cf5cd914072c36f Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 20 Jul 2020 09:34:03 -0700 Subject: bpf: net: Use precomputed btf_id for bpf iterators One additional field btf_id is added to struct bpf_ctx_arg_aux to store the precomputed btf_ids. The btf_id is computed at build time with BTF_ID_LIST or BTF_ID_LIST_GLOBAL macro definitions. All existing bpf iterators are changed to used pre-compute btf_ids. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200720163403.1393551-1-yhs@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1df1c0fd3f28..bae557ff2da8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -668,6 +668,7 @@ struct bpf_jit_poke_descriptor { struct bpf_ctx_arg_aux { u32 offset; enum bpf_reg_type reg_type; + u32 btf_id; }; struct bpf_prog_aux { -- cgit v1.2.3 From 76abf9cea6c8215ea45b9359f11f0e30127c544a Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Thu, 16 Jul 2020 15:20:33 -0700 Subject: remoteproc: Pass size and offset as arguments to segment dump function Change the segment dump API signature to include size and offset arguments. Refactor the qcom_q6v5_mss driver to use these arguments while copying the segment. Doing this lays the ground work for "inline" coredump functionality being added in the next patch. Tested-by: Sibi Sankar Reviewed-by: Bjorn Andersson Reviewed-by: Sibi Sankar Reviewed-by: Mathieu Poirier Signed-off-by: Rishabh Bhatnagar Link: https://lore.kernel.org/r/1594938035-7327-4-git-send-email-rishabhb@codeaurora.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 7c0567029f7c..5dab13b6baae 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -456,7 +456,7 @@ struct rproc_dump_segment { void *priv; void (*dump)(struct rproc *rproc, struct rproc_dump_segment *segment, - void *dest); + void *dest, size_t offset, size_t size); loff_t offset; }; @@ -638,7 +638,8 @@ int rproc_coredump_add_custom_segment(struct rproc *rproc, dma_addr_t da, size_t size, void (*dumpfn)(struct rproc *rproc, struct rproc_dump_segment *segment, - void *dest), + void *dest, size_t offset, + size_t size), void *priv); int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine); -- cgit v1.2.3 From c97319881c9116dc7c56dd30115567b4078c4ba6 Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Thu, 16 Jul 2020 15:20:34 -0700 Subject: remoteproc: Add inline coredump functionality The current coredump implementation uses vmalloc area to copy all the segments. But this might put strain on low memory targets as the firmware size sometimes is in tens of MBs. The situation becomes worse if there are multiple remote processors undergoing recovery at the same time. This patch adds inline coredump functionality that avoids extra memory usage. This requires recovery to be halted until data is read by userspace and free function is called. Reviewed-by: Bjorn Andersson Reviewed-by: Sibi Sankar Reviewed-by: Mathieu Poirier Signed-off-by: Rishabh Bhatnagar Tested-by: Sibi Sankar Link: https://lore.kernel.org/r/1594938035-7327-5-git-send-email-rishabhb@codeaurora.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 5dab13b6baae..0e8d2ff575b4 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -439,6 +439,20 @@ enum rproc_crash_type { RPROC_FATAL_ERROR, }; +/** + * enum rproc_dump_mechanism - Coredump options for core + * @RPROC_COREDUMP_DEFAULT: Copy dump to separate buffer and carry on with + recovery + * @RPROC_COREDUMP_INLINE: Read segments directly from device memory. Stall + recovery until all segments are read + * @RPROC_COREDUMP_DISABLED: Don't perform any dump + */ +enum rproc_dump_mechanism { + RPROC_COREDUMP_DEFAULT, + RPROC_COREDUMP_INLINE, + RPROC_COREDUMP_DISABLED, +}; + /** * struct rproc_dump_segment - segment info from ELF header * @node: list node related to the rproc segment list @@ -471,6 +485,7 @@ struct rproc_dump_segment { * @dev: virtual device for refcounting and common remoteproc behavior * @power: refcount of users who need this rproc powered up * @state: state of the device + * @dump_conf: Currently selected coredump configuration * @lock: lock which protects concurrent manipulations of the rproc * @dbg_dir: debugfs directory of this rproc device * @traces: list of trace buffers @@ -505,6 +520,7 @@ struct rproc { struct device dev; atomic_t power; unsigned int state; + enum rproc_dump_mechanism dump_conf; struct mutex lock; struct dentry *dbg_dir; struct list_head traces; -- cgit v1.2.3 From 1571e700fd610c39e8b50b0110b1ee9badb2fe6a Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jul 2020 12:04:36 +0100 Subject: net: phylink: in-band pause mode advertisement update for PCS Re-code the pause in-band advertisement update in light of the addition of PCS support, so that we perform the minimum required; only the PCS configuration function needs to be called in this case, followed by the request to trigger a restart of negotiation if the programmed advertisement changed. We need to change the pcs_config() signature to pass whether resolved pause should be passed to the MAC for setups such as mvneta and mvpp2 where doing so overrides the MAC manual flow controls. Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index b32b8b45421b..d9913d8e6b91 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -286,7 +286,8 @@ struct phylink_pcs_ops { struct phylink_link_state *state); int (*pcs_config)(struct phylink_config *config, unsigned int mode, phy_interface_t interface, - const unsigned long *advertising); + const unsigned long *advertising, + bool permit_pause_to_mac); void (*pcs_an_restart)(struct phylink_config *config); void (*pcs_link_up)(struct phylink_config *config, unsigned int mode, phy_interface_t interface, int speed, int duplex); @@ -317,9 +318,11 @@ void pcs_get_state(struct phylink_config *config, * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. * @interface: interface mode to be used * @advertising: adertisement ethtool link mode mask + * @permit_pause_to_mac: permit forwarding pause resolution to MAC * * Configure the PCS for the operating mode, the interface mode, and set - * the advertisement mask. + * the advertisement mask. @permit_pause_to_mac indicates whether the + * hardware may forward the pause mode resolution to the MAC. * * When operating in %MLO_AN_INBAND, inband should always be enabled, * otherwise inband should be disabled. -- cgit v1.2.3 From b7ad14c2fe2d4b2abee491e3adfa3d0123aa2d8c Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jul 2020 12:04:41 +0100 Subject: net: phylink: re-implement interface configuration with PCS With PCS support, how we implement interface reconfiguration (or other major reconfiguration) is not up to the job; we end up reconfiguring the PCS for an interface change while the link could potentially be up. In order to solve this, add two additional MAC methods for major configuration, one to prepare for the change, and one to finish the change. This allows mvneta and mvpp2 to shutdown what they require prior to the MAC and PCS configuration calls, and then restart as appropriate. This impacts ksettings_set(), which now needs to identify whether the change is a minor tweak to the advertisement masks or whether the interface mode has changed, and call the appropriate function for that update. Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index d9913d8e6b91..2f1315f32113 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -76,7 +76,9 @@ struct phylink_config { * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. * @mac_pcs_get_state: Read the current link state from the hardware. + * @mac_prepare: prepare for a major reconfiguration of the interface. * @mac_config: configure the MAC for the selected mode and state. + * @mac_finish: finish a major reconfiguration of the interface. * @mac_an_restart: restart 802.3z BaseX autonegotiation. * @mac_link_down: take the link down. * @mac_link_up: allow the link to come up. @@ -89,8 +91,12 @@ struct phylink_mac_ops { struct phylink_link_state *state); void (*mac_pcs_get_state)(struct phylink_config *config, struct phylink_link_state *state); + int (*mac_prepare)(struct phylink_config *config, unsigned int mode, + phy_interface_t iface); void (*mac_config)(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); + int (*mac_finish)(struct phylink_config *config, unsigned int mode, + phy_interface_t iface); void (*mac_an_restart)(struct phylink_config *config); void (*mac_link_down)(struct phylink_config *config, unsigned int mode, phy_interface_t interface); @@ -145,6 +151,31 @@ void validate(struct phylink_config *config, unsigned long *supported, void mac_pcs_get_state(struct phylink_config *config, struct phylink_link_state *state); +/** + * mac_prepare() - prepare to change the PHY interface mode + * @config: a pointer to a &struct phylink_config. + * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. + * @iface: interface mode to switch to + * + * phylink will call this method at the beginning of a full initialisation + * of the link, which includes changing the interface mode or at initial + * startup time. It may be called for the current mode. The MAC driver + * should perform whatever actions are required, e.g. disabling the + * Serdes PHY. + * + * This will be the first call in the sequence: + * - mac_prepare() + * - mac_config() + * - pcs_config() + * - possible pcs_an_restart() + * - mac_finish() + * + * Returns zero on success, or negative errno on failure which will be + * reported to the kernel log. + */ +int mac_prepare(struct phylink_config *config, unsigned int mode, + phy_interface_t iface); + /** * mac_config() - configure the MAC for the selected mode and state * @config: a pointer to a &struct phylink_config. @@ -220,6 +251,23 @@ void mac_pcs_get_state(struct phylink_config *config, void mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); +/** + * mac_finish() - finish a to change the PHY interface mode + * @config: a pointer to a &struct phylink_config. + * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. + * @iface: interface mode to switch to + * + * phylink will call this if it called mac_prepare() to allow the MAC to + * complete any necessary steps after the MAC and PCS have been configured + * for the @mode and @iface. E.g. a MAC driver may wish to re-enable the + * Serdes PHY here if it was previously disabled by mac_prepare(). + * + * Returns zero on success, or negative errno on failure which will be + * reported to the kernel log. + */ +int mac_finish(struct phylink_config *config, unsigned int mode, + phy_interface_t iface); + /** * mac_an_restart() - restart 802.3z BaseX autonegotiation * @config: a pointer to a &struct phylink_config. -- cgit v1.2.3 From 7137e18f6f889a67046d5004e1690a32d7d2108d Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jul 2020 12:04:46 +0100 Subject: net: phylink: add struct phylink_pcs Add a way for MAC PCS to have private data while keeping independence from struct phylink_config, which is used for the MAC itself. We need this independence as we will have stand-alone code for PCS that is independent of the MAC. Introduce struct phylink_pcs, which is designed to be embedded in a driver private data structure. This structure does not include a mdio_device as there are PCS implementations such as the Marvell DSA and network drivers where this is not necessary. Reviewed-by: Ioana Ciornei Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 45 ++++++++++++++++++++++++++++++--------------- 1 file changed, 30 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 2f1315f32113..057f78263a46 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -321,6 +321,21 @@ void mac_link_up(struct phylink_config *config, struct phy_device *phy, int speed, int duplex, bool tx_pause, bool rx_pause); #endif +struct phylink_pcs_ops; + +/** + * struct phylink_pcs - PHYLINK PCS instance + * @ops: a pointer to the &struct phylink_pcs_ops structure + * @poll: poll the PCS for link changes + * + * This structure is designed to be embedded within the PCS private data, + * and will be passed between phylink and the PCS. + */ +struct phylink_pcs { + const struct phylink_pcs_ops *ops; + bool poll; +}; + /** * struct phylink_pcs_ops - MAC PCS operations structure. * @pcs_get_state: read the current MAC PCS link state from the hardware. @@ -330,21 +345,21 @@ void mac_link_up(struct phylink_config *config, struct phy_device *phy, * (where necessary). */ struct phylink_pcs_ops { - void (*pcs_get_state)(struct phylink_config *config, + void (*pcs_get_state)(struct phylink_pcs *pcs, struct phylink_link_state *state); - int (*pcs_config)(struct phylink_config *config, unsigned int mode, + int (*pcs_config)(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, const unsigned long *advertising, bool permit_pause_to_mac); - void (*pcs_an_restart)(struct phylink_config *config); - void (*pcs_link_up)(struct phylink_config *config, unsigned int mode, + void (*pcs_an_restart)(struct phylink_pcs *pcs); + void (*pcs_link_up)(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); }; #if 0 /* For kernel-doc purposes only. */ /** * pcs_get_state() - Read the current inband link state from the hardware - * @config: a pointer to a &struct phylink_config. + * @pcs: a pointer to a &struct phylink_pcs. * @state: a pointer to a &struct phylink_link_state. * * Read the current inband link state from the MAC PCS, reporting the @@ -357,12 +372,12 @@ struct phylink_pcs_ops { * When present, this overrides mac_pcs_get_state() in &struct * phylink_mac_ops. */ -void pcs_get_state(struct phylink_config *config, +void pcs_get_state(struct phylink_pcs *pcs, struct phylink_link_state *state); /** * pcs_config() - Configure the PCS mode and advertisement - * @config: a pointer to a &struct phylink_config. + * @pcs: a pointer to a &struct phylink_pcs. * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. * @interface: interface mode to be used * @advertising: adertisement ethtool link mode mask @@ -382,21 +397,21 @@ void pcs_get_state(struct phylink_config *config, * * For most 10GBASE-R, there is no advertisement. */ -int (*pcs_config)(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, const unsigned long *advertising); +int pcs_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, const unsigned long *advertising); /** * pcs_an_restart() - restart 802.3z BaseX autonegotiation - * @config: a pointer to a &struct phylink_config. + * @pcs: a pointer to a &struct phylink_pcs. * * When PCS ops are present, this overrides mac_an_restart() in &struct * phylink_mac_ops. */ -void (*pcs_an_restart)(struct phylink_config *config); +void pcs_an_restart(struct phylink_pcs *pcs); /** * pcs_link_up() - program the PCS for the resolved link configuration - * @config: a pointer to a &struct phylink_config. + * @pcs: a pointer to a &struct phylink_pcs. * @mode: link autonegotiation mode * @interface: link &typedef phy_interface_t mode * @speed: link speed @@ -407,14 +422,14 @@ void (*pcs_an_restart)(struct phylink_config *config); * mode without in-band AN needs to be manually configured for the link * and duplex setting. Otherwise, this should be a no-op. */ -void (*pcs_link_up)(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, int speed, int duplex); +void pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, int speed, int duplex); #endif struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, phy_interface_t iface, const struct phylink_mac_ops *mac_ops); -void phylink_add_pcs(struct phylink *, const struct phylink_pcs_ops *ops); +void phylink_set_pcs(struct phylink *, struct phylink_pcs *pcs); void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); -- cgit v1.2.3 From 93eaceb0fcf87b7f70924f9da3ec27e3c73be53d Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jul 2020 12:04:51 +0100 Subject: net: phylink: add interface to configure clause 22 PCS PHY Add an interface to configure the advertisement for a clause 22 PCS PHY, and set the AN enable flag in the BMCR appropriately. Reviewed-by: Ioana Ciornei Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 057f78263a46..1aad2aea4610 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -478,6 +478,9 @@ void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, int phylink_mii_c22_pcs_set_advertisement(struct mdio_device *pcs, phy_interface_t interface, const unsigned long *advertising); +int phylink_mii_c22_pcs_config(struct mdio_device *pcs, unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising); void phylink_mii_c22_pcs_an_restart(struct mdio_device *pcs); void phylink_mii_c45_pcs_get_state(struct mdio_device *pcs, -- cgit v1.2.3 From ab673b987488c4fab7a0bc4824a48211f9d910e3 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 21 Jul 2020 15:59:19 -0700 Subject: fscrypt: use smp_load_acquire() for ->i_crypt_info Normally smp_store_release() or cmpxchg_release() is paired with smp_load_acquire(). Sometimes smp_load_acquire() can be replaced with the more lightweight READ_ONCE(). However, for this to be safe, all the published memory must only be accessed in a way that involves the pointer itself. This may not be the case if allocating the object also involves initializing a static or global variable, for example. fscrypt_info includes various sub-objects which are internal to and are allocated by other kernel subsystems such as keyrings and crypto. So by using READ_ONCE() for ->i_crypt_info, we're relying on internal implementation details of these other kernel subsystems. Remove this fragile assumption by using smp_load_acquire() instead. (Note: I haven't seen any real-world problems here. This change is just fixing the code to be guaranteed correct and less fragile.) Fixes: e37a784d8b6a ("fscrypt: use READ_ONCE() to access ->i_crypt_info") Link: https://lore.kernel.org/r/20200721225920.114347-5-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 29 ++++++++++++++++++++++++----- 1 file changed, 24 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index bb257411365f..991ff8575d0e 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -74,10 +74,15 @@ struct fscrypt_operations { struct request_queue **devs); }; -static inline bool fscrypt_has_encryption_key(const struct inode *inode) +static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode) { - /* pairs with cmpxchg_release() in fscrypt_get_encryption_info() */ - return READ_ONCE(inode->i_crypt_info) != NULL; + /* + * Pairs with the cmpxchg_release() in fscrypt_get_encryption_info(). + * I.e., another task may publish ->i_crypt_info concurrently, executing + * a RELEASE barrier. We need to use smp_load_acquire() here to safely + * ACQUIRE the memory the other task published. + */ + return smp_load_acquire(&inode->i_crypt_info); } /** @@ -234,9 +239,9 @@ static inline void fscrypt_set_ops(struct super_block *sb, } #else /* !CONFIG_FS_ENCRYPTION */ -static inline bool fscrypt_has_encryption_key(const struct inode *inode) +static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode) { - return false; + return NULL; } static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) @@ -619,6 +624,20 @@ static inline bool fscrypt_inode_uses_fs_layer_crypto(const struct inode *inode) !__fscrypt_inode_uses_inline_crypto(inode); } +/** + * fscrypt_has_encryption_key() - check whether an inode has had its key set up + * @inode: the inode to check + * + * Return: %true if the inode has had its encryption key set up, else %false. + * + * Usually this should be preceded by fscrypt_get_encryption_info() to try to + * set up the key first. + */ +static inline bool fscrypt_has_encryption_key(const struct inode *inode) +{ + return fscrypt_get_info(inode) != NULL; +} + /** * fscrypt_require_key() - require an inode's encryption key * @inode: the inode we need the key for -- cgit v1.2.3 From f3db0bed458314a835ccef5ccb130270c5b2cf04 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 21 Jul 2020 15:59:20 -0700 Subject: fs-verity: use smp_load_acquire() for ->i_verity_info Normally smp_store_release() or cmpxchg_release() is paired with smp_load_acquire(). Sometimes smp_load_acquire() can be replaced with the more lightweight READ_ONCE(). However, for this to be safe, all the published memory must only be accessed in a way that involves the pointer itself. This may not be the case if allocating the object also involves initializing a static or global variable, for example. fsverity_info::tree_params.hash_alg->tfm is a crypto_ahash object that's internal to and is allocated by the crypto subsystem. So by using READ_ONCE() for ->i_verity_info, we're relying on internal implementation details of the crypto subsystem. Remove this fragile assumption by using smp_load_acquire() instead. Also fix the cmpxchg logic to correctly execute an ACQUIRE barrier when losing the cmpxchg race, since cmpxchg doesn't guarantee a memory barrier on failure. (Note: I haven't seen any real-world problems here. This change is just fixing the code to be guaranteed correct and less fragile.) Fixes: fd2d1acfcadf ("fs-verity: add the hook for file ->open()") Link: https://lore.kernel.org/r/20200721225920.114347-6-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fsverity.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 78201a6d35f6..c1144a450392 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -115,8 +115,13 @@ struct fsverity_operations { static inline struct fsverity_info *fsverity_get_info(const struct inode *inode) { - /* pairs with the cmpxchg() in fsverity_set_info() */ - return READ_ONCE(inode->i_verity_info); + /* + * Pairs with the cmpxchg_release() in fsverity_set_info(). + * I.e., another task may publish ->i_verity_info concurrently, + * executing a RELEASE barrier. We need to use smp_load_acquire() here + * to safely ACQUIRE the memory the other task published. + */ + return smp_load_acquire(&inode->i_verity_info); } /* enable.c */ -- cgit v1.2.3 From 58877d347b58c9e971112df5eb311c13bb0acb28 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 2 Jul 2020 14:52:11 +0200 Subject: sched: Better document ttwu() Dave hit the problem fixed by commit: b6e13e85829f ("sched/core: Fix ttwu() race") and failed to understand much of the code involved. Per his request a few comments to (hopefully) clarify things. Requested-by: Dave Chinner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200702125211.GQ4800@hirez.programming.kicks-ass.net --- include/linux/sched.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 12b10ce51a08..5033813fecd5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -154,24 +154,24 @@ struct task_group; * * for (;;) { * set_current_state(TASK_UNINTERRUPTIBLE); - * if (!need_sleep) - * break; + * if (CONDITION) + * break; * * schedule(); * } * __set_current_state(TASK_RUNNING); * * If the caller does not need such serialisation (because, for instance, the - * condition test and condition change and wakeup are under the same lock) then + * CONDITION test and condition change and wakeup are under the same lock) then * use __set_current_state(). * * The above is typically ordered against the wakeup, which does: * - * need_sleep = false; + * CONDITION = 1; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * - * where wake_up_state() executes a full memory barrier before accessing the - * task state. + * where wake_up_state()/try_to_wake_up() executes a full memory barrier before + * accessing p->state. * * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a -- cgit v1.2.3 From 46132e3ac58cb2ee48051ed80bffc0070ad59b2e Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 1 Jul 2020 14:34:18 -0400 Subject: sched: nohz: stop passing around unused "ticks" parameter. The "ticks" parameter was added in commit 0f004f5a696a ("sched: Cure more NO_HZ load average woes") since calc_global_nohz() was called and needed the "ticks" argument. But in commit c308b56b5398 ("sched: Fix nohz load accounting -- again!") it became unused as the function calc_global_nohz() dropped using "ticks". Fixes: c308b56b5398 ("sched: Fix nohz load accounting -- again!") Signed-off-by: Paul Gortmaker Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1593628458-32290-1-git-send-email-paul.gortmaker@windriver.com --- include/linux/sched/loadavg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index 4859bea47a7b..83ec54b65e79 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -43,6 +43,6 @@ extern unsigned long calc_load_n(unsigned long load, unsigned long exp, #define LOAD_INT(x) ((x) >> FSHIFT) #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) -extern void calc_global_load(unsigned long ticks); +extern void calc_global_load(void); #endif /* _LINUX_SCHED_LOADAVG_H */ -- cgit v1.2.3 From e0078e2eb8620079d988f150ba02a4ce9b5a946a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 18:30:31 -0700 Subject: linux/sched/mm.h: drop duplicated words in comments Drop doubled words "to" and "that". Signed-off-by: Randy Dunlap Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/927ea8d8-3f6c-9b65-4c2b-63ab4bd59ef1@infradead.org --- include/linux/sched/mm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index a98604ea76f1..6be66f52a2ad 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -23,7 +23,7 @@ extern struct mm_struct *mm_alloc(void); * will still exist later on and mmget_not_zero() has to be used before * accessing it. * - * This is a preferred way to to pin @mm for a longer/unbounded amount + * This is a preferred way to pin @mm for a longer/unbounded amount * of time. * * Use mmdrop() to release the reference acquired by mmgrab(). @@ -232,7 +232,7 @@ static inline unsigned int memalloc_noio_save(void) * @flags: Flags to restore. * * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function. - * Always make sure that that the given flags is the return value from the + * Always make sure that the given flags is the return value from the * pairing memalloc_noio_save call. */ static inline void memalloc_noio_restore(unsigned int flags) @@ -263,7 +263,7 @@ static inline unsigned int memalloc_nofs_save(void) * @flags: Flags to restore. * * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function. - * Always make sure that that the given flags is the return value from the + * Always make sure that the given flags is the return value from the * pairing memalloc_nofs_save call. */ static inline void memalloc_nofs_restore(unsigned int flags) -- cgit v1.2.3 From 25980c7a79af42f2daa73e2f475ebf4cbac8253e Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Sun, 12 Jul 2020 17:59:15 +0100 Subject: arch_topology, sched/core: Cleanup thermal pressure definition The following commit: 14533a16c46d ("thermal/cpu-cooling, sched/core: Move the arch_set_thermal_pressure() API to generic scheduler code") moved the definition of arch_set_thermal_pressure() to sched/core.c, but kept its declaration in linux/arch_topology.h. When building e.g. an x86 kernel with CONFIG_SCHED_THERMAL_PRESSURE=y, cpufreq_cooling.c ends up getting the declaration of arch_set_thermal_pressure() from include/linux/arch_topology.h, which is somewhat awkward. On top of this, sched/core.c unconditionally defines o The thermal_pressure percpu variable o arch_set_thermal_pressure() while arch_scale_thermal_pressure() does nothing unless redefined by the architecture. arch_*() functions are meant to be defined by architectures, so revert the aforementioned commit and re-implement it in a way that keeps arch_set_thermal_pressure() architecture-definable, and doesn't define the thermal pressure percpu variable for kernels that don't need it (CONFIG_SCHED_THERMAL_PRESSURE=n). Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200712165917.9168-2-valentin.schneider@arm.com --- include/linux/arch_topology.h | 4 ++-- include/linux/sched/topology.h | 7 +++++++ 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 0566cb3314ef..69b1dabe39dc 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -39,8 +39,8 @@ static inline unsigned long topology_get_thermal_pressure(int cpu) return per_cpu(thermal_pressure, cpu); } -void arch_set_thermal_pressure(struct cpumask *cpus, - unsigned long th_pressure); +void topology_set_thermal_pressure(const struct cpumask *cpus, + unsigned long th_pressure); struct cpu_topology { int thread_id; diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index fb11091129b3..764222d637b7 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -232,6 +232,13 @@ unsigned long arch_scale_thermal_pressure(int cpu) } #endif +#ifndef arch_set_thermal_pressure +static __always_inline +void arch_set_thermal_pressure(const struct cpumask *cpus, + unsigned long th_pressure) +{ } +#endif + static inline int task_node(const struct task_struct *p) { return cpu_to_node(task_cpu(p)); -- cgit v1.2.3 From c2127e14c127de2775feefdfb1444e30a129a59f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:30:27 -0700 Subject: perf: : drop a duplicated word Drop the repeated word "the" in a comment. Signed-off-by: Randy Dunlap Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200719003027.20798-1-rdunlap@infradead.org --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 3b22db08b6fb..0edd257a5916 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -366,7 +366,7 @@ struct pmu { * ->stop() with PERF_EF_UPDATE will read the counter and update * period/count values like ->read() would. * - * ->start() with PERF_EF_RELOAD will reprogram the the counter + * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. */ void (*start) (struct perf_event *event, int flags); -- cgit v1.2.3 From aca7ed091117d9b4ce499855c383119afb2819a2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 17 Jul 2020 16:38:15 -0700 Subject: i2c: drop duplicated word in the header file Drop the doubled word "be" in a comment. Signed-off-by: Randy Dunlap Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index b8b8963f8bb9..ee328cf80bd9 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -56,7 +56,7 @@ struct property_entry; * on a bus (or read from them). Apart from two basic transfer functions to * transmit one message at a time, a more complex version can be used to * transmit an arbitrary number of messages without interruption. - * @count must be be less than 64k since msg.len is u16. + * @count must be less than 64k since msg.len is u16. */ int i2c_transfer_buffer_flags(const struct i2c_client *client, char *buf, int count, u16 flags); -- cgit v1.2.3 From df746b3f079c31db7350b282c86e9004fa1a88df Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 21 Jul 2020 16:23:33 -0500 Subject: misc: rtsx: Remove unused pcie_cap There are no more uses of struct rtsx_pcr.pcie_cap. Remove it. Signed-off-by: Bjorn Helgaas Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200721212336.1159079-3-helgaas@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 27a6ea82aeea..4ff7b221f36e 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1166,7 +1166,6 @@ struct rtsx_hw_param { struct rtsx_pcr { struct pci_dev *pci; unsigned int id; - int pcie_cap; struct rtsx_cr_option option; struct rtsx_hw_param hw_param; -- cgit v1.2.3 From 22bf3251d7b7da0339f41ec27f2c3d4e0ec02255 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 21 Jul 2020 16:23:34 -0500 Subject: misc: rtsx: Remove rtsx_pci_read/write_config() wrappers rtsx_pci_read_config_dword() and similar wrappers around the PCI config accessors add very little value, and they obscure the fact that often we are accessing standard PCI registers that should be coordinated with the PCI core. Remove the wrappers and use the PCI config accessors directly. No functional change intended. Signed-off-by: Bjorn Helgaas Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200721212336.1159079-4-helgaas@kernel.org [ fixed up some other instances as original patch was based on old tree - gregkh Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 4ff7b221f36e..b93573c3c5fc 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -99,18 +99,6 @@ #define rtsx_pci_readb(pcr, reg) \ ioread8((pcr)->remap_addr + reg) -#define rtsx_pci_read_config_byte(pcr, where, val) \ - pci_read_config_byte((pcr)->pci, where, val) - -#define rtsx_pci_write_config_byte(pcr, where, val) \ - pci_write_config_byte((pcr)->pci, where, val) - -#define rtsx_pci_read_config_dword(pcr, where, val) \ - pci_read_config_dword((pcr)->pci, where, val) - -#define rtsx_pci_write_config_dword(pcr, where, val) \ - pci_write_config_dword((pcr)->pci, where, val) - #define STATE_TRANS_NONE 0 #define STATE_TRANS_CMD 1 #define STATE_TRANS_BUF 2 -- cgit v1.2.3 From ed86a9877d05b99088a409a7603828b818a433dc Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 21 Jul 2020 16:23:35 -0500 Subject: misc: rtsx: Find L1 PM Substates capability instead of hard-coding Instead of hard-coding the location of the L1 PM Substates capability based on the Device ID, search for it in the extended capabilities list. This works for any device, as long as it implements the L1 PM Substates capability correctly, so it doesn't require maintenance as new devices are added. No functional change intended. Signed-off-by: Bjorn Helgaas Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200721212336.1159079-5-helgaas@kernel.org [ minor addition due to differences in my tree - gregkh] Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index b93573c3c5fc..f146ca413f38 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1037,10 +1037,6 @@ #define PHY_DIG1E_RX_EN_KEEP 0x0001 #define PHY_DUM_REG 0x1F -#define PCR_ASPM_SETTING_REG1 0x160 -#define PCR_ASPM_SETTING_REG2 0x168 -#define PCR_ASPM_SETTING_5260 0x178 - #define PCR_SETTING_REG1 0x724 #define PCR_SETTING_REG2 0x814 #define PCR_SETTING_REG3 0x747 -- cgit v1.2.3 From 7a4462a96777b64b22412f782de226c90290bf75 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 21 Jul 2020 16:23:36 -0500 Subject: misc: rtsx: Use standard PCI definitions When reading registers defined by the PCIe spec, use the names already defined by the PCI core. This makes maintenance of the PCI core and drivers easier. No functional change intended. Signed-off-by: Bjorn Helgaas Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20200721212336.1159079-6-helgaas@kernel.org [ additional replacements due to changes in my tree - gregkh ] Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index f146ca413f38..745f5e73f99a 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1083,11 +1083,6 @@ struct pcr_ops { enum PDEV_STAT {PDEV_STAT_IDLE, PDEV_STAT_RUN}; -#define ASPM_L1_1_EN_MASK BIT(3) -#define ASPM_L1_2_EN_MASK BIT(2) -#define PM_L1_1_EN_MASK BIT(1) -#define PM_L1_2_EN_MASK BIT(0) - #define ASPM_L1_1_EN BIT(0) #define ASPM_L1_2_EN BIT(1) #define PM_L1_1_EN BIT(2) -- cgit v1.2.3 From 55d5d3b46b08a4dc0b05343d24640744e7430ed7 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Thu, 16 Jul 2020 13:19:56 -0500 Subject: leds: multicolor: Introduce a multicolor class definition Introduce a multicolor class that groups colored LEDs within a LED node. The multicolor class groups monochrome LEDs and allows controlling two aspects of the final combined color: hue and lightness. The former is controlled via the intensity file and the latter is controlled via brightness file. Signed-off-by: Dan Murphy Acked-by: Jacek Anaszewski Signed-off-by: Pavel Machek [squashed leds: multicolor: Fix camel case in documentation in] --- include/linux/led-class-multicolor.h | 121 +++++++++++++++++++++++++++++++++++ 1 file changed, 121 insertions(+) create mode 100644 include/linux/led-class-multicolor.h (limited to 'include/linux') diff --git a/include/linux/led-class-multicolor.h b/include/linux/led-class-multicolor.h new file mode 100644 index 000000000000..5116f9a866cc --- /dev/null +++ b/include/linux/led-class-multicolor.h @@ -0,0 +1,121 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* LED Multicolor class interface + * Copyright (C) 2019-20 Texas Instruments Incorporated - http://www.ti.com/ + */ + +#ifndef _LINUX_MULTICOLOR_LEDS_H_INCLUDED +#define _LINUX_MULTICOLOR_LEDS_H_INCLUDED + +#include +#include + +struct mc_subled { + unsigned int color_index; + unsigned int brightness; + unsigned int intensity; + unsigned int channel; +}; + +struct led_classdev_mc { + /* led class device */ + struct led_classdev led_cdev; + unsigned int num_colors; + + struct mc_subled *subled_info; +}; + +static inline struct led_classdev_mc *lcdev_to_mccdev( + struct led_classdev *led_cdev) +{ + return container_of(led_cdev, struct led_classdev_mc, led_cdev); +} + +#if IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR) +/** + * led_classdev_multicolor_register_ext - register a new object of led_classdev + * class with support for multicolor LEDs + * @parent: the multicolor LED to register + * @mcled_cdev: the led_classdev_mc structure for this device + * @init_data: the LED class multicolor device initialization data + * + * Returns: 0 on success or negative error value on failure + */ +int led_classdev_multicolor_register_ext(struct device *parent, + struct led_classdev_mc *mcled_cdev, + struct led_init_data *init_data); + +static inline int led_classdev_multicolor_register(struct device *parent, + struct led_classdev_mc *mcled_cdev) +{ + return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL); +} + +/** + * led_classdev_multicolor_unregister - unregisters an object of led_classdev + * class with support for multicolor LEDs + * @mcled_cdev: the multicolor LED to unregister + * + * Unregister a previously registered via led_classdev_multicolor_register + * object + */ +void led_classdev_multicolor_unregister(struct led_classdev_mc *mcled_cdev); + +/* Calculate brightness for the monochrome LED cluster */ +int led_mc_calc_color_components(struct led_classdev_mc *mcled_cdev, + enum led_brightness brightness); + +int devm_led_classdev_multicolor_register_ext(struct device *parent, + struct led_classdev_mc *mcled_cdev, + struct led_init_data *init_data); + +static inline int devm_led_classdev_multicolor_register(struct device *parent, + struct led_classdev_mc *mcled_cdev) +{ + return devm_led_classdev_multicolor_register_ext(parent, mcled_cdev, + NULL); +} + +void devm_led_classdev_multicolor_unregister(struct device *parent, + struct led_classdev_mc *mcled_cdev); +#else + +static inline int led_classdev_multicolor_register_ext(struct device *parent, + struct led_classdev_mc *mcled_cdev, + struct led_init_data *init_data) +{ + return -EINVAL; +} + +static inline int led_classdev_multicolor_register(struct device *parent, + struct led_classdev_mc *mcled_cdev) +{ + return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL); +} + +static inline void led_classdev_multicolor_unregister(struct led_classdev_mc *mcled_cdev) {}; +static inline int led_mc_calc_color_components(struct led_classdev_mc *mcled_cdev, + enum led_brightness brightness) +{ + return -EINVAL; +} + +static inline int devm_led_classdev_multicolor_register_ext(struct device *parent, + struct led_classdev_mc *mcled_cdev, + struct led_init_data *init_data) +{ + return -EINVAL; +} + +static inline int devm_led_classdev_multicolor_register(struct device *parent, + struct led_classdev_mc *mcled_cdev) +{ + return devm_led_classdev_multicolor_register_ext(parent, mcled_cdev, + NULL); +} + +static inline void devm_led_classdev_multicolor_unregister(struct device *parent, + struct led_classdev_mc *mcled_cdev) +{}; + +#endif /* IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR) */ +#endif /* _LINUX_MULTICOLOR_LEDS_H_INCLUDED */ -- cgit v1.2.3 From 92a81562e695628086acb92f95090ab09d9b9ec0 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Thu, 16 Jul 2020 13:20:01 -0500 Subject: leds: lp55xx: Add multicolor framework support to lp55xx Add multicolor framework support for the lp55xx family. Acked-by: Pavel Machek Acked-by: Jacek Anaszewski Signed-off-by: Dan Murphy Signed-off-by: Pavel Machek --- include/linux/platform_data/leds-lp55xx.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h index 00492d6ff018..3441064713a3 100644 --- a/include/linux/platform_data/leds-lp55xx.h +++ b/include/linux/platform_data/leds-lp55xx.h @@ -13,18 +13,25 @@ #define _LEDS_LP55XX_H #include +#include /* Clock configuration */ #define LP55XX_CLOCK_AUTO 0 #define LP55XX_CLOCK_INT 1 #define LP55XX_CLOCK_EXT 2 +#define LP55XX_MAX_GROUPED_CHAN 4 + struct lp55xx_led_config { const char *name; const char *default_trigger; u8 chan_nr; u8 led_current; /* mA x10, 0 if led is not connected */ u8 max_current; + int num_colors; + unsigned int max_channel; + int color_id[LED_COLOR_ID_MAX]; + int output_num[LED_COLOR_ID_MAX]; }; struct lp55xx_predef_pattern { -- cgit v1.2.3 From 93690cdf3060c61dfce813121d0bfc055e7fa30d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Thu, 16 Jul 2020 19:17:28 +0200 Subject: leds: trigger: add support for LED-private device triggers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some LED controllers may come with an internal HW triggering mechanism for the LED and the ability to switch between SW control and the internal HW control. This includes most PHYs, various ethernet switches, the Turris Omnia LED controller or AXP20X PMIC. This adds support for registering such triggers. This code is based on work by Pavel Machek and Ondřej Jirman . Signed-off-by: Marek Behún Acked-by: Jacek Anaszewski Signed-off-by: Pavel Machek --- include/linux/leds.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 2451962d1ec5..6a8d6409c993 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -57,6 +57,10 @@ struct led_init_data { bool devname_mandatory; }; +struct led_hw_trigger_type { + int dummy; +}; + struct led_classdev { const char *name; enum led_brightness brightness; @@ -141,6 +145,9 @@ struct led_classdev { void *trigger_data; /* true if activated - deactivate routine uses it to do cleanup */ bool activated; + + /* LEDs that have private triggers have this set */ + struct led_hw_trigger_type *trigger_type; #endif #ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED @@ -345,6 +352,9 @@ struct led_trigger { int (*activate)(struct led_classdev *led_cdev); void (*deactivate)(struct led_classdev *led_cdev); + /* LED-private triggers have this set */ + struct led_hw_trigger_type *trigger_type; + /* LEDs under control by this trigger (for simple triggers) */ rwlock_t leddev_list_lock; struct list_head led_cdevs; -- cgit v1.2.3 From 2cf2f4f546f1dea54b63302a7eb28d1fe15f1e28 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:31 +0300 Subject: qed: reformat "qed_chain.h" a bit Reformat structs and macros definitions a bit prior to making functional changes. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 126 ++++++++++++++++++++++-------------------- 1 file changed, 66 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 7071dc92b4e2..087073517c09 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -26,9 +26,9 @@ enum qed_chain_mode { }; enum qed_chain_use_mode { - QED_CHAIN_USE_TO_PRODUCE, /* Chain starts empty */ - QED_CHAIN_USE_TO_CONSUME, /* Chain starts full */ - QED_CHAIN_USE_TO_CONSUME_PRODUCE, /* Chain starts empty */ + QED_CHAIN_USE_TO_PRODUCE, /* Chain starts empty */ + QED_CHAIN_USE_TO_CONSUME, /* Chain starts full */ + QED_CHAIN_USE_TO_CONSUME_PRODUCE, /* Chain starts empty */ }; enum qed_chain_cnt_type { @@ -40,84 +40,86 @@ enum qed_chain_cnt_type { }; struct qed_chain_next { - struct regpair next_phys; - void *next_virt; + struct regpair next_phys; + void *next_virt; }; struct qed_chain_pbl_u16 { - u16 prod_page_idx; - u16 cons_page_idx; + u16 prod_page_idx; + u16 cons_page_idx; }; struct qed_chain_pbl_u32 { - u32 prod_page_idx; - u32 cons_page_idx; + u32 prod_page_idx; + u32 cons_page_idx; }; struct qed_chain_ext_pbl { - dma_addr_t p_pbl_phys; - void *p_pbl_virt; + dma_addr_t p_pbl_phys; + void *p_pbl_virt; }; struct qed_chain_u16 { /* Cyclic index of next element to produce/consme */ - u16 prod_idx; - u16 cons_idx; + u16 prod_idx; + u16 cons_idx; }; struct qed_chain_u32 { /* Cyclic index of next element to produce/consme */ - u32 prod_idx; - u32 cons_idx; + u32 prod_idx; + u32 cons_idx; }; struct addr_tbl_entry { - void *virt_addr; - dma_addr_t dma_map; + void *virt_addr; + dma_addr_t dma_map; }; struct qed_chain { - /* fastpath portion of the chain - required for commands such + /* Fastpath portion of the chain - required for commands such * as produce / consume. */ + /* Point to next element to produce/consume */ - void *p_prod_elem; - void *p_cons_elem; + void *p_prod_elem; + void *p_cons_elem; /* Fastpath portions of the PBL [if exists] */ + struct { /* Table for keeping the virtual and physical addresses of the * chain pages, respectively to the physical addresses * in the pbl table. */ - struct addr_tbl_entry *pp_addr_tbl; + struct addr_tbl_entry *pp_addr_tbl; union { - struct qed_chain_pbl_u16 u16; - struct qed_chain_pbl_u32 u32; - } c; - } pbl; + struct qed_chain_pbl_u16 u16; + struct qed_chain_pbl_u32 u32; + } c; + } pbl; union { - struct qed_chain_u16 chain16; - struct qed_chain_u32 chain32; - } u; + struct qed_chain_u16 chain16; + struct qed_chain_u32 chain32; + } u; /* Capacity counts only usable elements */ - u32 capacity; - u32 page_cnt; + u32 capacity; + u32 page_cnt; - enum qed_chain_mode mode; + enum qed_chain_mode mode; /* Elements information for fast calculations */ - u16 elem_per_page; - u16 elem_per_page_mask; - u16 elem_size; - u16 next_page_mask; - u16 usable_per_page; - u8 elem_unusable; + u16 elem_per_page; + u16 elem_per_page_mask; + u16 elem_size; + u16 next_page_mask; + u16 usable_per_page; + u8 elem_unusable; - u8 cnt_type; + u8 cnt_type; /* Slowpath of the chain - required for initialization and destruction, * but isn't involved in regular functionality. @@ -125,43 +127,47 @@ struct qed_chain { /* Base address of a pre-allocated buffer for pbl */ struct { - dma_addr_t p_phys_table; - void *p_virt_table; - } pbl_sp; + dma_addr_t p_phys_table; + void *p_virt_table; + } pbl_sp; /* Address of first page of the chain - the address is required * for fastpath operation [consume/produce] but only for the SINGLE * flavour which isn't considered fastpath [== SPQ]. */ - void *p_virt_addr; - dma_addr_t p_phys_addr; + void *p_virt_addr; + dma_addr_t p_phys_addr; /* Total number of elements [for entire chain] */ - u32 size; + u32 size; - u8 intended_use; + u8 intended_use; - bool b_external_pbl; + bool b_external_pbl; }; -#define QED_CHAIN_PBL_ENTRY_SIZE (8) -#define QED_CHAIN_PAGE_SIZE (0x1000) -#define ELEMS_PER_PAGE(elem_size) (QED_CHAIN_PAGE_SIZE / (elem_size)) +#define QED_CHAIN_PBL_ENTRY_SIZE 8 +#define QED_CHAIN_PAGE_SIZE 0x1000 + +#define ELEMS_PER_PAGE(elem_size) \ + (QED_CHAIN_PAGE_SIZE / (elem_size)) -#define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode) \ - (((mode) == QED_CHAIN_MODE_NEXT_PTR) ? \ - (u8)(1 + ((sizeof(struct qed_chain_next) - 1) / \ - (elem_size))) : 0) +#define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode) \ + (((mode) == QED_CHAIN_MODE_NEXT_PTR) ? \ + (u8)(1 + ((sizeof(struct qed_chain_next) - 1) / (elem_size))) : \ + 0) -#define USABLE_ELEMS_PER_PAGE(elem_size, mode) \ - ((u32)(ELEMS_PER_PAGE(elem_size) - \ - UNUSABLE_ELEMS_PER_PAGE(elem_size, mode))) +#define USABLE_ELEMS_PER_PAGE(elem_size, mode) \ + ((u32)(ELEMS_PER_PAGE(elem_size) - \ + UNUSABLE_ELEMS_PER_PAGE((elem_size), (mode)))) -#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, mode) \ - DIV_ROUND_UP(elem_cnt, USABLE_ELEMS_PER_PAGE(elem_size, mode)) +#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, mode) \ + DIV_ROUND_UP((elem_cnt), USABLE_ELEMS_PER_PAGE((elem_size), (mode))) -#define is_chain_u16(p) ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U16) -#define is_chain_u32(p) ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U32) +#define is_chain_u16(p) \ + ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U16) +#define is_chain_u32(p) \ + ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U32) /* Accessors */ static inline u16 qed_chain_get_prod_idx(struct qed_chain *p_chain) -- cgit v1.2.3 From 9b6ee3cf95d322ab02e9927f5b08ebc870ca9f1f Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:35 +0300 Subject: qed: sanitize PBL chains allocation PBL chain elements are actually DMA addresses stored in __le64, but currently their size is hardcoded to 8, and DMA addresses are assigned via cast to variable-sized dma_addr_t without any bitwise conversions. Change the type of pbl_virt array to match the actual one, add a new field to store the size of allocated DMA memory and sanitize elements assignment. Misc: give more logic names to the members of qed_chain::pbl_sp embedded struct. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 087073517c09..265e0b671a5c 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -127,8 +127,9 @@ struct qed_chain { /* Base address of a pre-allocated buffer for pbl */ struct { - dma_addr_t p_phys_table; - void *p_virt_table; + __le64 *table_virt; + dma_addr_t table_phys; + size_t table_size; } pbl_sp; /* Address of first page of the chain - the address is required @@ -146,7 +147,6 @@ struct qed_chain { bool b_external_pbl; }; -#define QED_CHAIN_PBL_ENTRY_SIZE 8 #define QED_CHAIN_PAGE_SIZE 0x1000 #define ELEMS_PER_PAGE(elem_size) \ @@ -236,7 +236,7 @@ static inline u32 qed_chain_get_page_cnt(struct qed_chain *p_chain) static inline dma_addr_t qed_chain_get_pbl_phys(struct qed_chain *p_chain) { - return p_chain->pbl_sp.p_phys_table; + return p_chain->pbl_sp.table_phys; } /** @@ -527,8 +527,8 @@ static inline void qed_chain_init_params(struct qed_chain *p_chain, p_chain->capacity = p_chain->usable_per_page * page_cnt; p_chain->size = p_chain->elem_per_page * page_cnt; - p_chain->pbl_sp.p_phys_table = 0; - p_chain->pbl_sp.p_virt_table = NULL; + p_chain->pbl_sp.table_phys = 0; + p_chain->pbl_sp.table_virt = NULL; p_chain->pbl.pp_addr_tbl = NULL; } @@ -569,8 +569,8 @@ static inline void qed_chain_init_pbl_mem(struct qed_chain *p_chain, dma_addr_t p_phys_pbl, struct addr_tbl_entry *pp_addr_tbl) { - p_chain->pbl_sp.p_phys_table = p_phys_pbl; - p_chain->pbl_sp.p_virt_table = p_virt_pbl; + p_chain->pbl_sp.table_phys = p_phys_pbl; + p_chain->pbl_sp.table_virt = p_virt_pbl; p_chain->pbl.pp_addr_tbl = pp_addr_tbl; } -- cgit v1.2.3 From 5e776d8016119e13c27fbb6e87c9e1fd6f8b2a75 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:36 +0300 Subject: qed: move chain initialization inlines next to allocation functions qed_chain_init*() are used in one file/place on "cold" path only, so they can be uninlined and moved next to the call sites. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 112 ------------------------------------------ 1 file changed, 112 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 265e0b671a5c..a0d83095dc73 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -490,118 +490,6 @@ static inline void qed_chain_reset(struct qed_chain *p_chain) } } -/** - * @brief qed_chain_init - Initalizes a basic chain struct - * - * @param p_chain - * @param p_virt_addr - * @param p_phys_addr physical address of allocated buffer's beginning - * @param page_cnt number of pages in the allocated buffer - * @param elem_size size of each element in the chain - * @param intended_use - * @param mode - */ -static inline void qed_chain_init_params(struct qed_chain *p_chain, - u32 page_cnt, - u8 elem_size, - enum qed_chain_use_mode intended_use, - enum qed_chain_mode mode, - enum qed_chain_cnt_type cnt_type) -{ - /* chain fixed parameters */ - p_chain->p_virt_addr = NULL; - p_chain->p_phys_addr = 0; - p_chain->elem_size = elem_size; - p_chain->intended_use = (u8)intended_use; - p_chain->mode = mode; - p_chain->cnt_type = (u8)cnt_type; - - p_chain->elem_per_page = ELEMS_PER_PAGE(elem_size); - p_chain->usable_per_page = USABLE_ELEMS_PER_PAGE(elem_size, mode); - p_chain->elem_per_page_mask = p_chain->elem_per_page - 1; - p_chain->elem_unusable = UNUSABLE_ELEMS_PER_PAGE(elem_size, mode); - p_chain->next_page_mask = (p_chain->usable_per_page & - p_chain->elem_per_page_mask); - - p_chain->page_cnt = page_cnt; - p_chain->capacity = p_chain->usable_per_page * page_cnt; - p_chain->size = p_chain->elem_per_page * page_cnt; - - p_chain->pbl_sp.table_phys = 0; - p_chain->pbl_sp.table_virt = NULL; - p_chain->pbl.pp_addr_tbl = NULL; -} - -/** - * @brief qed_chain_init_mem - - * - * Initalizes a basic chain struct with its chain buffers - * - * @param p_chain - * @param p_virt_addr virtual address of allocated buffer's beginning - * @param p_phys_addr physical address of allocated buffer's beginning - * - */ -static inline void qed_chain_init_mem(struct qed_chain *p_chain, - void *p_virt_addr, dma_addr_t p_phys_addr) -{ - p_chain->p_virt_addr = p_virt_addr; - p_chain->p_phys_addr = p_phys_addr; -} - -/** - * @brief qed_chain_init_pbl_mem - - * - * Initalizes a basic chain struct with its pbl buffers - * - * @param p_chain - * @param p_virt_pbl pointer to a pre allocated side table which will hold - * virtual page addresses. - * @param p_phys_pbl pointer to a pre-allocated side table which will hold - * physical page addresses. - * @param pp_virt_addr_tbl - * pointer to a pre-allocated side table which will hold - * the virtual addresses of the chain pages. - * - */ -static inline void qed_chain_init_pbl_mem(struct qed_chain *p_chain, - void *p_virt_pbl, - dma_addr_t p_phys_pbl, - struct addr_tbl_entry *pp_addr_tbl) -{ - p_chain->pbl_sp.table_phys = p_phys_pbl; - p_chain->pbl_sp.table_virt = p_virt_pbl; - p_chain->pbl.pp_addr_tbl = pp_addr_tbl; -} - -/** - * @brief qed_chain_init_next_ptr_elem - - * - * Initalizes a next pointer element - * - * @param p_chain - * @param p_virt_curr virtual address of a chain page of which the next - * pointer element is initialized - * @param p_virt_next virtual address of the next chain page - * @param p_phys_next physical address of the next chain page - * - */ -static inline void -qed_chain_init_next_ptr_elem(struct qed_chain *p_chain, - void *p_virt_curr, - void *p_virt_next, dma_addr_t p_phys_next) -{ - struct qed_chain_next *p_next; - u32 size; - - size = p_chain->elem_size * p_chain->usable_per_page; - p_next = (struct qed_chain_next *)((u8 *)p_virt_curr + size); - - DMA_REGPAIR_LE(p_next->next_phys, p_phys_next); - - p_next->next_virt = p_virt_next; -} - /** * @brief qed_chain_get_last_elem - * -- cgit v1.2.3 From b6db3f71c976ea92361dbc7ebfb65db666ac9f02 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:38 +0300 Subject: qed: simplify chain allocation with init params struct To simplify qed_chain_alloc() prototype and call sites, introduce struct qed_chain_init_params to specify chain params, and pass a pointer to filled struct to the actual qed_chain_alloc() instead of a long list of separate arguments. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 21 ++++++++++++++------- include/linux/qed/qed_if.h | 9 ++------- 2 files changed, 16 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index a0d83095dc73..f5cfee0934e5 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -54,11 +54,6 @@ struct qed_chain_pbl_u32 { u32 cons_page_idx; }; -struct qed_chain_ext_pbl { - dma_addr_t p_pbl_phys; - void *p_pbl_virt; -}; - struct qed_chain_u16 { /* Cyclic index of next element to produce/consme */ u16 prod_idx; @@ -119,7 +114,7 @@ struct qed_chain { u16 usable_per_page; u8 elem_unusable; - u8 cnt_type; + enum qed_chain_cnt_type cnt_type; /* Slowpath of the chain - required for initialization and destruction, * but isn't involved in regular functionality. @@ -142,11 +137,23 @@ struct qed_chain { /* Total number of elements [for entire chain] */ u32 size; - u8 intended_use; + enum qed_chain_use_mode intended_use; bool b_external_pbl; }; +struct qed_chain_init_params { + enum qed_chain_mode mode; + enum qed_chain_use_mode intended_use; + enum qed_chain_cnt_type cnt_type; + + u32 num_elems; + size_t elem_size; + + void *ext_pbl_virt; + dma_addr_t ext_pbl_phys; +}; + #define QED_CHAIN_PAGE_SIZE 0x1000 #define ELEMS_PER_PAGE(elem_size) \ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index a5c6854343e6..cd6a5c7e56eb 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -948,13 +948,8 @@ struct qed_common_ops { u8 dp_level); int (*chain_alloc)(struct qed_dev *cdev, - enum qed_chain_use_mode intended_use, - enum qed_chain_mode mode, - enum qed_chain_cnt_type cnt_type, - u32 num_elems, - size_t elem_size, - struct qed_chain *p_chain, - struct qed_chain_ext_pbl *ext_pbl); + struct qed_chain *chain, + struct qed_chain_init_params *params); void (*chain_free)(struct qed_dev *cdev, struct qed_chain *p_chain); -- cgit v1.2.3 From 155065866bc36f20061c55fd2ca287a466911b16 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:39 +0300 Subject: qed: add support for different page sizes for chains Extend current infrastructure to store chain page size in a struct and use it in all functions instead of fixed QED_CHAIN_PAGE_SIZE. Its value remains the default one, but can be overridden in qed_chain_init_params before chain allocation. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index f5cfee0934e5..8a96c361cc19 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -120,6 +121,8 @@ struct qed_chain { * but isn't involved in regular functionality. */ + u32 page_size; + /* Base address of a pre-allocated buffer for pbl */ struct { __le64 *table_virt; @@ -147,6 +150,7 @@ struct qed_chain_init_params { enum qed_chain_use_mode intended_use; enum qed_chain_cnt_type cnt_type; + u32 page_size; u32 num_elems; size_t elem_size; @@ -154,22 +158,23 @@ struct qed_chain_init_params { dma_addr_t ext_pbl_phys; }; -#define QED_CHAIN_PAGE_SIZE 0x1000 +#define QED_CHAIN_PAGE_SIZE SZ_4K -#define ELEMS_PER_PAGE(elem_size) \ - (QED_CHAIN_PAGE_SIZE / (elem_size)) +#define ELEMS_PER_PAGE(elem_size, page_size) \ + ((page_size) / (elem_size)) #define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode) \ (((mode) == QED_CHAIN_MODE_NEXT_PTR) ? \ (u8)(1 + ((sizeof(struct qed_chain_next) - 1) / (elem_size))) : \ 0) -#define USABLE_ELEMS_PER_PAGE(elem_size, mode) \ - ((u32)(ELEMS_PER_PAGE(elem_size) - \ +#define USABLE_ELEMS_PER_PAGE(elem_size, page_size, mode) \ + ((u32)(ELEMS_PER_PAGE((elem_size), (page_size)) - \ UNUSABLE_ELEMS_PER_PAGE((elem_size), (mode)))) -#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, mode) \ - DIV_ROUND_UP((elem_cnt), USABLE_ELEMS_PER_PAGE((elem_size), (mode))) +#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, page_size, mode) \ + DIV_ROUND_UP((elem_cnt), \ + USABLE_ELEMS_PER_PAGE((elem_size), (page_size), (mode))) #define is_chain_u16(p) \ ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U16) @@ -604,7 +609,7 @@ static inline void qed_chain_pbl_zero_mem(struct qed_chain *p_chain) for (i = 0; i < page_cnt; i++) memset(p_chain->pbl.pp_addr_tbl[i].virt_addr, 0, - QED_CHAIN_PAGE_SIZE); + p_chain->page_size); } #endif -- cgit v1.2.3 From f2aefd20b02d83b8565c867c38eedd88853967e9 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:40 +0300 Subject: qed: optimize common chain accessors Constify chain pointers and refactor qed_chain_get_elem_left{,u32}() a bit. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 60 ++++++++++++++++++++++++------------------- 1 file changed, 33 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 8a96c361cc19..434479e2ab65 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -182,73 +182,79 @@ struct qed_chain_init_params { ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U32) /* Accessors */ -static inline u16 qed_chain_get_prod_idx(struct qed_chain *p_chain) + +static inline u16 qed_chain_get_prod_idx(const struct qed_chain *chain) +{ + return chain->u.chain16.prod_idx; +} + +static inline u16 qed_chain_get_cons_idx(const struct qed_chain *chain) { - return p_chain->u.chain16.prod_idx; + return chain->u.chain16.cons_idx; } -static inline u16 qed_chain_get_cons_idx(struct qed_chain *p_chain) +static inline u32 qed_chain_get_prod_idx_u32(const struct qed_chain *chain) { - return p_chain->u.chain16.cons_idx; + return chain->u.chain32.prod_idx; } -static inline u32 qed_chain_get_cons_idx_u32(struct qed_chain *p_chain) +static inline u32 qed_chain_get_cons_idx_u32(const struct qed_chain *chain) { - return p_chain->u.chain32.cons_idx; + return chain->u.chain32.cons_idx; } -static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain) +static inline u16 qed_chain_get_elem_left(const struct qed_chain *chain) { - u16 elem_per_page = p_chain->elem_per_page; - u32 prod = p_chain->u.chain16.prod_idx; - u32 cons = p_chain->u.chain16.cons_idx; + u32 prod = qed_chain_get_prod_idx(chain); + u32 cons = qed_chain_get_cons_idx(chain); + u16 elem_per_page = chain->elem_per_page; u16 used; if (prod < cons) prod += (u32)U16_MAX + 1; used = (u16)(prod - cons); - if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) - used -= prod / elem_per_page - cons / elem_per_page; + if (chain->mode == QED_CHAIN_MODE_NEXT_PTR) + used -= (u16)(prod / elem_per_page - cons / elem_per_page); - return (u16)(p_chain->capacity - used); + return (u16)(chain->capacity - used); } -static inline u32 qed_chain_get_elem_left_u32(struct qed_chain *p_chain) +static inline u32 qed_chain_get_elem_left_u32(const struct qed_chain *chain) { - u16 elem_per_page = p_chain->elem_per_page; - u64 prod = p_chain->u.chain32.prod_idx; - u64 cons = p_chain->u.chain32.cons_idx; + u64 prod = qed_chain_get_prod_idx_u32(chain); + u64 cons = qed_chain_get_cons_idx_u32(chain); + u16 elem_per_page = chain->elem_per_page; u32 used; if (prod < cons) prod += (u64)U32_MAX + 1; used = (u32)(prod - cons); - if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) + if (chain->mode == QED_CHAIN_MODE_NEXT_PTR) used -= (u32)(prod / elem_per_page - cons / elem_per_page); - return p_chain->capacity - used; + return chain->capacity - used; } -static inline u16 qed_chain_get_usable_per_page(struct qed_chain *p_chain) +static inline u16 qed_chain_get_usable_per_page(const struct qed_chain *chain) { - return p_chain->usable_per_page; + return chain->usable_per_page; } -static inline u8 qed_chain_get_unusable_per_page(struct qed_chain *p_chain) +static inline u8 qed_chain_get_unusable_per_page(const struct qed_chain *chain) { - return p_chain->elem_unusable; + return chain->elem_unusable; } -static inline u32 qed_chain_get_page_cnt(struct qed_chain *p_chain) +static inline u32 qed_chain_get_page_cnt(const struct qed_chain *chain) { - return p_chain->page_cnt; + return chain->page_cnt; } -static inline dma_addr_t qed_chain_get_pbl_phys(struct qed_chain *p_chain) +static inline dma_addr_t qed_chain_get_pbl_phys(const struct qed_chain *chain) { - return p_chain->pbl_sp.table_phys; + return chain->pbl_sp.table_phys; } /** -- cgit v1.2.3 From be0cec6ffd686364bbba2796bbe5eee2fad18181 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:41 +0300 Subject: qed: introduce qed_chain_get_elem_used{,u32}() Add reverse-variants of qed_chain_get_elem_left{,u32}() to be able to know current chain occupation. They will be used in the upcoming qede XDP_REDIRECT code. They share most of the logics with the mentioned ones, so were reused to collapse the latters. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 434479e2ab65..4d58dc8943f0 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -203,7 +203,7 @@ static inline u32 qed_chain_get_cons_idx_u32(const struct qed_chain *chain) return chain->u.chain32.cons_idx; } -static inline u16 qed_chain_get_elem_left(const struct qed_chain *chain) +static inline u16 qed_chain_get_elem_used(const struct qed_chain *chain) { u32 prod = qed_chain_get_prod_idx(chain); u32 cons = qed_chain_get_cons_idx(chain); @@ -217,10 +217,15 @@ static inline u16 qed_chain_get_elem_left(const struct qed_chain *chain) if (chain->mode == QED_CHAIN_MODE_NEXT_PTR) used -= (u16)(prod / elem_per_page - cons / elem_per_page); - return (u16)(chain->capacity - used); + return used; } -static inline u32 qed_chain_get_elem_left_u32(const struct qed_chain *chain) +static inline u16 qed_chain_get_elem_left(const struct qed_chain *chain) +{ + return (u16)(chain->capacity - qed_chain_get_elem_used(chain)); +} + +static inline u32 qed_chain_get_elem_used_u32(const struct qed_chain *chain) { u64 prod = qed_chain_get_prod_idx_u32(chain); u64 cons = qed_chain_get_cons_idx_u32(chain); @@ -234,7 +239,12 @@ static inline u32 qed_chain_get_elem_left_u32(const struct qed_chain *chain) if (chain->mode == QED_CHAIN_MODE_NEXT_PTR) used -= (u32)(prod / elem_per_page - cons / elem_per_page); - return chain->capacity - used; + return used; +} + +static inline u32 qed_chain_get_elem_left_u32(const struct qed_chain *chain) +{ + return chain->capacity - qed_chain_get_elem_used_u32(chain); } static inline u16 qed_chain_get_usable_per_page(const struct qed_chain *chain) -- cgit v1.2.3 From bd25b4886ddcebec92591f298ce2ce345d7f2ea9 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 14 Jul 2020 16:13:51 -0400 Subject: padata: remove start function padata_start() is only used right after pcrypt allocates an instance with all possible CPUs, when PADATA_INVALID can't happen, so there's no need for a separate "start" step. It can be done during allocation to save text, make using padata easier, and avoid unneeded calls in the future. Signed-off-by: Daniel Jordan Cc: Herbert Xu Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu --- include/linux/padata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index 7302efff5e65..20294cddc739 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -204,6 +204,5 @@ extern void padata_do_serial(struct padata_priv *padata); extern void __init padata_do_multithreaded(struct padata_mt_job *job); extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, cpumask_var_t cpumask); -extern int padata_start(struct padata_instance *pinst); extern void padata_stop(struct padata_instance *pinst); #endif -- cgit v1.2.3 From 350ef051d4edd884e8dea0be9f3685b4b32142fb Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 14 Jul 2020 16:13:52 -0400 Subject: padata: remove stop function padata_stop() has two callers and is unnecessary in both cases. When pcrypt calls it before padata_free(), it's being unloaded so there are no outstanding padata jobs[0]. When __padata_free() calls it, it's either along the same path or else pcrypt initialization failed, which of course means there are also no outstanding jobs. Removing it simplifies padata and saves text. [0] https://lore.kernel.org/linux-crypto/20191119225017.mjrak2fwa5vccazl@gondor.apana.org.au/ Signed-off-by: Daniel Jordan Cc: Herbert Xu Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu --- include/linux/padata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index 20294cddc739..7d53208b43da 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -204,5 +204,4 @@ extern void padata_do_serial(struct padata_priv *padata); extern void __init padata_do_multithreaded(struct padata_mt_job *job); extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, cpumask_var_t cpumask); -extern void padata_stop(struct padata_instance *pinst); #endif -- cgit v1.2.3 From d69e037bcc4a7e31fdd40ae416aa1bd768dd7d99 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 14 Jul 2020 16:13:54 -0400 Subject: padata: remove effective cpumasks from the instance A padata instance has effective cpumasks that store the user-supplied masks ANDed with the online mask, but this middleman is unnecessary. parallel_data keeps the same information around. Removing this saves text and code churn in future changes. Signed-off-by: Daniel Jordan Cc: Herbert Xu Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu --- include/linux/padata.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index 7d53208b43da..a941b96b7119 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -167,7 +167,6 @@ struct padata_mt_job { * @serial_wq: The workqueue used for serial work. * @pslist: List of padata_shell objects attached to this instance. * @cpumask: User supplied cpumasks for parallel and serial works. - * @rcpumask: Actual cpumasks based on user cpumask and cpu_online_mask. * @kobj: padata instance kernel object. * @lock: padata instance lock. * @flags: padata flags. @@ -179,7 +178,6 @@ struct padata_instance { struct workqueue_struct *serial_wq; struct list_head pslist; struct padata_cpumask cpumask; - struct padata_cpumask rcpumask; struct kobject kobj; struct mutex lock; u8 flags; -- cgit v1.2.3 From 3f257191d31d5eaf154ebdb696efc238837ddd51 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 14 Jul 2020 16:13:55 -0400 Subject: padata: fold padata_alloc_possible() into padata_alloc() There's no reason to have two interfaces when there's only one caller. Removing _possible saves text and simplifies future changes. Signed-off-by: Daniel Jordan Cc: Herbert Xu Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu --- include/linux/padata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index a941b96b7119..070a7d43e8af 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -192,7 +192,7 @@ extern void __init padata_init(void); static inline void __init padata_init(void) {} #endif -extern struct padata_instance *padata_alloc_possible(const char *name); +extern struct padata_instance *padata_alloc(const char *name); extern void padata_free(struct padata_instance *pinst); extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst); extern void padata_free_shell(struct padata_shell *ps); -- cgit v1.2.3 From f601c725a6ac072608f47083e7c8115a3f504f95 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 14 Jul 2020 16:13:56 -0400 Subject: padata: remove padata_parallel_queue Only its reorder field is actually used now, so remove the struct and embed @reorder directly in parallel_data. No functional change, just a cleanup. Signed-off-by: Daniel Jordan Cc: Herbert Xu Cc: Steffen Klassert Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu --- include/linux/padata.h | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index 070a7d43e8af..a433f13fc4bf 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -66,17 +66,6 @@ struct padata_serial_queue { struct parallel_data *pd; }; -/** - * struct padata_parallel_queue - The percpu padata parallel queue - * - * @reorder: List to wait for reordering after parallel processing. - * @num_obj: Number of objects that are processed by this cpu. - */ -struct padata_parallel_queue { - struct padata_list reorder; - atomic_t num_obj; -}; - /** * struct padata_cpumask - The cpumasks for the parallel/serial workers * @@ -93,7 +82,7 @@ struct padata_cpumask { * that depends on the cpumask in use. * * @ps: padata_shell object. - * @pqueue: percpu padata queues used for parallelization. + * @reorder_list: percpu reorder lists * @squeue: percpu padata queues used for serialuzation. * @refcnt: Number of objects holding a reference on this parallel_data. * @seq_nr: Sequence number of the parallelized data object. @@ -105,7 +94,7 @@ struct padata_cpumask { */ struct parallel_data { struct padata_shell *ps; - struct padata_parallel_queue __percpu *pqueue; + struct padata_list __percpu *reorder_list; struct padata_serial_queue __percpu *squeue; atomic_t refcnt; unsigned int seq_nr; -- cgit v1.2.3 From 34ec0aa62b40e55bcd5f41b89494242c38556f30 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:29:43 -0700 Subject: misc: mic: : drop a duplicated word Drop the repeated word "the" in a comment. Signed-off-by: Randy Dunlap Cc: Sudeep Dutt Cc: Ashutosh Dixit Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20200719002943.20624-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mic_bus.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mic_bus.h b/include/linux/mic_bus.h index 491156a2359f..e99c789424e0 100644 --- a/include/linux/mic_bus.h +++ b/include/linux/mic_bus.h @@ -6,7 +6,7 @@ * * Intel MIC Bus driver. * - * This implementation is very similar to the the virtio bus driver + * This implementation is very similar to the virtio bus driver * implementation @ include/linux/virtio.h. */ #ifndef _MIC_BUS_H_ -- cgit v1.2.3 From c1e18d4fb9590268105e724444792656fcb3927d Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Mon, 15 Jun 2020 22:35:21 +0200 Subject: platform/chrome: cros_ec_proto: Do not export cros_ec_cmd_xfer() Now that all the remaining users of cros_ec_cmd_xfer() has been removed, make this function private to the cros_ec_proto module. Signed-off-by: Enric Balletbo i Serra --- include/linux/platform_data/cros_ec_proto.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 383243326676..4a415ae851ef 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -216,9 +216,6 @@ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, int cros_ec_check_result(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, - struct cros_ec_command *msg); - int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -- cgit v1.2.3 From bf9b82b7fe4d3c7d4d432ef80b4299c9b6b4a1f8 Mon Sep 17 00:00:00 2001 From: Garrit Franke Date: Thu, 16 Jul 2020 22:31:01 +0200 Subject: kobject: remove unused KOBJ_MAX action The loop in libb/kobj_uevent.c that checked for KOBBJ_MAX is no longer present, we do a much more sane ARRAY_SIZE() check instead. See 5c5daf657cb5 ("Driver core: exclude kobject_uevent.c for !CONFIG_HOTPLUG"). Signed-off-by: Garrit Franke Link: https://lore.kernel.org/r/20200716203100.7959-1-garritfranke@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 6cba088bee24..ea30529fba08 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -59,7 +59,6 @@ enum kobject_action { KOBJ_OFFLINE, KOBJ_BIND, KOBJ_UNBIND, - KOBJ_MAX }; struct kobject { -- cgit v1.2.3 From 8fc3ed3a474d76cd76dd0a154ea904373e9a5530 Mon Sep 17 00:00:00 2001 From: Colton Lewis Date: Thu, 23 Jul 2020 09:58:28 +0000 Subject: gpio: Correct kernel-doc inconsistency Fix kernel-doc comment to match parameter name change "chip" to "gc" in gpiochip_add_data function. Signed-off-by: Colton Lewis Link: https://lore.kernel.org/r/20200723095658.234668-1-colton.w.lewis@protonmail.com Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index db82451776fc..6e9f1826ecd7 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -497,25 +497,25 @@ extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, /** * gpiochip_add_data() - register a gpio_chip - * @gc: the chip to register, with chip->base initialized + * @gc: the chip to register, with gc->base initialized * @data: driver-private data associated with this chip * * Context: potentially before irqs will work * * When gpiochip_add_data() is called very early during boot, so that GPIOs - * can be freely used, the chip->parent device must be registered before + * can be freely used, the gc->parent device must be registered before * the gpio framework's arch_initcall(). Otherwise sysfs initialization * for GPIOs will fail rudely. * * gpiochip_add_data() must only be called after gpiolib initialization, * ie after core_initcall(). * - * If chip->base is negative, this requests dynamic assignment of + * If gc->base is negative, this requests dynamic assignment of * a range of valid GPIOs. * * Returns: * A negative errno if the chip can't be registered, such as because the - * chip->base is invalid or already associated with a different chip. + * gc->base is invalid or already associated with a different chip. * Otherwise it returns zero as a success code. */ #ifdef CONFIG_LOCKDEP -- cgit v1.2.3 From a3b7a581823857fab4fae71be9d1c830af78a766 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Fri, 17 Jul 2020 18:47:58 +0300 Subject: bus: fsl-mc: add missing device types The MC bus has different types of devices that can be discovered on the bus. Add the missing device types. Signed-off-by: Ioana Ciornei Reviewed-by: Laurentiu Tudor Link: https://lore.kernel.org/r/20200717154800.17169-2-ioana.ciornei@nxp.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 2b5f8366dbe1..cdb03aca2aef 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -433,6 +433,11 @@ extern struct device_type fsl_mc_bus_dpmcp_type; extern struct device_type fsl_mc_bus_dpmac_type; extern struct device_type fsl_mc_bus_dprtc_type; extern struct device_type fsl_mc_bus_dpseci_type; +extern struct device_type fsl_mc_bus_dpdmux_type; +extern struct device_type fsl_mc_bus_dpdcei_type; +extern struct device_type fsl_mc_bus_dpaiop_type; +extern struct device_type fsl_mc_bus_dpci_type; +extern struct device_type fsl_mc_bus_dpdmai_type; static inline bool is_fsl_mc_bus_dprc(const struct fsl_mc_device *mc_dev) { @@ -454,6 +459,11 @@ static inline bool is_fsl_mc_bus_dpsw(const struct fsl_mc_device *mc_dev) return mc_dev->dev.type == &fsl_mc_bus_dpsw_type; } +static inline bool is_fsl_mc_bus_dpdmux(const struct fsl_mc_device *mc_dev) +{ + return mc_dev->dev.type == &fsl_mc_bus_dpdmux_type; +} + static inline bool is_fsl_mc_bus_dpbp(const struct fsl_mc_device *mc_dev) { return mc_dev->dev.type == &fsl_mc_bus_dpbp_type; @@ -484,6 +494,26 @@ static inline bool is_fsl_mc_bus_dpseci(const struct fsl_mc_device *mc_dev) return mc_dev->dev.type == &fsl_mc_bus_dpseci_type; } +static inline bool is_fsl_mc_bus_dpdcei(const struct fsl_mc_device *mc_dev) +{ + return mc_dev->dev.type == &fsl_mc_bus_dpdcei_type; +} + +static inline bool is_fsl_mc_bus_dpaiop(const struct fsl_mc_device *mc_dev) +{ + return mc_dev->dev.type == &fsl_mc_bus_dpaiop_type; +} + +static inline bool is_fsl_mc_bus_dpci(const struct fsl_mc_device *mc_dev) +{ + return mc_dev->dev.type == &fsl_mc_bus_dpci_type; +} + +static inline bool is_fsl_mc_bus_dpdmai(const struct fsl_mc_device *mc_dev) +{ + return mc_dev->dev.type == &fsl_mc_bus_dpdmai_type; +} + /* * Data Path Buffer Pool (DPBP) API * Contains initialization APIs and runtime control APIs for DPBP -- cgit v1.2.3 From 9a872def598195d2de4a4a74e17804142e2aa78e Mon Sep 17 00:00:00 2001 From: Laurentiu Tudor Date: Fri, 17 Jul 2020 18:47:59 +0300 Subject: bus: fsl-mc: use raw spin lock to serialize mc cmds Replace the spinlock that serializes the MC commands with a raw spinlock. This is needed for the RT kernel because there are MC commands sent in interrupt context. Signed-off-by: Laurentiu Tudor Signed-off-by: Ioana Ciornei Reviewed-by: Laurentiu Tudor Link: https://lore.kernel.org/r/20200717154800.17169-3-ioana.ciornei@nxp.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index cdb03aca2aef..a428c61ead6e 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -339,7 +339,7 @@ struct fsl_mc_io { * This field is only meaningful if the * FSL_MC_IO_ATOMIC_CONTEXT_PORTAL flag is set */ - spinlock_t spinlock; /* serializes mc_send_command() */ + raw_spinlock_t spinlock; /* serializes mc_send_command() */ }; }; -- cgit v1.2.3 From 5df96f2b9f58a5d2dc1f30fe7de75e197f2c25f2 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Thu, 23 Jul 2020 10:42:09 -0400 Subject: dm integrity: fix integrity recalculation that is improperly skipped Commit adc0daad366b62ca1bce3e2958a40b0b71a8b8b3 ("dm: report suspended device during destroy") broke integrity recalculation. The problem is dm_suspended() returns true not only during suspend, but also during resume. So this race condition could occur: 1. dm_integrity_resume calls queue_work(ic->recalc_wq, &ic->recalc_work) 2. integrity_recalc (&ic->recalc_work) preempts the current thread 3. integrity_recalc calls if (unlikely(dm_suspended(ic->ti))) goto unlock_ret; 4. integrity_recalc exits and no recalculating is done. To fix this race condition, add a function dm_post_suspending that is only true during the postsuspend phase and use it instead of dm_suspended(). Signed-off-by: Mikulas Patocka Fixes: adc0daad366b ("dm: report suspended device during destroy") Cc: stable vger kernel org # v4.18+ Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 8750f2dc5613..73dec4b5d5be 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -426,6 +426,7 @@ const char *dm_device_name(struct mapped_device *md); int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid); struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct dm_target *ti); +int dm_post_suspending(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); union map_info *dm_get_rq_mapinfo(struct request *rq); -- cgit v1.2.3 From 76be93fc0702322179bb0ea87295d820ee46ad14 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 23 Jul 2020 12:00:06 -0700 Subject: tcp: allow at most one TLP probe per flight Previously TLP may send multiple probes of new data in one flight. This happens when the sender is cwnd limited. After the initial TLP containing new data is sent, the sender receives another ACK that acks partial inflight. It may re-arm another TLP timer to send more, if no further ACK returns before the next TLP timeout (PTO) expires. The sender may send in theory a large amount of TLP until send queue is depleted. This only happens if the sender sees such irregular uncommon ACK pattern. But it is generally undesirable behavior during congestion especially. The original TLP design restrict only one TLP probe per inflight as published in "Reducing Web Latency: the Virtue of Gentle Aggression", SIGCOMM 2013. This patch changes TLP to send at most one probe per inflight. Note that if the sender is app-limited, TLP retransmits old data and did not have this issue. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 9aac824c523c..a1bbaa1c1a3a 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -220,7 +220,9 @@ struct tcp_sock { } rack; u16 advmss; /* Advertised MSS */ u8 compressed_ack; - u8 dup_ack_counter; + u8 dup_ack_counter:2, + tlp_retrans:1, /* TLP is a retransmission */ + unused:5; u32 chrono_start; /* Start time in jiffies of a TCP chrono */ u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u8 chrono_type:2, /* current chronograph type */ @@ -243,7 +245,7 @@ struct tcp_sock { save_syn:1, /* Save headers of SYN packet */ is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ syn_smc:1; /* SYN includes SMC */ - u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ + u32 tlp_high_seq; /* snd_nxt at the time of TLP */ u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ -- cgit v1.2.3 From 7f3d176f5f7e3f0477bf82df0f600fcddcdcc4e4 Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Fri, 10 Jul 2020 14:29:55 -0500 Subject: tpm: Require that all digests are present in TCG_PCR_EVENT2 structures Require that the TCG_PCR_EVENT2.digests.count value strictly matches the value of TCG_EfiSpecIdEvent.numberOfAlgorithms in the event field of the TCG_PCClientPCREvent event log header. Also require that TCG_EfiSpecIdEvent.numberOfAlgorithms is non-zero. The TCG PC Client Platform Firmware Profile Specification section 9.1 (Family "2.0", Level 00 Revision 1.04) states: For each Hash algorithm enumerated in the TCG_PCClientPCREvent entry, there SHALL be a corresponding digest in all TCG_PCR_EVENT2 structures. Note: This includes EV_NO_ACTION events which do not extend the PCR. Section 9.4.5.1 provides this description of TCG_EfiSpecIdEvent.numberOfAlgorithms: The number of Hash algorithms in the digestSizes field. This field MUST be set to a value of 0x01 or greater. Enforce these restrictions, as required by the above specification, in order to better identify and ignore invalid sequences of bytes at the end of an otherwise valid TPM2 event log. Firmware doesn't always have the means necessary to inform the kernel of the actual event log size so the kernel's event log parsing code should be stringent when parsing the event log for resiliency against firmware bugs. This is true, for example, when firmware passes the event log to the kernel via a reserved memory region described in device tree. POWER and some ARM systems use the "linux,sml-base" and "linux,sml-size" device tree properties to describe the memory region used to pass the event log from firmware to the kernel. Unfortunately, the "linux,sml-size" property describes the size of the entire reserved memory region rather than the size of the event long within the memory region and the event log format does not include information describing the size of the event log. tpm_read_log_of(), in drivers/char/tpm/eventlog/of.c, is where the "linux,sml-size" property is used. At the end of that function, log->bios_event_log_end is pointing at the end of the reserved memory region. That's typically 0x10000 bytes offset from "linux,sml-base", depending on what's defined in the device tree source. The firmware event log only fills a portion of those 0x10000 bytes and the rest of the memory region should be zeroed out by firmware. Even in the case of a properly zeroed bytes in the remainder of the memory region, the only thing allowing the kernel's event log parser to detect the end of the event log is the following conditional in __calc_tpm2_event_size(): if (event_type == 0 && event_field->event_size == 0) size = 0; If that wasn't there, __calc_tpm2_event_size() would think that a 16 byte sequence of zeroes, following an otherwise valid event log, was a valid event. However, problems can occur if a single bit is set in the offset corresponding to either the TCG_PCR_EVENT2.eventType or TCG_PCR_EVENT2.eventSize fields, after the last valid event log entry. This could confuse the parser into thinking that an additional entry is present in the event log and exposing this invalid entry to userspace in the /sys/kernel/security/tpm0/binary_bios_measurements file. Such problems have been seen if firmware does not fully zero the memory region upon a warm reboot. This patch significantly raises the bar on how difficult it is for stale/invalid memory to confuse the kernel's event log parser but there's still, ultimately, a reliance on firmware to properly initialize the remainder of the memory region reserved for the event log as the parser cannot be expected to detect a stale but otherwise properly formatted firmware event log entry. Fixes: fd5c78694f3f ("tpm: fix handling of the TPM 2.0 event logs") Signed-off-by: Tyler Hicks Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/linux/tpm_eventlog.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 64356b199e94..739ba9a03ec1 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -211,9 +211,16 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, efispecid = (struct tcg_efi_specid_event_head *)event_header->event; - /* Check if event is malformed. */ + /* + * Perform validation of the event in order to identify malformed + * events. This function may be asked to parse arbitrary byte sequences + * immediately following a valid event log. The caller expects this + * function to recognize that the byte sequence is not a valid event + * and to return an event size of 0. + */ if (memcmp(efispecid->signature, TCG_SPECID_SIG, - sizeof(TCG_SPECID_SIG)) || count > efispecid->num_algs) { + sizeof(TCG_SPECID_SIG)) || + !efispecid->num_algs || count != efispecid->num_algs) { size = 0; goto out; } -- cgit v1.2.3 From 6c4e79d99e6f42b79040f1a33cd4018f5425030b Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Fri, 3 Jul 2020 01:55:59 +0300 Subject: tpm: Unify the mismatching TPM space buffer sizes The size of the buffers for storing context's and sessions can vary from arch to arch as PAGE_SIZE can be anything between 4 kB and 256 kB (the maximum for PPC64). Define a fixed buffer size set to 16 kB. This should be enough for most use with three handles (that is how many we allow at the moment). Parametrize the buffer size while doing this, so that it is easier to revisit this later on if required. Cc: stable@vger.kernel.org Reported-by: Stefan Berger Fixes: 745b361e989a ("tpm: infrastructure for TPM spaces") Reviewed-by: Jerry Snitselaar Tested-by: Stefan Berger Signed-off-by: Jarkko Sakkinen --- include/linux/tpm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 03e9b184411b..8f4ff39f51e7 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -96,6 +96,7 @@ struct tpm_space { u8 *context_buf; u32 session_tbl[3]; u8 *session_buf; + u32 buf_size; }; struct tpm_bios_log { -- cgit v1.2.3 From 5f77d6ca5ca74e4b4a5e2e010f7ff50c45dea326 Mon Sep 17 00:00:00 2001 From: Liu Yi L Date: Fri, 24 Jul 2020 09:49:14 +0800 Subject: iommu/vt-d: Enforce PASID devTLB field mask Set proper masks to avoid invalid input spillover to reserved bits. Signed-off-by: Liu Yi L Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20200724014925.15523-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 3e8fa1c7a1e6..311117b50e93 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -381,8 +381,8 @@ enum { #define QI_DEV_EIOTLB_ADDR(a) ((u64)(a) & VTD_PAGE_MASK) #define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) -#define QI_DEV_EIOTLB_GLOB(g) ((u64)g) -#define QI_DEV_EIOTLB_PASID(p) (((u64)p) << 32) +#define QI_DEV_EIOTLB_GLOB(g) ((u64)(g) & 0x1) +#define QI_DEV_EIOTLB_PASID(p) ((u64)((p) & 0xfffff) << 32) #define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) #define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) #define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ -- cgit v1.2.3 From 78df6c86f0691f5b6e325006aeb470de443351ea Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 24 Jul 2020 09:49:15 +0800 Subject: iommu/vt-d: Remove global page support in devTLB flush Global pages support is removed from VT-d spec 3.0 for dev TLB invalidation. This patch is to remove the bits for vSVA. Similar change already made for the native SVA. See the link below. Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/linux-iommu/20190830142919.GE11578@8bytes.org/T/ Link: https://lore.kernel.org/r/20200724014925.15523-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 311117b50e93..c7a8aae36771 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -381,7 +381,6 @@ enum { #define QI_DEV_EIOTLB_ADDR(a) ((u64)(a) & VTD_PAGE_MASK) #define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) -#define QI_DEV_EIOTLB_GLOB(g) ((u64)(g) & 0x1) #define QI_DEV_EIOTLB_PASID(p) ((u64)((p) & 0xfffff) << 32) #define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) #define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) @@ -705,7 +704,7 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, u32 pasid, u16 qdep, u64 addr, - unsigned int size_order, u64 granu); + unsigned int size_order); void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, int pasid); -- cgit v1.2.3 From dd6692f1b883bac46036000a1e3a0b3785f89e87 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Fri, 24 Jul 2020 09:49:21 +0800 Subject: iommu/vt-d: Refactor device_to_iommu() helper It is refactored in two ways: - Make it global so that it could be used in other files. - Make bus/devfn optional so that callers could ignore these two returned values when they only want to get the coresponding iommu pointer. Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20200724014925.15523-9-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index c7a8aae36771..a57ffbcc84c7 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -727,6 +727,7 @@ void iommu_flush_write_buffer(struct intel_iommu *iommu); int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev); struct dmar_domain *find_domain(struct device *dev); struct device_domain_info *get_domain_info(struct device *dev); +struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); #ifdef CONFIG_INTEL_IOMMU_SVM extern void intel_svm_check(struct intel_iommu *iommu); @@ -765,8 +766,6 @@ struct intel_svm { struct list_head devs; struct list_head list; }; - -extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev); #else static inline void intel_svm_check(struct intel_iommu *iommu) {} #endif -- cgit v1.2.3 From 8b73712115ebd603b75876f7d96d59e41d9107ad Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Fri, 24 Jul 2020 09:49:24 +0800 Subject: iommu/vt-d: Add page response ops support After page requests are handled, software must respond to the device which raised the page request with the result. This is done through the iommu ops.page_response if the request was reported to outside of vendor iommu driver through iommu_report_device_fault(). This adds the VT-d implementation of page_response ops. Co-developed-by: Jacob Pan Co-developed-by: Liu Yi L Signed-off-by: Jacob Pan Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20200724014925.15523-12-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index a57ffbcc84c7..9ff5e340948b 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -740,6 +740,9 @@ struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata); void intel_svm_unbind(struct iommu_sva *handle); int intel_svm_get_pasid(struct iommu_sva *handle); +int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt, + struct iommu_page_response *msg); + struct svm_dev_ops; struct intel_svm_dev { -- cgit v1.2.3 From 75c88143f3b879664cc5bf68b91854c1a98f5e5b Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Wed, 22 Jul 2020 10:38:20 +0300 Subject: clk: at91: clk-master: add master clock support for SAMA7G5 Add master clock support (MCK1..4) for SAMA7G5. SAMA7G5's PMC has multiple master clocks feeding different subsystems. One of them feeds image subsystem and is changeable based on image subsystem needs. Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/1595403506-8209-13-git-send-email-claudiu.beznea@microchip.com Signed-off-by: Stephen Boyd --- include/linux/clk/at91_pmc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index 49a53a137610..77d6dabc4c3c 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -174,6 +174,7 @@ #define AT91_PMC_MOSCRCS (1 << 17) /* Main On-Chip RC [some SAM9] */ #define AT91_PMC_CFDEV (1 << 18) /* Clock Failure Detector Event [some SAM9] */ #define AT91_PMC_GCKRDY (1 << 24) /* Generated Clocks */ +#define AT91_PMC_MCKXRDY (1 << 26) /* Master Clock x [x=1..4] Ready Status */ #define AT91_PMC_IMR 0x6c /* Interrupt Mask Register */ #define AT91_PMC_FSMR 0x70 /* Fast Startup Mode Register */ -- cgit v1.2.3 From 0416824edca1cdcb6e00e6f909423bf0fc529eef Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Wed, 22 Jul 2020 10:38:23 +0300 Subject: clk: at91: add macro for pll ids mask Add macro for PLL IDs mask. Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/1595403506-8209-16-git-send-email-claudiu.beznea@microchip.com Signed-off-by: Stephen Boyd --- include/linux/clk/at91_pmc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index 77d6dabc4c3c..dc5e85f124e0 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -59,6 +59,7 @@ #define AT91_PMC_PLL_UPDT 0x1C /* PMC PLL update register [for SAM9X60] */ #define AT91_PMC_PLL_UPDT_UPDATE (1 << 8) /* Update PLL settings */ #define AT91_PMC_PLL_UPDT_ID (1 << 0) /* PLL ID */ +#define AT91_PMC_PLL_UPDT_ID_MSK (0xf) /* PLL ID mask */ #define AT91_PMC_PLL_UPDT_STUPTIM (0xff << 16) /* Startup time */ #define AT91_CKGR_MOR 0x20 /* Main Oscillator Register [not on SAM9RL] */ -- cgit v1.2.3 From ef396df99251b848596c717b63ff4fe74a941193 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Wed, 22 Jul 2020 10:38:25 +0300 Subject: clk: at91: clk-utmi: add utmi support for sama7g5 Add UTMI support for SAMA7G5. SAMA7G5's UTMI control is done via XTALF register. Values written at bits 2..0 in this register correspond to the on board crystal oscillator frequency. Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/1595403506-8209-18-git-send-email-claudiu.beznea@microchip.com Signed-off-by: Stephen Boyd --- include/linux/clk/at91_pmc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index dc5e85f124e0..a4f82e836a7c 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -137,6 +137,8 @@ #define AT91_PMC_PLLADIV2_ON (1 << 12) #define AT91_PMC_H32MXDIV BIT(24) +#define AT91_PMC_XTALF 0x34 /* Main XTAL Frequency Register [SAMA7G5 only] */ + #define AT91_PMC_USB 0x38 /* USB Clock Register [some SAM9 only] */ #define AT91_PMC_USBS (0x1 << 0) /* USB OHCI Input clock selection */ #define AT91_PMC_USBS_PLLA (0 << 0) -- cgit v1.2.3 From d19e789f068b3d633cbac430764962f404198022 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 24 Jul 2020 13:50:25 +0200 Subject: compiler.h: Move instrumentation_begin()/end() to new header Linus pointed out that compiler.h - which is a key header that gets included in every single one of the 28,000+ kernel files during a kernel build - was bloated in: 655389666643: ("vmlinux.lds.h: Create section for protection against instrumentation") Linus noted: > I have pulled this, but do we really want to add this to a header file > that is _so_ core that it gets included for basically every single > file built? > > I don't even see those instrumentation_begin/end() things used > anywhere right now. > > It seems excessive. That 53 lines is maybe not a lot, but it pushed > that header file to over 12kB, and while it's mostly comments, it's > extra IO and parsing basically for _every_ single file compiled in the > kernel. > > For what appears to be absolutely zero upside right now, and I really > don't see why this should be in such a core header file! Move these primitives into a new header: , and include that header in the headers that make use of it. Unfortunately one of these headers is asm-generic/bug.h, which does get included in a lot of places, similarly to compiler.h. So the de-bloating effect isn't as good as we'd like it to be - but at least the interfaces are defined separately. No change to functionality intended. Reported-by: Linus Torvalds Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200604071921.GA1361070@gmail.com Cc: Thomas Gleixner Cc: Borislav Petkov Cc: Peter Zijlstra --- include/linux/compiler.h | 53 ------------------------------------- include/linux/context_tracking.h | 2 ++ include/linux/instrumentation.h | 57 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 59 insertions(+), 53 deletions(-) create mode 100644 include/linux/instrumentation.h (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 204e76856435..681894bfde99 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -120,65 +120,12 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(.rodata..c_jump_table) -#ifdef CONFIG_DEBUG_ENTRY -/* Begin/end of an instrumentation safe region */ -#define instrumentation_begin() ({ \ - asm volatile("%c0: nop\n\t" \ - ".pushsection .discard.instr_begin\n\t" \ - ".long %c0b - .\n\t" \ - ".popsection\n\t" : : "i" (__COUNTER__)); \ -}) - -/* - * Because instrumentation_{begin,end}() can nest, objtool validation considers - * _begin() a +1 and _end() a -1 and computes a sum over the instructions. - * When the value is greater than 0, we consider instrumentation allowed. - * - * There is a problem with code like: - * - * noinstr void foo() - * { - * instrumentation_begin(); - * ... - * if (cond) { - * instrumentation_begin(); - * ... - * instrumentation_end(); - * } - * bar(); - * instrumentation_end(); - * } - * - * If instrumentation_end() would be an empty label, like all the other - * annotations, the inner _end(), which is at the end of a conditional block, - * would land on the instruction after the block. - * - * If we then consider the sum of the !cond path, we'll see that the call to - * bar() is with a 0-value, even though, we meant it to happen with a positive - * value. - * - * To avoid this, have _end() be a NOP instruction, this ensures it will be - * part of the condition block and does not escape. - */ -#define instrumentation_end() ({ \ - asm volatile("%c0: nop\n\t" \ - ".pushsection .discard.instr_end\n\t" \ - ".long %c0b - .\n\t" \ - ".popsection\n\t" : : "i" (__COUNTER__)); \ -}) -#endif /* CONFIG_DEBUG_ENTRY */ - #else #define annotate_reachable() #define annotate_unreachable() #define __annotate_jump_table #endif -#ifndef instrumentation_begin -#define instrumentation_begin() do { } while(0) -#define instrumentation_end() do { } while(0) -#endif - #ifndef ASM_UNREACHABLE # define ASM_UNREACHABLE #endif diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 981b880d5b60..d53cd331c4dd 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -5,6 +5,8 @@ #include #include #include +#include + #include diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h new file mode 100644 index 000000000000..93e2ad67fc10 --- /dev/null +++ b/include/linux/instrumentation.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_INSTRUMENTATION_H +#define __LINUX_INSTRUMENTATION_H + +#if defined(CONFIG_DEBUG_ENTRY) && defined(CONFIG_STACK_VALIDATION) + +/* Begin/end of an instrumentation safe region */ +#define instrumentation_begin() ({ \ + asm volatile("%c0: nop\n\t" \ + ".pushsection .discard.instr_begin\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__COUNTER__)); \ +}) + +/* + * Because instrumentation_{begin,end}() can nest, objtool validation considers + * _begin() a +1 and _end() a -1 and computes a sum over the instructions. + * When the value is greater than 0, we consider instrumentation allowed. + * + * There is a problem with code like: + * + * noinstr void foo() + * { + * instrumentation_begin(); + * ... + * if (cond) { + * instrumentation_begin(); + * ... + * instrumentation_end(); + * } + * bar(); + * instrumentation_end(); + * } + * + * If instrumentation_end() would be an empty label, like all the other + * annotations, the inner _end(), which is at the end of a conditional block, + * would land on the instruction after the block. + * + * If we then consider the sum of the !cond path, we'll see that the call to + * bar() is with a 0-value, even though, we meant it to happen with a positive + * value. + * + * To avoid this, have _end() be a NOP instruction, this ensures it will be + * part of the condition block and does not escape. + */ +#define instrumentation_end() ({ \ + asm volatile("%c0: nop\n\t" \ + ".pushsection .discard.instr_end\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__COUNTER__)); \ +}) +#else +# define instrumentation_begin() do { } while(0) +# define instrumentation_end() do { } while(0) +#endif + +#endif /* __LINUX_INSTRUMENTATION_H */ -- cgit v1.2.3 From f34ce7a7018c2f71d78fc7f512f6daf01e487114 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 12 Jun 2020 11:39:55 +0800 Subject: iommu: Add gfp parameter to io_pgtable_ops->map() Now the ARM page tables are always allocated by GFP_ATOMIC parameter, but the iommu_ops->map() function has been added a gfp_t parameter by commit 781ca2de89ba ("iommu: Add gfp parameter to iommu_ops::map"), thus io_pgtable_ops->map() should use the gfp parameter passed from iommu_ops->map() to allocate page pages, which can avoid wasting the memory allocators atomic pools for some non-atomic contexts. Signed-off-by: Baolin Wang Acked-by: Will Deacon Link: https://lore.kernel.org/r/3093df4cb95497aaf713fca623ce4ecebb197c2e.1591930156.git.baolin.wang@linux.alibaba.com Signed-off-by: Joerg Roedel --- include/linux/io-pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 53d53c6c2be9..23285ba645db 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -155,7 +155,7 @@ struct io_pgtable_cfg { */ struct io_pgtable_ops { int (*map)(struct io_pgtable_ops *ops, unsigned long iova, - phys_addr_t paddr, size_t size, int prot); + phys_addr_t paddr, size_t size, int prot, gfp_t gfp); size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova, size_t size, struct iommu_iotlb_gather *gather); phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops, -- cgit v1.2.3 From b1012ca8dc4f9b1a1fe8e2cb1590dd6d43ea3849 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 23 Jul 2020 09:34:37 +0800 Subject: iommu/vt-d: Skip TE disabling on quirky gfx dedicated iommu The VT-d spec requires (10.4.4 Global Command Register, TE field) that: Hardware implementations supporting DMA draining must drain any in-flight DMA read/write requests queued within the Root-Complex before completing the translation enable command and reflecting the status of the command through the TES field in the Global Status register. Unfortunately, some integrated graphic devices fail to do so after some kind of power state transition. As the result, the system might stuck in iommu_disable_translation(), waiting for the completion of TE transition. This provides a quirk list for those devices and skips TE disabling if the qurik hits. Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=208363 Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=206571 Signed-off-by: Lu Baolu Tested-by: Koba Ko Tested-by: Jun Miao Cc: Ashok Raj Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200723013437.2268-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/dmar.h | 1 + include/linux/intel-iommu.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index d7bf029df737..65565820328a 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -48,6 +48,7 @@ struct dmar_drhd_unit { u16 segment; /* PCI domain */ u8 ignored:1; /* ignore drhd */ u8 include_all:1; + u8 gfx_dedicated:1; /* graphic dedicated */ struct intel_iommu *iommu; }; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 9ff5e340948b..b1ed2f25f7c0 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -599,6 +599,8 @@ struct intel_iommu { struct iommu_device iommu; /* IOMMU core code handle */ int node; u32 flags; /* Software defined flags */ + + struct dmar_drhd_unit *drhd; }; /* PCI domain-device relationship */ -- cgit v1.2.3 From 6823ecabf03031d610a6c5afe7ed4b4fd659a99f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 22 Jul 2020 23:59:55 +0200 Subject: seccomp: Provide stub for __secure_computing() To avoid #ifdeffery in the upcoming generic syscall entry work code provide a stub for __secure_computing() as this is preferred over secure_computing() because the TIF flag is already evaluated. Signed-off-by: Thomas Gleixner Acked-by: Kees Cook Link: https://lkml.kernel.org/r/20200722220519.404974280@linutronix.de --- include/linux/seccomp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 4192369b8418..03d28c32ad01 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -61,6 +61,7 @@ struct seccomp_filter { }; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER static inline int secure_computing(void) { return 0; } +static inline int __secure_computing(void) { return 0; } #else static inline void secure_computing_strict(int this_syscall) { return; } #endif -- cgit v1.2.3 From 142781e108b13b2b0e8f035cfb5bfbbc8f14d887 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 22 Jul 2020 23:59:56 +0200 Subject: entry: Provide generic syscall entry functionality On syscall entry certain work needs to be done: - Establish state (lockdep, context tracking, tracing) - Conditional work (ptrace, seccomp, audit...) This code is needlessly duplicated and different in all architectures. Provide a generic version based on the x86 implementation which has all the RCU and instrumentation bits right. As interrupt/exception entry from user space needs parts of the same functionality, provide a function for this as well. syscall_enter_from_user_mode() and irqentry_enter_from_user_mode() must be called right after the low level ASM entry. The calling code must be non-instrumentable. After the functions returns state is correct and the subsequent functions can be instrumented. Signed-off-by: Thomas Gleixner Acked-by: Kees Cook Link: https://lkml.kernel.org/r/20200722220519.513463269@linutronix.de --- include/linux/entry-common.h | 121 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 121 insertions(+) create mode 100644 include/linux/entry-common.h (limited to 'include/linux') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h new file mode 100644 index 000000000000..42fc8e4632bb --- /dev/null +++ b/include/linux/entry-common.h @@ -0,0 +1,121 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_ENTRYCOMMON_H +#define __LINUX_ENTRYCOMMON_H + +#include +#include +#include +#include + +#include + +/* + * Define dummy _TIF work flags if not defined by the architecture or for + * disabled functionality. + */ +#ifndef _TIF_SYSCALL_EMU +# define _TIF_SYSCALL_EMU (0) +#endif + +#ifndef _TIF_SYSCALL_TRACEPOINT +# define _TIF_SYSCALL_TRACEPOINT (0) +#endif + +#ifndef _TIF_SECCOMP +# define _TIF_SECCOMP (0) +#endif + +#ifndef _TIF_SYSCALL_AUDIT +# define _TIF_SYSCALL_AUDIT (0) +#endif + +/* + * TIF flags handled in syscall_enter_from_usermode() + */ +#ifndef ARCH_SYSCALL_ENTER_WORK +# define ARCH_SYSCALL_ENTER_WORK (0) +#endif + +#define SYSCALL_ENTER_WORK \ + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ + _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_EMU | \ + ARCH_SYSCALL_ENTER_WORK) + +/** + * arch_check_user_regs - Architecture specific sanity check for user mode regs + * @regs: Pointer to currents pt_regs + * + * Defaults to an empty implementation. Can be replaced by architecture + * specific code. + * + * Invoked from syscall_enter_from_user_mode() in the non-instrumentable + * section. Use __always_inline so the compiler cannot push it out of line + * and make it instrumentable. + */ +static __always_inline void arch_check_user_regs(struct pt_regs *regs); + +#ifndef arch_check_user_regs +static __always_inline void arch_check_user_regs(struct pt_regs *regs) {} +#endif + +/** + * arch_syscall_enter_tracehook - Wrapper around tracehook_report_syscall_entry() + * @regs: Pointer to currents pt_regs + * + * Returns: 0 on success or an error code to skip the syscall. + * + * Defaults to tracehook_report_syscall_entry(). Can be replaced by + * architecture specific code. + * + * Invoked from syscall_enter_from_user_mode() + */ +static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs); + +#ifndef arch_syscall_enter_tracehook +static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs) +{ + return tracehook_report_syscall_entry(regs); +} +#endif + +/** + * syscall_enter_from_user_mode - Check and handle work before invoking + * a syscall + * @regs: Pointer to currents pt_regs + * @syscall: The syscall number + * + * Invoked from architecture specific syscall entry code with interrupts + * disabled. The calling code has to be non-instrumentable. When the + * function returns all state is correct and the subsequent functions can be + * instrumented. + * + * Returns: The original or a modified syscall number + * + * If the returned syscall number is -1 then the syscall should be + * skipped. In this case the caller may invoke syscall_set_error() or + * syscall_set_return_value() first. If neither of those are called and -1 + * is returned, then the syscall will fail with ENOSYS. + * + * The following functionality is handled here: + * + * 1) Establish state (lockdep, RCU (context tracking), tracing) + * 2) TIF flag dependent invocations of arch_syscall_enter_tracehook(), + * __secure_computing(), trace_sys_enter() + * 3) Invocation of audit_syscall_entry() + */ +long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall); + +/** + * irqentry_enter_from_user_mode - Establish state before invoking the irq handler + * @regs: Pointer to currents pt_regs + * + * Invoked from architecture specific entry code with interrupts disabled. + * Can only be called when the interrupt entry came from user mode. The + * calling code must be non-instrumentable. When the function returns all + * state is correct and the subsequent functions can be instrumented. + * + * The function establishes state (lockdep, RCU (context tracking), tracing) + */ +void irqentry_enter_from_user_mode(struct pt_regs *regs); + +#endif -- cgit v1.2.3 From a9f3a74a29af095f3e1b89e9176f8127912ae0f0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 22 Jul 2020 23:59:57 +0200 Subject: entry: Provide generic syscall exit function Like syscall entry all architectures have similar and pointlessly different code to handle pending work before returning from a syscall to user space. 1) One-time syscall exit work: - rseq syscall exit - audit - syscall tracing - tracehook (single stepping) 2) Preparatory work - Exit to user mode loop (common TIF handling). - Architecture specific one time work arch_exit_to_user_mode_prepare() - Address limit and lockdep checks 3) Final transition (lockdep, tracing, context tracking, RCU). Invokes arch_exit_to_user_mode() to handle e.g. speculation mitigations Provide a generic version based on the x86 code which has all the RCU and instrumentation protections right. Provide a variant for interrupt return to user mode as well which shares the above #2 and #3 work items. After syscall_exit_to_user_mode() and irqentry_exit_to_user_mode() the architecture code just has to return to user space. The code after returning from these functions must not be instrumented. Signed-off-by: Thomas Gleixner Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200722220519.613977173@linutronix.de --- include/linux/entry-common.h | 189 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 189 insertions(+) (limited to 'include/linux') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 42fc8e4632bb..c4a57be9cde4 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -29,6 +29,14 @@ # define _TIF_SYSCALL_AUDIT (0) #endif +#ifndef _TIF_PATCH_PENDING +# define _TIF_PATCH_PENDING (0) +#endif + +#ifndef _TIF_UPROBE +# define _TIF_UPROBE (0) +#endif + /* * TIF flags handled in syscall_enter_from_usermode() */ @@ -41,6 +49,29 @@ _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_EMU | \ ARCH_SYSCALL_ENTER_WORK) +/* + * TIF flags handled in syscall_exit_to_user_mode() + */ +#ifndef ARCH_SYSCALL_EXIT_WORK +# define ARCH_SYSCALL_EXIT_WORK (0) +#endif + +#define SYSCALL_EXIT_WORK \ + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ + _TIF_SYSCALL_TRACEPOINT | ARCH_SYSCALL_EXIT_WORK) + +/* + * TIF flags handled in exit_to_user_mode_loop() + */ +#ifndef ARCH_EXIT_TO_USER_MODE_WORK +# define ARCH_EXIT_TO_USER_MODE_WORK (0) +#endif + +#define EXIT_TO_USER_MODE_WORK \ + (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | \ + ARCH_EXIT_TO_USER_MODE_WORK) + /** * arch_check_user_regs - Architecture specific sanity check for user mode regs * @regs: Pointer to currents pt_regs @@ -105,6 +136,149 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs */ long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall); +/** + * local_irq_enable_exit_to_user - Exit to user variant of local_irq_enable() + * @ti_work: Cached TIF flags gathered with interrupts disabled + * + * Defaults to local_irq_enable(). Can be supplied by architecture specific + * code. + */ +static inline void local_irq_enable_exit_to_user(unsigned long ti_work); + +#ifndef local_irq_enable_exit_to_user +static inline void local_irq_enable_exit_to_user(unsigned long ti_work) +{ + local_irq_enable(); +} +#endif + +/** + * local_irq_disable_exit_to_user - Exit to user variant of local_irq_disable() + * + * Defaults to local_irq_disable(). Can be supplied by architecture specific + * code. + */ +static inline void local_irq_disable_exit_to_user(void); + +#ifndef local_irq_disable_exit_to_user +static inline void local_irq_disable_exit_to_user(void) +{ + local_irq_disable(); +} +#endif + +/** + * arch_exit_to_user_mode_work - Architecture specific TIF work for exit + * to user mode. + * @regs: Pointer to currents pt_regs + * @ti_work: Cached TIF flags gathered with interrupts disabled + * + * Invoked from exit_to_user_mode_loop() with interrupt enabled + * + * Defaults to NOOP. Can be supplied by architecture specific code. + */ +static inline void arch_exit_to_user_mode_work(struct pt_regs *regs, + unsigned long ti_work); + +#ifndef arch_exit_to_user_mode_work +static inline void arch_exit_to_user_mode_work(struct pt_regs *regs, + unsigned long ti_work) +{ +} +#endif + +/** + * arch_exit_to_user_mode_prepare - Architecture specific preparation for + * exit to user mode. + * @regs: Pointer to currents pt_regs + * @ti_work: Cached TIF flags gathered with interrupts disabled + * + * Invoked from exit_to_user_mode_prepare() with interrupt disabled as the last + * function before return. Defaults to NOOP. + */ +static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, + unsigned long ti_work); + +#ifndef arch_exit_to_user_mode_prepare +static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, + unsigned long ti_work) +{ +} +#endif + +/** + * arch_exit_to_user_mode - Architecture specific final work before + * exit to user mode. + * + * Invoked from exit_to_user_mode() with interrupt disabled as the last + * function before return. Defaults to NOOP. + * + * This needs to be __always_inline because it is non-instrumentable code + * invoked after context tracking switched to user mode. + * + * An architecture implementation must not do anything complex, no locking + * etc. The main purpose is for speculation mitigations. + */ +static __always_inline void arch_exit_to_user_mode(void); + +#ifndef arch_exit_to_user_mode +static __always_inline void arch_exit_to_user_mode(void) { } +#endif + +/** + * arch_do_signal - Architecture specific signal delivery function + * @regs: Pointer to currents pt_regs + * + * Invoked from exit_to_user_mode_loop(). + */ +void arch_do_signal(struct pt_regs *regs); + +/** + * arch_syscall_exit_tracehook - Wrapper around tracehook_report_syscall_exit() + * @regs: Pointer to currents pt_regs + * @step: Indicator for single step + * + * Defaults to tracehook_report_syscall_exit(). Can be replaced by + * architecture specific code. + * + * Invoked from syscall_exit_to_user_mode() + */ +static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step); + +#ifndef arch_syscall_exit_tracehook +static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step) +{ + tracehook_report_syscall_exit(regs, step); +} +#endif + +/** + * syscall_exit_to_user_mode - Handle work before returning to user mode + * @regs: Pointer to currents pt_regs + * + * Invoked with interrupts enabled and fully valid regs. Returns with all + * work handled, interrupts disabled such that the caller can immediately + * switch to user mode. Called from architecture specific syscall and ret + * from fork code. + * + * The call order is: + * 1) One-time syscall exit work: + * - rseq syscall exit + * - audit + * - syscall tracing + * - tracehook (single stepping) + * + * 2) Preparatory work + * - Exit to user mode loop (common TIF handling). Invokes + * arch_exit_to_user_mode_work() for architecture specific TIF work + * - Architecture specific one time work arch_exit_to_user_mode_prepare() + * - Address limit and lockdep checks + * + * 3) Final transition (lockdep, tracing, context tracking, RCU). Invokes + * arch_exit_to_user_mode() to handle e.g. speculation mitigations + */ +void syscall_exit_to_user_mode(struct pt_regs *regs); + /** * irqentry_enter_from_user_mode - Establish state before invoking the irq handler * @regs: Pointer to currents pt_regs @@ -118,4 +292,19 @@ long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall); */ void irqentry_enter_from_user_mode(struct pt_regs *regs); +/** + * irqentry_exit_to_user_mode - Interrupt exit work + * @regs: Pointer to current's pt_regs + * + * Invoked with interrupts disbled and fully valid regs. Returns with all + * work handled, interrupts disabled such that the caller can immediately + * switch to user mode. Called from architecture specific interrupt + * handling code. + * + * The call order is #2 and #3 as described in syscall_exit_to_user_mode(). + * Interrupt exit is not invoking #1 which is the syscall specific one time + * work. + */ +void irqentry_exit_to_user_mode(struct pt_regs *regs); + #endif -- cgit v1.2.3 From a5497bab5f72dce38a259a53fd3ac1239a7ecf40 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 22 Jul 2020 23:59:58 +0200 Subject: entry: Provide generic interrupt entry/exit code Like the syscall entry/exit code interrupt/exception entry after the real low level ASM bits should not be different accross architectures. Provide a generic version based on the x86 code. irqentry_enter() is called after the low level entry code and irqentry_exit() must be invoked right before returning to the low level code which just contains the actual return logic. The code before irqentry_enter() and irqentry_exit() must not be instrumented. Code after irqentry_enter() and before irqentry_exit() can be instrumented. irqentry_enter() invokes irqentry_enter_from_user_mode() if the interrupt/exception came from user mode. If if entered from kernel mode it handles the kernel mode variant of establishing state for lockdep, RCU and tracing depending on the kernel context it interrupted (idle, non-idle). Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20200722220519.723703209@linutronix.de --- include/linux/entry-common.h | 62 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) (limited to 'include/linux') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index c4a57be9cde4..efebbffcd5cc 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -307,4 +307,66 @@ void irqentry_enter_from_user_mode(struct pt_regs *regs); */ void irqentry_exit_to_user_mode(struct pt_regs *regs); +#ifndef irqentry_state +typedef struct irqentry_state { + bool exit_rcu; +} irqentry_state_t; +#endif + +/** + * irqentry_enter - Handle state tracking on ordinary interrupt entries + * @regs: Pointer to pt_regs of interrupted context + * + * Invokes: + * - lockdep irqflag state tracking as low level ASM entry disabled + * interrupts. + * + * - Context tracking if the exception hit user mode. + * + * - The hardirq tracer to keep the state consistent as low level ASM + * entry disabled interrupts. + * + * As a precondition, this requires that the entry came from user mode, + * idle, or a kernel context in which RCU is watching. + * + * For kernel mode entries RCU handling is done conditional. If RCU is + * watching then the only RCU requirement is to check whether the tick has + * to be restarted. If RCU is not watching then rcu_irq_enter() has to be + * invoked on entry and rcu_irq_exit() on exit. + * + * Avoiding the rcu_irq_enter/exit() calls is an optimization but also + * solves the problem of kernel mode pagefaults which can schedule, which + * is not possible after invoking rcu_irq_enter() without undoing it. + * + * For user mode entries irqentry_enter_from_user_mode() is invoked to + * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit + * would not be possible. + * + * Returns: An opaque object that must be passed to idtentry_exit() + */ +irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs); + +/** + * irqentry_exit_cond_resched - Conditionally reschedule on return from interrupt + * + * Conditional reschedule with additional sanity checks. + */ +void irqentry_exit_cond_resched(void); + +/** + * irqentry_exit - Handle return from exception that used irqentry_enter() + * @regs: Pointer to pt_regs (exception entry regs) + * @state: Return value from matching call to irqentry_enter() + * + * Depending on the return target (kernel/user) this runs the necessary + * preemption and work checks if possible and reguired and returns to + * the caller with interrupts disabled and no further work pending. + * + * This is the last action before returning to the low level ASM code which + * just needs to return to the appropriate context. + * + * Counterpart to irqentry_enter(). + */ +void noinstr irqentry_exit(struct pt_regs *regs, irqentry_state_t state); + #endif -- cgit v1.2.3 From 935ace2fb5cc49ae88bd1f1735ddc51cdc2ebfb3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 22 Jul 2020 23:59:59 +0200 Subject: entry: Provide infrastructure for work before transitioning to guest mode Entering a guest is similar to exiting to user space. Pending work like handling signals, rescheduling, task work etc. needs to be handled before that. Provide generic infrastructure to avoid duplication of the same handling code all over the place. The transfer to guest mode handling is different from the exit to usermode handling, e.g. vs. rseq and live patching, so a separate function is used. The initial list of work items handled is: TIF_SIGPENDING, TIF_NEED_RESCHED, TIF_NOTIFY_RESUME Architecture specific TIF flags can be added via defines in the architecture specific include files. The calling convention is also different from the syscall/interrupt entry functions as KVM invokes this from the outer vcpu_run() loop with interrupts and preemption enabled. To prevent missing a pending work item it invokes a check for pending TIF work from interrupt disabled code right before transitioning to guest mode. The lockdep, RCU and tracing state handling is also done directly around the switch to and from guest mode. Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20200722220519.833296398@linutronix.de --- include/linux/entry-kvm.h | 80 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/kvm_host.h | 8 +++++ 2 files changed, 88 insertions(+) create mode 100644 include/linux/entry-kvm.h (limited to 'include/linux') diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h new file mode 100644 index 000000000000..0cef17afb41a --- /dev/null +++ b/include/linux/entry-kvm.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_ENTRYKVM_H +#define __LINUX_ENTRYKVM_H + +#include + +/* Transfer to guest mode work */ +#ifdef CONFIG_KVM_XFER_TO_GUEST_WORK + +#ifndef ARCH_XFER_TO_GUEST_MODE_WORK +# define ARCH_XFER_TO_GUEST_MODE_WORK (0) +#endif + +#define XFER_TO_GUEST_MODE_WORK \ + (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ + _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK) + +struct kvm_vcpu; + +/** + * arch_xfer_to_guest_mode_handle_work - Architecture specific xfer to guest + * mode work handling function. + * @vcpu: Pointer to current's VCPU data + * @ti_work: Cached TIF flags gathered in xfer_to_guest_mode_handle_work() + * + * Invoked from xfer_to_guest_mode_handle_work(). Defaults to NOOP. Can be + * replaced by architecture specific code. + */ +static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu, + unsigned long ti_work); + +#ifndef arch_xfer_to_guest_mode_work +static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu, + unsigned long ti_work) +{ + return 0; +} +#endif + +/** + * xfer_to_guest_mode_handle_work - Check and handle pending work which needs + * to be handled before going to guest mode + * @vcpu: Pointer to current's VCPU data + * + * Returns: 0 or an error code + */ +int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu); + +/** + * __xfer_to_guest_mode_work_pending - Check if work is pending + * + * Returns: True if work pending, False otherwise. + * + * Bare variant of xfer_to_guest_mode_work_pending(). Can be called from + * interrupt enabled code for racy quick checks with care. + */ +static inline bool __xfer_to_guest_mode_work_pending(void) +{ + unsigned long ti_work = READ_ONCE(current_thread_info()->flags); + + return !!(ti_work & XFER_TO_GUEST_MODE_WORK); +} + +/** + * xfer_to_guest_mode_work_pending - Check if work is pending which needs to be + * handled before returning to guest mode + * + * Returns: True if work pending, False otherwise. + * + * Has to be invoked with interrupts disabled before the transition to + * guest mode. + */ +static inline bool xfer_to_guest_mode_work_pending(void) +{ + lockdep_assert_irqs_disabled(); + return __xfer_to_guest_mode_work_pending(); +} +#endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */ + +#endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d564855243d8..ac83e9c1d82c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1439,4 +1439,12 @@ int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn, uintptr_t data, const char *name, struct task_struct **thread_ptr); +#ifdef CONFIG_KVM_XFER_TO_GUEST_WORK +static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) +{ + vcpu->run->exit_reason = KVM_EXIT_INTR; + vcpu->stat.signal_exits++; +} +#endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */ + #endif -- cgit v1.2.3 From 3f9a7a13fe4cb6e119e4e4745fbf975d30bfac9b Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Thu, 23 Jul 2020 15:37:29 -0700 Subject: PCI/ATS: Add pci_pri_supported() to check device or associated PF For SR-IOV, the PF PRI is shared between the PF and any associated VFs, and the PRI Capability is allowed for PFs but not for VFs. Searching for the PRI Capability on a VF always fails, even if its associated PF supports PRI. Add pci_pri_supported() to check whether device or its associated PF supports PRI. [bhelgaas: commit log, avoid "!!"] Fixes: b16d0cb9e2fc ("iommu/vt-d: Always enable PASID/PRI PCI capabilities before ATS") Link: https://lore.kernel.org/r/1595543849-19692-1-git-send-email-ashok.raj@intel.com Signed-off-by: Ashok Raj Signed-off-by: Bjorn Helgaas Reviewed-by: Lu Baolu Acked-by: Joerg Roedel Cc: stable@vger.kernel.org # v4.4+ --- include/linux/pci-ats.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index f75c307f346d..df54cd5b15db 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -28,6 +28,10 @@ int pci_enable_pri(struct pci_dev *pdev, u32 reqs); void pci_disable_pri(struct pci_dev *pdev); int pci_reset_pri(struct pci_dev *pdev); int pci_prg_resp_pasid_required(struct pci_dev *pdev); +bool pci_pri_supported(struct pci_dev *pdev); +#else +static inline bool pci_pri_supported(struct pci_dev *pdev) +{ return false; } #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID -- cgit v1.2.3 From e5ebffe18e5add85acb23c7a0f74509749967204 Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Sun, 19 Jul 2020 17:10:45 -0600 Subject: dyndbg: rename __verbose section to __dyndbg dyndbg populates its callsite info into __verbose section, change that to a more specific and descriptive name, __dyndbg. Also, per checkpatch: simplify __attribute(..) to __section(__dyndbg) declaration. and 1 spelling fix, decriptor Acked-by: Signed-off-by: Jim Cromie Link: https://lore.kernel.org/r/20200719231058.1586423-6-jim.cromie@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/dynamic_debug.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index abcd5fde30eb..aa9ff9e1c0b3 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -80,7 +80,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, #define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ static struct _ddebug __aligned(8) \ - __attribute__((section("__verbose"))) name = { \ + __section(__dyndbg) name = { \ .modname = KBUILD_MODNAME, \ .function = __func__, \ .filename = __FILE__, \ @@ -133,7 +133,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, /* * "Factory macro" for generating a call to func, guarded by a - * DYNAMIC_DEBUG_BRANCH. The dynamic debug decriptor will be + * DYNAMIC_DEBUG_BRANCH. The dynamic debug descriptor will be * initialized using the fmt argument. The function will be called with * the address of the descriptor as first argument, followed by all * the varargs. Note that fmt is repeated in invocations of this -- cgit v1.2.3 From dd6f843a9fca8f225c86fee5f50da429c369c045 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 18 Jul 2020 11:32:51 +0300 Subject: tasks: add put_task_struct_many() put_task_struct_many() is as put_task_struct() but puts several references at once. Useful to batching it. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/sched/task.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 38359071236a..1301077f9c24 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -126,6 +126,12 @@ static inline void put_task_struct(struct task_struct *t) __put_task_struct(t); } +static inline void put_task_struct_many(struct task_struct *t, int nr) +{ + if (refcount_sub_and_test(nr, &t->usage)) + __put_task_struct(t); +} + void put_task_struct_rcu_user(struct task_struct *task); #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT -- cgit v1.2.3 From 042dd05bddbd84e6a52b337a65d1994003c9b9bb Mon Sep 17 00:00:00 2001 From: Meir Lichtinger Date: Thu, 4 Jun 2020 08:49:38 +0300 Subject: RDMA/mlx5: ConnectX-7 new capabilities to set relaxed ordering by UMR Up to ConnectX-7 setting mkey relaxed ordering read/write attributes by UMR is not supported. ConnectX-7 supports this option, which is indicated by two new HCA capabilities - relaxed_ordering_write_umr and relaxed_ordering_read_umr. Signed-off-by: Meir Lichtinger Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 435ab47d5362..0257329431e8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1240,7 +1240,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_sgl_for_optimized_performance[0x8]; u8 log_max_cq_sz[0x8]; - u8 reserved_at_d0[0x9]; + u8 relaxed_ordering_write_umr[0x1]; + u8 relaxed_ordering_read_umr[0x1]; + u8 reserved_at_d2[0x7]; u8 virtio_net_device_emualtion_manager[0x1]; u8 virtio_blk_device_emualtion_manager[0x1]; u8 log_max_cq[0x5]; -- cgit v1.2.3 From 3bef735ad7b7d987069181e7b58588043cbd1509 Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Thu, 23 Jul 2020 21:15:14 -0700 Subject: vfs/xattr: mm/shmem: kernfs: release simple xattr entry in a right way After commit fdc85222d58e ("kernfs: kvmalloc xattr value instead of kmalloc"), simple xattr entry is allocated with kvmalloc() instead of kmalloc(), so we should release it with kvfree() instead of kfree(). Fixes: fdc85222d58e ("kernfs: kvmalloc xattr value instead of kmalloc") Signed-off-by: Chengguang Xu Signed-off-by: Andrew Morton Acked-by: Hugh Dickins Acked-by: Tejun Heo Cc: Daniel Xu Cc: Chris Down Cc: Andreas Dilger Cc: Greg Kroah-Hartman Cc: Al Viro Cc: [5.7] Link: http://lkml.kernel.org/r/20200704051608.15043-1-cgxu519@mykernel.net Signed-off-by: Linus Torvalds --- include/linux/xattr.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 47eaa34f8761..c5afaf8ca7a2 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -15,6 +15,7 @@ #include #include #include +#include #include struct inode; @@ -94,7 +95,7 @@ static inline void simple_xattrs_free(struct simple_xattrs *xattrs) list_for_each_entry_safe(xattr, node, &xattrs->head, list) { kfree(xattr->name); - kfree(xattr); + kvfree(xattr); } } -- cgit v1.2.3 From e0b3e0b1a04367fc15c07f44e78361545b55357c Mon Sep 17 00:00:00 2001 From: "Michael J. Ruhl" Date: Thu, 23 Jul 2020 21:15:46 -0700 Subject: io-mapping: indicate mapping failure The !ATOMIC_IOMAP version of io_maping_init_wc will always return success, even when the ioremap fails. Since the ATOMIC_IOMAP version returns NULL when the init fails, and callers check for a NULL return on error this is unexpected. During a device probe, where the ioremap failed, a crash can look like this: BUG: unable to handle page fault for address: 0000000000210000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page Oops: 0002 [#1] PREEMPT SMP CPU: 0 PID: 177 Comm: RIP: 0010:fill_page_dma [i915] gen8_ppgtt_create [i915] i915_ppgtt_create [i915] intel_gt_init [i915] i915_gem_init [i915] i915_driver_probe [i915] pci_device_probe really_probe driver_probe_device The remap failure occurred much earlier in the probe. If it had been propagated, the driver would have exited with an error. Return NULL on ioremap failure. [akpm@linux-foundation.org: detect ioremap_wc() errors earlier] Fixes: cafaf14a5d8f ("io-mapping: Always create a struct to hold metadata about the io-mapping") Signed-off-by: Michael J. Ruhl Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Mike Rapoport Cc: Andy Shevchenko Cc: Chris Wilson Cc: Daniel Vetter Cc: Link: http://lkml.kernel.org/r/20200721171936.81563-1-michael.j.ruhl@intel.com Signed-off-by: Linus Torvalds --- include/linux/io-mapping.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 0beaa3eba155..c75e4d3d8833 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -107,9 +107,12 @@ io_mapping_init_wc(struct io_mapping *iomap, resource_size_t base, unsigned long size) { + iomap->iomem = ioremap_wc(base, size); + if (!iomap->iomem) + return NULL; + iomap->base = base; iomap->size = size; - iomap->iomem = ioremap_wc(base, size); #if defined(pgprot_noncached_wc) /* archs can't agree on a name ... */ iomap->prot = pgprot_noncached_wc(PAGE_KERNEL); #elif defined(pgprot_writecombine) -- cgit v1.2.3 From 0c2a34937f7e4c4776bb261114c475392da2355c Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 30 Jun 2020 18:24:40 +0200 Subject: i2c: revert "i2c: core: Allow drivers to disable i2c-core irq mapping" This manually reverts commit d1d84bb95364ed604015c2b788caaf3dbca0262f. The only user has gone two years ago with commit 589edb56b424 ("ACPI / scan: Create platform device for INT33FE ACPI nodes") and no new user has showed up. Remove and hope we will never need it again. Signed-off-by: Wolfram Sang Acked-by: Hans de Goede Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index b8b8963f8bb9..098405df431f 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -231,7 +231,6 @@ enum i2c_alert_protocol { * @detect: Callback for device detection * @address_list: The I2C addresses to probe (for detect) * @clients: List of detected clients we created (for i2c-core use only) - * @disable_i2c_core_irq_mapping: Tell the i2c-core to not do irq-mapping * * The driver.owner field should be set to the module owner of this driver. * The driver.name field should be set to the name of this driver. @@ -290,8 +289,6 @@ struct i2c_driver { int (*detect)(struct i2c_client *client, struct i2c_board_info *info); const unsigned short *address_list; struct list_head clients; - - bool disable_i2c_core_irq_mapping; }; #define to_i2c_driver(d) container_of(d, struct i2c_driver, driver) -- cgit v1.2.3 From 43148b1cab44dbabf91cb70749ef3f9b24592e91 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Fri, 24 Jul 2020 14:19:12 -0700 Subject: soc: ti: k3-ringacc: add request pair of rings api. Add new API k3_ringacc_request_rings_pair() to request pair of rings at once, as in the most cases Rings are used with DMA channels, which need to request pair of rings - one to feed DMA with descriptors (TX/RX FDQ) and one to receive completions (RX/TX CQ). This will allow to simplify Ringacc API users. Signed-off-by: Grygorii Strashko Reviewed-by: Peter Ujfalusi Signed-off-by: Santosh Shilimkar --- include/linux/soc/ti/k3-ringacc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/ti/k3-ringacc.h b/include/linux/soc/ti/k3-ringacc.h index 26f73df0a524..7ac115432fa1 100644 --- a/include/linux/soc/ti/k3-ringacc.h +++ b/include/linux/soc/ti/k3-ringacc.h @@ -107,6 +107,10 @@ struct k3_ringacc *of_k3_ringacc_get_by_phandle(struct device_node *np, struct k3_ring *k3_ringacc_request_ring(struct k3_ringacc *ringacc, int id, u32 flags); +int k3_ringacc_request_rings_pair(struct k3_ringacc *ringacc, + int fwd_id, int compl_id, + struct k3_ring **fwd_ring, + struct k3_ring **compl_ring); /** * k3_ringacc_ring_reset - ring reset * @ring: pointer on Ring -- cgit v1.2.3 From 2ea17d504a0ee9b357a5fd2bde257c2ec37ceca7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 24 Jul 2020 14:42:03 -0700 Subject: soc: ti/ti_sci_protocol.h: drop a duplicated word + clarify Drop the repeated word "an" in a comment. Insert "and" between "source" and "destination" as is done a few lines earlier. Signed-off-by: Randy Dunlap Reviewed-by: Tero Kristo Signed-off-by: Santosh Shilimkar --- include/linux/soc/ti/ti_sci_protocol.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 9531ec823298..6c728dad8c10 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -226,8 +226,8 @@ struct ti_sci_rm_core_ops { * and destination * @set_event_map: Set an Event based peripheral irq to Interrupt * Aggregator. - * @free_irq: Free an an IRQ route between the requested source - * destination. + * @free_irq: Free an IRQ route between the requested source + * and destination. * @free_event_map: Free an event based peripheral irq to Interrupt * Aggregator. */ -- cgit v1.2.3 From a6df49f4224324dd8588f6a0d9cff53cd61a196b Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Fri, 24 Jul 2020 14:43:48 -0700 Subject: firmware: ti_sci: Replace HTTP links with HTTPS ones Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. Signed-off-by: Alexander A. Klimov Acked-by: Rob Herring Signed-off-by: Santosh Shilimkar --- include/linux/soc/ti/ti_sci_inta_msi.h | 2 +- include/linux/soc/ti/ti_sci_protocol.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/ti/ti_sci_inta_msi.h b/include/linux/soc/ti/ti_sci_inta_msi.h index 11fb5048f5f6..e3aa8b14612e 100644 --- a/include/linux/soc/ti/ti_sci_inta_msi.h +++ b/include/linux/soc/ti/ti_sci_inta_msi.h @@ -2,7 +2,7 @@ /* * Texas Instruments' K3 TI SCI INTA MSI helper * - * Copyright (C) 2018-2019 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2018-2019 Texas Instruments Incorporated - https://www.ti.com/ * Lokesh Vutla */ diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 6c728dad8c10..49c5d29cd33c 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -2,7 +2,7 @@ /* * Texas Instruments System Control Interface Protocol * - * Copyright (C) 2015-2016 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2015-2016 Texas Instruments Incorporated - https://www.ti.com/ * Nishanth Menon */ -- cgit v1.2.3 From 0cb09aff9d49d92305c3969fc84b785117412968 Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Thu, 23 Jul 2020 01:03:00 +0300 Subject: net/flow_dissector: add packet hash dissection Retreive a hash value from the SKB and store it in the dissector key for future matching. Signed-off-by: Ariel Levkovich Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6a82d4a8229e..fa817a105517 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1342,6 +1342,10 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); +void skb_flow_dissect_hash(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container); + static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) -- cgit v1.2.3 From ba423fdaa589d972473083defedf9e862626d268 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:46 +0200 Subject: net: add a new sockptr_t type Add a uptr_t type that can hold a pointer to either a user or kernel memory region, and simply helpers to copy to and from it. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/sockptr.h | 104 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 104 insertions(+) create mode 100644 include/linux/sockptr.h (limited to 'include/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h new file mode 100644 index 000000000000..700856e13ea0 --- /dev/null +++ b/include/linux/sockptr.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2020 Christoph Hellwig. + * + * Support for "universal" pointers that can point to either kernel or userspace + * memory. + */ +#ifndef _LINUX_SOCKPTR_H +#define _LINUX_SOCKPTR_H + +#include +#include + +typedef struct { + union { + void *kernel; + void __user *user; + }; + bool is_kernel : 1; +} sockptr_t; + +static inline bool sockptr_is_kernel(sockptr_t sockptr) +{ + return sockptr.is_kernel; +} + +static inline sockptr_t KERNEL_SOCKPTR(void *p) +{ + return (sockptr_t) { .kernel = p, .is_kernel = true }; +} + +static inline sockptr_t USER_SOCKPTR(void __user *p) +{ + return (sockptr_t) { .user = p }; +} + +static inline bool sockptr_is_null(sockptr_t sockptr) +{ + return !sockptr.user && !sockptr.kernel; +} + +static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) +{ + if (!sockptr_is_kernel(src)) + return copy_from_user(dst, src.user, size); + memcpy(dst, src.kernel, size); + return 0; +} + +static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) +{ + if (!sockptr_is_kernel(dst)) + return copy_to_user(dst.user, src, size); + memcpy(dst.kernel, src, size); + return 0; +} + +static inline void *memdup_sockptr(sockptr_t src, size_t len) +{ + void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); + + if (!p) + return ERR_PTR(-ENOMEM); + if (copy_from_sockptr(p, src, len)) { + kfree(p); + return ERR_PTR(-EFAULT); + } + return p; +} + +static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) +{ + char *p = kmalloc_track_caller(len + 1, GFP_KERNEL); + + if (!p) + return ERR_PTR(-ENOMEM); + if (copy_from_sockptr(p, src, len)) { + kfree(p); + return ERR_PTR(-EFAULT); + } + p[len] = '\0'; + return p; +} + +static inline void sockptr_advance(sockptr_t sockptr, size_t len) +{ + if (sockptr_is_kernel(sockptr)) + sockptr.kernel += len; + else + sockptr.user += len; +} + +static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) +{ + if (sockptr_is_kernel(src)) { + size_t len = min(strnlen(src.kernel, count - 1) + 1, count); + + memcpy(dst, src.kernel, len); + return len; + } + return strncpy_from_user(dst, src.user, count); +} + +#endif /* _LINUX_SOCKPTR_H */ -- cgit v1.2.3 From b1ea9ff6aff2deae84eccaf0a07cd14912669680 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:47 +0200 Subject: net: switch copy_bpf_fprog_from_user to sockptr_t Pass a sockptr_t to prepare for set_fs-less handling of the kernel pointer from bpf-cgroup. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/filter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 1c6b6d982bf4..d07a6e973a7d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -1276,7 +1277,7 @@ struct bpf_sockopt_kern { s32 retval; }; -int copy_bpf_fprog_from_user(struct sock_fprog *dst, void __user *src, int len); +int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); struct bpf_sk_lookup_kern { u16 family; -- cgit v1.2.3 From ab214d1bf8c7ef1ed7af803a72491cb29edfa8f5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:53 +0200 Subject: netfilter: switch xt_copy_counters to sockptr_t Pass a sockptr_t to prepare for set_fs-less handling of the kernel pointer from bpf-cgroup. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index b8b943ee7b8b..5deb099d156d 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -301,8 +301,8 @@ int xt_target_to_user(const struct xt_entry_target *t, int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size); -void *xt_copy_counters_from_user(const void __user *user, unsigned int len, - struct xt_counters_info *info); +void *xt_copy_counters(sockptr_t arg, unsigned int len, + struct xt_counters_info *info); struct xt_counters *xt_counters_alloc(unsigned int counters); struct xt_table *xt_register_table(struct net *net, -- cgit v1.2.3 From c2f12630c60ff33a9cafd221646053fc10ec59b6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:54 +0200 Subject: netfilter: switch nf_setsockopt to sockptr_t Pass a sockptr_t to prepare for set_fs-less handling of the kernel pointer from bpf-cgroup. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/netfilter.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 711b4d4486f0..0101747de549 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -13,6 +13,7 @@ #include #include #include +#include #include static inline int NF_DROP_GETERR(int verdict) @@ -163,7 +164,8 @@ struct nf_sockopt_ops { /* Non-inclusive ranges: use 0/0/NULL to never get called. */ int set_optmin; int set_optmax; - int (*set)(struct sock *sk, int optval, void __user *user, unsigned int len); + int (*set)(struct sock *sk, int optval, sockptr_t arg, + unsigned int len); int get_optmin; int get_optmax; int (*get)(struct sock *sk, int optval, void __user *user, int *len); @@ -338,7 +340,7 @@ NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, } /* Call setsockopt() */ -int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, +int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, sockptr_t opt, unsigned int len); int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); -- cgit v1.2.3 From b03afaa82ece13b2a008f0e3a7127bead578e3e6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:55 +0200 Subject: bpfilter: switch bpfilter_ip_set_sockopt to sockptr_t This is mostly to prepare for cleaning up the callers, as bpfilter by design can't handle kernel pointers. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/bpfilter.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index 9b114c718a76..2ae3c8e1d83c 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -4,9 +4,10 @@ #include #include +#include struct sock; -int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, +int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen); int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen); @@ -16,8 +17,7 @@ struct bpfilter_umh_ops { struct umd_info info; /* since ip_getsockopt() can run in parallel, serialize access to umh */ struct mutex lock; - int (*sockopt)(struct sock *sk, int optname, - char __user *optval, + int (*sockopt)(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen, bool is_set); int (*start)(void); }; -- cgit v1.2.3 From 01ccb5b48f08f59ca3746d59221f4990aec1b194 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:56 +0200 Subject: net/ipv4: switch ip_mroute_setsockopt to sockptr_t Pass a sockptr_t to prepare for set_fs-less handling of the kernel pointer from bpf-cgroup. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/mroute.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 9a36fad9e068..6cbbfe94348c 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -8,6 +8,7 @@ #include #include #include +#include #ifdef CONFIG_IP_MROUTE static inline int ip_mroute_opt(int opt) @@ -15,7 +16,7 @@ static inline int ip_mroute_opt(int opt) return opt >= MRT_BASE && opt <= MRT_MAX; } -int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); +int ip_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int); int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); @@ -23,7 +24,7 @@ int ip_mr_init(void); bool ipmr_rule_default(const struct fib_rule *rule); #else static inline int ip_mroute_setsockopt(struct sock *sock, int optname, - char __user *optval, unsigned int optlen) + sockptr_t optval, unsigned int optlen) { return -ENOPROTOOPT; } -- cgit v1.2.3 From b43c6153132c92745317f92174af84f57b160b76 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:59 +0200 Subject: net/ipv6: switch ip6_mroute_setsockopt to sockptr_t Pass a sockptr_t to prepare for set_fs-less handling of the kernel pointer from bpf-cgroup. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/mroute6.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index c4a45859f586..bc351a85ce9b 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #ifdef CONFIG_IPV6_MROUTE @@ -25,7 +26,7 @@ static inline int ip6_mroute_opt(int opt) struct sock; #ifdef CONFIG_IPV6_MROUTE -extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); +extern int ip6_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int); extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *); extern int ip6_mr_input(struct sk_buff *skb); extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg); @@ -33,9 +34,8 @@ extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *ar extern int ip6_mr_init(void); extern void ip6_mr_cleanup(void); #else -static inline -int ip6_mroute_setsockopt(struct sock *sock, - int optname, char __user *optval, unsigned int optlen) +static inline int ip6_mroute_setsockopt(struct sock *sock, int optname, + sockptr_t optval, unsigned int optlen) { return -ENOPROTOOPT; } -- cgit v1.2.3 From a7b75c5a8c41445f33efb663887ff5f5c3b4454b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:09:07 +0200 Subject: net: pass a sockptr_t into ->setsockopt Rework the remaining setsockopt code to pass a sockptr_t instead of a plain user pointer. This removes the last remaining set_fs(KERNEL_DS) outside of architecture specific code. Signed-off-by: Christoph Hellwig Acked-by: Stefan Schmidt [ieee802154] Acked-by: Matthieu Baerts Signed-off-by: David S. Miller --- include/linux/net.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 858ff1d98154..d48ff1180879 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -21,6 +21,7 @@ #include #include #include +#include #include @@ -162,7 +163,8 @@ struct proto_ops { int (*listen) (struct socket *sock, int len); int (*shutdown) (struct socket *sock, int flags); int (*setsockopt)(struct socket *sock, int level, - int optname, char __user *optval, unsigned int optlen); + int optname, sockptr_t optval, + unsigned int optlen); int (*getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); void (*show_fdinfo)(struct seq_file *m, struct socket *sock); -- cgit v1.2.3 From 6d04fe15f78acdf8e32329e208552e226f7a8ae6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:09:08 +0200 Subject: net: optimize the sockptr_t for unified kernel/user address spaces For architectures like x86 and arm64 we don't need the separate bit to indicate that a pointer is a kernel pointer as the address spaces are unified. That way the sockptr_t can be reduced to a union of two pointers, which leads to nicer calling conventions. The only caveat is that we need to check that users don't pass in kernel address and thus gain access to kernel memory. Thus the USER_SOCKPTR helper is replaced with a init_user_sockptr function that does this check and returns an error if it fails. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/sockptr.h | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 700856e13ea0..7d5cdb2b30b5 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -8,9 +8,34 @@ #ifndef _LINUX_SOCKPTR_H #define _LINUX_SOCKPTR_H +#include #include #include +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE +typedef union { + void *kernel; + void __user *user; +} sockptr_t; + +static inline bool sockptr_is_kernel(sockptr_t sockptr) +{ + return (unsigned long)sockptr.kernel >= TASK_SIZE; +} + +static inline sockptr_t KERNEL_SOCKPTR(void *p) +{ + return (sockptr_t) { .kernel = p }; +} + +static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p) +{ + if ((unsigned long)p >= TASK_SIZE) + return -EFAULT; + sp->user = p; + return 0; +} +#else /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ typedef struct { union { void *kernel; @@ -29,10 +54,13 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p) return (sockptr_t) { .kernel = p, .is_kernel = true }; } -static inline sockptr_t USER_SOCKPTR(void __user *p) +static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p) { - return (sockptr_t) { .user = p }; + sp->user = p; + sp->is_kernel = false; + return 0; } +#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ static inline bool sockptr_is_null(sockptr_t sockptr) { -- cgit v1.2.3 From 178c49d9f9a4b5ade00c93480d714708fe971e24 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 24 Jul 2020 09:03:09 -0400 Subject: icmp: prepare rfc 4884 for ipv6 The RFC 4884 spec is largely the same between IPv4 and IPv6. Factor out the IPv4 specific parts in preparation for IPv6 support: - icmp types supported - icmp header size, and thus offset to original datagram start - datagram length field offset in icmp(6)hdr. - datagram length field word size: 4B for IPv4, 8B for IPv6. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/icmp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/icmp.h b/include/linux/icmp.h index 8fc38a34cb20..0af4d210ee31 100644 --- a/include/linux/icmp.h +++ b/include/linux/icmp.h @@ -37,6 +37,7 @@ static inline bool icmp_is_err(int type) } void ip_icmp_error_rfc4884(const struct sk_buff *skb, - struct sock_ee_data_rfc4884 *out); + struct sock_ee_data_rfc4884 *out, + int thlen, int off); #endif /* _LINUX_ICMP_H */ -- cgit v1.2.3 From 01370434df85eb76ecb1527a4466013c4aca2436 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 24 Jul 2020 09:03:10 -0400 Subject: icmp6: support rfc 4884 Extend the rfc 4884 read interface introduced for ipv4 in commit eba75c587e81 ("icmp: support rfc 4884") to ipv6. Add socket option SOL_IPV6/IPV6_RECVERR_RFC4884. Changes v1->v2: - make ipv6_icmp_error_rfc4884 static (file scope) Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 8d8f877e7f81..a44789d027cc 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -283,6 +283,7 @@ struct ipv6_pinfo { autoflowlabel:1, autoflowlabel_set:1, mc_all:1, + recverr_rfc4884:1, rtalert_isolate:1; __u8 min_hopcount; __u8 tclass; -- cgit v1.2.3 From 0f206514749be9988a083ca364b889a7fcff7f78 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 10 Jul 2020 00:20:08 -0700 Subject: scsi: firmware: qcom_scm: Add support for programming inline crypto keys Add support for the Inline Crypto Engine (ICE) key programming interface that's needed for the ufs-qcom driver to use inline encryption on Snapdragon SoCs. This interface consists of two SCM calls: one to program a key into a keyslot, and one to invalidate a keyslot. Although the UFS specification defines a standard way to do this, on these SoCs the Linux kernel isn't permitted to access the needed crypto configuration registers directly; these SCM calls must be used instead. Link: https://lore.kernel.org/r/20200710072013.177481-2-ebiggers@kernel.org Acked-by: Bjorn Andersson Signed-off-by: Eric Biggers Signed-off-by: Martin K. Petersen --- include/linux/qcom_scm.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 3d6a24697761..2e1193a3fb5f 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -44,6 +44,13 @@ enum qcom_scm_sec_dev_id { QCOM_SCM_ICE_DEV_ID = 20, }; +enum qcom_scm_ice_cipher { + QCOM_SCM_ICE_CIPHER_AES_128_XTS = 0, + QCOM_SCM_ICE_CIPHER_AES_128_CBC = 1, + QCOM_SCM_ICE_CIPHER_AES_256_XTS = 3, + QCOM_SCM_ICE_CIPHER_AES_256_CBC = 4, +}; + #define QCOM_SCM_VMID_HLOS 0x3 #define QCOM_SCM_VMID_MSS_MSA 0xF #define QCOM_SCM_VMID_WLAN 0x18 @@ -88,6 +95,12 @@ extern int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, extern int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, u32 size); +extern bool qcom_scm_ice_available(void); +extern int qcom_scm_ice_invalidate_key(u32 index); +extern int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size, + enum qcom_scm_ice_cipher cipher, + u32 data_unit_size); + extern bool qcom_scm_hdcp_available(void); extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp); @@ -138,6 +151,12 @@ static inline int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, static inline int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, u32 size) { return -ENODEV; } +static inline bool qcom_scm_ice_available(void) { return false; } +static inline int qcom_scm_ice_invalidate_key(u32 index) { return -ENODEV; } +static inline int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size, + enum qcom_scm_ice_cipher cipher, + u32 data_unit_size) { return -ENODEV; } + static inline bool qcom_scm_hdcp_available(void) { return false; } static inline int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp) { return -ENODEV; } -- cgit v1.2.3 From 2d38dbf89a06d0f689daec9842c5d3295c49777f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 24 Jul 2020 14:36:22 -0700 Subject: test_firmware: Test platform fw loading on non-EFI systems On non-EFI systems, it wasn't possible to test the platform firmware loader because it will have never set "checked_fw" during __init. Instead, allow the test code to override this check. Additionally split the declarations into a private header file so it there is greater enforcement of the symbol visibility. Fixes: 548193cba2a7 ("test_firmware: add support for firmware_request_platform") Cc: stable@vger.kernel.org Acked-by: Scott Branden Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20200724213640.389191-2-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/efi_embedded_fw.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h index 57eac5241303..4ad5db9f5312 100644 --- a/include/linux/efi_embedded_fw.h +++ b/include/linux/efi_embedded_fw.h @@ -7,19 +7,6 @@ #define EFI_EMBEDDED_FW_PREFIX_LEN 8 -/* - * This struct and efi_embedded_fw_list are private to the efi-embedded fw - * implementation they are in this header for use by lib/test_firmware.c only! - */ -struct efi_embedded_fw { - struct list_head list; - const char *name; - const u8 *data; - size_t length; -}; - -extern struct list_head efi_embedded_fw_list; - /** * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw * code to search for embedded firmwares. -- cgit v1.2.3 From 92fe2aa859f52ce6aa595ca97fec110dc7100e63 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:07:30 -0700 Subject: libnvdimm: Validate command family indices The ND_CMD_CALL format allows for a general passthrough of passlisted commands targeting a given command set. However there is no validation of the family index relative to what the bus supports. - Update the NFIT bus implementation (the only one that supports ND_CMD_CALL passthrough) to also passlist the valid set of command family indices. - Update the generic __nd_ioctl() path to validate that field on behalf of all implementations. Fixes: 31eca76ba2fc ("nfit, libnvdimm: limited/whitelisted dimm command marshaling mechanism") Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- include/linux/libnvdimm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 18da4059be09..bd39a2cf7972 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -78,6 +78,8 @@ struct nvdimm_bus_descriptor { const struct attribute_group **attr_groups; unsigned long bus_dsm_mask; unsigned long cmd_mask; + unsigned long dimm_family_mask; + unsigned long bus_family_mask; struct module *module; char *provider_name; struct device_node *of_node; -- cgit v1.2.3 From d46e6a2176f8edf7030db34aeb54a4f016fabe0a Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:07:35 -0700 Subject: ACPI: NFIT: Move bus_dsm_mask out of generic nvdimm_bus_descriptor DSMs are strictly an ACPI mechanism, evict the bus_dsm_mask concept from the generic 'struct nvdimm_bus_descriptor' object. As a side effect the test facility ->bus_nfit_cmd_force_en is no longer necessary. The test infrastructure can communicate that information directly in ->bus_dsm_mask. Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- include/linux/libnvdimm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index bd39a2cf7972..ad9898ece7d3 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -76,7 +76,6 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc, struct device_node; struct nvdimm_bus_descriptor { const struct attribute_group **attr_groups; - unsigned long bus_dsm_mask; unsigned long cmd_mask; unsigned long dimm_family_mask; unsigned long bus_family_mask; -- cgit v1.2.3 From 60d360acddc54344409a710af07c561e025f13f5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:08:07 -0700 Subject: driver-core: Introduce DEVICE_ATTR_ADMIN_{RO,RW} A common pattern for using plain DEVICE_ATTR() instead of DEVICE_ATTR_RO() and DEVICE_ATTR_RW() is for attributes that want to limit read to only root. I.e. many users of DEVICE_ATTR() are specifying 0400 or 0600 for permissions. Given the expectation that CAP_SYS_ADMIN is needed to access these sensitive attributes add an explicit helper with the _ADMIN_ identifier for DEVICE_ATTR_ADMIN_{RO,RW}. Cc: "Rafael J. Wysocki" Reviewed-by: Greg Kroah-Hartman Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- include/linux/device.h | 4 ++++ include/linux/sysfs.h | 7 +++++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 15460a5ac024..d7c2570368fa 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -128,8 +128,12 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, __ATTR_PREALLOC(_name, _mode, _show, _store) #define DEVICE_ATTR_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW(_name) +#define DEVICE_ATTR_ADMIN_RW(_name) \ + struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600) #define DEVICE_ATTR_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO(_name) +#define DEVICE_ATTR_ADMIN_RO(_name) \ + struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400) #define DEVICE_ATTR_WO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_WO(_name) #define DEVICE_ULONG_ATTR(_name, _mode, _var) \ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 86067dbe7745..34e84122f635 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -123,6 +123,13 @@ struct attribute_group { .show = _name##_show, \ } +#define __ATTR_RW_MODE(_name, _mode) { \ + .attr = { .name = __stringify(_name), \ + .mode = VERIFY_OCTAL_PERMISSIONS(_mode) }, \ + .show = _name##_show, \ + .store = _name##_store, \ +} + #define __ATTR_WO(_name) { \ .attr = { .name = __stringify(_name), .mode = 0200 }, \ .store = _name##_store, \ -- cgit v1.2.3 From a228a64fc1e4428e2b96dc68e9ad3c447095c9e7 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 1 Jul 2020 18:10:18 -0700 Subject: bpf: Add bpf_prog iterator It's mostly a copy paste of commit 6086d29def80 ("bpf: Add bpf_map iterator") that is use to implement bpf_seq_file opreations to traverse all bpf programs. v1->v2: Tweak to use build time btf_id Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Acked-by: Daniel Borkmann --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bae557ff2da8..72221aea1c60 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1117,6 +1117,7 @@ int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); struct bpf_map *bpf_map_get_curr_or_next(u32 *id); +struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); extern int sysctl_unprivileged_bpf_disabled; -- cgit v1.2.3 From 14fc6bd6b79c430f615500d0fe6cea4722110db8 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:09 -0700 Subject: bpf: Refactor bpf_iter_reg to have separate seq_info member There is no functionality change for this patch. Struct bpf_iter_reg is used to register a bpf_iter target, which includes information for both prog_load, link_create and seq_file creation. This patch puts fields related seq_file creation into a different structure. This will be useful for map elements iterator where one iterator covers different map types and different map types may have different seq_ops, init/fini private_data function and private_data size. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184109.590030-1-yhs@fb.com --- include/linux/bpf.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 72221aea1c60..127067f71fd4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -37,6 +37,15 @@ struct seq_operations; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; +typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); +typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); +struct bpf_iter_seq_info { + const struct seq_operations *seq_ops; + bpf_iter_init_seq_priv_t init_seq_private; + bpf_iter_fini_seq_priv_t fini_seq_private; + u32 seq_priv_size; +}; + /* map is generic key/value storage optionally accesible by eBPF programs */ struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ @@ -1189,18 +1198,12 @@ int bpf_obj_get_user(const char __user *pathname, int flags); extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } -typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); -typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); - #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; - const struct seq_operations *seq_ops; - bpf_iter_init_seq_priv_t init_seq_private; - bpf_iter_fini_seq_priv_t fini_seq_private; - u32 seq_priv_size; u32 ctx_arg_info_size; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; + const struct bpf_iter_seq_info *seq_info; }; struct bpf_iter_meta { -- cgit v1.2.3 From f9c792729581bd8b8473af163e8ab426c2c61d89 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:10 -0700 Subject: bpf: Refactor to provide aux info to bpf_iter_init_seq_priv_t This patch refactored target bpf_iter_init_seq_priv_t callback function to accept additional information. This will be needed in later patches for map element targets since a particular map should be passed to traverse elements for that particular map. In the future, other information may be passed to target as well, e.g., pid, cgroup id, etc. to customize the iterator. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184110.590156-1-yhs@fb.com --- include/linux/bpf.h | 7 ++++++- include/linux/proc_fs.h | 3 ++- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 127067f71fd4..ef52717336cf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -33,11 +33,13 @@ struct btf; struct btf_type; struct exception_table_entry; struct seq_operations; +struct bpf_iter_aux_info; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; -typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); +typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, + struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); struct bpf_iter_seq_info { const struct seq_operations *seq_ops; @@ -1198,6 +1200,9 @@ int bpf_obj_get_user(const char __user *pathname, int flags); extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } +struct bpf_iter_aux_info { +}; + #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index d1eed1b43651..2df965cd0974 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -133,7 +133,8 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo void *data); extern struct pid *tgid_pidfd_to_pid(const struct file *file); -extern int bpf_iter_init_seq_net(void *priv_data); +struct bpf_iter_aux_info; +extern int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux); extern void bpf_iter_fini_seq_net(void *priv_data); #ifdef CONFIG_PROC_PID_ARCH_STATUS -- cgit v1.2.3 From afbf21dce668ef59482037596eaffbe5041e094c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:11 -0700 Subject: bpf: Support readonly/readwrite buffers in verifier Readonly and readwrite buffer register states are introduced. Totally four states, PTR_TO_RDONLY_BUF[_OR_NULL] and PTR_TO_RDWR_BUF[_OR_NULL] are supported. As suggested by their respective names, PTR_TO_RDONLY_BUF[_OR_NULL] are for readonly buffers and PTR_TO_RDWR_BUF[_OR_NULL] for read/write buffers. These new register states will be used by later bpf map element iterator. New register states share some similarity to PTR_TO_TP_BUFFER as it will calculate accessed buffer size during verification time. The accessed buffer size will be later compared to other metrics during later attach/link_create time. Similar to reg_state PTR_TO_BTF_ID_OR_NULL in bpf iterator programs, PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL reg_types can be set at prog->aux->bpf_ctx_arg_aux, and bpf verifier will retrieve the values during btf_ctx_access(). Later bpf map element iterator implementation will show how such information will be assigned during target registeration time. The verifier is also enhanced such that PTR_TO_RDONLY_BUF can be passed to ARG_PTR_TO_MEM[_OR_NULL] helper argument, and PTR_TO_RDWR_BUF can be passed to ARG_PTR_TO_MEM[_OR_NULL] or ARG_PTR_TO_UNINIT_MEM. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184111.590274-1-yhs@fb.com --- include/linux/bpf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ef52717336cf..f9c4bb08f616 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -353,6 +353,10 @@ enum bpf_reg_type { PTR_TO_BTF_ID_OR_NULL, /* reg points to kernel struct or NULL */ PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */ + PTR_TO_RDONLY_BUF, /* reg points to a readonly buffer */ + PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */ + PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */ + PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -694,6 +698,8 @@ struct bpf_prog_aux { u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ u32 ctx_arg_info_size; + u32 max_rdonly_access; + u32 max_rdwr_access; const struct bpf_ctx_arg_aux *ctx_arg_info; struct bpf_prog *linked_prog; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ -- cgit v1.2.3 From a5cbe05a6673b85bed2a63ffcfea6a96c6410cff Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:12 -0700 Subject: bpf: Implement bpf iterator for map elements The bpf iterator for map elements are implemented. The bpf program will receive four parameters: bpf_iter_meta *meta: the meta data bpf_map *map: the bpf_map whose elements are traversed void *key: the key of one element void *value: the value of the same element Here, meta and map pointers are always valid, and key has register type PTR_TO_RDONLY_BUF_OR_NULL and value has register type PTR_TO_RDWR_BUF_OR_NULL. The kernel will track the access range of key and value during verification time. Later, these values will be compared against the values in the actual map to ensure all accesses are within range. A new field iter_seq_info is added to bpf_map_ops which is used to add map type specific information, i.e., seq_ops, init/fini seq_file func and seq_file private data size. Subsequent patches will have actual implementation for bpf_map_ops->iter_seq_info. In user space, BPF_ITER_LINK_MAP_FD needs to be specified in prog attr->link_create.flags, which indicates that attr->link_create.target_fd is a map_fd. The reason for such an explicit flag is for possible future cases where one bpf iterator may allow more than one possible customization, e.g., pid and cgroup id for task_file. Current kernel internal implementation only allows the target to register at most one required bpf_iter_link_info. To support the above case, optional bpf_iter_link_info's are needed, the target can be extended to register such link infos, and user provided link_info needs to match one of target supported ones. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184112.590360-1-yhs@fb.com --- include/linux/bpf.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f9c4bb08f616..4175cf1f4665 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -107,6 +107,9 @@ struct bpf_map_ops { /* BTF name and id of struct allocated by map_alloc */ const char * const map_btf_name; int *map_btf_id; + + /* bpf_iter info used to open a seq_file */ + const struct bpf_iter_seq_info *iter_seq_info; }; struct bpf_map_memory { @@ -1207,12 +1210,18 @@ int bpf_obj_get_user(const char __user *pathname, int flags); int __init bpf_iter_ ## target(args) { return 0; } struct bpf_iter_aux_info { + struct bpf_map *map; }; +typedef int (*bpf_iter_check_target_t)(struct bpf_prog *prog, + struct bpf_iter_aux_info *aux); + #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; + bpf_iter_check_target_t check_target; u32 ctx_arg_info_size; + enum bpf_iter_link_info req_linfo; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; }; @@ -1223,6 +1232,13 @@ struct bpf_iter_meta { u64 seq_num; }; +struct bpf_iter__bpf_map_elem { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct bpf_map *, map); + __bpf_md_ptr(void *, key); + __bpf_md_ptr(void *, value); +}; + int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); -- cgit v1.2.3 From 7b04d6d60fcfb5b2200ffebb9cfb90927bdfeec7 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 23 Jul 2020 11:06:44 -0700 Subject: bpf: Separate bpf_get_[stack|stackid] for perf events BPF Calling get_perf_callchain() on perf_events from PEBS entries may cause unwinder errors. To fix this issue, the callchain is fetched early. Such perf_events are marked with __PERF_SAMPLE_CALLCHAIN_EARLY. Similarly, calling bpf_get_[stack|stackid] on perf_events from PEBS may also cause unwinder errors. To fix this, add separate version of these two helpers, bpf_get_[stack|stackid]_pe. These two hepers use callchain in bpf_perf_event_data_kern->data->callchain. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723180648.1429892-2-songliubraving@fb.com --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4175cf1f4665..8357be349133 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1675,6 +1675,8 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_get_task_stack_proto; +extern const struct bpf_func_proto bpf_get_stackid_proto_pe; +extern const struct bpf_func_proto bpf_get_stack_proto_pe; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; -- cgit v1.2.3 From 5d99cb2c86775b4780c02a339a9578bf9471ead9 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 23 Jul 2020 11:06:45 -0700 Subject: bpf: Fail PERF_EVENT_IOC_SET_BPF when bpf_get_[stack|stackid] cannot work bpf_get_[stack|stackid] on perf_events with precise_ip uses callchain attached to perf_sample_data. If this callchain is not presented, do not allow attaching BPF program that calls bpf_get_[stack|stackid] to this event. In the error case, -EPROTO is returned so that libbpf can identify this error and print proper hint message. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723180648.1429892-3-songliubraving@fb.com --- include/linux/filter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index d07a6e973a7d..0a355b005bf4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -533,7 +533,8 @@ struct bpf_prog { is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ has_callchain_buf:1, /* callchain buffer allocated? */ - enforce_expected_attach_type:1; /* Enforce expected_attach_type checking at attach time */ + enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ + call_get_stack:1; /* Do we call bpf_get_stack() or bpf_get_stackid() */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ -- cgit v1.2.3 From 7d9c3427894fe70d1347b4820476bf37736d2ff0 Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Thu, 23 Jul 2020 23:47:43 -0500 Subject: bpf: Make cgroup storages shared between programs on the same cgroup This change comes in several parts: One, the restriction that the CGROUP_STORAGE map can only be used by one program is removed. This results in the removal of the field 'aux' in struct bpf_cgroup_storage_map, and removal of relevant code associated with the field, and removal of now-noop functions bpf_free_cgroup_storage and bpf_cgroup_storage_release. Second, we permit a key of type u64 as the key to the map. Providing such a key type indicates that the map should ignore attach type when comparing map keys. However, for simplicity newly linked storage will still have the attach type at link time in its key struct. cgroup_storage_check_btf is adapted to accept u64 as the type of the key. Third, because the storages are now shared, the storages cannot be unconditionally freed on program detach. There could be two ways to solve this issue: * A. Reference count the usage of the storages, and free when the last program is detached. * B. Free only when the storage is impossible to be referred to again, i.e. when either the cgroup_bpf it is attached to, or the map itself, is freed. Option A has the side effect that, when the user detach and reattach a program, whether the program gets a fresh storage depends on whether there is another program attached using that storage. This could trigger races if the user is multi-threaded, and since nondeterminism in data races is evil, go with option B. The both the map and the cgroup_bpf now tracks their associated storages, and the storage unlink and free are removed from cgroup_bpf_detach and added to cgroup_bpf_release and cgroup_storage_map_free. The latter also new holds the cgroup_mutex to prevent any races with the former. Fourth, on attach, we reuse the old storage if the key already exists in the map, via cgroup_storage_lookup. If the storage does not exist yet, we create a new one, and publish it at the last step in the attach process. This does not create a race condition because for the whole attach the cgroup_mutex is held. We keep track of an array of new storages that was allocated and if the process fails only the new storages would get freed. Signed-off-by: YiFei Zhu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/d5401c6106728a00890401190db40020a1f84ff1.1595565795.git.zhuyifei@google.com --- include/linux/bpf-cgroup.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 2c6f26670acc..64f367044e25 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -46,7 +46,8 @@ struct bpf_cgroup_storage { }; struct bpf_cgroup_storage_map *map; struct bpf_cgroup_storage_key key; - struct list_head list; + struct list_head list_map; + struct list_head list_cg; struct rb_node node; struct rcu_head rcu; }; @@ -78,6 +79,9 @@ struct cgroup_bpf { struct list_head progs[MAX_BPF_ATTACH_TYPE]; u32 flags[MAX_BPF_ATTACH_TYPE]; + /* list of cgroup shared storages */ + struct list_head storages; + /* temp storage for effective prog array used by prog_attach/detach */ struct bpf_prog_array *inactive; @@ -161,6 +165,9 @@ static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage this_cpu_write(bpf_cgroup_storage[stype], storage[stype]); } +struct bpf_cgroup_storage * +cgroup_storage_lookup(struct bpf_cgroup_storage_map *map, + void *key, bool locked); struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, enum bpf_cgroup_storage_type stype); void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage); @@ -169,7 +176,6 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, enum bpf_attach_type type); void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map); -void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *map); int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, @@ -383,8 +389,6 @@ static inline void bpf_cgroup_storage_set( struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) {} static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } -static inline void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, - struct bpf_map *map) {} static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return NULL; } static inline void bpf_cgroup_storage_free( -- cgit v1.2.3 From 6cc7d1e8e9e06d45f9d1a39a5f465288d7cd8f9a Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Jul 2020 23:45:54 -0700 Subject: bpf: Make bpf_link API available indepently of CONFIG_BPF_SYSCALL Similarly to bpf_prog, make bpf_link and related generic API available unconditionally to make it easier to have bpf_link support in various parts of the kernel. Stub out init/prime/settle/cleanup and inc/put APIs. Reported-by: kernel test robot Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200722064603.3350758-2-andriin@fb.com --- include/linux/bpf.h | 81 ++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 55 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8357be349133..40c5e206ecf2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -781,6 +781,32 @@ struct bpf_array_aux { struct work_struct work; }; +struct bpf_link { + atomic64_t refcnt; + u32 id; + enum bpf_link_type type; + const struct bpf_link_ops *ops; + struct bpf_prog *prog; + struct work_struct work; +}; + +struct bpf_link_ops { + void (*release)(struct bpf_link *link); + void (*dealloc)(struct bpf_link *link); + int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, + struct bpf_prog *old_prog); + void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); + int (*fill_link_info)(const struct bpf_link *link, + struct bpf_link_info *info); +}; + +struct bpf_link_primer { + struct bpf_link *link; + struct file *file; + int fd; + u32 id; +}; + struct bpf_struct_ops_value; struct btf_type; struct btf_member; @@ -1164,32 +1190,6 @@ static inline bool bpf_bypass_spec_v4(void) int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); -struct bpf_link { - atomic64_t refcnt; - u32 id; - enum bpf_link_type type; - const struct bpf_link_ops *ops; - struct bpf_prog *prog; - struct work_struct work; -}; - -struct bpf_link_primer { - struct bpf_link *link; - struct file *file; - int fd; - u32 id; -}; - -struct bpf_link_ops { - void (*release)(struct bpf_link *link); - void (*dealloc)(struct bpf_link *link); - int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, - struct bpf_prog *old_prog); - void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); - int (*fill_link_info)(const struct bpf_link *link, - struct bpf_link_info *info); -}; - void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog); int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); @@ -1401,6 +1401,35 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } +static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, + const struct bpf_link_ops *ops, + struct bpf_prog *prog) +{ +} + +static inline int bpf_link_prime(struct bpf_link *link, + struct bpf_link_primer *primer) +{ + return -EOPNOTSUPP; +} + +static inline int bpf_link_settle(struct bpf_link_primer *primer) +{ + return -EOPNOTSUPP; +} + +static inline void bpf_link_cleanup(struct bpf_link_primer *primer) +{ +} + +static inline void bpf_link_inc(struct bpf_link *link) +{ +} + +static inline void bpf_link_put(struct bpf_link *link) +{ +} + static inline int bpf_obj_get_user(const char __user *pathname, int flags) { return -EOPNOTSUPP; -- cgit v1.2.3 From 7f0a838254bdd9114b978ef2541a6ce330307e9e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Jul 2020 23:45:55 -0700 Subject: bpf, xdp: Maintain info on attached XDP BPF programs in net_device Instead of delegating to drivers, maintain information about which BPF programs are attached in which XDP modes (generic/skb, driver, or hardware) locally in net_device. This effectively obsoletes XDP_QUERY_PROG command. Such re-organization simplifies existing code already. But it also allows to further add bpf_link-based XDP attachments without drivers having to know about any of this at all, which seems like a good setup. XDP_SETUP_PROG/XDP_SETUP_PROG_HW are just low-level commands to driver to install/uninstall active BPF program. All the higher-level concerns about prog/link interaction will be contained within generic driver-agnostic logic. All the XDP_QUERY_PROG calls to driver in dev_xdp_uninstall() were removed. It's not clear for me why dev_xdp_uninstall() were passing previous prog_flags when resetting installed programs. That seems unnecessary, plus most drivers don't populate prog_flags anyways. Having XDP_SETUP_PROG vs XDP_SETUP_PROG_HW should be enough of an indicator of what is required of driver to correctly reset active BPF program. dev_xdp_uninstall() is also generalized as an iteration over all three supported mode. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200722064603.3350758-3-andriin@fb.com --- include/linux/netdevice.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ac2cd3f49aba..cad44b40c776 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -889,6 +889,17 @@ struct netlink_ext_ack; struct xdp_umem; struct xdp_dev_bulk_queue; +enum bpf_xdp_mode { + XDP_MODE_SKB = 0, + XDP_MODE_DRV = 1, + XDP_MODE_HW = 2, + __MAX_XDP_MODE +}; + +struct bpf_xdp_entity { + struct bpf_prog *prog; +}; + struct netdev_bpf { enum bpf_netdev_command command; union { @@ -2142,6 +2153,9 @@ struct net_device { #endif const struct udp_tunnel_nic_info *udp_tunnel_nic_info; struct udp_tunnel_nic *udp_tunnel_nic; + + /* protected by rtnl_lock */ + struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE]; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -3817,8 +3831,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags); -u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op, - enum bpf_netdev_command cmd); +u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); int xdp_umem_query(struct net_device *dev, u16 queue_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); -- cgit v1.2.3 From aa8d3a716b59db6c1ad6c68fb8aa05e31980da60 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Jul 2020 23:45:57 -0700 Subject: bpf, xdp: Add bpf_link-based XDP attachment API Add bpf_link-based API (bpf_xdp_link) to attach BPF XDP program through BPF_LINK_CREATE command. bpf_xdp_link is mutually exclusive with direct BPF program attachment, previous BPF program should be detached prior to attempting to create a new bpf_xdp_link attachment (for a given XDP mode). Once BPF link is attached, it can't be replaced by other BPF program attachment or link attachment. It will be detached only when the last BPF link FD is closed. bpf_xdp_link will be auto-detached when net_device is shutdown, similarly to how other BPF links behave (cgroup, flow_dissector). At that point bpf_link will become defunct, but won't be destroyed until last FD is closed. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200722064603.3350758-5-andriin@fb.com --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cad44b40c776..7d3c412fcfe5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -888,6 +888,7 @@ struct bpf_prog_offload_ops; struct netlink_ext_ack; struct xdp_umem; struct xdp_dev_bulk_queue; +struct bpf_xdp_link; enum bpf_xdp_mode { XDP_MODE_SKB = 0, @@ -898,6 +899,7 @@ enum bpf_xdp_mode { struct bpf_xdp_entity { struct bpf_prog *prog; + struct bpf_xdp_link *link; }; struct netdev_bpf { @@ -3831,7 +3833,9 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags); +int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); + int xdp_umem_query(struct net_device *dev, u16 queue_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); -- cgit v1.2.3 From e8407fdeb9a6866784e249881f6c786a0835faba Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Jul 2020 23:46:02 -0700 Subject: bpf, xdp: Remove XDP_QUERY_PROG and XDP_QUERY_PROG_HW XDP commands Now that BPF program/link management is centralized in generic net_device code, kernel code never queries program id from drivers, so XDP_QUERY_PROG/XDP_QUERY_PROG_HW commands are unnecessary. This patch removes all the implementations of those commands in kernel, along the xdp_attachment_query(). This patch was compile-tested on allyesconfig. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200722064603.3350758-10-andriin@fb.com --- include/linux/netdevice.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7d3c412fcfe5..1046763cd0dc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -876,8 +876,6 @@ enum bpf_netdev_command { */ XDP_SETUP_PROG, XDP_SETUP_PROG_HW, - XDP_QUERY_PROG, - XDP_QUERY_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, @@ -911,12 +909,6 @@ struct netdev_bpf { struct bpf_prog *prog; struct netlink_ext_ack *extack; }; - /* XDP_QUERY_PROG, XDP_QUERY_PROG_HW */ - struct { - u32 prog_id; - /* flags with which program was installed */ - u32 prog_flags; - }; /* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */ struct { struct bpf_offloaded_map *offmap; -- cgit v1.2.3 From 3135f5b73592988af0eb1b11ccbb72a8667be201 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 26 Jul 2020 18:14:43 +0200 Subject: entry: Correct __secure_computing() stub The original version of that used secure_computing() which has no arguments. Review requested to switch to __secure_computing() which has one. The function name was correct, but no argument added and of course compiling without SECCOMP was deemed overrated. Add the missing function argument. Fixes: 6823ecabf030 ("seccomp: Provide stub for __secure_computing()") Reported-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/seccomp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 03d28c32ad01..51f234b6d28f 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -58,10 +58,11 @@ static inline int seccomp_mode(struct seccomp *s) struct seccomp { }; struct seccomp_filter { }; +struct seccomp_data; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER static inline int secure_computing(void) { return 0; } -static inline int __secure_computing(void) { return 0; } +static inline int __secure_computing(const struct seccomp_data *sd) { return 0; } #else static inline void secure_computing_strict(int this_syscall) { return; } #endif -- cgit v1.2.3 From ab92ffd5f6ac3ebd4a7650ef906702ab86127b45 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 18:30:01 -0700 Subject: power: fix duplicated words in bq2415x_charger.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drop the doubled word "for". Change "It it" to "If it". Signed-off-by: Randy Dunlap Cc: linux-pm@vger.kernel.org Acked-by: Pali Rohár Signed-off-by: Sebastian Reichel --- include/linux/power/bq2415x_charger.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/power/bq2415x_charger.h b/include/linux/power/bq2415x_charger.h index 4ca08321e251..f3c267f2a467 100644 --- a/include/linux/power/bq2415x_charger.h +++ b/include/linux/power/bq2415x_charger.h @@ -14,8 +14,8 @@ * value is -1 then default chip value (specified in datasheet) will be * used. * - * Value resistor_sense is needed for for configuring charge and - * termination current. It it is less or equal to zero, configuring charge + * Value resistor_sense is needed for configuring charge and + * termination current. If it is less or equal to zero, configuring charge * and termination current will not be possible. * * For automode support is needed to provide name of power supply device -- cgit v1.2.3 From a070bdbbb06d7787ec7844a4f1e059cf8b55205d Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Sun, 26 Jul 2020 01:23:37 +0200 Subject: gpio: regmap: fix type clash GPIO_REGMAP_ADDR_ZERO() cast to unsigned long but the actual config parameters are unsigned int. We use unsigned int here because that is the type which is used by the underlying regmap. Fixes: ebe363197e52 ("gpio: add a reusable generic gpio_chip using regmap") Reported-by: kernel test robot Signed-off-by: Michael Walle Link: https://lore.kernel.org/r/20200725232337.27581-1-michael@walle.cc Signed-off-by: Linus Walleij --- include/linux/gpio/regmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/regmap.h b/include/linux/gpio/regmap.h index 4c1e6b34e824..ad76f3d0a6ba 100644 --- a/include/linux/gpio/regmap.h +++ b/include/linux/gpio/regmap.h @@ -8,7 +8,7 @@ struct gpio_regmap; struct irq_domain; struct regmap; -#define GPIO_REGMAP_ADDR_ZERO ((unsigned long)(-1)) +#define GPIO_REGMAP_ADDR_ZERO ((unsigned int)(-1)) #define GPIO_REGMAP_ADDR(addr) ((addr) ? : GPIO_REGMAP_ADDR_ZERO) /** -- cgit v1.2.3 From 6d4c4479f80141a2a24ac798a86942b1225206df Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Tue, 30 Jun 2020 21:41:26 +0800 Subject: irqchip/gic-v3: Remove unused register definition [maz: The GICv3 spec has evolved quite a bit since the draft the Linux driver was written against, and some register definitions are simply gone] As per the GICv3 specification, GIC{D,R}_SEIR are not assigned and the locations (0x0068) are actually Reserved. GICR_MOV{LPI,ALL}R are two IMP DEF registers and might be defined by some specific micro-architecture. As they're not used anywhere in the kernel, just drop all of them. Signed-off-by: Zenghui Yu [maz: added context explaination] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20200630134126.880-1-yuzenghui@huawei.com --- include/linux/irqchip/arm-gic-v3.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 6c36b6cc3edf..f6d092fdb93d 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -19,7 +19,6 @@ #define GICD_CLRSPI_NSR 0x0048 #define GICD_SETSPI_SR 0x0050 #define GICD_CLRSPI_SR 0x0058 -#define GICD_SEIR 0x0068 #define GICD_IGROUPR 0x0080 #define GICD_ISENABLER 0x0100 #define GICD_ICENABLER 0x0180 @@ -119,14 +118,11 @@ #define GICR_WAKER 0x0014 #define GICR_SETLPIR 0x0040 #define GICR_CLRLPIR 0x0048 -#define GICR_SEIR GICD_SEIR #define GICR_PROPBASER 0x0070 #define GICR_PENDBASER 0x0078 #define GICR_INVLPIR 0x00A0 #define GICR_INVALLR 0x00B0 #define GICR_SYNCR 0x00C0 -#define GICR_MOVLPIR 0x0100 -#define GICR_MOVALLR 0x0110 #define GICR_IDREGS GICD_IDREGS #define GICR_PIDR2 GICD_PIDR2 -- cgit v1.2.3 From b7640d765dbbde794c49198c9851f6026fb6e43e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:28:53 -0700 Subject: irqchip: irq-bcm2836.h: drop a duplicated word Drop the repeated word "the" in a comment. Signed-off-by: Randy Dunlap Signed-off-by: Marc Zyngier Cc: Thomas Gleixner Cc: Jason Cooper Cc: Marc Zyngier Link: https://lore.kernel.org/r/20200719002853.20419-1-rdunlap@infradead.org --- include/linux/irqchip/irq-bcm2836.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/irq-bcm2836.h b/include/linux/irqchip/irq-bcm2836.h index f224d6f9e550..ac5719d8f56b 100644 --- a/include/linux/irqchip/irq-bcm2836.h +++ b/include/linux/irqchip/irq-bcm2836.h @@ -30,7 +30,7 @@ */ #define LOCAL_MAILBOX_INT_CONTROL0 0x050 /* - * The CPU's interrupt status register. Bits are defined by the the + * The CPU's interrupt status register. Bits are defined by the * LOCAL_IRQ_* bits below. */ #define LOCAL_IRQ_PENDING0 0x060 -- cgit v1.2.3 From f8410e626569324cfe831aaecc0504cafc12b471 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 17 Jul 2020 17:06:34 -0700 Subject: irqchip: Add IRQCHIP_PLATFORM_DRIVER_BEGIN/END and IRQCHIP_MATCH helper macros Compiling an irqchip driver as a platform driver needs to bunch of things to be done right: - Making sure the parent domain is initialized first - Making sure the device can't be unbound from sysfs - Disallowing module unload if it's built as a module - Finding the parent node - Etc. Instead of trying to make sure all future irqchip platform drivers get this right, provide boilerplate macros that take care of all of this. An example use would look something like this. Where acme_foo_init and acme_bar_init are similar to what would be passed to IRQCHIP_DECLARE. IRQCHIP_PLATFORM_DRIVER_BEGIN(acme_irq) IRQCHIP_MATCH("acme,foo", acme_foo_init) IRQCHIP_MATCH("acme,bar", acme_bar_init) IRQCHIP_PLATFORM_DRIVER_END(acme_irq) Signed-off-by: Saravana Kannan Signed-off-by: Marc Zyngier Cc: John Stultz Link: https://lore.kernel.org/r/20200718000637.3632841-2-saravanak@google.com --- include/linux/irqchip.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index 447f22880a69..8e754d8b8155 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -13,6 +13,7 @@ #include #include +#include /* * This macro must be used by the different irqchip drivers to declare @@ -26,6 +27,28 @@ */ #define IRQCHIP_DECLARE(name, compat, fn) OF_DECLARE_2(irqchip, name, compat, fn) +extern int platform_irqchip_probe(struct platform_device *pdev); + +#define IRQCHIP_PLATFORM_DRIVER_BEGIN(drv_name) \ +static const struct of_device_id drv_name##_irqchip_match_table[] = { + +#define IRQCHIP_MATCH(compat, fn) { .compatible = compat, .data = fn }, + +#define IRQCHIP_PLATFORM_DRIVER_END(drv_name) \ + {}, \ +}; \ +MODULE_DEVICE_TABLE(of, drv_name##_irqchip_match_table); \ +static struct platform_driver drv_name##_driver = { \ + .probe = platform_irqchip_probe, \ + .driver = { \ + .name = #drv_name, \ + .owner = THIS_MODULE, \ + .of_match_table = drv_name##_irqchip_match_table, \ + .suppress_bind_attrs = true, \ + }, \ +}; \ +builtin_platform_driver(drv_name##_driver) + /* * This macro must be used by the different irqchip drivers to declare * the association between their version and their initialization function. -- cgit v1.2.3 From 762a21fd45e056e9ccd2ef5787b4ee0c5af9bec8 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 26 Jul 2020 11:12:36 +0100 Subject: irqchip: Fix IRQCHIP_PLATFORM_DRIVER_* compilation by including module.h The newly introduced IRQCHIP_PLATFORM_DRIVER_* macros expand into module-related macros, but do so without including module.h. Depending on the driver and/or architecture, this happens to work, or not. Unconditionnaly include linux/module.h to sort it out. Fixes: f3b5e608ed6d ("irqchip: Add IRQCHIP_PLATFORM_DRIVER_BEGIN/END and IRQCHIP_MATCH helper macros") Reported-by: kernel test robot Cc: Saravana Kannan Signed-off-by: Marc Zyngier --- include/linux/irqchip.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index 8e754d8b8155..67351aac65ef 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -12,6 +12,7 @@ #define _LINUX_IRQCHIP_H #include +#include #include #include -- cgit v1.2.3 From b4a461e72bcb28a512bbdd29a4cb70aede2d68d3 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 21 Jul 2020 16:22:48 +1000 Subject: printk: Make linux/printk.h self-contained As it stands if you include printk.h by itself it will fail to compile because it requires definitions from ratelimit.h. However, simply including ratelimit.h from printk.h does not work due to inclusion loops involving sched.h and kernel.h. This patch solves this by moving bits from ratelimit.h into a new header file which can then be included by printk.h without any worries about header loops. The build bot then revealed some intriguing failures arising out of this patch. On s390 there is an inclusion loop with asm/bug.h and linux/kernel.h that triggers a compile failure, because kernel.h will cause asm-generic/bug.h to be included before s390's own asm/bug.h has finished processing. This has been fixed by not including kernel.h in arch/s390/include/asm/bug.h. Signed-off-by: Herbert Xu Reviewed-by: Andy Shevchenko Reviewed-by: Sergey Senozhatsky Acked-by: Petr Mladek Acked-by: Steven Rostedt (VMware) Signed-off-by: Sergey Senozhatsky Link: https://lore.kernel.org/r/20200721062248.GA18383@gondor.apana.org.au --- include/linux/printk.h | 1 + include/linux/ratelimit.h | 36 +--------------------------------- include/linux/ratelimit_types.h | 43 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 45 insertions(+), 35 deletions(-) create mode 100644 include/linux/ratelimit_types.h (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index fc8f03c54543..34c1a7be3e01 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -7,6 +7,7 @@ #include #include #include +#include extern const char linux_banner[]; extern const char linux_proc_banner[]; diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h index 8ddf79e9207a..b17e0cd0a30c 100644 --- a/include/linux/ratelimit.h +++ b/include/linux/ratelimit.h @@ -2,41 +2,10 @@ #ifndef _LINUX_RATELIMIT_H #define _LINUX_RATELIMIT_H -#include +#include #include #include -#define DEFAULT_RATELIMIT_INTERVAL (5 * HZ) -#define DEFAULT_RATELIMIT_BURST 10 - -/* issue num suppressed message on exit */ -#define RATELIMIT_MSG_ON_RELEASE BIT(0) - -struct ratelimit_state { - raw_spinlock_t lock; /* protect the state */ - - int interval; - int burst; - int printed; - int missed; - unsigned long begin; - unsigned long flags; -}; - -#define RATELIMIT_STATE_INIT(name, interval_init, burst_init) { \ - .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ - .interval = interval_init, \ - .burst = burst_init, \ - } - -#define RATELIMIT_STATE_INIT_DISABLED \ - RATELIMIT_STATE_INIT(ratelimit_state, 0, DEFAULT_RATELIMIT_BURST) - -#define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init) \ - \ - struct ratelimit_state name = \ - RATELIMIT_STATE_INIT(name, interval_init, burst_init) \ - static inline void ratelimit_state_init(struct ratelimit_state *rs, int interval, int burst) { @@ -73,9 +42,6 @@ ratelimit_set_flags(struct ratelimit_state *rs, unsigned long flags) extern struct ratelimit_state printk_ratelimit_state; -extern int ___ratelimit(struct ratelimit_state *rs, const char *func); -#define __ratelimit(state) ___ratelimit(state, __func__) - #ifdef CONFIG_PRINTK #define WARN_ON_RATELIMIT(condition, state) ({ \ diff --git a/include/linux/ratelimit_types.h b/include/linux/ratelimit_types.h new file mode 100644 index 000000000000..b676aa419eef --- /dev/null +++ b/include/linux/ratelimit_types.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_RATELIMIT_TYPES_H +#define _LINUX_RATELIMIT_TYPES_H + +#include +#include +#include + +#define DEFAULT_RATELIMIT_INTERVAL (5 * HZ) +#define DEFAULT_RATELIMIT_BURST 10 + +/* issue num suppressed message on exit */ +#define RATELIMIT_MSG_ON_RELEASE BIT(0) + +struct ratelimit_state { + raw_spinlock_t lock; /* protect the state */ + + int interval; + int burst; + int printed; + int missed; + unsigned long begin; + unsigned long flags; +}; + +#define RATELIMIT_STATE_INIT(name, interval_init, burst_init) { \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ + .interval = interval_init, \ + .burst = burst_init, \ + } + +#define RATELIMIT_STATE_INIT_DISABLED \ + RATELIMIT_STATE_INIT(ratelimit_state, 0, DEFAULT_RATELIMIT_BURST) + +#define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init) \ + \ + struct ratelimit_state name = \ + RATELIMIT_STATE_INIT(name, interval_init, burst_init) \ + +extern int ___ratelimit(struct ratelimit_state *rs, const char *func); +#define __ratelimit(state) ___ratelimit(state, __func__) + +#endif /* _LINUX_RATELIMIT_TYPES_H */ -- cgit v1.2.3 From d97758e048e5fe91c7d8ff9ce5f030ee88d92161 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Thu, 23 Jul 2020 03:58:41 +0300 Subject: dmaengine: Introduce min burst length capability Some hardware aside from default 0/1 may have greater minimum burst transactions length constraints. Here we introduce the DMA device and slave capability, which if required can be initialized by the DMA engine driver with the device-specific value. Signed-off-by: Serge Semin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200723005848.31907-4-Sergey.Semin@baikalelectronics.ru Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 883e1e087de5..7d6e2aa26980 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -467,6 +467,7 @@ enum dma_residue_granularity { * Since the enum dma_transfer_direction is not defined as bit flag for * each type, the dma controller should set BIT() and same * should be checked by controller as well + * @min_burst: min burst capability per-transfer * @max_burst: max burst capability per-transfer * @cmd_pause: true, if pause is supported (i.e. for reading residue or * for resume later) @@ -480,6 +481,7 @@ struct dma_slave_caps { u32 src_addr_widths; u32 dst_addr_widths; u32 directions; + u32 min_burst; u32 max_burst; bool cmd_pause; bool cmd_resume; @@ -771,6 +773,7 @@ struct dma_filter { * Since the enum dma_transfer_direction is not defined as bit flag for * each type, the dma controller should set BIT() and same * should be checked by controller as well + * @min_burst: min burst capability per-transfer * @max_burst: max burst capability per-transfer * @residue_granularity: granularity of the transfer residue reported * by tx_status @@ -841,6 +844,7 @@ struct dma_device { u32 src_addr_widths; u32 dst_addr_widths; u32 directions; + u32 min_burst; u32 max_burst; bool descriptor_reuse; enum dma_residue_granularity residue_granularity; -- cgit v1.2.3 From b1b40b8fe7e8fb26e33bad1766ce322d2c63a6c7 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Thu, 23 Jul 2020 03:58:42 +0300 Subject: dmaengine: Introduce max SG burst capability Some devices may lack the support of the hardware accelerated SG list entries automatic walking through and execution. In this case a burden of the SG list traversal and DMA engine re-initialization lies on the DMA engine driver (normally implemented by using a DMA transfer completion IRQ to recharge the DMA device with a next SG list entry). But such solution may not be suitable for some DMA consumers. In particular SPI devices need both Tx and Rx DMA channels work synchronously in order to avoid the Rx FIFO overflow. In case if Rx DMA channel is paused for some time while the Tx DMA channel works implicitly pulling data into the Rx FIFO, the later will be eventually overflown, which will cause the data loss. So if SG list entries aren't automatically fetched by the DMA engine, but are one-by-one manually selected for execution in the ISRs/deferred work/etc., such problem will eventually happen due to the non-deterministic latencies of the service execution. In order to let the DMA consumer know about the DMA device capabilities regarding the hardware accelerated SG list traversal we introduce the max_sg_burst capability. It is supposed to be initialized by the DMA engine driver with 0 if there is no limitation of the number of SG entries atomically executed and with non-zero value if there is such constraints, so the upper limit is determined by the number set to the property. Suggested-by: Andy Shevchenko Signed-off-by: Serge Semin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200723005848.31907-5-Sergey.Semin@baikalelectronics.ru Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 7d6e2aa26980..4cbe09e66db2 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -469,6 +469,9 @@ enum dma_residue_granularity { * should be checked by controller as well * @min_burst: min burst capability per-transfer * @max_burst: max burst capability per-transfer + * @max_sg_burst: max number of SG list entries executed in a single burst + * DMA tansaction with no software intervention for reinitialization. + * Zero value means unlimited number of entries. * @cmd_pause: true, if pause is supported (i.e. for reading residue or * for resume later) * @cmd_resume: true, if resume is supported @@ -483,6 +486,7 @@ struct dma_slave_caps { u32 directions; u32 min_burst; u32 max_burst; + u32 max_sg_burst; bool cmd_pause; bool cmd_resume; bool cmd_terminate; @@ -775,6 +779,9 @@ struct dma_filter { * should be checked by controller as well * @min_burst: min burst capability per-transfer * @max_burst: max burst capability per-transfer + * @max_sg_burst: max number of SG list entries executed in a single burst + * DMA tansaction with no software intervention for reinitialization. + * Zero value means unlimited number of entries. * @residue_granularity: granularity of the transfer residue reported * by tx_status * @device_alloc_chan_resources: allocate resources and return the @@ -846,6 +853,7 @@ struct dma_device { u32 directions; u32 min_burst; u32 max_burst; + u32 max_sg_burst; bool descriptor_reuse; enum dma_residue_granularity residue_granularity; -- cgit v1.2.3 From 3b6d694eb3eebd86ec44a119e730943ac8e03a6b Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Thu, 23 Jul 2020 03:58:43 +0300 Subject: dmaengine: Introduce DMA-device device_caps callback There are DMA devices (like ours version of Synopsys DW DMAC) which have DMA capabilities non-uniformly redistributed between the device channels. In order to provide a way of exposing the channel-specific parameters to the DMA engine consumers, we introduce a new DMA-device callback. In case if provided it gets called from the dma_get_slave_caps() method and is able to override the generic DMA-device capabilities. Signed-off-by: Serge Semin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200723005848.31907-6-Sergey.Semin@baikalelectronics.ru Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 4cbe09e66db2..d718671bfd25 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -801,6 +801,8 @@ struct dma_filter { * be called after period_len bytes have been transferred. * @device_prep_interleaved_dma: Transfer expression in a generic way. * @device_prep_dma_imm_data: DMA's 8 byte immediate data to the dst address + * @device_caps: May be used to override the generic DMA slave capabilities + * with per-channel specific ones * @device_config: Pushes a new configuration to a channel, return 0 or an error * code * @device_pause: Pauses any transfer happening on a channel. Returns @@ -901,6 +903,8 @@ struct dma_device { struct dma_chan *chan, dma_addr_t dst, u64 data, unsigned long flags); + void (*device_caps)(struct dma_chan *chan, + struct dma_slave_caps *caps); int (*device_config)(struct dma_chan *chan, struct dma_slave_config *config); int (*device_pause)(struct dma_chan *chan); -- cgit v1.2.3 From 585d35451e94b2e1b0bf59ef55d3b4a1c8ab3d77 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Thu, 23 Jul 2020 03:58:46 +0300 Subject: dmaengine: dw: Initialize min and max burst DMA device capability According to the DW APB DMAC data book the minimum burst transaction length is 1 and it's true for any version of the controller since isn't parametrised in the coreAssembler so can't be changed at the IP-core synthesis stage. The maximum burst transaction can vary from channel to channel and from controller to controller depending on a IP-core parameter the system engineer activated during the IP-core synthesis. Let's initialise both min_burst and max_burst members of the DMA controller descriptor with extreme values so the DMA clients could use them to properly optimize the DMA requests. The channels and controller-specific max_burst length initialization will be introduced by the follow-up patches. Signed-off-by: Serge Semin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200723005848.31907-9-Sergey.Semin@baikalelectronics.ru Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-dw.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index f3eaf9ec00a1..369e41e9dcc9 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -12,6 +12,8 @@ #define DW_DMA_MAX_NR_MASTERS 4 #define DW_DMA_MAX_NR_CHANNELS 8 +#define DW_DMA_MIN_BURST 1 +#define DW_DMA_MAX_BURST 256 /** * struct dw_dma_slave - Controller-specific information about a slave -- cgit v1.2.3 From ca7f2851712e7072e8f327882dc4bdaaae3a8079 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Thu, 23 Jul 2020 03:58:47 +0300 Subject: dmaengine: dw: Introduce max burst length hw config IP core of the DW DMA controller may be synthesized with different max burst length of the transfers per each channel. According to Synopsis having the fixed maximum burst transactions length may provide some performance gain. At the same time setting up the source and destination multi size exceeding the max burst length limitation may cause a serious problems. In our case the DMA transaction just hangs up. In order to fix this lets introduce the max burst length platform config of the DW DMA controller device and don't let the DMA channels configuration code exceed the burst length hardware limitation. Note the maximum burst length parameter can be detected either in runtime from the DWC parameter registers or from the dedicated DT property. Depending on the IP core configuration the maximum value can vary from channel to channel so by overriding the channel slave max_burst capability we make sure a DMA consumer will get the channel-specific max burst length. Signed-off-by: Serge Semin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200723005848.31907-10-Sergey.Semin@baikalelectronics.ru Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-dw.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index 369e41e9dcc9..4f681df85c27 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -44,6 +44,8 @@ struct dw_dma_slave { * @data_width: Maximum data width supported by hardware per AHB master * (in bytes, power of 2) * @multi_block: Multi block transfers supported by hardware per channel. + * @max_burst: Maximum value of burst transaction size supported by hardware + * per channel (in units of CTL.SRC_TR_WIDTH/CTL.DST_TR_WIDTH). * @protctl: Protection control signals setting per channel. */ struct dw_dma_platform_data { @@ -58,6 +60,7 @@ struct dw_dma_platform_data { unsigned char nr_masters; unsigned char data_width[DW_DMA_MAX_NR_MASTERS]; unsigned char multi_block[DW_DMA_MAX_NR_CHANNELS]; + u32 max_burst[DW_DMA_MAX_NR_CHANNELS]; #define CHAN_PROTCTL_PRIVILEGED BIT(0) #define CHAN_PROTCTL_BUFFERABLE BIT(1) #define CHAN_PROTCTL_CACHEABLE BIT(2) -- cgit v1.2.3 From 6bd0dffa1a6e19e73964ae47c964f57c625cce05 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 21 Jul 2020 16:08:44 +0300 Subject: dmaengine: dw: Don't include unneeded header to platform data header Including device.h is too much for the dma-dw.h platform data header. Replace it with the headers of which dma-dw.h is direct user. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200721130844.64162-1-andriy.shevchenko@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-dw.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index 4f681df85c27..fbbeb2f6189b 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -8,13 +8,16 @@ #ifndef _PLATFORM_DATA_DMA_DW_H #define _PLATFORM_DATA_DMA_DW_H -#include +#include +#include #define DW_DMA_MAX_NR_MASTERS 4 #define DW_DMA_MAX_NR_CHANNELS 8 #define DW_DMA_MIN_BURST 1 #define DW_DMA_MAX_BURST 256 +struct device; + /** * struct dw_dma_slave - Controller-specific information about a slave * -- cgit v1.2.3 From 280c7f95f858b103e62d84cae2d5ed9f5cf54d41 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 27 Jul 2020 12:14:28 +0200 Subject: Revert "test_firmware: Test platform fw loading on non-EFI systems" This reverts commit 2d38dbf89a06d0f689daec9842c5d3295c49777f as it broke the build in linux-next Reported-by: Stephen Rothwell Fixes: 2d38dbf89a06 ("test_firmware: Test platform fw loading on non-EFI systems") Cc: stable@vger.kernel.org Cc: Scott Branden Cc: Kees Cook Link: https://lore.kernel.org/r/20200727165539.0e8797ab@canb.auug.org.au Signed-off-by: Greg Kroah-Hartman --- include/linux/efi_embedded_fw.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h index 4ad5db9f5312..57eac5241303 100644 --- a/include/linux/efi_embedded_fw.h +++ b/include/linux/efi_embedded_fw.h @@ -7,6 +7,19 @@ #define EFI_EMBEDDED_FW_PREFIX_LEN 8 +/* + * This struct and efi_embedded_fw_list are private to the efi-embedded fw + * implementation they are in this header for use by lib/test_firmware.c only! + */ +struct efi_embedded_fw { + struct list_head list; + const char *name; + const u8 *data; + size_t length; +}; + +extern struct list_head efi_embedded_fw_list; + /** * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw * code to search for embedded firmwares. -- cgit v1.2.3 From 7a82e97a11b91a78e9da06ab3f70545953c07b5c Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Thu, 16 Jul 2020 14:42:48 +0200 Subject: PM: core: introduce pm_ptr() macro This macro is analogous to the infamous of_match_ptr(). If CONFIG_PM is enabled, this macro will resolve to its argument, otherwise to NULL. Signed-off-by: Paul Cercueil Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 121c104a4090..1f227c518db3 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -374,6 +374,12 @@ const struct dev_pm_ops name = { \ SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } +#ifdef CONFIG_PM +#define pm_ptr(_ptr) (_ptr) +#else +#define pm_ptr(_ptr) NULL +#endif + /* * PM_EVENT_ messages * -- cgit v1.2.3 From 756a64ce349cf2646c60456b110f7f1756bb8699 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Thu, 16 Jul 2020 14:42:49 +0200 Subject: PM: Make *_DEV_PM_OPS macros use __maybe_unused This way, when the dev_pm_ops instance is not referenced anywhere, it will simply be dropped by the compiler without a warning. Signed-off-by: Paul Cercueil Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 1f227c518db3..a30a4b54df52 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -351,7 +351,7 @@ struct dev_pm_ops { * to RAM and hibernation. */ #define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ -const struct dev_pm_ops name = { \ +const struct dev_pm_ops __maybe_unused name = { \ SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ } @@ -369,7 +369,7 @@ const struct dev_pm_ops name = { \ * .runtime_resume(), respectively (and analogously for hibernation). */ #define UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ -const struct dev_pm_ops name = { \ +const struct dev_pm_ops __maybe_unused name = { \ SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } -- cgit v1.2.3 From 0585c1c06a550c2a606c33ad45954892245512f6 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Mon, 27 Jul 2020 17:29:38 +0800 Subject: ACPI: Use valid link to the ACPI specification Currently, acpi.info is an invalid link to access ACPI specification, the new valid link is https://uefi.org/specifications. Signed-off-by: Tiezhu Yang Signed-off-by: Rafael J. Wysocki --- include/linux/tboot.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tboot.h b/include/linux/tboot.h index c7e424766360..5146d2574e85 100644 --- a/include/linux/tboot.h +++ b/include/linux/tboot.h @@ -44,7 +44,7 @@ struct tboot_acpi_generic_address { /* * combines Sx info from FADT and FACS tables per ACPI 2.0+ spec - * (http://www.acpi.info/) + * (https://uefi.org/specifications) */ struct tboot_acpi_sleep_info { struct tboot_acpi_generic_address pm1a_cnt_blk; -- cgit v1.2.3 From 8365a898fe53f85529566501d3b3d88640b3975e Mon Sep 17 00:00:00 2001 From: Sumeet Pawnikar Date: Thu, 16 Jul 2020 23:14:55 +0530 Subject: powercap: Add Power Limit4 support Modern Intel Mobile platforms support power limit4 (PL4), which is the SoC package level maximum power limit (in Watts). It can be used to preemptively limits potential SoC power to prevent power spikes from tripping the power adapter and battery over-current protection. This patch enables this feature by exposing package level peak power capping control to userspace via RAPL sysfs interface. With this, application like DTPF can modify PL4 power limit, the similar way of other package power limit (PL1). As this feature is not tested on previous generations, here it is enabled only for the platform that has been verified to work, for safety concerns. Signed-off-by: Sumeet Pawnikar Co-developed-by: Zhang Rui Signed-off-by: Zhang Rui Reviewed-by: Srinivas Pandruvada Tested-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki --- include/linux/intel_rapl.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index efb3ce892c20..3582176a1eca 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -29,6 +29,7 @@ enum rapl_domain_reg_id { RAPL_DOMAIN_REG_PERF, RAPL_DOMAIN_REG_POLICY, RAPL_DOMAIN_REG_INFO, + RAPL_DOMAIN_REG_PL4, RAPL_DOMAIN_REG_MAX, }; @@ -38,12 +39,14 @@ enum rapl_primitives { ENERGY_COUNTER, POWER_LIMIT1, POWER_LIMIT2, + POWER_LIMIT4, FW_LOCK, PL1_ENABLE, /* power limit 1, aka long term */ PL1_CLAMP, /* allow frequency to go below OS request */ PL2_ENABLE, /* power limit 2, aka short term, instantaneous */ PL2_CLAMP, + PL4_ENABLE, /* power limit 4, aka max peak power */ TIME_WINDOW1, /* long term */ TIME_WINDOW2, /* short term */ @@ -65,7 +68,7 @@ struct rapl_domain_data { unsigned long timestamp; }; -#define NR_POWER_LIMITS (2) +#define NR_POWER_LIMITS (3) struct rapl_power_limit { struct powercap_zone_constraint *constraint; int prim_id; /* primitive ID used to enable */ -- cgit v1.2.3 From a233547660a3915973d41e2a9a0923d0cf317a62 Mon Sep 17 00:00:00 2001 From: Pi-Hsun Shih Date: Fri, 24 Jul 2020 16:03:55 +0800 Subject: platform/chrome: cros_ec: Fix host command for regulator control. Since the host command number 0x012B conflicts with other EC host command, add one to all regulator control related host command. Also fix a wrong alignment on struct and sync the comment with the one in ChromeOS EC codebase. Fixes: dff08caf35ec ("platform/chrome: cros_ec: Add command for regulator control.") Signed-off-by: Pi-Hsun Shih Acked-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20200724080358.619245-1-pihsun@chromium.org Signed-off-by: Mark Brown --- include/linux/platform_data/cros_ec_commands.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index a417b51b5764..91e77f53414d 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -5438,7 +5438,7 @@ struct ec_response_rollback_info { * * Returns the regulator name and supported voltage list in mV. */ -#define EC_CMD_REGULATOR_GET_INFO 0x012B +#define EC_CMD_REGULATOR_GET_INFO 0x012C /* Maximum length of regulator name */ #define EC_REGULATOR_NAME_MAX_LEN 16 @@ -5454,12 +5454,12 @@ struct ec_response_regulator_get_info { char name[EC_REGULATOR_NAME_MAX_LEN]; uint16_t num_voltages; uint16_t voltages_mv[EC_REGULATOR_VOLTAGE_MAX_COUNT]; -} __ec_align1; +} __ec_align2; /* * Configure the regulator as enabled / disabled. */ -#define EC_CMD_REGULATOR_ENABLE 0x012C +#define EC_CMD_REGULATOR_ENABLE 0x012D struct ec_params_regulator_enable { uint32_t index; @@ -5471,7 +5471,7 @@ struct ec_params_regulator_enable { * * Returns 1 if the regulator is enabled, 0 if not. */ -#define EC_CMD_REGULATOR_IS_ENABLED 0x012D +#define EC_CMD_REGULATOR_IS_ENABLED 0x012E struct ec_params_regulator_is_enabled { uint32_t index; @@ -5489,7 +5489,7 @@ struct ec_response_regulator_is_enabled { * Also note that this might be called before the regulator is enabled, and the * setting should be in effect after the regulator is enabled. */ -#define EC_CMD_REGULATOR_SET_VOLTAGE 0x012E +#define EC_CMD_REGULATOR_SET_VOLTAGE 0x012F struct ec_params_regulator_set_voltage { uint32_t index; @@ -5500,9 +5500,10 @@ struct ec_params_regulator_set_voltage { /* * Get the currently configured voltage for the voltage regulator. * - * Note that this might be called before the regulator is enabled. + * Note that this might be called before the regulator is enabled, and this + * should return the configured output voltage if the regulator is enabled. */ -#define EC_CMD_REGULATOR_GET_VOLTAGE 0x012F +#define EC_CMD_REGULATOR_GET_VOLTAGE 0x0130 struct ec_params_regulator_get_voltage { uint32_t index; -- cgit v1.2.3 From cfd97f94d036bf36122fa19d075c5741347aa178 Mon Sep 17 00:00:00 2001 From: Colton Lewis Date: Sat, 25 Jul 2020 05:02:57 +0000 Subject: spi: correct kernel-doc inconsistency Silence documentation build warnings by correcting kernel-doc comment for spi_transfer struct. Signed-off-by: Colton Lewis Link: https://lore.kernel.org/r/20200725050242.279548-1-colton.w.lewis@protonmail.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index f8b721fcd5c6..99380c0825db 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -329,6 +329,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * every chipselect is connected to a slave. * @dma_alignment: SPI controller constraint on DMA buffers alignment. * @mode_bits: flags understood by this controller driver + * @buswidth_override_bits: flags to override for this controller driver * @bits_per_word_mask: A mask indicating which values of bits_per_word are * supported by the driver. Bit n indicates that a bits_per_word n+1 is * supported. If set, the SPI core will reject any transfer with an @@ -846,12 +847,7 @@ extern void spi_res_release(struct spi_controller *ctlr, * processed the word, i.e. the "pre" timestamp should be taken before * transmitting the "pre" word, and the "post" timestamp after receiving * transmit confirmation from the controller for the "post" word. - * @timestamped_pre: Set by the SPI controller driver to denote it has acted - * upon the @ptp_sts request. Not set when the SPI core has taken care of - * the task. SPI device drivers are free to print a warning if this comes - * back unset and they need the better resolution. - * @timestamped_post: See above. The reason why both exist is that these - * booleans are also used to keep state in the core SPI logic. + * @timestamped: true if the transfer has been timestamped * @error: Error status logged by spi controller driver. * * SPI transfers always write the same number of bytes as they read. -- cgit v1.2.3 From 2224635938814fc63004e30f7c41943812bd6f1c Mon Sep 17 00:00:00 2001 From: Meir Lichtinger Date: Thu, 16 Jul 2020 13:52:47 +0300 Subject: RDMA/mlx5: Use MLX5_SET macro instead of local structure Use generic mlx5 structure defined in mlx5_ifc.h to represent ConnectX device data structures instead of using structure defined specifically for mlx5_ib module. Link: https://lore.kernel.org/r/20200716105248.1423452-3-leon@kernel.org Signed-off-by: Meir Lichtinger Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/device.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 2aacf9a8ee4d..d184b579617f 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1007,7 +1007,6 @@ enum { MLX5_MKEY_REMOTE_INVAL = 1 << 24, MLX5_MKEY_FLAG_SYNC_UMR = 1 << 29, MLX5_MKEY_BSF_EN = 1 << 30, - MLX5_MKEY_LEN64 = 1 << 31, }; struct mlx5_mkey_seg { -- cgit v1.2.3 From 896ec9735336f5adb576d372ed7e411bce2fc74c Mon Sep 17 00:00:00 2001 From: Meir Lichtinger Date: Thu, 16 Jul 2020 13:52:48 +0300 Subject: RDMA/mlx5: Set mkey relaxed ordering by UMR with ConnectX-7 Up to ConnectX-7 UMR is not used when user passes relaxed ordering access flag. ConnectX-7 supports setting relaxed ordering read/write mkey attribute by UMR, indicated by new HCA capabilities. With ConnectX-7 driver uses UMR when user set relaxed ordering access flag, in contrast to previous silicon models. Specifically it includes setting relvant flags of mkey context mask in UMR control segment, and relaxed ordering write and read flags in UMR mkey context segment. Link: https://lore.kernel.org/r/20200716105248.1423452-4-leon@kernel.org Signed-off-by: Meir Lichtinger Reviewed-by: Michael Guralnik Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/device.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index d184b579617f..4d3376e20f5e 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -276,7 +276,9 @@ enum { MLX5_MKEY_MASK_RW = 1ull << 20, MLX5_MKEY_MASK_A = 1ull << 21, MLX5_MKEY_MASK_SMALL_FENCE = 1ull << 23, - MLX5_MKEY_MASK_FREE = 1ull << 29, + MLX5_MKEY_MASK_RELAXED_ORDERING_WRITE = 1ull << 25, + MLX5_MKEY_MASK_FREE = 1ull << 29, + MLX5_MKEY_MASK_RELAXED_ORDERING_READ = 1ull << 47, }; enum { -- cgit v1.2.3 From f0c7baca180046824e07fc5f1326e83a8fd150c7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 24 Jul 2020 22:44:41 +0200 Subject: genirq/affinity: Make affinity setting if activated opt-in John reported that on a RK3288 system the perf per CPU interrupts are all affine to CPU0 and provided the analysis: "It looks like what happens is that because the interrupts are not per-CPU in the hardware, armpmu_request_irq() calls irq_force_affinity() while the interrupt is deactivated and then request_irq() with IRQF_PERCPU | IRQF_NOBALANCING. Now when irq_startup() runs with IRQ_STARTUP_NORMAL, it calls irq_setup_affinity() which returns early because IRQF_PERCPU and IRQF_NOBALANCING are set, leaving the interrupt on its original CPU." This was broken by the recent commit which blocked interrupt affinity setting in hardware before activation of the interrupt. While this works in general, it does not work for this particular case. As contrary to the initial analysis not all interrupt chip drivers implement an activate callback, the safe cure is to make the deferred interrupt affinity setting at activation time opt-in. Implement the necessary core logic and make the two irqchip implementations for which this is required opt-in. In hindsight this would have been the right thing to do, but ... Fixes: baedb87d1b53 ("genirq/affinity: Handle affinity setting on inactive interrupts correctly") Reported-by: John Keeping Signed-off-by: Thomas Gleixner Tested-by: Marc Zyngier Acked-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/87blk4tzgm.fsf@nanos.tec.linutronix.de --- include/linux/irq.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 8d5bc2c237d7..1b7f4dfee35b 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -213,6 +213,8 @@ struct irq_data { * required * IRQD_HANDLE_ENFORCE_IRQCTX - Enforce that handle_irq_*() is only invoked * from actual interrupt context. + * IRQD_AFFINITY_ON_ACTIVATE - Affinity is set on activation. Don't call + * irq_chip::irq_set_affinity() when deactivated. */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -237,6 +239,7 @@ enum { IRQD_CAN_RESERVE = (1 << 26), IRQD_MSI_NOMASK_QUIRK = (1 << 27), IRQD_HANDLE_ENFORCE_IRQCTX = (1 << 28), + IRQD_AFFINITY_ON_ACTIVATE = (1 << 29), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -421,6 +424,16 @@ static inline bool irqd_msi_nomask_quirk(struct irq_data *d) return __irqd_to_state(d) & IRQD_MSI_NOMASK_QUIRK; } +static inline void irqd_set_affinity_on_activate(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_AFFINITY_ON_ACTIVATE; +} + +static inline bool irqd_affinity_on_activate(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_AFFINITY_ON_ACTIVATE; +} + #undef __irqd_to_state static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) -- cgit v1.2.3 From 229f5879facf96e5640c0385f62b8cb5f27b8a43 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Wed, 22 Jul 2020 16:33:05 +0530 Subject: linux/kernel.h: Add PTR_ALIGN_DOWN macro Add a macro for aligning down a pointer. This is useful to get an aligned register address when a device allows only word access and doesn't allow half word or byte access. Link: https://lore.kernel.org/r/20200722110317.4744-4-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Acked-by: Rob Herring --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 82d91547d122..7339a00c895e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -34,6 +34,7 @@ #define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) #define __ALIGN_MASK(x, mask) __ALIGN_KERNEL_MASK((x), (mask)) #define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) +#define PTR_ALIGN_DOWN(p, a) ((typeof(p))ALIGN_DOWN((unsigned long)(p), (a))) #define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) /* generic data direction definitions */ -- cgit v1.2.3 From b54cecf5e2293d15620f7b3f8d1bf486243d5643 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sun, 7 Jun 2020 12:10:40 +0300 Subject: fsnotify: pass dir argument to handle_event() callback The 'inode' argument to handle_event(), sometimes referred to as 'to_tell' is somewhat obsolete. It is a remnant from the times when a group could only have an inode mark associated with an event. We now pass an iter_info array to the callback, with all marks associated with an event. Most backends ignore this argument, with two exceptions: 1. dnotify uses it for sanity check that event is on directory 2. fanotify uses it to report fid of directory on directory entry modification events Remove the 'inode' argument and add a 'dir' argument. The callback function signature is deliberately changed, because the meaning of the argument has changed and the arguments have been documented. The 'dir' argument is set to when 'file_name' is specified and it is referring to the directory that the 'file_name' entry belongs to. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 97300f3b8ff0..0de130cbf72d 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -108,6 +108,17 @@ struct mem_cgroup; * these operations for each relevant group. * * handle_event - main call for a group to handle an fs event + * @group: group to notify + * @mask: event type and flags + * @data: object that event happened on + * @data_type: type of object for fanotify_data_XXX() accessors + * @dir: optional directory associated with event - + * if @file_name is not NULL, this is the directory that + * @file_name is relative to + * @file_name: optional file name associated with event + * @cookie: inotify rename cookie + * @iter_info: array of marks from this group that are interested in the event + * * free_group_priv - called when a group refcnt hits 0 to clean up the private union * freeing_mark - called when a mark is being destroyed for some reason. The group * MUST be holding a reference on each mark and that reference must be @@ -115,9 +126,8 @@ struct mem_cgroup; * userspace messages that marks have been removed. */ struct fsnotify_ops { - int (*handle_event)(struct fsnotify_group *group, - struct inode *inode, - u32 mask, const void *data, int data_type, + int (*handle_event)(struct fsnotify_group *group, u32 mask, + const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info); void (*free_group_priv)(struct fsnotify_group *group); -- cgit v1.2.3 From 8be23aec0ee151de731626d5578973fde25b2285 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 25 Jul 2020 16:07:36 +0200 Subject: i2c: also convert placeholder function to return errno All i2c_new_device-alike functions return ERR_PTR these days, but this fallback function was missed. Fixes: 2dea645ffc21 ("i2c: acpi: Return error pointers from i2c_acpi_new_device()") Signed-off-by: Wolfram Sang Reviewed-by: Andy Shevchenko [wsa: changed from 'ENOSYS' to 'ENODEV'] Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index ee328cf80bd9..4e7714c88f95 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -1001,7 +1001,7 @@ static inline u32 i2c_acpi_find_bus_speed(struct device *dev) static inline struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, struct i2c_board_info *info) { - return NULL; + return ERR_PTR(-ENODEV); } static inline struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle) { -- cgit v1.2.3 From b4e9c9549f62329d2412f899635fddc5212b9cd4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 1 Jun 2020 19:42:40 -0400 Subject: introduction of regset ->get() wrappers, switching ELF coredumps to those Two new helpers: given a process and regset, dump into a buffer. regset_get() takes a buffer and size, regset_get_alloc() takes size and allocates a buffer. Return value in both cases is the amount of data actually dumped in case of success or -E... on error. In both cases the size is capped by regset->n * regset->size, so ->get() is called with offset 0 and size no more than what regset expects. binfmt_elf.c callers of ->get() are switched to using those; the other caller (copy_regset_to_user()) will need some preparations to switch. Signed-off-by: Al Viro --- include/linux/regset.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h index 46d6ae68c455..968a032922d5 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -353,6 +353,15 @@ static inline int user_regset_copyin_ignore(unsigned int *pos, return 0; } +extern int regset_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int size, void *data); + +extern int regset_get_alloc(struct task_struct *target, + const struct user_regset *regset, + unsigned int size, + void **data); + /** * copy_regset_to_user - fetch a thread's user_regset data into user memory * @target: thread to be examined -- cgit v1.2.3 From 1e6b57d6421f0343dd11619612e5ff8930cddf38 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 11 Jun 2020 11:11:32 -0400 Subject: unexport linux/elfcore.h It's unusable from userland - it uses elf_gregset_t, which is not provided by exported headers. glibc has it in sys/procfs.h, but the same file defines struct elf_prstatus, so linux/elfcore.h can't be included once sys/procfs.h has been pulled. Same goes for uclibc and dietlibc simply doesn't have elf_gregset_t defined anywhere. IOW, no userland source is including that thing. Signed-off-by: Al Viro --- include/linux/elfcore.h | 69 ++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 66 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 4cad0e784b28..96ab215dad2d 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -5,12 +5,75 @@ #include #include #include - -#include -#include +#include +#include +#include +#include +#include +#include struct coredump_params; +struct elf_siginfo +{ + int si_signo; /* signal number */ + int si_code; /* extra code */ + int si_errno; /* errno */ +}; + +/* + * Definitions to generate Intel SVR4-like core files. + * These mostly have the same names as the SVR4 types with "elf_" + * tacked on the front to prevent clashes with linux definitions, + * and the typedef forms have been avoided. This is mostly like + * the SVR4 structure, but more Linuxy, with things that Linux does + * not support and which gdb doesn't really use excluded. + */ +struct elf_prstatus +{ + struct elf_siginfo pr_info; /* Info associated with signal */ + short pr_cursig; /* Current signal */ + unsigned long pr_sigpend; /* Set of pending signals */ + unsigned long pr_sighold; /* Set of held signals */ + pid_t pr_pid; + pid_t pr_ppid; + pid_t pr_pgrp; + pid_t pr_sid; + struct __kernel_old_timeval pr_utime; /* User time */ + struct __kernel_old_timeval pr_stime; /* System time */ + struct __kernel_old_timeval pr_cutime; /* Cumulative user time */ + struct __kernel_old_timeval pr_cstime; /* Cumulative system time */ + elf_gregset_t pr_reg; /* GP registers */ +#ifdef CONFIG_BINFMT_ELF_FDPIC + /* When using FDPIC, the loadmap addresses need to be communicated + * to GDB in order for GDB to do the necessary relocations. The + * fields (below) used to communicate this information are placed + * immediately after ``pr_reg'', so that the loadmap addresses may + * be viewed as part of the register set if so desired. + */ + unsigned long pr_exec_fdpic_loadmap; + unsigned long pr_interp_fdpic_loadmap; +#endif + int pr_fpvalid; /* True if math co-processor being used. */ +}; + +#define ELF_PRARGSZ (80) /* Number of chars for args */ + +struct elf_prpsinfo +{ + char pr_state; /* numeric process state */ + char pr_sname; /* char for pr_state */ + char pr_zomb; /* zombie */ + char pr_nice; /* nice val */ + unsigned long pr_flag; /* flags */ + __kernel_uid_t pr_uid; + __kernel_gid_t pr_gid; + pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; + /* Lots missing */ + char pr_fname[16]; /* filename of executable */ + char pr_psargs[ELF_PRARGSZ]; /* initial part of arg list */ +}; + static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *regs) { #ifdef ELF_CORE_COPY_REGS -- cgit v1.2.3 From 16aead81018ca404efe9bd928786824e7168151f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 14 Jun 2020 09:52:06 -0400 Subject: take fdpic-related parts of elf_prstatus out The only architecture where we might end up using both is arm, and there we definitely don't want fdpic-related fields in elf_prstatus - coredump layout of ELF binaries should not depend upon having the kernel built with the support of ELF_FDPIC ones. Just move the fdpic-modified variant into binfmt_elf_fdpic.c (and call it elf_prstatus_fdpic there) [name stolen from nico] Signed-off-by: Al Viro --- include/linux/elfcore-compat.h | 4 ---- include/linux/elfcore.h | 10 ---------- 2 files changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h index 7a37f4ce9fd2..10485f0c9740 100644 --- a/include/linux/elfcore-compat.h +++ b/include/linux/elfcore-compat.h @@ -32,10 +32,6 @@ struct compat_elf_prstatus struct old_timeval32 pr_cutime; struct old_timeval32 pr_cstime; compat_elf_gregset_t pr_reg; -#ifdef CONFIG_BINFMT_ELF_FDPIC - compat_ulong_t pr_exec_fdpic_loadmap; - compat_ulong_t pr_interp_fdpic_loadmap; -#endif compat_int_t pr_fpvalid; }; diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 96ab215dad2d..adb8ee89f3fd 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -44,16 +44,6 @@ struct elf_prstatus struct __kernel_old_timeval pr_cutime; /* Cumulative user time */ struct __kernel_old_timeval pr_cstime; /* Cumulative system time */ elf_gregset_t pr_reg; /* GP registers */ -#ifdef CONFIG_BINFMT_ELF_FDPIC - /* When using FDPIC, the loadmap addresses need to be communicated - * to GDB in order for GDB to do the necessary relocations. The - * fields (below) used to communicate this information are placed - * immediately after ``pr_reg'', so that the loadmap addresses may - * be viewed as part of the register set if so desired. - */ - unsigned long pr_exec_fdpic_loadmap; - unsigned long pr_interp_fdpic_loadmap; -#endif int pr_fpvalid; /* True if math co-processor being used. */ }; -- cgit v1.2.3 From 7a896028adcfbff4552e6748e8fc8d06036c132c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 13 Jun 2020 00:23:31 -0400 Subject: kill elf_fpxregs_t all uses are conditional upon ELF_CORE_COPY_XFPREGS, which has not been defined on any architecture since 2010 Signed-off-by: Al Viro --- include/linux/elfcore.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index adb8ee89f3fd..46c3d691f677 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -104,13 +104,6 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg #endif } -#ifdef ELF_CORE_COPY_XFPREGS -static inline int elf_core_copy_task_xfpregs(struct task_struct *t, elf_fpxregset_t *xfpu) -{ - return ELF_CORE_COPY_XFPREGS(t, xfpu); -} -#endif - /* * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out * extra segments containing the gate DSO contents. Dumping its -- cgit v1.2.3 From dc12d7968f9c9540494deb1285854b18ca4465ec Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 17 Feb 2020 12:25:14 -0500 Subject: copy_regset_to_user(): do all copyout at once. Turn copy_regset_to_user() into regset_get_alloc() + copy_to_user(). Now all ->get() calls have a kernel buffer as destination. Note that we'd already eliminated the callers of copy_regset_to_user() with non-zero offset; now that argument is simply unused. Uninlined, while we are at it. Signed-off-by: Al Viro --- include/linux/regset.h | 29 ++++------------------------- 1 file changed, 4 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h index 968a032922d5..af57c1db1924 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -362,31 +362,10 @@ extern int regset_get_alloc(struct task_struct *target, unsigned int size, void **data); -/** - * copy_regset_to_user - fetch a thread's user_regset data into user memory - * @target: thread to be examined - * @view: &struct user_regset_view describing user thread machine state - * @setno: index in @view->regsets - * @offset: offset into the regset data, in bytes - * @size: amount of data to copy, in bytes - * @data: user-mode pointer to copy into - */ -static inline int copy_regset_to_user(struct task_struct *target, - const struct user_regset_view *view, - unsigned int setno, - unsigned int offset, unsigned int size, - void __user *data) -{ - const struct user_regset *regset = &view->regsets[setno]; - - if (!regset->get) - return -EOPNOTSUPP; - - if (!access_ok(data, size)) - return -EFAULT; - - return regset->get(target, regset, offset, size, NULL, data); -} +extern int copy_regset_to_user(struct task_struct *target, + const struct user_regset_view *view, + unsigned int setno, unsigned int offset, + unsigned int size, void __user *data); /** * copy_regset_from_user - store into thread's user_regset data from user memory -- cgit v1.2.3 From 7717cb9bdd0421faa432a4e0d499fdba6e2394c8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 20 Feb 2020 20:48:16 -0500 Subject: regset: new method and helpers for it ->regset_get() takes task+regset+buffer, returns the amount of free space left in the buffer on success and -E... on error. buffer is represented as struct membuf - a pair of (kernel) pointer and amount of space left Primitives for writing to such: * membuf_write(buf, data, size) * membuf_zero(buf, size) * membuf_store(buf, value) These are implemented as inlines (in case of membuf_store - a macro). All writes are sequential; they become no-ops when there's no space left. Return value of all primitives is the amount of space left after the operation, so they can be used as return values of ->regset_get(). Example of use: // stores pt_regs of task + 64 bytes worth of zeroes + 32bit PID of task int foo_get(struct task_struct *task, const struct regset *regset, struct membuf to) { membuf_write(&to, task_pt_regs(task), sizeof(struct pt_regs)); membuf_zero(&to, 64); return membuf_store(&to, (u32)task_tgid_vnr(task)); } regset_get()/regset_get_alloc() taught to use that thing if present. By the end of the series all users of ->get() will be converted; then ->get() and ->get_size() can go. Note that unlike ->get() this thing always starts at offset 0 and, since it only writes to kernel buffer, can't fail on copyout. It can, of course, fail for other reasons, but those tend to be less numerous. The caller guarantees that the buffer size won't be bigger than regset->n * regset->size. That simplifies life for quite a few instances. Signed-off-by: Al Viro --- include/linux/regset.h | 51 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h index af57c1db1924..f6125a7d949d 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -17,6 +17,52 @@ struct task_struct; struct user_regset; +struct membuf { + void *p; + size_t left; +}; + +static inline int membuf_zero(struct membuf *s, size_t size) +{ + if (s->left) { + if (size > s->left) + size = s->left; + memset(s->p, 0, size); + s->p += size; + s->left -= size; + } + return s->left; +} + +static inline int membuf_write(struct membuf *s, const void *v, size_t size) +{ + if (s->left) { + if (size > s->left) + size = s->left; + memcpy(s->p, v, size); + s->p += size; + s->left -= size; + } + return s->left; +} + +/* current s->p must be aligned for v; v must be a scalar */ +#define membuf_store(s, v) \ +({ \ + struct membuf *__s = (s); \ + if (__s->left) { \ + typeof(v) __v = (v); \ + size_t __size = sizeof(__v); \ + if (unlikely(__size > __s->left)) { \ + __size = __s->left; \ + memcpy(__s->p, &__v, __size); \ + } else { \ + *(typeof(__v + 0) *)__s->p = __v; \ + } \ + __s->p += __size; \ + __s->left -= __size; \ + } \ + __s->left;}) /** * user_regset_active_fn - type of @active function in &struct user_regset @@ -57,6 +103,10 @@ typedef int user_regset_get_fn(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf); +typedef int user_regset_get2_fn(struct task_struct *target, + const struct user_regset *regset, + struct membuf to); + /** * user_regset_set_fn - type of @set function in &struct user_regset * @target: thread being examined @@ -186,6 +236,7 @@ typedef unsigned int user_regset_get_size_fn(struct task_struct *target, */ struct user_regset { user_regset_get_fn *get; + user_regset_get2_fn *regset_get; user_regset_set_fn *set; user_regset_active_fn *active; user_regset_writeback_fn *writeback; -- cgit v1.2.3 From 1e6986c9db21265bac1435a344b4446c51a3f4d8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 16 Jun 2020 15:34:20 -0400 Subject: regset: kill ->get() no instances left Signed-off-by: Al Viro --- include/linux/regset.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h index f6125a7d949d..2a4a555b1617 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -82,27 +82,6 @@ static inline int membuf_write(struct membuf *s, const void *v, size_t size) typedef int user_regset_active_fn(struct task_struct *target, const struct user_regset *regset); -/** - * user_regset_get_fn - type of @get function in &struct user_regset - * @target: thread being examined - * @regset: regset being examined - * @pos: offset into the regset data to access, in bytes - * @count: amount of data to copy, in bytes - * @kbuf: if not %NULL, a kernel-space pointer to copy into - * @ubuf: if @kbuf is %NULL, a user-space pointer to copy into - * - * Fetch register values. Return %0 on success; -%EIO or -%ENODEV - * are usual failure returns. The @pos and @count values are in - * bytes, but must be properly aligned. If @kbuf is non-null, that - * buffer is used and @ubuf is ignored. If @kbuf is %NULL, then - * ubuf gives a userland pointer to access directly, and an -%EFAULT - * return value is possible. - */ -typedef int user_regset_get_fn(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf); - typedef int user_regset_get2_fn(struct task_struct *target, const struct user_regset *regset, struct membuf to); @@ -235,7 +214,6 @@ typedef unsigned int user_regset_get_size_fn(struct task_struct *target, * omitted when there is an @active function and it returns zero. */ struct user_regset { - user_regset_get_fn *get; user_regset_get2_fn *regset_get; user_regset_set_fn *set; user_regset_active_fn *active; -- cgit v1.2.3 From c522401e0656b51e6a65ec112489cb078801aa9c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 17 Jun 2020 09:57:08 -0400 Subject: regset(): kill ->get_size() not used anymore Signed-off-by: Al Viro --- include/linux/regset.h | 48 +----------------------------------------------- 1 file changed, 1 insertion(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h index 2a4a555b1617..6b951a27bcaf 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -132,28 +132,6 @@ typedef int user_regset_writeback_fn(struct task_struct *target, const struct user_regset *regset, int immediate); -/** - * user_regset_get_size_fn - type of @get_size function in &struct user_regset - * @target: thread being examined - * @regset: regset being examined - * - * This call is optional; usually the pointer is %NULL. - * - * When provided, this function must return the current size of regset - * data, as observed by the @get function in &struct user_regset. The - * value returned must be a multiple of @size. The returned size is - * required to be valid only until the next time (if any) @regset is - * modified for @target. - * - * This function is intended for dynamically sized regsets. A regset - * that is statically sized does not need to implement it. - * - * This function should not be called directly: instead, callers should - * call regset_size() to determine the current size of a regset. - */ -typedef unsigned int user_regset_get_size_fn(struct task_struct *target, - const struct user_regset *regset); - /** * struct user_regset - accessible thread CPU state * @n: Number of slots (registers). @@ -165,7 +143,6 @@ typedef unsigned int user_regset_get_size_fn(struct task_struct *target, * @set: Function to store values. * @active: Function to report if regset is active, or %NULL. * @writeback: Function to write data back to user memory, or %NULL. - * @get_size: Function to return the regset's size, or %NULL. * * This data structure describes a machine resource we call a register set. * This is part of the state of an individual thread, not necessarily @@ -173,12 +150,7 @@ typedef unsigned int user_regset_get_size_fn(struct task_struct *target, * similar slots, given by @n. Each slot is @size bytes, and aligned to * @align bytes (which is at least @size). For dynamically-sized * regsets, @n must contain the maximum possible number of slots for the - * regset, and @get_size must point to a function that returns the - * current regset size. - * - * Callers that need to know only the current size of the regset and do - * not care about its internal structure should call regset_size() - * instead of inspecting @n or calling @get_size. + * regset. * * For backward compatibility, the @get and @set methods must pad to, or * accept, @n * @size bytes, even if the current regset size is smaller. @@ -218,7 +190,6 @@ struct user_regset { user_regset_set_fn *set; user_regset_active_fn *active; user_regset_writeback_fn *writeback; - user_regset_get_size_fn *get_size; unsigned int n; unsigned int size; unsigned int align; @@ -422,21 +393,4 @@ static inline int copy_regset_from_user(struct task_struct *target, return regset->set(target, regset, offset, size, NULL, data); } -/** - * regset_size - determine the current size of a regset - * @target: thread to be examined - * @regset: regset to be examined - * - * Note that the returned size is valid only until the next time - * (if any) @regset is modified for @target. - */ -static inline unsigned int regset_size(struct task_struct *target, - const struct user_regset *regset) -{ - if (!regset->get_size) - return regset->n * regset->size; - else - return regset->get_size(target, regset); -} - #endif /* */ -- cgit v1.2.3 From ce327e1c54119179066d6f3573a28001febc9265 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 17 Jun 2020 13:40:03 -0400 Subject: regset: kill user_regset_copyout{,_zero}() no callers left Signed-off-by: Al Viro --- include/linux/regset.h | 67 -------------------------------------------------- 1 file changed, 67 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h index 6b951a27bcaf..c3403f328257 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -238,44 +238,6 @@ struct user_regset_view { */ const struct user_regset_view *task_user_regset_view(struct task_struct *tsk); - -/* - * These are helpers for writing regset get/set functions in arch code. - * Because @start_pos and @end_pos are always compile-time constants, - * these are inlined into very little code though they look large. - * - * Use one or more calls sequentially for each chunk of regset data stored - * contiguously in memory. Call with constants for @start_pos and @end_pos, - * giving the range of byte positions in the regset that data corresponds - * to; @end_pos can be -1 if this chunk is at the end of the regset layout. - * Each call updates the arguments to point past its chunk. - */ - -static inline int user_regset_copyout(unsigned int *pos, unsigned int *count, - void **kbuf, - void __user **ubuf, const void *data, - const int start_pos, const int end_pos) -{ - if (*count == 0) - return 0; - BUG_ON(*pos < start_pos); - if (end_pos < 0 || *pos < end_pos) { - unsigned int copy = (end_pos < 0 ? *count - : min(*count, end_pos - *pos)); - data += *pos - start_pos; - if (*kbuf) { - memcpy(*kbuf, data, copy); - *kbuf += copy; - } else if (__copy_to_user(*ubuf, data, copy)) - return -EFAULT; - else - *ubuf += copy; - *pos += copy; - *count -= copy; - } - return 0; -} - static inline int user_regset_copyin(unsigned int *pos, unsigned int *count, const void **kbuf, const void __user **ubuf, void *data, @@ -301,35 +263,6 @@ static inline int user_regset_copyin(unsigned int *pos, unsigned int *count, return 0; } -/* - * These two parallel the two above, but for portions of a regset layout - * that always read as all-zero or for which writes are ignored. - */ -static inline int user_regset_copyout_zero(unsigned int *pos, - unsigned int *count, - void **kbuf, void __user **ubuf, - const int start_pos, - const int end_pos) -{ - if (*count == 0) - return 0; - BUG_ON(*pos < start_pos); - if (end_pos < 0 || *pos < end_pos) { - unsigned int copy = (end_pos < 0 ? *count - : min(*count, end_pos - *pos)); - if (*kbuf) { - memset(*kbuf, 0, copy); - *kbuf += copy; - } else if (clear_user(*ubuf, copy)) - return -EFAULT; - else - *ubuf += copy; - *pos += copy; - *count -= copy; - } - return 0; -} - static inline int user_regset_copyin_ignore(unsigned int *pos, unsigned int *count, const void **kbuf, -- cgit v1.2.3 From 6414e9b09ffd197803f8e86ce2fafdaf1de4e8e4 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 12 Jul 2020 20:09:52 -0700 Subject: fs: define inode flags using bit numbers Define the VFS inode flags using bit numbers instead of hardcoding powers of 2, which has become unwieldy now that we're up to 65536. No change in the actual values. Signed-off-by: Eric Biggers Signed-off-by: Al Viro --- include/linux/fs.h | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6c4ab4dc1cd7..9bf7a32f2932 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1982,27 +1982,27 @@ struct super_operations { /* * Inode flags - they have no relation to superblock flags now */ -#define S_SYNC 1 /* Writes are synced at once */ -#define S_NOATIME 2 /* Do not update access times */ -#define S_APPEND 4 /* Append-only file */ -#define S_IMMUTABLE 8 /* Immutable file */ -#define S_DEAD 16 /* removed, but still open directory */ -#define S_NOQUOTA 32 /* Inode is not counted to quota */ -#define S_DIRSYNC 64 /* Directory modifications are synchronous */ -#define S_NOCMTIME 128 /* Do not update file c/mtime */ -#define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */ -#define S_PRIVATE 512 /* Inode is fs-internal */ -#define S_IMA 1024 /* Inode has an associated IMA struct */ -#define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */ -#define S_NOSEC 4096 /* no suid or xattr security attributes */ +#define S_SYNC (1 << 0) /* Writes are synced at once */ +#define S_NOATIME (1 << 1) /* Do not update access times */ +#define S_APPEND (1 << 2) /* Append-only file */ +#define S_IMMUTABLE (1 << 3) /* Immutable file */ +#define S_DEAD (1 << 4) /* removed, but still open directory */ +#define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ +#define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ +#define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ +#define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ +#define S_PRIVATE (1 << 9) /* Inode is fs-internal */ +#define S_IMA (1 << 10) /* Inode has an associated IMA struct */ +#define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ +#define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX -#define S_DAX 8192 /* Direct Access, avoiding the page cache */ +#define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ #else -#define S_DAX 0 /* Make all the DAX code disappear */ +#define S_DAX 0 /* Make all the DAX code disappear */ #endif -#define S_ENCRYPTED 16384 /* Encrypted file (using fs/crypto/) */ -#define S_CASEFOLD 32768 /* Casefolded file */ -#define S_VERITY 65536 /* Verity file (using fs/verity/) */ +#define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ +#define S_CASEFOLD (1 << 15) /* Casefolded file */ +#define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system -- cgit v1.2.3 From 08b95c338e0c5a96e47f4ca314ea1e7580ecb5d7 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 8 Jul 2020 14:11:52 +0300 Subject: fanotify: remove event FAN_DIR_MODIFY It was never enabled in uapi and its functionality is about to be superseded by events FAN_CREATE, FAN_DELETE, FAN_MOVE with group flag FAN_REPORT_NAME. Keep a place holder variable name_event instead of removing the name recording code since it will be used by the new events. Link: https://lore.kernel.org/r/20200708111156.24659-17-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 6 ------ include/linux/fsnotify_backend.h | 4 +--- 2 files changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 316c9b820517..9b2566d273a9 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -30,12 +30,6 @@ static inline void fsnotify_name(struct inode *dir, __u32 mask, const struct qstr *name, u32 cookie) { fsnotify(dir, mask, child, FSNOTIFY_EVENT_INODE, name, cookie); - /* - * Send another flavor of the event without child inode data and - * without the specific event type (e.g. FS_CREATE|FS_IS_DIR). - * The name is relative to the dir inode the event is reported to. - */ - fsnotify(dir, FS_DIR_MODIFY, dir, FSNOTIFY_EVENT_INODE, name, 0); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 0de130cbf72d..94a4ff3d5bbe 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -47,7 +47,6 @@ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ -#define FS_DIR_MODIFY 0x00080000 /* Directory entry was modified */ #define FS_EXCL_UNLINK 0x04000000 /* do not send events if object is unlinked */ /* This inode cares about things that happen to its children. Always set for @@ -67,8 +66,7 @@ * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ -#define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | \ - FS_DIR_MODIFY) +#define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE) #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ FS_OPEN_EXEC_PERM) -- cgit v1.2.3 From d809daf1b6add51eec001bf60b17885d697a299d Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 16 Jul 2020 11:42:12 +0300 Subject: fanotify: generalize test for FAN_REPORT_FID As preparation for new flags that report fids, define a bit set of flags for a group reporting fids, currently containing the only bit FAN_REPORT_FID. Link: https://lore.kernel.org/r/20200716084230.30611-5-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index b79fa9bb7359..bbbee11d2521 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -18,8 +18,10 @@ #define FANOTIFY_CLASS_BITS (FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \ FAN_CLASS_PRE_CONTENT) -#define FANOTIFY_INIT_FLAGS (FANOTIFY_CLASS_BITS | \ - FAN_REPORT_TID | FAN_REPORT_FID | \ +#define FANOTIFY_FID_BITS (FAN_REPORT_FID) + +#define FANOTIFY_INIT_FLAGS (FANOTIFY_CLASS_BITS | FANOTIFY_FID_BITS | \ + FAN_REPORT_TID | \ FAN_CLOEXEC | FAN_NONBLOCK | \ FAN_UNLIMITED_QUEUE | FAN_UNLIMITED_MARKS) -- cgit v1.2.3 From 6ba8d7107f27c1bde60a80bc5def027979af3e8e Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 16 Jul 2020 11:42:16 +0300 Subject: fsnotify: add object type "child" to object type iterator The object type iterator is used to collect all the marks of a specific group that have interest in an event. It is used by fanotify to get a single handle_event callback when an event has a match to either of inode/sb/mount marks of the group. The nature of fsnotify events is that they are associated with at most one sb at most one mount and at most one inode. When a parent and child are both watching, two events are sent to backend, one associated to parent inode and one associated to the child inode. This results in duplicate events in fanotify, which usually get merged before user reads them, but this is sub-optimal. It would be better if the same event is sent to backend with an object type iterator that has both the child inode and its parent, and let the backend decide if the event should be reported once (fanotify) or twice (inotify). Link: https://lore.kernel.org/r/20200716084230.30611-9-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 94a4ff3d5bbe..d22519001027 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -253,6 +253,7 @@ static inline const struct path *fsnotify_data_path(const void *data, enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_INODE, + FSNOTIFY_OBJ_TYPE_CHILD, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, @@ -260,6 +261,7 @@ enum fsnotify_obj_type { }; #define FSNOTIFY_OBJ_TYPE_INODE_FL (1U << FSNOTIFY_OBJ_TYPE_INODE) +#define FSNOTIFY_OBJ_TYPE_CHILD_FL (1U << FSNOTIFY_OBJ_TYPE_CHILD) #define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT) #define FSNOTIFY_OBJ_TYPE_SB_FL (1U << FSNOTIFY_OBJ_TYPE_SB) #define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) @@ -304,6 +306,7 @@ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ } FSNOTIFY_ITER_FUNCS(inode, INODE) +FSNOTIFY_ITER_FUNCS(child, CHILD) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) -- cgit v1.2.3 From 8b7beaf9f185249f29912b5e2d7bc4147c5c2a6a Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Mon, 27 Jul 2020 13:43:39 -0600 Subject: PCI: Add Intel QuickAssist device IDs Add device IDs for the following Intel QuickAssist devices: DH895XCC, C3XXX and C62X. The defines in this patch are going to be referenced in two independent drivers, qat and vfio-pci. Signed-off-by: Giovanni Cabiddu Acked-by: Bjorn Helgaas Reviewed-by: Fiona Trahe Reviewed-by: Andy Shevchenko Signed-off-by: Alex Williamson --- include/linux/pci_ids.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 0ad57693f392..f3166b1425ca 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2659,6 +2659,8 @@ #define PCI_DEVICE_ID_INTEL_80332_1 0x0332 #define PCI_DEVICE_ID_INTEL_80333_0 0x0370 #define PCI_DEVICE_ID_INTEL_80333_1 0x0372 +#define PCI_DEVICE_ID_INTEL_QAT_DH895XCC 0x0435 +#define PCI_DEVICE_ID_INTEL_QAT_DH895XCC_VF 0x0443 #define PCI_DEVICE_ID_INTEL_82375 0x0482 #define PCI_DEVICE_ID_INTEL_82424 0x0483 #define PCI_DEVICE_ID_INTEL_82378 0x0484 @@ -2708,6 +2710,8 @@ #define PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_4C_NHI 0x1577 #define PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_4C_BRIDGE 0x1578 #define PCI_DEVICE_ID_INTEL_80960_RP 0x1960 +#define PCI_DEVICE_ID_INTEL_QAT_C3XXX 0x19e2 +#define PCI_DEVICE_ID_INTEL_QAT_C3XXX_VF 0x19e3 #define PCI_DEVICE_ID_INTEL_82840_HB 0x1a21 #define PCI_DEVICE_ID_INTEL_82845_HB 0x1a30 #define PCI_DEVICE_ID_INTEL_IOAT 0x1a38 @@ -2924,6 +2928,8 @@ #define PCI_DEVICE_ID_INTEL_IOAT_JSF7 0x3717 #define PCI_DEVICE_ID_INTEL_IOAT_JSF8 0x3718 #define PCI_DEVICE_ID_INTEL_IOAT_JSF9 0x3719 +#define PCI_DEVICE_ID_INTEL_QAT_C62X 0x37c8 +#define PCI_DEVICE_ID_INTEL_QAT_C62X_VF 0x37c9 #define PCI_DEVICE_ID_INTEL_ICH10_0 0x3a14 #define PCI_DEVICE_ID_INTEL_ICH10_1 0x3a16 #define PCI_DEVICE_ID_INTEL_ICH10_2 0x3a18 -- cgit v1.2.3 From 82ace1efb3cb1d49a1681cc6e31156047d5ae1f2 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 22 Jul 2020 15:58:44 +0300 Subject: fsnotify: create helper fsnotify_inode() Simple helper to consolidate biolerplate code. Link: https://lore.kernel.org/r/20200722125849.17418-5-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 9b2566d273a9..f9db7c9b3ef1 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -38,6 +38,14 @@ static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0); } +static inline void fsnotify_inode(struct inode *inode, __u32 mask) +{ + if (S_ISDIR(inode->i_mode)) + mask |= FS_ISDIR; + + fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); +} + /* Notify this dentry's parent about a child's events. */ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) @@ -105,12 +113,7 @@ static inline int fsnotify_perm(struct file *file, int mask) */ static inline void fsnotify_link_count(struct inode *inode) { - __u32 mask = FS_ATTRIB; - - if (S_ISDIR(inode->i_mode)) - mask |= FS_ISDIR; - - fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); + fsnotify_inode(inode, FS_ATTRIB); } /* @@ -125,7 +128,6 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; - __u32 mask = FS_MOVE_SELF; const struct qstr *new_name = &moved->d_name; if (old_dir == new_dir) @@ -134,7 +136,6 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; - mask |= FS_ISDIR; } fsnotify_name(old_dir, old_dir_mask, source, old_name, fs_cookie); @@ -144,7 +145,7 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, fsnotify_link_count(target); if (source) - fsnotify(source, mask, source, FSNOTIFY_EVENT_INODE, NULL, 0); + fsnotify_inode(source, FS_MOVE_SELF); audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE); } @@ -169,12 +170,7 @@ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) */ static inline void fsnotify_inoderemove(struct inode *inode) { - __u32 mask = FS_DELETE_SELF; - - if (S_ISDIR(inode->i_mode)) - mask |= FS_ISDIR; - - fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); + fsnotify_inode(inode, FS_DELETE_SELF); __fsnotify_inode_delete(inode); } -- cgit v1.2.3 From 40a100d3adc1ad7f0a34875468c499fcecd20ba4 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 22 Jul 2020 15:58:46 +0300 Subject: fsnotify: pass dir and inode arguments to fsnotify() The arguments of fsnotify() are overloaded and mean different things for different event types. Replace the to_tell argument with separate arguments @dir and @inode, because we may be sending to both dir and child. Using the @data argument to pass the child is not enough, because dirent events pass this argument (for audit), but we do not report to child. Document the new fsnotify() function argumenets. Link: https://lore.kernel.org/r/20200722125849.17418-7-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 9 +++++---- include/linux/fsnotify_backend.h | 10 ++++++---- 2 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index f9db7c9b3ef1..99922cac4fcd 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -23,13 +23,14 @@ * have changed (i.e. renamed over). * * Unlike fsnotify_parent(), the event will be reported regardless of the - * FS_EVENT_ON_CHILD mask on the parent inode. + * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only + * the child is interested and not the parent. */ static inline void fsnotify_name(struct inode *dir, __u32 mask, struct inode *child, const struct qstr *name, u32 cookie) { - fsnotify(dir, mask, child, FSNOTIFY_EVENT_INODE, name, cookie); + fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, @@ -43,7 +44,7 @@ static inline void fsnotify_inode(struct inode *inode, __u32 mask) if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; - fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); + fsnotify(mask, inode, FSNOTIFY_EVENT_INODE, NULL, NULL, inode, 0); } /* Notify this dentry's parent about a child's events. */ @@ -61,7 +62,7 @@ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, return __fsnotify_parent(dentry, mask, data, data_type); notify_child: - return fsnotify(inode, mask, data, data_type, NULL, 0); + return fsnotify(mask, data, data_type, NULL, NULL, inode, 0); } /* diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index d22519001027..152520635bd3 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -387,8 +387,9 @@ struct fsnotify_mark { /* called from the vfs helpers */ /* main fsnotify call to send events */ -extern int fsnotify(struct inode *to_tell, __u32 mask, const void *data, - int data_type, const struct qstr *name, u32 cookie); +extern int fsnotify(__u32 mask, const void *data, int data_type, + struct inode *dir, const struct qstr *name, + struct inode *inode, u32 cookie); extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type); extern void __fsnotify_inode_delete(struct inode *inode); @@ -545,8 +546,9 @@ static inline void fsnotify_init_event(struct fsnotify_event *event, #else -static inline int fsnotify(struct inode *to_tell, __u32 mask, const void *data, - int data_type, const struct qstr *name, u32 cookie) +static inline int fsnotify(__u32 mask, const void *data, int data_type, + struct inode *dir, const struct qstr *name, + struct inode *inode, u32 cookie) { return 0; } -- cgit v1.2.3 From 9b93f33105f5f9bd3d016ff870eb6000c9d89eff Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 16 Jul 2020 11:42:23 +0300 Subject: fsnotify: send event with parent/name info to sb/mount/non-dir marks Similar to events "on child" to watching directory, send event with parent/name info if sb/mount/non-dir marks are interested in parent/name info. The FS_EVENT_ON_CHILD flag can be set on sb/mount/non-dir marks to specify interest in parent/name info for events on non-directory inodes. Events on "orphan" children (disconnected dentries) are sent without parent/name info. Events on directories are sent with parent/name info only if the parent directory is watching. After this change, even groups that do not subscribe to events on children could get an event with mark iterator type TYPE_CHILD and without mark iterator type TYPE_INODE if fanotify has marks on the same objects. dnotify and inotify event handlers can already cope with that situation. audit does not subscribe to events that are possible on child, so won't get to this situation. nfsd does not access the marks iterator from its event handler at the moment, so it is not affected. This is a bit too fragile, so we should prepare all groups to cope with mark type TYPE_CHILD preferably using a generic helper. Link: https://lore.kernel.org/r/20200716084230.30611-16-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 10 ++++++++-- include/linux/fsnotify_backend.h | 32 ++++++++++++++++++++++++++++---- 2 files changed, 36 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 99922cac4fcd..6e63f7e10da0 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -53,10 +53,16 @@ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, { struct inode *inode = d_inode(dentry); - if (S_ISDIR(inode->i_mode)) + if (S_ISDIR(inode->i_mode)) { mask |= FS_ISDIR; - if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) + /* sb/mount marks are not interested in name of directory */ + if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) + goto notify_child; + } + + /* disconnected dentry cannot notify parent */ + if (IS_ROOT(dentry)) goto notify_child; return __fsnotify_parent(dentry, mask, data, data_type); diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 152520635bd3..32104cfc27a5 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -49,8 +49,11 @@ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ #define FS_EXCL_UNLINK 0x04000000 /* do not send events if object is unlinked */ -/* This inode cares about things that happen to its children. Always set for - * dnotify and inotify. */ +/* + * Set on inode mark that cares about things that happen to its children. + * Always set for dnotify and inotify. + * Set on inode/sb/mount marks that care about parent/name info. + */ #define FS_EVENT_ON_CHILD 0x08000000 #define FS_DN_RENAME 0x10000000 /* file renamed */ @@ -72,14 +75,22 @@ FS_OPEN_EXEC_PERM) /* - * This is a list of all events that may get sent to a parent based on fs event - * happening to inodes inside that directory. + * This is a list of all events that may get sent to a parent that is watching + * with flag FS_EVENT_ON_CHILD based on fs event on a child of that directory. */ #define FS_EVENTS_POSS_ON_CHILD (ALL_FSNOTIFY_PERM_EVENTS | \ FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \ FS_OPEN | FS_OPEN_EXEC) +/* + * This is a list of all events that may get sent with the parent inode as the + * @to_tell argument of fsnotify(). + * It may include events that can be sent to an inode/sb/mount mark, but cannot + * be sent to a parent watching children. + */ +#define FS_EVENTS_POSS_TO_PARENT (FS_EVENTS_POSS_ON_CHILD) + /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ @@ -397,6 +408,19 @@ extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern void fsnotify_sb_delete(struct super_block *sb); extern u32 fsnotify_get_cookie(void); +static inline __u32 fsnotify_parent_needed_mask(__u32 mask) +{ + /* FS_EVENT_ON_CHILD is set on marks that want parent/name info */ + if (!(mask & FS_EVENT_ON_CHILD)) + return 0; + /* + * This object might be watched by a mark that cares about parent/name + * info, does it care about the specific set of events that can be + * reported with parent/name info? + */ + return mask & FS_EVENTS_POSS_TO_PARENT; +} + static inline int fsnotify_inode_watches_children(struct inode *inode) { /* FS_EVENT_ON_CHILD is set if the inode may care */ -- cgit v1.2.3 From 79cb299c7e181fad683bf6191edb8224b2412512 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 16 Jul 2020 11:42:24 +0300 Subject: fsnotify: remove check that source dentry is positive Remove the unneeded check for positive source dentry in fsnotify_move(). fsnotify_move() hook is mostly called from vfs_rename() under lock_rename() and vfs_rename() starts with may_delete() test that verifies positive source dentry. The only other caller of fsnotify_move() - debugfs_rename() also verifies positive source. Link: https://lore.kernel.org/r/20200716084230.30611-17-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 6e63f7e10da0..f8acddcf54fb 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -150,9 +150,7 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, if (target) fsnotify_link_count(target); - - if (source) - fsnotify_inode(source, FS_MOVE_SELF); + fsnotify_inode(source, FS_MOVE_SELF); audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE); } -- cgit v1.2.3 From 83b7a59896dd24015a34b7f00027f0ff3747972f Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 16 Jul 2020 11:42:26 +0300 Subject: fanotify: add basic support for FAN_REPORT_DIR_FID For now, the flag is mutually exclusive with FAN_REPORT_FID. Events include a single info record of type FAN_EVENT_INFO_TYPE_DFID with a directory file handle. For now, events are only reported for: - Directory modification events - Events on children of a watching directory - Events on directory objects Soon, we will add support for reporting the parent directory fid for events on non-directories with filesystem/mount mark and support for reporting both parent directory fid and child fid. Link: https://lore.kernel.org/r/20200716084230.30611-19-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index bbbee11d2521..4ddac97b2bf7 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -18,7 +18,7 @@ #define FANOTIFY_CLASS_BITS (FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \ FAN_CLASS_PRE_CONTENT) -#define FANOTIFY_FID_BITS (FAN_REPORT_FID) +#define FANOTIFY_FID_BITS (FAN_REPORT_FID | FAN_REPORT_DIR_FID) #define FANOTIFY_INIT_FLAGS (FANOTIFY_CLASS_BITS | FANOTIFY_FID_BITS | \ FAN_REPORT_TID | \ -- cgit v1.2.3 From 929943b38daf817f2e6d303ea04401651fc3bc05 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 16 Jul 2020 11:42:28 +0300 Subject: fanotify: add support for FAN_REPORT_NAME Introduce a new fanotify_init() flag FAN_REPORT_NAME. It requires the flag FAN_REPORT_DIR_FID and there is a constant for setting both flags named FAN_REPORT_DFID_NAME. For a group with flag FAN_REPORT_NAME, the parent fid and name are reported for directory entry modification events (create/detete/move) and for events on non-directory objects. Events on directories themselves are reported with their own fid and "." as the name. The parent fid and name are reported with an info record of type FAN_EVENT_INFO_TYPE_DFID_NAME, similar to the way that parent fid is reported with into type FAN_EVENT_INFO_TYPE_DFID, but with an appended null terminated name string. Link: https://lore.kernel.org/r/20200716084230.30611-21-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 4ddac97b2bf7..3e9c56ee651f 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -18,7 +18,7 @@ #define FANOTIFY_CLASS_BITS (FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \ FAN_CLASS_PRE_CONTENT) -#define FANOTIFY_FID_BITS (FAN_REPORT_FID | FAN_REPORT_DIR_FID) +#define FANOTIFY_FID_BITS (FAN_REPORT_FID | FAN_REPORT_DFID_NAME) #define FANOTIFY_INIT_FLAGS (FANOTIFY_CLASS_BITS | FANOTIFY_FID_BITS | \ FAN_REPORT_TID | \ -- cgit v1.2.3 From b9a1b9772509cbc6f6aa8bcd0b019f6347a2b631 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 22 Jul 2020 15:58:48 +0300 Subject: fsnotify: create method handle_inode_event() in fsnotify_operations The method handle_event() grew a lot of complexity due to the design of fanotify and merging of ignore masks. Most backends do not care about this complex functionality, so we can hide this complexity from them. Introduce a method handle_inode_event() that serves those backends and passes a single inode mark and less arguments. This change converts all backends except fanotify and inotify to use the simplified handle_inode_event() method. In pricipal, inotify could have also used the new method, but that would require passing more arguments on the simple helper (data, data_type, cookie), so we leave it with the handle_event() method. Link: https://lore.kernel.org/r/20200722125849.17418-9-amir73il@gmail.com Suggested-by: Jan Kara Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 32104cfc27a5..f8529a3a2923 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -128,17 +128,30 @@ struct mem_cgroup; * @cookie: inotify rename cookie * @iter_info: array of marks from this group that are interested in the event * + * handle_inode_event - simple variant of handle_event() for groups that only + * have inode marks and don't have ignore mask + * @mark: mark to notify + * @mask: event type and flags + * @inode: inode that event happened on + * @dir: optional directory associated with event - + * if @file_name is not NULL, this is the directory that + * @file_name is relative to. + * @file_name: optional file name associated with event + * * free_group_priv - called when a group refcnt hits 0 to clean up the private union * freeing_mark - called when a mark is being destroyed for some reason. The group - * MUST be holding a reference on each mark and that reference must be - * dropped in this function. inotify uses this function to send - * userspace messages that marks have been removed. + * MUST be holding a reference on each mark and that reference must be + * dropped in this function. inotify uses this function to send + * userspace messages that marks have been removed. */ struct fsnotify_ops { int (*handle_event)(struct fsnotify_group *group, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info); + int (*handle_inode_event)(struct fsnotify_mark *mark, u32 mask, + struct inode *inode, struct inode *dir, + const struct qstr *file_name); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event)(struct fsnotify_event *event); -- cgit v1.2.3 From c1b7b8d42b5422627b0a8268416a60748f8d000f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E7=8E=8B=E6=96=87=E8=99=8E?= Date: Mon, 27 Jul 2020 21:39:51 +0800 Subject: sched: Fix a typo in a comment Change the comment typo: "direcly" -> "directly". Signed-off-by: Wang Wenhu Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/AAcAXwBTDSpsKN-5iyIOtaqk.1.1595857191899.Hmail.wenhu.wang@vivo.com --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5033813fecd5..adf0125190d4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -374,7 +374,7 @@ struct util_est { * For cfs_rq, they are the aggregated values of all runnable and blocked * sched_entities. * - * The load/runnable/util_avg doesn't direcly factor frequency scaling and CPU + * The load/runnable/util_avg doesn't directly factor frequency scaling and CPU * capacity scaling. The scaling is done through the rq_clock_pelt that is used * for computing those signals (see update_rq_clock_pelt()) * -- cgit v1.2.3 From af60459a543483c5ad155a92daa8c3a6c00a0829 Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Fri, 24 Jul 2020 20:21:47 +0800 Subject: math64: New DIV_S64_ROUND_CLOSEST helper Provide DIV_S64_ROUND_CLOSEST helper which uses div_s64 to perform division rounded to the closest integer using signed 64bit dividend and signed 32bit divisor. Signed-off-by: Chunyan Zhang Signed-off-by: Sebastian Reichel --- include/linux/math64.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index 11a267413e8e..cd0693989436 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -279,4 +279,23 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) #define DIV64_U64_ROUND_CLOSEST(dividend, divisor) \ ({ u64 _tmp = (divisor); div64_u64((dividend) + _tmp / 2, _tmp); }) +/* + * DIV_S64_ROUND_CLOSEST - signed 64bit divide with 32bit divisor rounded to nearest integer + * @dividend: signed 64bit dividend + * @divisor: signed 32bit divisor + * + * Divide signed 64bit dividend by signed 32bit divisor + * and round to closest integer. + * + * Return: dividend / divisor rounded to nearest integer + */ +#define DIV_S64_ROUND_CLOSEST(dividend, divisor)( \ +{ \ + s64 __x = (dividend); \ + s32 __d = (divisor); \ + ((__x > 0) == (__d > 0)) ? \ + div_s64((__x + (__d / 2)), __d) : \ + div_s64((__x - (__d / 2)), __d); \ +} \ +) #endif /* _LINUX_MATH64_H */ -- cgit v1.2.3 From 62b9825827518843f0f93dec6730ddcde14eb5b2 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Mon, 17 Feb 2020 09:26:43 +0800 Subject: usb: chipidea: add query_available_role interface The glue layer may need to know current available role to do some setting, eg, the wakeup setting. So we add ci_hdrc_query_available_role for that. Signed-off-by: Peter Chen --- include/linux/usb/chipidea.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 54167a2d28ea..025b41687ce9 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -99,5 +99,7 @@ struct platform_device *ci_hdrc_add_device(struct device *dev, struct ci_hdrc_platform_data *platdata); /* Remove ci hdrc device */ void ci_hdrc_remove_device(struct platform_device *pdev); +/* Get current available role */ +enum usb_dr_mode ci_hdrc_query_available_role(struct platform_device *pdev); #endif -- cgit v1.2.3 From e885d5d94793ef342e49d55672baabbc16e32bb1 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 16 Jul 2020 16:36:50 +1000 Subject: lockdep: Move list.h inclusion into lockdep.h Currently lockdep_types.h includes list.h without actually using any of its macros or functions. All it needs are the type definitions which were moved into types.h long ago. This potentially causes inclusion loops because both are included by many core header files. This patch moves the list.h inclusion into lockdep.h. Note that we could probably remove it completely but that could potentially result in compile failures should any end users not include list.h directly and also be unlucky enough to not get list.h via some other header file. Reported-by: Petr Mladek Signed-off-by: Herbert Xu Signed-off-by: Peter Zijlstra (Intel) Tested-by: Petr Mladek Link: https://lkml.kernel.org/r/20200716063649.GA23065@gondor.apana.org.au --- include/linux/lockdep.h | 1 + include/linux/lockdep_types.h | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 3b73cf84f77d..b1ad5c045353 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -21,6 +21,7 @@ extern int lock_stat; #ifdef CONFIG_LOCKDEP #include +#include #include #include diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index 7b9350624577..bb35b449f533 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -32,8 +32,6 @@ enum lockdep_wait_type { #ifdef CONFIG_LOCKDEP -#include - /* * We'd rather not expose kernel/lockdep_states.h this wide, but we do need * the total number of states... :-( -- cgit v1.2.3 From d6945242f45d4745a8169fdab7afeb40f4e36f06 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 18 May 2020 11:13:52 +0300 Subject: net/mlx5: Hold pages RB tree per VF Per page request event, FW request to allocated or release pages for a single function. Driver maintains FW pages object per function, so there is no need to hold one global page data-base. Instead, have a page data-base per function, which will improve performance release flow in all cases, especially for "release all pages". As the range of function IDs is large and not sequential, use xarray to store a per function ID page data-base, where the function ID is the key. Upon first allocation of a page to a function ID, create the page data-base per function. This data-base will be released only at pagealloc mechanism cleanup. NIC: ConnectX-4 Lx CPU: Intel(R) Xeon(R) CPU E5-2650 v2 @ 2.60GHz Test case: 32 VFs, measure release pages on one VF as part of FLR Before: 0.021 Sec After: 0.014 Sec The improvement depends on amount of VFs and memory utilization by them. Time measurements above were taken from idle system. Signed-off-by: Eran Ben Elisha Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6a97ad601991..a0fcc4d13e93 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -541,7 +541,7 @@ struct mlx5_priv { /* pages stuff */ struct mlx5_nb pg_nb; struct workqueue_struct *pg_wq; - struct rb_root page_root; + struct xarray page_root_xa; int fw_pages; atomic_t reg_pages; struct list_head free_list; -- cgit v1.2.3 From d1718a1b7a86743b9c517bf9521695ba909c734f Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Fri, 19 Jun 2020 09:20:03 +0100 Subject: ACPI/IORT: Make iort_get_device_domain IRQ domain agnostic iort_get_device_domain() is PCI specific but it need not be, since it can be used to retrieve IRQ domain nexus of any kind by adding an irq_domain_bus_token input to it. Make it PCI agnostic by also renaming the requestor ID input to a more generic ID name. Signed-off-by: Lorenzo Pieralisi Acked-by: Bjorn Helgaas # pci/msi.c Cc: Will Deacon Cc: Hanjun Guo Cc: Bjorn Helgaas Cc: Sudeep Holla Cc: Robin Murphy Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20200619082013.13661-3-lorenzo.pieralisi@arm.com Signed-off-by: Catalin Marinas --- include/linux/acpi_iort.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 8e7e2ec37f1b..08ec6bd2297f 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -29,7 +29,8 @@ struct fwnode_handle *iort_find_domain_token(int trans_id); #ifdef CONFIG_ACPI_IORT void acpi_iort_init(void); u32 iort_msi_map_rid(struct device *dev, u32 req_id); -struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id); +struct irq_domain *iort_get_device_domain(struct device *dev, u32 id, + enum irq_domain_bus_token bus_token); void acpi_configure_pmsi_domain(struct device *dev); int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); /* IOMMU interface */ @@ -40,8 +41,8 @@ int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head); static inline void acpi_iort_init(void) { } static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id) { return req_id; } -static inline struct irq_domain *iort_get_device_domain(struct device *dev, - u32 req_id) +static inline struct irq_domain *iort_get_device_domain( + struct device *dev, u32 id, enum irq_domain_bus_token bus_token) { return NULL; } static inline void acpi_configure_pmsi_domain(struct device *dev) { } /* IOMMU interface */ -- cgit v1.2.3 From 39c3cf566ceafa7c1ae331a5f26fbb685d670001 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Fri, 19 Jun 2020 09:20:04 +0100 Subject: ACPI/IORT: Make iort_msi_map_rid() PCI agnostic There is nothing PCI specific in iort_msi_map_rid(). Rename the function using a bus protocol agnostic name, iort_msi_map_id(), and convert current callers to it. Signed-off-by: Lorenzo Pieralisi Acked-by: Bjorn Helgaas Cc: Will Deacon Cc: Hanjun Guo Cc: Bjorn Helgaas Cc: Sudeep Holla Cc: Robin Murphy Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20200619082013.13661-4-lorenzo.pieralisi@arm.com Signed-off-by: Catalin Marinas --- include/linux/acpi_iort.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 08ec6bd2297f..e51425e083da 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -28,7 +28,7 @@ void iort_deregister_domain_token(int trans_id); struct fwnode_handle *iort_find_domain_token(int trans_id); #ifdef CONFIG_ACPI_IORT void acpi_iort_init(void); -u32 iort_msi_map_rid(struct device *dev, u32 req_id); +u32 iort_msi_map_id(struct device *dev, u32 id); struct irq_domain *iort_get_device_domain(struct device *dev, u32 id, enum irq_domain_bus_token bus_token); void acpi_configure_pmsi_domain(struct device *dev); @@ -39,8 +39,8 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev); int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head); #else static inline void acpi_iort_init(void) { } -static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id) -{ return req_id; } +static inline u32 iort_msi_map_id(struct device *dev, u32 id) +{ return id; } static inline struct irq_domain *iort_get_device_domain( struct device *dev, u32 id, enum irq_domain_bus_token bus_token) { return NULL; } -- cgit v1.2.3 From b8e069a2a8da02137605ba585837a3a0c45df01a Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Fri, 19 Jun 2020 09:20:06 +0100 Subject: ACPI/IORT: Add an input ID to acpi_dma_configure() Some HW devices are created as child devices of proprietary busses, that have a bus specific policy defining how the child devices wires representing the devices ID are translated into IOMMU and IRQ controllers device IDs. Current IORT code provides translations for: - PCI devices, where the device ID is well identified at bus level as the requester ID (RID) - Platform devices that are endpoint devices where the device ID is retrieved from the ACPI object IORT mappings (Named components single mappings). A platform device is represented in IORT as a named component node For devices that are child devices of proprietary busses the IORT firmware represents the bus node as a named component node in IORT and it is up to that named component node to define in/out bus specific ID translations for the bus child devices that are allocated and created in a bus specific manner. In order to make IORT ID translations available for proprietary bus child devices, the current ACPI (and IORT) code must be augmented to provide an additional ID parameter to acpi_dma_configure() representing the child devices input ID. This ID is bus specific and it is retrieved in bus specific code. By adding an ID parameter to acpi_dma_configure(), the IORT code can map the child device ID to an IOMMU stream ID through the IORT named component representing the bus in/out ID mappings. Signed-off-by: Lorenzo Pieralisi Cc: Will Deacon Cc: Hanjun Guo Cc: Sudeep Holla Cc: Robin Murphy Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20200619082013.13661-6-lorenzo.pieralisi@arm.com Signed-off-by: Catalin Marinas --- include/linux/acpi.h | 7 +++++++ include/linux/acpi_iort.h | 7 ++++--- 2 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d661cd0ee64d..6d2c47489d90 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -905,6 +905,13 @@ static inline int acpi_dma_configure(struct device *dev, return 0; } +static inline int acpi_dma_configure_id(struct device *dev, + enum dev_dma_attr attr, + const u32 *input_id) +{ + return 0; +} + #define ACPI_PTR(_ptr) (NULL) static inline void acpi_device_set_enumerated(struct acpi_device *adev) diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index e51425e083da..20a32120bb88 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -35,7 +35,8 @@ void acpi_configure_pmsi_domain(struct device *dev); int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); /* IOMMU interface */ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size); -const struct iommu_ops *iort_iommu_configure(struct device *dev); +const struct iommu_ops *iort_iommu_configure_id(struct device *dev, + const u32 *id_in); int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head); #else static inline void acpi_iort_init(void) { } @@ -48,8 +49,8 @@ static inline void acpi_configure_pmsi_domain(struct device *dev) { } /* IOMMU interface */ static inline void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size) { } -static inline const struct iommu_ops *iort_iommu_configure( - struct device *dev) +static inline const struct iommu_ops *iort_iommu_configure_id( + struct device *dev, const u32 *id_in) { return NULL; } static inline int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) -- cgit v1.2.3 From 746a71d02b5d15817fcb13c956ba999a87773952 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Fri, 19 Jun 2020 09:20:07 +0100 Subject: of/iommu: Make of_map_rid() PCI agnostic There is nothing PCI specific (other than the RID - requester ID) in the of_map_rid() implementation, so the same function can be reused for input/output IDs mapping for other busses just as well. Rename the RID instances/names to a generic "id" tag. No functionality change intended. Signed-off-by: Lorenzo Pieralisi Reviewed-by: Rob Herring Acked-by: Joerg Roedel Cc: Rob Herring Cc: Joerg Roedel Cc: Robin Murphy Cc: Marc Zyngier Link: https://lore.kernel.org/r/20200619082013.13661-7-lorenzo.pieralisi@arm.com Signed-off-by: Catalin Marinas --- include/linux/of.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index c669c0a4732f..60abe3f636ad 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -554,7 +554,7 @@ bool of_console_check(struct device_node *dn, char *name, int index); extern int of_cpu_node_to_id(struct device_node *np); -int of_map_rid(struct device_node *np, u32 rid, +int of_map_id(struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out); @@ -978,7 +978,7 @@ static inline int of_cpu_node_to_id(struct device_node *np) return -ENODEV; } -static inline int of_map_rid(struct device_node *np, u32 rid, +static inline int of_map_id(struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out) { -- cgit v1.2.3 From a081bd4af4ce80d845a0bab355ab5d0822db8058 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Fri, 19 Jun 2020 09:20:08 +0100 Subject: of/device: Add input id to of_dma_configure() Devices sitting on proprietary busses have a device ID space that is owned by the respective bus and related firmware bindings. In order to let the generic OF layer handle the input translations to an IOMMU id, for such busses the current of_dma_configure() interface should be extended in order to allow the bus layer to provide the device input id parameter - that is retrieved/assigned in bus specific code and firmware. Augment of_dma_configure() to add an optional input_id parameter, leaving current functionality unchanged. Signed-off-by: Lorenzo Pieralisi Reviewed-by: Rob Herring Cc: Rob Herring Cc: Robin Murphy Cc: Joerg Roedel Cc: Laurentiu Tudor Link: https://lore.kernel.org/r/20200619082013.13661-8-lorenzo.pieralisi@arm.com Signed-off-by: Catalin Marinas --- include/linux/of_device.h | 16 ++++++++++++++-- include/linux/of_iommu.h | 6 ++++-- 2 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 8d31e39dd564..07ca187fc5e4 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -55,9 +55,15 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) return of_node_get(cpu_dev->of_node); } -int of_dma_configure(struct device *dev, +int of_dma_configure_id(struct device *dev, struct device_node *np, - bool force_dma); + bool force_dma, const u32 *id); +static inline int of_dma_configure(struct device *dev, + struct device_node *np, + bool force_dma) +{ + return of_dma_configure_id(dev, np, force_dma, NULL); +} #else /* CONFIG_OF */ static inline int of_driver_match_device(struct device *dev, @@ -106,6 +112,12 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) return NULL; } +static inline int of_dma_configure_id(struct device *dev, + struct device_node *np, + bool force_dma) +{ + return 0; +} static inline int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h index f3d40dd7bb66..16f4b3e87f20 100644 --- a/include/linux/of_iommu.h +++ b/include/linux/of_iommu.h @@ -13,7 +13,8 @@ extern int of_get_dma_window(struct device_node *dn, const char *prefix, size_t *size); extern const struct iommu_ops *of_iommu_configure(struct device *dev, - struct device_node *master_np); + struct device_node *master_np, + const u32 *id); #else @@ -25,7 +26,8 @@ static inline int of_get_dma_window(struct device_node *dn, const char *prefix, } static inline const struct iommu_ops *of_iommu_configure(struct device *dev, - struct device_node *master_np) + struct device_node *master_np, + const u32 *id) { return NULL; } -- cgit v1.2.3 From 6f881aba01109a01a43e4f135673c19190f61133 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Fri, 19 Jun 2020 09:20:10 +0100 Subject: of/irq: make of_msi_map_get_device_domain() bus agnostic of_msi_map_get_device_domain() is PCI specific but it need not be and can be easily changed to be bus agnostic in order to be used by other busses by adding an IRQ domain bus token as an input parameter. Signed-off-by: Diana Craciun Signed-off-by: Lorenzo Pieralisi Reviewed-by: Rob Herring Acked-by: Bjorn Helgaas # pci/msi.c Cc: Bjorn Helgaas Cc: Rob Herring Cc: Marc Zyngier Link: https://lore.kernel.org/r/20200619082013.13661-10-lorenzo.pieralisi@arm.com Signed-off-by: Catalin Marinas --- include/linux/of_irq.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 1214cabb2247..7142a3722758 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -52,7 +52,8 @@ extern struct irq_domain *of_msi_get_domain(struct device *dev, struct device_node *np, enum irq_domain_bus_token token); extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, - u32 rid); + u32 id, + u32 bus_token); extern void of_msi_configure(struct device *dev, struct device_node *np); u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in); #else @@ -85,7 +86,7 @@ static inline struct irq_domain *of_msi_get_domain(struct device *dev, return NULL; } static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev, - u32 rid) + u32 id, u32 bus_token) { return NULL; } -- cgit v1.2.3 From 2bcdd8f2c07f1aa1bfd34fa0dab8e06949e34846 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Fri, 19 Jun 2020 09:20:11 +0100 Subject: of/irq: Make of_msi_map_rid() PCI bus agnostic There is nothing PCI bus specific in the of_msi_map_rid() implementation other than the requester ID tag for the input ID space. Rename requester ID to a more generic ID so that the translation code can be used by all busses that require input/output ID translations. No functional change intended. Signed-off-by: Lorenzo Pieralisi Reviewed-by: Rob Herring Cc: Bjorn Helgaas Cc: Rob Herring Cc: Marc Zyngier Link: https://lore.kernel.org/r/20200619082013.13661-11-lorenzo.pieralisi@arm.com Signed-off-by: Catalin Marinas --- include/linux/of_irq.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 7142a3722758..e8b78139f78c 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -55,7 +55,7 @@ extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 id, u32 bus_token); extern void of_msi_configure(struct device *dev, struct device_node *np); -u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in); +u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in); #else static inline int of_irq_count(struct device_node *dev) { @@ -93,10 +93,10 @@ static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev static inline void of_msi_configure(struct device *dev, struct device_node *np) { } -static inline u32 of_msi_map_rid(struct device *dev, - struct device_node *msi_np, u32 rid_in) +static inline u32 of_msi_map_id(struct device *dev, + struct device_node *msi_np, u32 id_in) { - return rid_in; + return id_in; } #endif -- cgit v1.2.3 From 0516c2f6ae6570a0c4a081189d71a48cfadc34a7 Mon Sep 17 00:00:00 2001 From: Daniel Wagner Date: Tue, 28 Jul 2020 18:20:36 +0200 Subject: block: Remove callback typedefs for blk_mq_ops No need to define typedefs for the callbacks, because there is not a single user except blk_mq_ops. Signed-off-by: Daniel Wagner Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 50 ++++++++++++++++++-------------------------------- 1 file changed, 18 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 23230c1d031e..9d2d5ad367a4 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -267,27 +267,9 @@ struct blk_mq_queue_data { bool last; }; -typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, - const struct blk_mq_queue_data *); -typedef void (commit_rqs_fn)(struct blk_mq_hw_ctx *); -typedef bool (get_budget_fn)(struct request_queue *); -typedef void (put_budget_fn)(struct request_queue *); -typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool); -typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int); -typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int); -typedef int (init_request_fn)(struct blk_mq_tag_set *set, struct request *, - unsigned int, unsigned int); -typedef void (exit_request_fn)(struct blk_mq_tag_set *set, struct request *, - unsigned int); - typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, bool); typedef bool (busy_tag_iter_fn)(struct request *, void *, bool); -typedef int (poll_fn)(struct blk_mq_hw_ctx *); -typedef int (map_queues_fn)(struct blk_mq_tag_set *set); -typedef bool (busy_fn)(struct request_queue *); -typedef void (complete_fn)(struct request *); -typedef void (cleanup_rq_fn)(struct request *); /** * struct blk_mq_ops - Callback functions that implements block driver @@ -297,7 +279,8 @@ struct blk_mq_ops { /** * @queue_rq: Queue a new request from block IO. */ - queue_rq_fn *queue_rq; + blk_status_t (*queue_rq)(struct blk_mq_hw_ctx *, + const struct blk_mq_queue_data *); /** * @commit_rqs: If a driver uses bd->last to judge when to submit @@ -306,7 +289,7 @@ struct blk_mq_ops { * purpose of kicking the hardware (which the last request otherwise * would have done). */ - commit_rqs_fn *commit_rqs; + void (*commit_rqs)(struct blk_mq_hw_ctx *); /** * @get_budget: Reserve budget before queue request, once .queue_rq is @@ -314,37 +297,38 @@ struct blk_mq_ops { * reserved budget. Also we have to handle failure case * of .get_budget for avoiding I/O deadlock. */ - get_budget_fn *get_budget; + bool (*get_budget)(struct request_queue *); + /** * @put_budget: Release the reserved budget. */ - put_budget_fn *put_budget; + void (*put_budget)(struct request_queue *); /** * @timeout: Called on request timeout. */ - timeout_fn *timeout; + enum blk_eh_timer_return (*timeout)(struct request *, bool); /** * @poll: Called to poll for completion of a specific tag. */ - poll_fn *poll; + int (*poll)(struct blk_mq_hw_ctx *); /** * @complete: Mark the request as complete. */ - complete_fn *complete; + void (*complete)(struct request *); /** * @init_hctx: Called when the block layer side of a hardware queue has * been set up, allowing the driver to allocate/init matching * structures. */ - init_hctx_fn *init_hctx; + int (*init_hctx)(struct blk_mq_hw_ctx *, void *, unsigned int); /** * @exit_hctx: Ditto for exit/teardown. */ - exit_hctx_fn *exit_hctx; + void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); /** * @init_request: Called for every command allocated by the block layer @@ -353,11 +337,13 @@ struct blk_mq_ops { * Tag greater than or equal to queue_depth is for setting up * flush request. */ - init_request_fn *init_request; + int (*init_request)(struct blk_mq_tag_set *set, struct request *, + unsigned int, unsigned int); /** * @exit_request: Ditto for exit/teardown. */ - exit_request_fn *exit_request; + void (*exit_request)(struct blk_mq_tag_set *set, struct request *, + unsigned int); /** * @initialize_rq_fn: Called from inside blk_get_request(). @@ -368,18 +354,18 @@ struct blk_mq_ops { * @cleanup_rq: Called before freeing one request which isn't completed * yet, and usually for freeing the driver private data. */ - cleanup_rq_fn *cleanup_rq; + void (*cleanup_rq)(struct request *); /** * @busy: If set, returns whether or not this queue currently is busy. */ - busy_fn *busy; + bool (*busy)(struct request_queue *); /** * @map_queues: This allows drivers specify their own queue mapping by * overriding the setup-time function that builds the mq_map. */ - map_queues_fn *map_queues; + int (*map_queues)(struct blk_mq_tag_set *set); #ifdef CONFIG_BLK_DEBUG_FS /** -- cgit v1.2.3 From 5143192cd410c4fc83be09a2e73423765aee072b Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Thu, 23 Jul 2020 15:30:00 -0700 Subject: mm/migrate: add a flags parameter to migrate_vma The src_owner field in struct migrate_vma is being used for two purposes, it acts as a selection filter for which types of pages are to be migrated and it identifies device private pages owned by the caller. Split this into separate parameters so the src_owner field can be used just to identify device private pages owned by the caller of migrate_vma_setup(). Rename the src_owner field to pgmap_owner to reflect it is now used only to identify which device private pages to migrate. Link: https://lore.kernel.org/r/20200723223004.9586-3-rcampbell@nvidia.com Signed-off-by: Ralph Campbell Reviewed-by: Bharata B Rao Signed-off-by: Jason Gunthorpe --- include/linux/migrate.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 3e546cbf03dd..16e03a51e5cf 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -180,6 +180,11 @@ static inline unsigned long migrate_pfn(unsigned long pfn) return (pfn << MIGRATE_PFN_SHIFT) | MIGRATE_PFN_VALID; } +enum migrate_vma_direction { + MIGRATE_VMA_SELECT_SYSTEM = 1 << 0, + MIGRATE_VMA_SELECT_DEVICE_PRIVATE = 1 << 1, +}; + struct migrate_vma { struct vm_area_struct *vma; /* @@ -199,11 +204,11 @@ struct migrate_vma { /* * Set to the owner value also stored in page->pgmap->owner for - * migrating out of device private memory. If set only device - * private pages with this owner are migrated. If not set - * device private pages are not migrated at all. + * migrating out of device private memory. The flags also need to + * be set to MIGRATE_VMA_SELECT_DEVICE_PRIVATE. */ - void *src_owner; + void *pgmap_owner; + unsigned long flags; }; int migrate_vma_setup(struct migrate_vma *args); -- cgit v1.2.3 From 998427b3ad2c769082853880cf353557ec0ec77d Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Thu, 23 Jul 2020 15:30:01 -0700 Subject: mm/notifier: add migration invalidation type Currently migrate_vma_setup() calls mmu_notifier_invalidate_range_start() which flushes all device private page mappings whether or not a page is being migrated to/from device private memory. In order to not disrupt device mappings that are not being migrated, shift the responsibility for clearing device private mappings to the device driver and leave CPU page table unmapping handled by migrate_vma_setup(). To support this, the caller of migrate_vma_setup() should always set struct migrate_vma::pgmap_owner to a non NULL value that matches the device private page->pgmap->owner. This value is then passed to the struct mmu_notifier_range with a new event type which the driver's invalidation function can use to avoid device MMU invalidations. Link: https://lore.kernel.org/r/20200723223004.9586-4-rcampbell@nvidia.com Signed-off-by: Ralph Campbell Signed-off-by: Jason Gunthorpe --- include/linux/migrate.h | 3 +++ include/linux/mmu_notifier.h | 6 ++++++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 16e03a51e5cf..540998d9810b 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -206,6 +206,9 @@ struct migrate_vma { * Set to the owner value also stored in page->pgmap->owner for * migrating out of device private memory. The flags also need to * be set to MIGRATE_VMA_SELECT_DEVICE_PRIVATE. + * The caller should always set this field when using mmu notifier + * callbacks to avoid device MMU invalidations for device private + * pages that are not being migrated. */ void *pgmap_owner; unsigned long flags; diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index fc68f3570e19..c6f0708195cd 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -38,6 +38,10 @@ struct mmu_interval_notifier; * * @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal * that the mm refcount is zero and the range is no longer accessible. + * + * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal + * a device driver to possibly ignore the invalidation if the + * migrate_pgmap_owner field matches the driver's device private pgmap owner. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, @@ -46,6 +50,7 @@ enum mmu_notifier_event { MMU_NOTIFY_PROTECTION_PAGE, MMU_NOTIFY_SOFT_DIRTY, MMU_NOTIFY_RELEASE, + MMU_NOTIFY_MIGRATE, }; #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) @@ -264,6 +269,7 @@ struct mmu_notifier_range { unsigned long end; unsigned flags; enum mmu_notifier_event event; + void *migrate_pgmap_owner; }; static inline int mm_has_notifiers(struct mm_struct *mm) -- cgit v1.2.3 From 7d0314b11cdd92bca8b89684c06953bf114605fc Mon Sep 17 00:00:00 2001 From: Ron Diskin Date: Sun, 5 Apr 2020 13:58:40 +0300 Subject: net/mlx5e: Modify uplink state on interface up/down When setting the PF interface up/down, notify the firmware to update uplink state via MODIFY_VPORT_STATE, when E-Switch is enabled. This behavior will prevent sending traffic out on uplink port when PF is down, such as sending traffic from a VF interface which is still up. Currently when calling mlx5e_open/close(), the driver only sends PAOS command to notify the firmware to set the physical port state to up/down, however, it is not sufficient. When VF is in "auto" state, it follows the uplink state, which was not updated on mlx5e_open/close() before this patch. When switchdev mode is enabled and uplink representor is first enabled, set the uplink port state value back to its FW default "AUTO". Fixes: 63bfd399de55 ("net/mlx5e: Send PAOS command on interface up/down") Signed-off-by: Ron Diskin Reviewed-by: Roi Dayan Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 073b79eacc99..1340e02b14ef 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4381,6 +4381,7 @@ struct mlx5_ifc_query_vport_state_out_bits { enum { MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT = 0x0, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT = 0x1, + MLX5_VPORT_STATE_OP_MOD_UPLINK = 0x2, }; struct mlx5_ifc_arm_monitor_counter_in_bits { -- cgit v1.2.3 From 035bfd051eae5b365368be915dfaf916aa501a52 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 28 Jul 2020 18:38:34 +0200 Subject: net: make sockptr_is_null strict aliasing safe While the kernel in general is not strict aliasing safe we can trivially do that in sockptr_is_null without affecting code generation, so always check the actually assigned union member. Reported-by: Jan Engelhardt Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/sockptr.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 7d5cdb2b30b5..b13ea1422f93 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -64,7 +64,9 @@ static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p) static inline bool sockptr_is_null(sockptr_t sockptr) { - return !sockptr.user && !sockptr.kernel; + if (sockptr_is_kernel(sockptr)) + return !sockptr.kernel; + return !sockptr.user; } static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) -- cgit v1.2.3 From d3c48151512922dd35f1f393b30b9138e4441d14 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 28 Jul 2020 18:38:35 +0200 Subject: net: remove sockptr_advance sockptr_advance never properly worked. Replace it with _offset variants of copy_from_sockptr and copy_to_sockptr. Fixes: ba423fdaa589 ("net: add a new sockptr_t type") Reported-by: Jason A. Donenfeld Reported-by: Ido Schimmel Signed-off-by: Christoph Hellwig Acked-by: Jason A. Donenfeld Tested-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/sockptr.h | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index b13ea1422f93..9e6c81d474cb 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -69,19 +69,26 @@ static inline bool sockptr_is_null(sockptr_t sockptr) return !sockptr.user; } -static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) +static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, + size_t offset, size_t size) { if (!sockptr_is_kernel(src)) - return copy_from_user(dst, src.user, size); - memcpy(dst, src.kernel, size); + return copy_from_user(dst, src.user + offset, size); + memcpy(dst, src.kernel + offset, size); return 0; } -static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) +static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) +{ + return copy_from_sockptr_offset(dst, src, 0, size); +} + +static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, + const void *src, size_t size) { if (!sockptr_is_kernel(dst)) - return copy_to_user(dst.user, src, size); - memcpy(dst.kernel, src, size); + return copy_to_user(dst.user + offset, src, size); + memcpy(dst.kernel + offset, src, size); return 0; } @@ -112,14 +119,6 @@ static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) return p; } -static inline void sockptr_advance(sockptr_t sockptr, size_t len) -{ - if (sockptr_is_kernel(sockptr)) - sockptr.kernel += len; - else - sockptr.user += len; -} - static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) { if (sockptr_is_kernel(src)) { -- cgit v1.2.3 From a31edb2059ed4e498f9aa8230c734b59d0ad797a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 28 Jul 2020 18:38:36 +0200 Subject: net: improve the user pointer check in init_user_sockptr Make sure not just the pointer itself but the whole range lies in the user address space. For that pass the length and then use the access_ok helper to do the check. Fixes: 6d04fe15f78a ("net: optimize the sockptr_t for unified kernel/user address spaces") Reported-by: David Laight Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/sockptr.h | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 9e6c81d474cb..96840def9d69 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -27,14 +27,6 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p }; } - -static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p) -{ - if ((unsigned long)p >= TASK_SIZE) - return -EFAULT; - sp->user = p; - return 0; -} #else /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ typedef struct { union { @@ -53,14 +45,16 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p, .is_kernel = true }; } +#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ -static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p) +static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p, + size_t size) { - sp->user = p; - sp->is_kernel = false; + if (!access_ok(p, size)) + return -EFAULT; + *sp = (sockptr_t) { .user = p }; return 0; } -#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ static inline bool sockptr_is_null(sockptr_t sockptr) { -- cgit v1.2.3 From 2f96593ecc37e98bf99525f0629128080533867f Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 28 Jul 2020 23:36:55 +0800 Subject: of_address: Add bus type match for pci ranges parser So the parser can be used to parse range property of ISA bus. As they're all using PCI-like method of range property, there is no need start a new parser. Signed-off-by: Jiaxun Yang Reviewed-by: Rob Herring Signed-off-by: Thomas Bogendoerfer --- include/linux/of_address.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 763022ed3456..88bc943405cd 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -6,8 +6,11 @@ #include #include +struct of_bus; + struct of_pci_range_parser { struct device_node *node; + struct of_bus *bus; const __be32 *range; const __be32 *end; int na; @@ -119,6 +122,7 @@ static inline void __iomem *of_iomap(struct device_node *device, int index) return NULL; } #endif +#define of_range_parser_init of_pci_range_parser_init #if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_PCI) extern const __be32 *of_get_pci_address(struct device_node *dev, int bar_no, -- cgit v1.2.3 From b8265621f4888af9494e1d685620871ec81bc33d Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Thu, 23 Jul 2020 17:21:59 -0700 Subject: Add pldmfw library for PLDM firmware update The pldmfw library is used to implement common logic needed to flash devices based on firmware files using the format described by the PLDM for Firmware Update standard. This library consists of logic to parse the PLDM file format from a firmware file object, as well as common logic for sending the relevant PLDM header data to the device firmware. A simple ops table is provided so that device drivers can implement device specific hardware interactions while keeping the common logic to the pldmfw library. This library will be used by the Intel ice networking driver as part of implementing device flash update via devlink. The library aims to be vendor and device agnostic. For this reason, it has been placed in lib/pldmfw, in the hopes that other devices which use the PLDM firmware file format may benefit from it in the future. However, do note that not all features defined in the PLDM standard have been implemented. Signed-off-by: Jacob Keller Signed-off-by: David S. Miller --- include/linux/pldmfw.h | 165 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 165 insertions(+) create mode 100644 include/linux/pldmfw.h (limited to 'include/linux') diff --git a/include/linux/pldmfw.h b/include/linux/pldmfw.h new file mode 100644 index 000000000000..0fc831338226 --- /dev/null +++ b/include/linux/pldmfw.h @@ -0,0 +1,165 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2018-2019, Intel Corporation. */ + +#ifndef _PLDMFW_H_ +#define _PLDMFW_H_ + +#include +#include + +#define PLDM_DEVICE_UPDATE_CONTINUE_AFTER_FAIL BIT(0) + +#define PLDM_STRING_TYPE_UNKNOWN 0 +#define PLDM_STRING_TYPE_ASCII 1 +#define PLDM_STRING_TYPE_UTF8 2 +#define PLDM_STRING_TYPE_UTF16 3 +#define PLDM_STRING_TYPE_UTF16LE 4 +#define PLDM_STRING_TYPE_UTF16BE 5 + +struct pldmfw_record { + struct list_head entry; + + /* List of descriptor TLVs */ + struct list_head descs; + + /* Component Set version string*/ + const u8 *version_string; + u8 version_type; + u8 version_len; + + /* Package Data length */ + u16 package_data_len; + + /* Bitfield of Device Update Flags */ + u32 device_update_flags; + + /* Package Data block */ + const u8 *package_data; + + /* Bitmap of components applicable to this record */ + unsigned long *component_bitmap; + u16 component_bitmap_len; +}; + +/* Standard descriptor TLV identifiers */ +#define PLDM_DESC_ID_PCI_VENDOR_ID 0x0000 +#define PLDM_DESC_ID_IANA_ENTERPRISE_ID 0x0001 +#define PLDM_DESC_ID_UUID 0x0002 +#define PLDM_DESC_ID_PNP_VENDOR_ID 0x0003 +#define PLDM_DESC_ID_ACPI_VENDOR_ID 0x0004 +#define PLDM_DESC_ID_PCI_DEVICE_ID 0x0100 +#define PLDM_DESC_ID_PCI_SUBVENDOR_ID 0x0101 +#define PLDM_DESC_ID_PCI_SUBDEV_ID 0x0102 +#define PLDM_DESC_ID_PCI_REVISION_ID 0x0103 +#define PLDM_DESC_ID_PNP_PRODUCT_ID 0x0104 +#define PLDM_DESC_ID_ACPI_PRODUCT_ID 0x0105 +#define PLDM_DESC_ID_VENDOR_DEFINED 0xFFFF + +struct pldmfw_desc_tlv { + struct list_head entry; + + const u8 *data; + u16 type; + u16 size; +}; + +#define PLDM_CLASSIFICATION_UNKNOWN 0x0000 +#define PLDM_CLASSIFICATION_OTHER 0x0001 +#define PLDM_CLASSIFICATION_DRIVER 0x0002 +#define PLDM_CLASSIFICATION_CONFIG_SW 0x0003 +#define PLDM_CLASSIFICATION_APP_SW 0x0004 +#define PLDM_CLASSIFICATION_INSTRUMENTATION 0x0005 +#define PLDM_CLASSIFICATION_BIOS 0x0006 +#define PLDM_CLASSIFICATION_DIAGNOSTIC_SW 0x0007 +#define PLDM_CLASSIFICATION_OS 0x0008 +#define PLDM_CLASSIFICATION_MIDDLEWARE 0x0009 +#define PLDM_CLASSIFICATION_FIRMWARE 0x000A +#define PLDM_CLASSIFICATION_CODE 0x000B +#define PLDM_CLASSIFICATION_SERVICE_PACK 0x000C +#define PLDM_CLASSIFICATION_SOFTWARE_BUNDLE 0x000D + +#define PLDM_ACTIVATION_METHOD_AUTO BIT(0) +#define PLDM_ACTIVATION_METHOD_SELF_CONTAINED BIT(1) +#define PLDM_ACTIVATION_METHOD_MEDIUM_SPECIFIC BIT(2) +#define PLDM_ACTIVATION_METHOD_REBOOT BIT(3) +#define PLDM_ACTIVATION_METHOD_DC_CYCLE BIT(4) +#define PLDM_ACTIVATION_METHOD_AC_CYCLE BIT(5) + +#define PLDMFW_COMPONENT_OPTION_FORCE_UPDATE BIT(0) +#define PLDMFW_COMPONENT_OPTION_USE_COMPARISON_STAMP BIT(1) + +struct pldmfw_component { + struct list_head entry; + + /* component identifier */ + u16 classification; + u16 identifier; + + u16 options; + u16 activation_method; + + u32 comparison_stamp; + + u32 component_size; + const u8 *component_data; + + /* Component version string */ + const u8 *version_string; + u8 version_type; + u8 version_len; + + /* component index */ + u8 index; + +}; + +/* Transfer flag used for sending components to the firmware */ +#define PLDM_TRANSFER_FLAG_START BIT(0) +#define PLDM_TRANSFER_FLAG_MIDDLE BIT(1) +#define PLDM_TRANSFER_FLAG_END BIT(2) + +struct pldmfw_ops; + +/* Main entry point to the PLDM firmware update engine. Device drivers + * should embed this in a private structure and use container_of to obtain + * a pointer to their own data, used to implement the device specific + * operations. + */ +struct pldmfw { + const struct pldmfw_ops *ops; + struct device *dev; +}; + +bool pldmfw_op_pci_match_record(struct pldmfw *context, struct pldmfw_record *record); + +/* Operations invoked by the generic PLDM firmware update engine. Used to + * implement device specific logic. + * + * @match_record: check if the device matches the given record. For + * convenience, a standard implementation is provided for PCI devices. + * + * @send_package_data: send the package data associated with the matching + * record to firmware. + * + * @send_component_table: send the component data associated with a given + * component to firmware. Called once for each applicable component. + * + * @flash_component: Flash the data for a given component to the device. + * Called once for each applicable component, after all component tables have + * been sent. + * + * @finalize_update: (optional) Finish the update. Called after all components + * have been flashed. + */ +struct pldmfw_ops { + bool (*match_record)(struct pldmfw *context, struct pldmfw_record *record); + int (*send_package_data)(struct pldmfw *context, const u8 *data, u16 length); + int (*send_component_table)(struct pldmfw *context, struct pldmfw_component *component, + u8 transfer_flag); + int (*flash_component)(struct pldmfw *context, struct pldmfw_component *component); + int (*finalize_update)(struct pldmfw *context); +}; + +int pldmfw_flash_image(struct pldmfw *context, const struct firmware *fw); + +#endif -- cgit v1.2.3 From 1748f6a2cbc4694523f16da1c892b59861045b9d Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 24 Jul 2020 20:12:53 +1000 Subject: rhashtable: Fix unprotected RCU dereference in __rht_ptr The rcu_dereference call in rht_ptr_rcu is completely bogus because we've already dereferenced the value in __rht_ptr and operated on it. This causes potential double readings which could be fatal. The RCU dereference must occur prior to the comparison in __rht_ptr. This patch changes the order of RCU dereference so that it is done first and the result is then fed to __rht_ptr. The RCU marking changes have been minimised using casts which will be removed in a follow-up patch. Fixes: ba6306e3f648 ("rhashtable: Remove RCU marking from...") Reported-by: "Gong, Sishuai" Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index d3432ee65de7..b8feb5da7c5a 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -349,11 +349,11 @@ static inline void rht_unlock(struct bucket_table *tbl, local_bh_enable(); } -static inline struct rhash_head __rcu *__rht_ptr( - struct rhash_lock_head *const *bkt) +static inline struct rhash_head *__rht_ptr( + struct rhash_lock_head *p, struct rhash_lock_head __rcu *const *bkt) { - return (struct rhash_head __rcu *) - ((unsigned long)*bkt & ~BIT(0) ?: + return (struct rhash_head *) + ((unsigned long)p & ~BIT(0) ?: (unsigned long)RHT_NULLS_MARKER(bkt)); } @@ -365,25 +365,26 @@ static inline struct rhash_head __rcu *__rht_ptr( * access is guaranteed, such as when destroying the table. */ static inline struct rhash_head *rht_ptr_rcu( - struct rhash_lock_head *const *bkt) + struct rhash_lock_head *const *p) { - struct rhash_head __rcu *p = __rht_ptr(bkt); - - return rcu_dereference(p); + struct rhash_lock_head __rcu *const *bkt = (void *)p; + return __rht_ptr(rcu_dereference(*bkt), bkt); } static inline struct rhash_head *rht_ptr( - struct rhash_lock_head *const *bkt, + struct rhash_lock_head *const *p, struct bucket_table *tbl, unsigned int hash) { - return rht_dereference_bucket(__rht_ptr(bkt), tbl, hash); + struct rhash_lock_head __rcu *const *bkt = (void *)p; + return __rht_ptr(rht_dereference_bucket(*bkt, tbl, hash), bkt); } static inline struct rhash_head *rht_ptr_exclusive( - struct rhash_lock_head *const *bkt) + struct rhash_lock_head *const *p) { - return rcu_dereference_protected(__rht_ptr(bkt), 1); + struct rhash_lock_head __rcu *const *bkt = (void *)p; + return __rht_ptr(rcu_dereference_protected(*bkt, 1), bkt); } static inline void rht_assign_locked(struct rhash_lock_head **bkt, -- cgit v1.2.3 From ce9b362bf6db51a083c4221ef0f93c16cfb1facf Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 24 Jul 2020 20:14:34 +1000 Subject: rhashtable: Restore RCU marking on rhash_lock_head This patch restores the RCU marking on bucket_table->buckets as it really does need RCU protection. Its removal had led to a fatal bug. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 56 ++++++++++++++++++++-------------------------- 1 file changed, 24 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index b8feb5da7c5a..68dab3e08aad 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -84,7 +84,7 @@ struct bucket_table { struct lockdep_map dep_map; - struct rhash_lock_head *buckets[] ____cacheline_aligned_in_smp; + struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; /* @@ -261,13 +261,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, void *arg); void rhashtable_destroy(struct rhashtable *ht); -struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash); -struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash); -struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht, - struct bucket_table *tbl, - unsigned int hash); +struct rhash_lock_head __rcu **rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash); +struct rhash_lock_head __rcu **__rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash); +struct rhash_lock_head __rcu **rht_bucket_nested_insert( + struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash); #define rht_dereference(p, ht) \ rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht)) @@ -284,21 +283,21 @@ struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht, #define rht_entry(tpos, pos, member) \ ({ tpos = container_of(pos, typeof(*tpos), member); 1; }) -static inline struct rhash_lock_head *const *rht_bucket( +static inline struct rhash_lock_head __rcu *const *rht_bucket( const struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } -static inline struct rhash_lock_head **rht_bucket_var( +static inline struct rhash_lock_head __rcu **rht_bucket_var( struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } -static inline struct rhash_lock_head **rht_bucket_insert( +static inline struct rhash_lock_head __rcu **rht_bucket_insert( struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) : @@ -325,7 +324,7 @@ static inline struct rhash_lock_head **rht_bucket_insert( */ static inline void rht_lock(struct bucket_table *tbl, - struct rhash_lock_head **bkt) + struct rhash_lock_head __rcu **bkt) { local_bh_disable(); bit_spin_lock(0, (unsigned long *)bkt); @@ -333,7 +332,7 @@ static inline void rht_lock(struct bucket_table *tbl, } static inline void rht_lock_nested(struct bucket_table *tbl, - struct rhash_lock_head **bucket, + struct rhash_lock_head __rcu **bucket, unsigned int subclass) { local_bh_disable(); @@ -342,7 +341,7 @@ static inline void rht_lock_nested(struct bucket_table *tbl, } static inline void rht_unlock(struct bucket_table *tbl, - struct rhash_lock_head **bkt) + struct rhash_lock_head __rcu **bkt) { lock_map_release(&tbl->dep_map); bit_spin_unlock(0, (unsigned long *)bkt); @@ -365,48 +364,41 @@ static inline struct rhash_head *__rht_ptr( * access is guaranteed, such as when destroying the table. */ static inline struct rhash_head *rht_ptr_rcu( - struct rhash_lock_head *const *p) + struct rhash_lock_head __rcu *const *bkt) { - struct rhash_lock_head __rcu *const *bkt = (void *)p; return __rht_ptr(rcu_dereference(*bkt), bkt); } static inline struct rhash_head *rht_ptr( - struct rhash_lock_head *const *p, + struct rhash_lock_head __rcu *const *bkt, struct bucket_table *tbl, unsigned int hash) { - struct rhash_lock_head __rcu *const *bkt = (void *)p; return __rht_ptr(rht_dereference_bucket(*bkt, tbl, hash), bkt); } static inline struct rhash_head *rht_ptr_exclusive( - struct rhash_lock_head *const *p) + struct rhash_lock_head __rcu *const *bkt) { - struct rhash_lock_head __rcu *const *bkt = (void *)p; return __rht_ptr(rcu_dereference_protected(*bkt, 1), bkt); } -static inline void rht_assign_locked(struct rhash_lock_head **bkt, +static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt, struct rhash_head *obj) { - struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; - if (rht_is_a_nulls(obj)) obj = NULL; - rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(0))); + rcu_assign_pointer(*bkt, (void *)((unsigned long)obj | BIT(0))); } static inline void rht_assign_unlock(struct bucket_table *tbl, - struct rhash_lock_head **bkt, + struct rhash_lock_head __rcu **bkt, struct rhash_head *obj) { - struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; - if (rht_is_a_nulls(obj)) obj = NULL; lock_map_release(&tbl->dep_map); - rcu_assign_pointer(*p, obj); + rcu_assign_pointer(*bkt, (void *)obj); preempt_enable(); __release(bitlock); local_bh_enable(); @@ -594,7 +586,7 @@ static inline struct rhash_head *__rhashtable_lookup( .ht = ht, .key = key, }; - struct rhash_lock_head *const *bkt; + struct rhash_lock_head __rcu *const *bkt; struct bucket_table *tbl; struct rhash_head *he; unsigned int hash; @@ -710,7 +702,7 @@ static inline void *__rhashtable_insert_fast( .ht = ht, .key = key, }; - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct bucket_table *tbl; struct rhash_head *head; @@ -996,7 +988,7 @@ static inline int __rhashtable_remove_fast_one( struct rhash_head *obj, const struct rhashtable_params params, bool rhlist) { - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; unsigned int hash; @@ -1148,7 +1140,7 @@ static inline int __rhashtable_replace_fast( struct rhash_head *obj_old, struct rhash_head *obj_new, const struct rhashtable_params params) { - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; unsigned int hash; -- cgit v1.2.3 From 2f3ee5e481ce850b5b51a306b01a5e9187b206ae Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 24 Jul 2020 13:11:42 -0500 Subject: remoteproc: kill IPA notify code The IPA code now uses the generic remoteproc SSR notification mechanism. This makes the original IPA notification code unused and unnecessary, so get rid of it. This is effectively a revert of commit d7f5f3c89c1a ("remoteproc: add IPA notification to q6v5 driver"). Reviewed-by: Bjorn Andersson Signed-off-by: Alex Elder Link: https://lore.kernel.org/r/20200724181142.13581-3-elder@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/remoteproc/qcom_q6v5_ipa_notify.h | 82 ------------------------- 1 file changed, 82 deletions(-) delete mode 100644 include/linux/remoteproc/qcom_q6v5_ipa_notify.h (limited to 'include/linux') diff --git a/include/linux/remoteproc/qcom_q6v5_ipa_notify.h b/include/linux/remoteproc/qcom_q6v5_ipa_notify.h deleted file mode 100644 index 0820edc0ab7d..000000000000 --- a/include/linux/remoteproc/qcom_q6v5_ipa_notify.h +++ /dev/null @@ -1,82 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Copyright (C) 2019 Linaro Ltd. */ - -#ifndef __QCOM_Q6V5_IPA_NOTIFY_H__ -#define __QCOM_Q6V5_IPA_NOTIFY_H__ - -#if IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) - -#include - -enum qcom_rproc_event { - MODEM_STARTING = 0, /* Modem is about to be started */ - MODEM_RUNNING = 1, /* Startup complete; modem is operational */ - MODEM_STOPPING = 2, /* Modem is about to shut down */ - MODEM_CRASHED = 3, /* Modem has crashed (implies stopping) */ - MODEM_OFFLINE = 4, /* Modem is now offline */ - MODEM_REMOVING = 5, /* Modem is about to be removed */ -}; - -typedef void (*qcom_ipa_notify_t)(void *data, enum qcom_rproc_event event); - -struct qcom_rproc_ipa_notify { - struct rproc_subdev subdev; - - qcom_ipa_notify_t notify; - void *data; -}; - -/** - * qcom_add_ipa_notify_subdev() - Register IPA notification subdevice - * @rproc: rproc handle - * @ipa_notify: IPA notification subdevice handle - * - * Register the @ipa_notify subdevice with the @rproc so modem events - * can be sent to IPA when they occur. - * - * This is defined in "qcom_q6v5_ipa_notify.c". - */ -void qcom_add_ipa_notify_subdev(struct rproc *rproc, - struct qcom_rproc_ipa_notify *ipa_notify); - -/** - * qcom_remove_ipa_notify_subdev() - Remove IPA SSR subdevice - * @rproc: rproc handle - * @ipa_notify: IPA notification subdevice handle - * - * This is defined in "qcom_q6v5_ipa_notify.c". - */ -void qcom_remove_ipa_notify_subdev(struct rproc *rproc, - struct qcom_rproc_ipa_notify *ipa_notify); - -/** - * qcom_register_ipa_notify() - Register IPA notification function - * @rproc: Remote processor handle - * @notify: Non-null IPA notification callback function pointer - * @data: Data supplied to IPA notification callback function - * - * @Return: 0 if successful, or a negative error code otherwise - * - * This is defined in "qcom_q6v5_mss.c". - */ -int qcom_register_ipa_notify(struct rproc *rproc, qcom_ipa_notify_t notify, - void *data); -/** - * qcom_deregister_ipa_notify() - Deregister IPA notification function - * @rproc: Remote processor handle - * - * This is defined in "qcom_q6v5_mss.c". - */ -void qcom_deregister_ipa_notify(struct rproc *rproc); - -#else /* !IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) */ - -struct qcom_rproc_ipa_notify { /* empty */ }; - -#define qcom_add_ipa_notify_subdev(rproc, ipa_notify) /* no-op */ -#define qcom_remove_ipa_notify_subdev(rproc, ipa_notify) /* no-op */ - -#endif /* !IS_ENABLED(CONFIG_QCOM_Q6V5_IPA_NOTIFY) */ - -#endif /* !__QCOM_Q6V5_IPA_NOTIFY_H__ */ -- cgit v1.2.3 From 48001ea50d17f3eb06a552e9ecf21f7fc01b25da Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:08:18 -0700 Subject: PM, libnvdimm: Add runtime firmware activation support Abstract platform specific mechanics for nvdimm firmware activation behind a handful of generic ops. At the bus level ->activate_state() indicates the unified state (idle, busy, armed) of all DIMMs on the bus, and ->capability() indicates the system state expectations for activate. At the DIMM level ->activate_state() indicates the per-DIMM state, ->activate_result() indicates the outcome of the last activation attempt, and ->arm() attempts to transition the DIMM from 'idle' to 'armed'. A new hibernate_quiet_exec() facility is added to support firmware activation in an OS defined system quiesce state. It leverages the fact that the hibernate-freeze state wants to assert that a memory hibernation snapshot can be taken. This is in contrast to a platform firmware defined quiesce state that may forcefully quiet the memory controller independent of whether an individual device-driver properly supports hibernate-freeze. The libnvdimm sysfs interface is extended to support detection of a firmware activate capability. The mechanism supports enumeration and triggering of firmware activate, optionally in the hibernate_quiet_exec() context. [rafael: hibernate_quiet_exec() proposal] [vishal: fix up sparse warning, grammar in Documentation/] Cc: Pavel Machek Cc: Ira Weiny Cc: Len Brown Cc: Jonathan Corbet Cc: Dave Jiang Cc: Vishal Verma Reported-by: kernel test robot Co-developed-by: "Rafael J. Wysocki" Signed-off-by: "Rafael J. Wysocki" Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- include/linux/libnvdimm.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/suspend.h | 6 ++++++ 2 files changed, 50 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index ad9898ece7d3..15dbcb718316 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -86,6 +86,7 @@ struct nvdimm_bus_descriptor { int (*flush_probe)(struct nvdimm_bus_descriptor *nd_desc); int (*clear_to_send)(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, unsigned int cmd, void *data); + const struct nvdimm_bus_fw_ops *fw_ops; }; struct nd_cmd_desc { @@ -200,6 +201,49 @@ struct nvdimm_security_ops { int (*query_overwrite)(struct nvdimm *nvdimm); }; +enum nvdimm_fwa_state { + NVDIMM_FWA_INVALID, + NVDIMM_FWA_IDLE, + NVDIMM_FWA_ARMED, + NVDIMM_FWA_BUSY, + NVDIMM_FWA_ARM_OVERFLOW, +}; + +enum nvdimm_fwa_trigger { + NVDIMM_FWA_ARM, + NVDIMM_FWA_DISARM, +}; + +enum nvdimm_fwa_capability { + NVDIMM_FWA_CAP_INVALID, + NVDIMM_FWA_CAP_NONE, + NVDIMM_FWA_CAP_QUIESCE, + NVDIMM_FWA_CAP_LIVE, +}; + +enum nvdimm_fwa_result { + NVDIMM_FWA_RESULT_INVALID, + NVDIMM_FWA_RESULT_NONE, + NVDIMM_FWA_RESULT_SUCCESS, + NVDIMM_FWA_RESULT_NOTSTAGED, + NVDIMM_FWA_RESULT_NEEDRESET, + NVDIMM_FWA_RESULT_FAIL, +}; + +struct nvdimm_bus_fw_ops { + enum nvdimm_fwa_state (*activate_state) + (struct nvdimm_bus_descriptor *nd_desc); + enum nvdimm_fwa_capability (*capability) + (struct nvdimm_bus_descriptor *nd_desc); + int (*activate)(struct nvdimm_bus_descriptor *nd_desc); +}; + +struct nvdimm_fw_ops { + enum nvdimm_fwa_state (*activate_state)(struct nvdimm *nvdimm); + enum nvdimm_fwa_result (*activate_result)(struct nvdimm *nvdimm); + int (*arm)(struct nvdimm *nvdimm, enum nvdimm_fwa_trigger arg); +}; + void badrange_init(struct badrange *badrange); int badrange_add(struct badrange *badrange, u64 addr, u64 length); void badrange_forget(struct badrange *badrange, phys_addr_t start, diff --git a/include/linux/suspend.h b/include/linux/suspend.h index b960098acfb0..cb9afad82a90 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -453,6 +453,8 @@ extern bool hibernation_available(void); asmlinkage int swsusp_save(void); extern struct pbe *restore_pblist; int pfn_is_nosave(unsigned long pfn); + +int hibernate_quiet_exec(int (*func)(void *data), void *data); #else /* CONFIG_HIBERNATION */ static inline void register_nosave_region(unsigned long b, unsigned long e) {} static inline void register_nosave_region_late(unsigned long b, unsigned long e) {} @@ -464,6 +466,10 @@ static inline void hibernation_set_ops(const struct platform_hibernation_ops *op static inline int hibernate(void) { return -ENOSYS; } static inline bool system_entering_hibernation(void) { return false; } static inline bool hibernation_available(void) { return false; } + +static inline int hibernate_quiet_exec(int (*func)(void *data), void *data) { + return -ENOTSUPP; +} #endif /* CONFIG_HIBERNATION */ #ifdef CONFIG_HIBERNATION_SNAPSHOT_DEV -- cgit v1.2.3 From a1facc1fffc17a65e2c12a8de7434b9325ec0324 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:08:24 -0700 Subject: ACPI: NFIT: Add runtime firmware activate support Plumb the platform specific backend for the generic libnvdimm firmware activate interface. Register dimm level operations to arm/disarm activation, and register bus level operations to report the dynamic platform-quiesce time relative to the number of dimms armed for firmware activation. A new nfit-specific bus attribute "firmware_activate_noidle" is added to allow the activation to switch between platform enforced, and OS opportunistic device quiesce. In other words, let the hibernate cycle handle in-flight device-dma rather than the platform attempting to increase PCI-E timeouts and the like. Cc: Dave Jiang Cc: Ira Weiny Cc: Vishal Verma Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- include/linux/libnvdimm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 15dbcb718316..01f251b6e36c 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -269,14 +269,15 @@ struct nvdimm *__nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data, const struct attribute_group **groups, unsigned long flags, unsigned long cmd_mask, int num_flush, struct resource *flush_wpq, const char *dimm_id, - const struct nvdimm_security_ops *sec_ops); + const struct nvdimm_security_ops *sec_ops, + const struct nvdimm_fw_ops *fw_ops); static inline struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data, const struct attribute_group **groups, unsigned long flags, unsigned long cmd_mask, int num_flush, struct resource *flush_wpq) { return __nvdimm_create(nvdimm_bus, provider_data, groups, flags, - cmd_mask, num_flush, flush_wpq, NULL, NULL); + cmd_mask, num_flush, flush_wpq, NULL, NULL, NULL); } const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd); -- cgit v1.2.3 From fe5e26a70cc544004b9aa9c3b96cb1d1cc132e09 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:30:15 -0700 Subject: nvme-fc: drop a duplicated word in a comment Drop the repeated word "a" in a comment. Signed-off-by: Randy Dunlap Signed-off-by: Christoph Hellwig --- include/linux/nvme-fc-driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 41e7795a3ee4..2a38f2b477a5 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -672,7 +672,7 @@ enum { * Values set by the LLDD indicating completion status of the FCP operation. * Must be set prior to calling the done() callback. * @transferred_length: amount of DATA_OUT payload data received by a - * a WRITEDATA operation. If not a WRITEDATA operation, value must + * WRITEDATA operation. If not a WRITEDATA operation, value must * be set to 0. Should equal transfer_length on success. * @fcp_error: status of the FCP operation. Must be 0 on success; on failure * must be a NVME_SC_FC_xxxx value. -- cgit v1.2.3 From c1fef73f793b7fd9d2ffcb5ef85807ea55bf7adb Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Fri, 24 Jul 2020 11:25:17 -0600 Subject: nvmet: add passthru code to process commands Add passthru command handling capability for the NVMeOF target and export passthru APIs which are used to integrate passthru code with nvmet-core. The new file passthru.c handles passthru cmd parsing and execution. In the passthru mode, we create a block layer request from the nvmet request and map the data on to the block layer request. Admin commands and features are on an allow list as there are a number of each that don't make too much sense with passthrough. We use an allow list such that new commands can be considered before being blindly passed through. In both cases, vendor specific commands are always allowed. We also reject reservation IO commands as the underlying device cannot differentiate between multiple hosts behind a fabric. Based-on-a-patch-by: Chaitanya Kulkarni Signed-off-by: Logan Gunthorpe Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 1643005d21e3..d92535997687 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -312,6 +312,7 @@ enum { NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, NVME_CTRL_ONCS_DSM = 1 << 2, NVME_CTRL_ONCS_WRITE_ZEROES = 1 << 3, + NVME_CTRL_ONCS_RESERVATIONS = 1 << 5, NVME_CTRL_ONCS_TIMESTAMP = 1 << 6, NVME_CTRL_VWC_PRESENT = 1 << 0, NVME_CTRL_OACS_SEC_SUPP = 1 << 0, @@ -982,6 +983,7 @@ enum nvme_admin_opcode { nvme_admin_security_recv = 0x82, nvme_admin_sanitize_nvm = 0x84, nvme_admin_get_lba_status = 0x86, + nvme_admin_vendor_start = 0xC0, }; #define nvme_admin_opcode_name(opcode) { opcode, #opcode } @@ -1045,6 +1047,8 @@ enum { NVME_FEAT_RESV_MASK = 0x82, NVME_FEAT_RESV_PERSIST = 0x83, NVME_FEAT_WRITE_PROTECT = 0x84, + NVME_FEAT_VENDOR_START = 0xC0, + NVME_FEAT_VENDOR_END = 0xFF, NVME_LOG_ERROR = 0x01, NVME_LOG_SMART = 0x02, NVME_LOG_FW_SLOT = 0x03, -- cgit v1.2.3 From 13685c4a08fca9dd76bf53bfcbadc044ab2a08cb Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Thu, 16 Jul 2020 12:03:45 +0100 Subject: sched/uclamp: Add a new sysctl to control RT default boost value RT tasks by default run at the highest capacity/performance level. When uclamp is selected this default behavior is retained by enforcing the requested uclamp.min (p->uclamp_req[UCLAMP_MIN]) of the RT tasks to be uclamp_none(UCLAMP_MAX), which is SCHED_CAPACITY_SCALE; the maximum value. This is also referred to as 'the default boost value of RT tasks'. See commit 1a00d999971c ("sched/uclamp: Set default clamps for RT tasks"). On battery powered devices, it is desired to control this default (currently hardcoded) behavior at runtime to reduce energy consumed by RT tasks. For example, a mobile device manufacturer where big.LITTLE architecture is dominant, the performance of the little cores varies across SoCs, and on high end ones the big cores could be too power hungry. Given the diversity of SoCs, the new knob allows manufactures to tune the best performance/power for RT tasks for the particular hardware they run on. They could opt to further tune the value when the user selects a different power saving mode or when the device is actively charging. The runtime aspect of it further helps in creating a single kernel image that can be run on multiple devices that require different tuning. Keep in mind that a lot of RT tasks in the system are created by the kernel. On Android for instance I can see over 50 RT tasks, only a handful of which created by the Android framework. To control the default behavior globally by system admins and device integrator, introduce the new sysctl_sched_uclamp_util_min_rt_default to change the default boost value of the RT tasks. I anticipate this to be mostly in the form of modifying the init script of a particular device. To avoid polluting the fast path with unnecessary code, the approach taken is to synchronously do the update by traversing all the existing tasks in the system. This could race with a concurrent fork(), which is dealt with by introducing sched_post_fork() function which will ensure the racy fork will get the right update applied. Tested on Juno-r2 in combination with the RT capacity awareness [1]. By default an RT task will go to the highest capacity CPU and run at the maximum frequency, which is particularly energy inefficient on high end mobile devices because the biggest core[s] are 'huge' and power hungry. With this patch the RT task can be controlled to run anywhere by default, and doesn't cause the frequency to be maximum all the time. Yet any task that really needs to be boosted can easily escape this default behavior by modifying its requested uclamp.min value (p->uclamp_req[UCLAMP_MIN]) via sched_setattr() syscall. [1] 804d402fb6f6: ("sched/rt: Make RT capacity-aware") Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200716110347.19553-2-qais.yousef@arm.com --- include/linux/sched.h | 10 ++++++++-- include/linux/sched/sysctl.h | 1 + include/linux/sched/task.h | 1 + 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index adf0125190d4..a6bf77c34687 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -686,9 +686,15 @@ struct task_struct { struct sched_dl_entity dl; #ifdef CONFIG_UCLAMP_TASK - /* Clamp values requested for a scheduling entity */ + /* + * Clamp values requested for a scheduling entity. + * Must be updated with task_rq_lock() held. + */ struct uclamp_se uclamp_req[UCLAMP_CNT]; - /* Effective clamp values used for a scheduling entity */ + /* + * Effective clamp values used for a scheduling entity. + * Must be updated with task_rq_lock() held. + */ struct uclamp_se uclamp[UCLAMP_CNT]; #endif diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 24be30a40814..3c31ba88aca5 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -67,6 +67,7 @@ extern unsigned int sysctl_sched_dl_period_min; #ifdef CONFIG_UCLAMP_TASK extern unsigned int sysctl_sched_uclamp_util_min; extern unsigned int sysctl_sched_uclamp_util_max; +extern unsigned int sysctl_sched_uclamp_util_min_rt_default; #endif #ifdef CONFIG_CFS_BANDWIDTH diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 38359071236a..e7ddab095baf 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -55,6 +55,7 @@ extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); +extern void sched_post_fork(struct task_struct *p); extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); -- cgit v1.2.3 From f891f19736bdf404845f97d8038054be37160ea8 Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Wed, 29 Jul 2020 17:09:19 +0530 Subject: kexec_file: Allow archs to handle special regions while locating memory hole Some architectures may have special memory regions, within the given memory range, which can't be used for the buffer in a kexec segment. Implement weak arch_kexec_locate_mem_hole() definition which arch code may override, to take care of special regions, while trying to locate a memory hole. Also, add the missing declarations for arch overridable functions and and drop the __weak descriptors in the declarations to avoid non-weak definitions from becoming weak. Signed-off-by: Hari Bathini Tested-by: Pingfan Liu Reviewed-by: Thiago Jung Bauermann Acked-by: Dave Young Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/159602273603.575379.17665852963340380839.stgit@hbathini --- include/linux/kexec.h | 29 ++++++++++++++++++----------- 1 file changed, 18 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index ea67910ae6b7..9e93bef52968 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -183,17 +183,24 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, bool get_value); void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); -int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf, - unsigned long buf_len); -void * __weak arch_kexec_kernel_image_load(struct kimage *image); -int __weak arch_kexec_apply_relocations_add(struct purgatory_info *pi, - Elf_Shdr *section, - const Elf_Shdr *relsec, - const Elf_Shdr *symtab); -int __weak arch_kexec_apply_relocations(struct purgatory_info *pi, - Elf_Shdr *section, - const Elf_Shdr *relsec, - const Elf_Shdr *symtab); +/* Architectures may override the below functions */ +int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len); +void *arch_kexec_kernel_image_load(struct kimage *image); +int arch_kexec_apply_relocations_add(struct purgatory_info *pi, + Elf_Shdr *section, + const Elf_Shdr *relsec, + const Elf_Shdr *symtab); +int arch_kexec_apply_relocations(struct purgatory_info *pi, + Elf_Shdr *section, + const Elf_Shdr *relsec, + const Elf_Shdr *symtab); +int arch_kimage_file_post_load_cleanup(struct kimage *image); +#ifdef CONFIG_KEXEC_SIG +int arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, + unsigned long buf_len); +#endif +int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf); extern int kexec_add_buffer(struct kexec_buf *kbuf); int kexec_locate_mem_hole(struct kexec_buf *kbuf); -- cgit v1.2.3 From 7ca8cf5347f720b07a0b32a924b768f5710547e7 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 29 Jul 2020 22:31:05 +1000 Subject: locking/atomic: Move ATOMIC_INIT into linux/types.h This patch moves ATOMIC_INIT from asm/atomic.h into linux/types.h. This allows users of atomic_t to use ATOMIC_INIT without having to include atomic.h as that way may lead to header loops. Signed-off-by: Herbert Xu Signed-off-by: Peter Zijlstra (Intel) Acked-by: Waiman Long Link: https://lkml.kernel.org/r/20200729123105.GB7047@gondor.apana.org.au --- include/linux/types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/types.h b/include/linux/types.h index d3021c879179..a147977602b5 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -167,6 +167,8 @@ typedef struct { int counter; } atomic_t; +#define ATOMIC_INIT(i) { (i) } + #ifdef CONFIG_64BIT typedef struct { s64 counter; -- cgit v1.2.3 From 0d24f65e933ca89d55d17f6dbdb2a72ca88f0992 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:07 +0200 Subject: Documentation: locking: Describe seqlock design and usage Proper documentation for the design and usage of sequence counters and sequential locks does not exist. Complete the seqlock.h documentation as follows: - Divide all documentation on a seqcount_t vs. seqlock_t basis. The description for both mechanisms was intermingled, which is incorrect since the usage constrains for each type are vastly different. - Add an introductory paragraph describing the internal design of, and rationale for, sequence counters. - Document seqcount_t writer non-preemptibility requirement, which was not previously documented anywhere, and provide a clear rationale. - Provide template code for seqcount_t and seqlock_t initialization and reader/writer critical sections. - Recommend using seqlock_t by default. It implicitly handles the serialization and non-preemptibility requirements of writers. At seqlock.h: - Remove references to brlocks as they've long been removed from the kernel. - Remove references to gcc-3.x since the kernel's minimum supported gcc version is 4.9. References: 0f6ed63b1707 ("no need to keep brlock macros anymore...") References: 6ec4476ac825 ("Raise gcc version requirement to 4.9") Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-2-a.darwish@linutronix.de --- include/linux/seqlock.h | 85 +++++++++++++++++++++++-------------------------- 1 file changed, 40 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 8b97204f35a7..299d68f10325 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -1,36 +1,15 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SEQLOCK_H #define __LINUX_SEQLOCK_H + /* - * Reader/writer consistent mechanism without starving writers. This type of - * lock for data where the reader wants a consistent set of information - * and is willing to retry if the information changes. There are two types - * of readers: - * 1. Sequence readers which never block a writer but they may have to retry - * if a writer is in progress by detecting change in sequence number. - * Writers do not wait for a sequence reader. - * 2. Locking readers which will wait if a writer or another locking reader - * is in progress. A locking reader in progress will also block a writer - * from going forward. Unlike the regular rwlock, the read lock here is - * exclusive so that only one locking reader can get it. - * - * This is not as cache friendly as brlock. Also, this may not work well - * for data that contains pointers, because any writer could - * invalidate a pointer that a reader was following. - * - * Expected non-blocking reader usage: - * do { - * seq = read_seqbegin(&foo); - * ... - * } while (read_seqretry(&foo, seq)); - * - * - * On non-SMP the spin locks disappear but the writer still needs - * to increment the sequence variables because an interrupt routine could - * change the state of the data. - * - * Based on x86_64 vsyscall gettimeofday - * by Keith Owens and Andrea Arcangeli + * seqcount_t / seqlock_t - a reader-writer consistency mechanism with + * lockless readers (read-only retry loops), and no writer starvation. + * + * See Documentation/locking/seqlock.rst + * + * Copyrights: + * - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli */ #include @@ -41,8 +20,8 @@ #include /* - * The seqlock interface does not prescribe a precise sequence of read - * begin/retry/end. For readers, typically there is a call to + * The seqlock seqcount_t interface does not prescribe a precise sequence of + * read begin/retry/end. For readers, typically there is a call to * read_seqcount_begin() and read_seqcount_retry(), however, there are more * esoteric cases which do not follow this pattern. * @@ -50,16 +29,30 @@ * via seqcount_t under KCSAN: upon beginning a seq-reader critical section, * pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as * atomics; if there is a matching read_seqcount_retry() call, no following - * memory operations are considered atomic. Usage of seqlocks via seqlock_t - * interface is not affected. + * memory operations are considered atomic. Usage of the seqlock_t interface + * is not affected. */ #define KCSAN_SEQLOCK_REGION_MAX 1000 /* - * Version using sequence counter only. - * This can be used when code has its own mutex protecting the - * updating starting before the write_seqcountbeqin() and ending - * after the write_seqcount_end(). + * Sequence counters (seqcount_t) + * + * This is the raw counting mechanism, without any writer protection. + * + * Write side critical sections must be serialized and non-preemptible. + * + * If readers can be invoked from hardirq or softirq contexts, + * interrupts or bottom halves must also be respectively disabled before + * entering the write section. + * + * This mechanism can't be used if the protected data contains pointers, + * as the writer can invalidate a pointer that a reader is following. + * + * If it's desired to automatically handle the sequence counter writer + * serialization and non-preemptibility requirements, use a sequential + * lock (seqlock_t) instead. + * + * See Documentation/locking/seqlock.rst */ typedef struct seqcount { unsigned sequence; @@ -398,10 +391,6 @@ static inline void raw_write_seqcount_latch(seqcount_t *s) smp_wmb(); /* increment "sequence" before following stores */ } -/* - * Sequence counter only version assumes that callers are using their - * own mutexing. - */ static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass) { raw_write_seqcount_begin(s); @@ -434,15 +423,21 @@ static inline void write_seqcount_invalidate(seqcount_t *s) kcsan_nestable_atomic_end(); } +/* + * Sequential locks (seqlock_t) + * + * Sequence counters with an embedded spinlock for writer serialization + * and non-preemptibility. + * + * For more info, see: + * - Comments on top of seqcount_t + * - Documentation/locking/seqlock.rst + */ typedef struct { struct seqcount seqcount; spinlock_t lock; } seqlock_t; -/* - * These macros triggered gcc-3.x compile-time problems. We think these are - * OK now. Be cautious. - */ #define __SEQLOCK_UNLOCKED(lockname) \ { \ .seqcount = SEQCNT_ZERO(lockname), \ -- cgit v1.2.3 From 15cbe67bbd3adeb4854c42713dbeaf2ff876beee Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:08 +0200 Subject: seqlock: Properly format kernel-doc code samples Align the code samples and note sections inside kernel-doc comments with tabs. This way they can be properly parsed and rendered by Sphinx. It also makes the code samples easier to read from text editors. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-3-a.darwish@linutronix.de --- include/linux/seqlock.h | 108 +++++++++++++++++++++++++----------------------- 1 file changed, 56 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 299d68f10325..6c4f68ef1393 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -263,32 +263,32 @@ static inline void raw_write_seqcount_end(seqcount_t *s) * atomically, avoiding compiler optimizations; b) to document which writes are * meant to propagate to the reader critical section. This is necessary because * neither writes before and after the barrier are enclosed in a seq-writer - * critical section that would ensure readers are aware of ongoing writes. + * critical section that would ensure readers are aware of ongoing writes:: * - * seqcount_t seq; - * bool X = true, Y = false; + * seqcount_t seq; + * bool X = true, Y = false; * - * void read(void) - * { - * bool x, y; + * void read(void) + * { + * bool x, y; * - * do { - * int s = read_seqcount_begin(&seq); + * do { + * int s = read_seqcount_begin(&seq); * - * x = X; y = Y; + * x = X; y = Y; * - * } while (read_seqcount_retry(&seq, s)); + * } while (read_seqcount_retry(&seq, s)); * - * BUG_ON(!x && !y); + * BUG_ON(!x && !y); * } * * void write(void) * { - * WRITE_ONCE(Y, true); + * WRITE_ONCE(Y, true); * - * raw_write_seqcount_barrier(seq); + * raw_write_seqcount_barrier(seq); * - * WRITE_ONCE(X, false); + * WRITE_ONCE(X, false); * } */ static inline void raw_write_seqcount_barrier(seqcount_t *s) @@ -325,64 +325,68 @@ static inline int raw_read_seqcount_latch(seqcount_t *s) * Very simply put: we first modify one copy and then the other. This ensures * there is always one copy in a stable state, ready to give us an answer. * - * The basic form is a data structure like: + * The basic form is a data structure like:: * - * struct latch_struct { - * seqcount_t seq; - * struct data_struct data[2]; - * }; + * struct latch_struct { + * seqcount_t seq; + * struct data_struct data[2]; + * }; * * Where a modification, which is assumed to be externally serialized, does the - * following: + * following:: * - * void latch_modify(struct latch_struct *latch, ...) - * { - * smp_wmb(); <- Ensure that the last data[1] update is visible - * latch->seq++; - * smp_wmb(); <- Ensure that the seqcount update is visible + * void latch_modify(struct latch_struct *latch, ...) + * { + * smp_wmb(); // Ensure that the last data[1] update is visible + * latch->seq++; + * smp_wmb(); // Ensure that the seqcount update is visible * - * modify(latch->data[0], ...); + * modify(latch->data[0], ...); * - * smp_wmb(); <- Ensure that the data[0] update is visible - * latch->seq++; - * smp_wmb(); <- Ensure that the seqcount update is visible + * smp_wmb(); // Ensure that the data[0] update is visible + * latch->seq++; + * smp_wmb(); // Ensure that the seqcount update is visible * - * modify(latch->data[1], ...); - * } + * modify(latch->data[1], ...); + * } * - * The query will have a form like: + * The query will have a form like:: * - * struct entry *latch_query(struct latch_struct *latch, ...) - * { - * struct entry *entry; - * unsigned seq, idx; + * struct entry *latch_query(struct latch_struct *latch, ...) + * { + * struct entry *entry; + * unsigned seq, idx; * - * do { - * seq = raw_read_seqcount_latch(&latch->seq); + * do { + * seq = raw_read_seqcount_latch(&latch->seq); * - * idx = seq & 0x01; - * entry = data_query(latch->data[idx], ...); + * idx = seq & 0x01; + * entry = data_query(latch->data[idx], ...); * - * smp_rmb(); - * } while (seq != latch->seq); + * smp_rmb(); + * } while (seq != latch->seq); * - * return entry; - * } + * return entry; + * } * * So during the modification, queries are first redirected to data[1]. Then we * modify data[0]. When that is complete, we redirect queries back to data[0] * and we can modify data[1]. * - * NOTE: The non-requirement for atomic modifications does _NOT_ include - * the publishing of new entries in the case where data is a dynamic - * data structure. + * NOTE: + * + * The non-requirement for atomic modifications does _NOT_ include + * the publishing of new entries in the case where data is a dynamic + * data structure. + * + * An iteration might start in data[0] and get suspended long enough + * to miss an entire modification sequence, once it resumes it might + * observe the new entry. * - * An iteration might start in data[0] and get suspended long enough - * to miss an entire modification sequence, once it resumes it might - * observe the new entry. + * NOTE: * - * NOTE: When data is a dynamic data structure; one should use regular RCU - * patterns to manage the lifetimes of the objects within. + * When data is a dynamic data structure; one should use regular RCU + * patterns to manage the lifetimes of the objects within. */ static inline void raw_write_seqcount_latch(seqcount_t *s) { -- cgit v1.2.3 From d3b35b87f436c1b226a8061bee9c8875ba6658bd Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:09 +0200 Subject: seqlock: seqcount_t latch: End read sections with read_seqcount_retry() The seqcount_t latch reader example at the raw_write_seqcount_latch() kernel-doc comment ends the latch read section with a manual smp memory barrier and sequence counter comparison. This is technically correct, but it is suboptimal: read_seqcount_retry() already contains the same logic of an smp memory barrier and sequence counter comparison. End the latch read critical section example with read_seqcount_retry(). Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-4-a.darwish@linutronix.de --- include/linux/seqlock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 6c4f68ef1393..d724b5e5408d 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -363,8 +363,8 @@ static inline int raw_read_seqcount_latch(seqcount_t *s) * idx = seq & 0x01; * entry = data_query(latch->data[idx], ...); * - * smp_rmb(); - * } while (seq != latch->seq); + * // read_seqcount_retry() includes needed smp_rmb() + * } while (read_seqcount_retry(&latch->seq, seq)); * * return entry; * } -- cgit v1.2.3 From f4a27cbcec90ac04ee60e04b222e1449dcdba0bd Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:10 +0200 Subject: seqlock: Reorder seqcount_t and seqlock_t API definitions The seqlock.h seqcount_t and seqlock_t API definitions are presented in the chronological order of their development rather than the order that makes most sense to readers. This makes it hard to follow and understand the header file code. Group and reorder all of the exported seqlock.h functions according to their function. First, group together the seqcount_t standard read path functions: - __read_seqcount_begin() - raw_read_seqcount_begin() - read_seqcount_begin() since each function is implemented exactly in terms of the one above it. Then, group the special-case seqcount_t readers on their own as: - raw_read_seqcount() - raw_seqcount_begin() since the only difference between the two functions is that the second one masks the sequence counter LSB while the first one does not. Note that raw_seqcount_begin() can actually be implemented in terms of raw_read_seqcount(), which will be done in a follow-up commit. Then, group the seqcount_t write path functions, instead of injecting unrelated seqcount_t latch functions between them, and order them as: - raw_write_seqcount_begin() - raw_write_seqcount_end() - write_seqcount_begin_nested() - write_seqcount_begin() - write_seqcount_end() - raw_write_seqcount_barrier() - write_seqcount_invalidate() which is the expected natural order. This also isolates the seqcount_t latch functions into their own area, at the end of the sequence counters section, and before jumping to the next one: sequential locks (seqlock_t). Do a similar grouping and reordering for seqlock_t "locking" readers vs. the "conditionally locking or lockless" ones. No implementation code was changed in any of the reordering above. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-5-a.darwish@linutronix.de --- include/linux/seqlock.h | 158 ++++++++++++++++++++++++------------------------ 1 file changed, 78 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index d724b5e5408d..4c1456008d89 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -128,23 +128,6 @@ repeat: return ret; } -/** - * raw_read_seqcount - Read the raw seqcount - * @s: pointer to seqcount_t - * Returns: count to be passed to read_seqcount_retry - * - * raw_read_seqcount opens a read critical section of the given - * seqcount without any lockdep checking and without checking or - * masking the LSB. Calling code is responsible for handling that. - */ -static inline unsigned raw_read_seqcount(const seqcount_t *s) -{ - unsigned ret = READ_ONCE(s->sequence); - smp_rmb(); - kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); - return ret; -} - /** * raw_read_seqcount_begin - start seq-read critical section w/o lockdep * @s: pointer to seqcount_t @@ -176,6 +159,23 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s) return raw_read_seqcount_begin(s); } +/** + * raw_read_seqcount - Read the raw seqcount + * @s: pointer to seqcount_t + * Returns: count to be passed to read_seqcount_retry + * + * raw_read_seqcount opens a read critical section of the given + * seqcount without any lockdep checking and without checking or + * masking the LSB. Calling code is responsible for handling that. + */ +static inline unsigned raw_read_seqcount(const seqcount_t *s) +{ + unsigned ret = READ_ONCE(s->sequence); + smp_rmb(); + kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); + return ret; +} + /** * raw_seqcount_begin - begin a seq-read critical section * @s: pointer to seqcount_t @@ -234,8 +234,6 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) return __read_seqcount_retry(s, start); } - - static inline void raw_write_seqcount_begin(seqcount_t *s) { kcsan_nestable_atomic_begin(); @@ -250,6 +248,23 @@ static inline void raw_write_seqcount_end(seqcount_t *s) kcsan_nestable_atomic_end(); } +static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass) +{ + raw_write_seqcount_begin(s); + seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); +} + +static inline void write_seqcount_begin(seqcount_t *s) +{ + write_seqcount_begin_nested(s, 0); +} + +static inline void write_seqcount_end(seqcount_t *s) +{ + seqcount_release(&s->dep_map, _RET_IP_); + raw_write_seqcount_end(s); +} + /** * raw_write_seqcount_barrier - do a seq write barrier * @s: pointer to seqcount_t @@ -300,6 +315,21 @@ static inline void raw_write_seqcount_barrier(seqcount_t *s) kcsan_nestable_atomic_end(); } +/** + * write_seqcount_invalidate - invalidate in-progress read-side seq operations + * @s: pointer to seqcount_t + * + * After write_seqcount_invalidate, no read-side seq operations will complete + * successfully and see data older than this. + */ +static inline void write_seqcount_invalidate(seqcount_t *s) +{ + smp_wmb(); + kcsan_nestable_atomic_begin(); + s->sequence+=2; + kcsan_nestable_atomic_end(); +} + static inline int raw_read_seqcount_latch(seqcount_t *s) { /* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */ @@ -395,38 +425,6 @@ static inline void raw_write_seqcount_latch(seqcount_t *s) smp_wmb(); /* increment "sequence" before following stores */ } -static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass) -{ - raw_write_seqcount_begin(s); - seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); -} - -static inline void write_seqcount_begin(seqcount_t *s) -{ - write_seqcount_begin_nested(s, 0); -} - -static inline void write_seqcount_end(seqcount_t *s) -{ - seqcount_release(&s->dep_map, _RET_IP_); - raw_write_seqcount_end(s); -} - -/** - * write_seqcount_invalidate - invalidate in-progress read-side seq operations - * @s: pointer to seqcount_t - * - * After write_seqcount_invalidate, no read-side seq operations will complete - * successfully and see data older than this. - */ -static inline void write_seqcount_invalidate(seqcount_t *s) -{ - smp_wmb(); - kcsan_nestable_atomic_begin(); - s->sequence+=2; - kcsan_nestable_atomic_end(); -} - /* * Sequential locks (seqlock_t) * @@ -555,35 +553,6 @@ static inline void read_sequnlock_excl(seqlock_t *sl) spin_unlock(&sl->lock); } -/** - * read_seqbegin_or_lock - begin a sequence number check or locking block - * @lock: sequence lock - * @seq : sequence number to be checked - * - * First try it once optimistically without taking the lock. If that fails, - * take the lock. The sequence number is also used as a marker for deciding - * whether to be a reader (even) or writer (odd). - * N.B. seq must be initialized to an even number to begin with. - */ -static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) -{ - if (!(*seq & 1)) /* Even */ - *seq = read_seqbegin(lock); - else /* Odd */ - read_seqlock_excl(lock); -} - -static inline int need_seqretry(seqlock_t *lock, int seq) -{ - return !(seq & 1) && read_seqretry(lock, seq); -} - -static inline void done_seqretry(seqlock_t *lock, int seq) -{ - if (seq & 1) - read_sequnlock_excl(lock); -} - static inline void read_seqlock_excl_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); @@ -621,6 +590,35 @@ read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags) spin_unlock_irqrestore(&sl->lock, flags); } +/** + * read_seqbegin_or_lock - begin a sequence number check or locking block + * @lock: sequence lock + * @seq : sequence number to be checked + * + * First try it once optimistically without taking the lock. If that fails, + * take the lock. The sequence number is also used as a marker for deciding + * whether to be a reader (even) or writer (odd). + * N.B. seq must be initialized to an even number to begin with. + */ +static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) +{ + if (!(*seq & 1)) /* Even */ + *seq = read_seqbegin(lock); + else /* Odd */ + read_seqlock_excl(lock); +} + +static inline int need_seqretry(seqlock_t *lock, int seq) +{ + return !(seq & 1) && read_seqretry(lock, seq); +} + +static inline void done_seqretry(seqlock_t *lock, int seq) +{ + if (seq & 1) + read_sequnlock_excl(lock); +} + static inline unsigned long read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq) { -- cgit v1.2.3 From 89b88845e05752b3d684eaf147f457c8dfa99c5f Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:11 +0200 Subject: seqlock: Add kernel-doc for seqcount_t and seqlock_t APIs seqlock.h is now included by kernel's RST documentation, but a small number of the the exported seqlock.h functions are kernel-doc annotated. Add kernel-doc for all seqlock.h exported APIs. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-6-a.darwish@linutronix.de --- include/linux/seqlock.h | 425 +++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 348 insertions(+), 77 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 4c1456008d89..85fb3ac93ffb 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -75,6 +75,10 @@ static inline void __seqcount_init(seqcount_t *s, const char *name, # define SEQCOUNT_DEP_MAP_INIT(lockname) \ .dep_map = { .name = #lockname } \ +/** + * seqcount_init() - runtime initializer for seqcount_t + * @s: Pointer to the seqcount_t instance + */ # define seqcount_init(s) \ do { \ static struct lock_class_key __key; \ @@ -98,13 +102,15 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) # define seqcount_lockdep_reader_access(x) #endif -#define SEQCNT_ZERO(lockname) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(lockname)} - +/** + * SEQCNT_ZERO() - static initializer for seqcount_t + * @name: Name of the seqcount_t instance + */ +#define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) } /** - * __read_seqcount_begin - begin a seq-read critical section (without barrier) - * @s: pointer to seqcount_t - * Returns: count to be passed to read_seqcount_retry + * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier + * @s: Pointer to seqcount_t * * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is @@ -113,6 +119,8 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) * * Use carefully, only in critical code, and comment how the barrier is * provided. + * + * Return: count to be passed to read_seqcount_retry() */ static inline unsigned __read_seqcount_begin(const seqcount_t *s) { @@ -129,13 +137,10 @@ repeat: } /** - * raw_read_seqcount_begin - start seq-read critical section w/o lockdep - * @s: pointer to seqcount_t - * Returns: count to be passed to read_seqcount_retry + * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep + * @s: Pointer to seqcount_t * - * raw_read_seqcount_begin opens a read critical section of the given - * seqcount, but without any lockdep checking. Validity of the critical - * section is tested by checking read_seqcount_retry function. + * Return: count to be passed to read_seqcount_retry() */ static inline unsigned raw_read_seqcount_begin(const seqcount_t *s) { @@ -145,13 +150,10 @@ static inline unsigned raw_read_seqcount_begin(const seqcount_t *s) } /** - * read_seqcount_begin - begin a seq-read critical section - * @s: pointer to seqcount_t - * Returns: count to be passed to read_seqcount_retry + * read_seqcount_begin() - begin a seqcount_t read critical section + * @s: Pointer to seqcount_t * - * read_seqcount_begin opens a read critical section of the given seqcount. - * Validity of the critical section is tested by checking read_seqcount_retry - * function. + * Return: count to be passed to read_seqcount_retry() */ static inline unsigned read_seqcount_begin(const seqcount_t *s) { @@ -160,13 +162,15 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s) } /** - * raw_read_seqcount - Read the raw seqcount - * @s: pointer to seqcount_t - * Returns: count to be passed to read_seqcount_retry + * raw_read_seqcount() - read the raw seqcount_t counter value + * @s: Pointer to seqcount_t * * raw_read_seqcount opens a read critical section of the given - * seqcount without any lockdep checking and without checking or - * masking the LSB. Calling code is responsible for handling that. + * seqcount_t, without any lockdep checking, and without checking or + * masking the sequence counter LSB. Calling code is responsible for + * handling that. + * + * Return: count to be passed to read_seqcount_retry() */ static inline unsigned raw_read_seqcount(const seqcount_t *s) { @@ -177,18 +181,21 @@ static inline unsigned raw_read_seqcount(const seqcount_t *s) } /** - * raw_seqcount_begin - begin a seq-read critical section - * @s: pointer to seqcount_t - * Returns: count to be passed to read_seqcount_retry + * raw_seqcount_begin() - begin a seqcount_t read critical section w/o + * lockdep and w/o counter stabilization + * @s: Pointer to seqcount_t * - * raw_seqcount_begin opens a read critical section of the given seqcount. - * Validity of the critical section is tested by checking read_seqcount_retry - * function. + * raw_seqcount_begin opens a read critical section of the given + * seqcount_t. Unlike read_seqcount_begin(), this function will not wait + * for the count to stabilize. If a writer is active when it begins, it + * will fail the read_seqcount_retry() at the end of the read critical + * section instead of stabilizing at the beginning of it. * - * Unlike read_seqcount_begin(), this function will not wait for the count - * to stabilize. If a writer is active when we begin, we will fail the - * read_seqcount_retry() instead of stabilizing at the beginning of the - * critical section. + * Use this only in special kernel hot paths where the read section is + * small and has a high probability of success through other external + * means. It will save a single branching instruction. + * + * Return: count to be passed to read_seqcount_retry() */ static inline unsigned raw_seqcount_begin(const seqcount_t *s) { @@ -199,10 +206,9 @@ static inline unsigned raw_seqcount_begin(const seqcount_t *s) } /** - * __read_seqcount_retry - end a seq-read critical section (without barrier) - * @s: pointer to seqcount_t - * @start: count, from read_seqcount_begin - * Returns: 1 if retry is required, else 0 + * __read_seqcount_retry() - end a seqcount_t read section w/o barrier + * @s: Pointer to seqcount_t + * @start: count, from read_seqcount_begin() * * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is @@ -211,6 +217,8 @@ static inline unsigned raw_seqcount_begin(const seqcount_t *s) * * Use carefully, only in critical code, and comment how the barrier is * provided. + * + * Return: true if a read section retry is required, else false */ static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start) { @@ -219,14 +227,15 @@ static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start) } /** - * read_seqcount_retry - end a seq-read critical section - * @s: pointer to seqcount_t - * @start: count, from read_seqcount_begin - * Returns: 1 if retry is required, else 0 + * read_seqcount_retry() - end a seqcount_t read critical section + * @s: Pointer to seqcount_t + * @start: count, from read_seqcount_begin() * - * read_seqcount_retry closes a read critical section of the given seqcount. - * If the critical section was invalid, it must be ignored (and typically - * retried). + * read_seqcount_retry closes the read critical section of given + * seqcount_t. If the critical section was invalid, it must be ignored + * (and typically retried). + * + * Return: true if a read section retry is required, else false */ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) { @@ -234,6 +243,10 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) return __read_seqcount_retry(s, start); } +/** + * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep + * @s: Pointer to seqcount_t + */ static inline void raw_write_seqcount_begin(seqcount_t *s) { kcsan_nestable_atomic_begin(); @@ -241,6 +254,10 @@ static inline void raw_write_seqcount_begin(seqcount_t *s) smp_wmb(); } +/** + * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep + * @s: Pointer to seqcount_t + */ static inline void raw_write_seqcount_end(seqcount_t *s) { smp_wmb(); @@ -248,17 +265,42 @@ static inline void raw_write_seqcount_end(seqcount_t *s) kcsan_nestable_atomic_end(); } +/** + * write_seqcount_begin_nested() - start a seqcount_t write section with + * custom lockdep nesting level + * @s: Pointer to seqcount_t + * @subclass: lockdep nesting level + * + * See Documentation/locking/lockdep-design.rst + */ static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass) { raw_write_seqcount_begin(s); seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); } +/** + * write_seqcount_begin() - start a seqcount_t write side critical section + * @s: Pointer to seqcount_t + * + * write_seqcount_begin opens a write side critical section of the given + * seqcount_t. + * + * Context: seqcount_t write side critical sections must be serialized and + * non-preemptible. If readers can be invoked from hardirq or softirq + * context, interrupts or bottom halves must be respectively disabled. + */ static inline void write_seqcount_begin(seqcount_t *s) { write_seqcount_begin_nested(s, 0); } +/** + * write_seqcount_end() - end a seqcount_t write side critical section + * @s: Pointer to seqcount_t + * + * The write section must've been opened with write_seqcount_begin(). + */ static inline void write_seqcount_end(seqcount_t *s) { seqcount_release(&s->dep_map, _RET_IP_); @@ -266,12 +308,12 @@ static inline void write_seqcount_end(seqcount_t *s) } /** - * raw_write_seqcount_barrier - do a seq write barrier - * @s: pointer to seqcount_t + * raw_write_seqcount_barrier() - do a seqcount_t write barrier + * @s: Pointer to seqcount_t * - * This can be used to provide an ordering guarantee instead of the - * usual consistency guarantee. It is one wmb cheaper, because we can - * collapse the two back-to-back wmb()s. + * This can be used to provide an ordering guarantee instead of the usual + * consistency guarantee. It is one wmb cheaper, because it can collapse + * the two back-to-back wmb()s. * * Note that writes surrounding the barrier should be declared atomic (e.g. * via WRITE_ONCE): a) to ensure the writes become visible to other threads @@ -316,11 +358,12 @@ static inline void raw_write_seqcount_barrier(seqcount_t *s) } /** - * write_seqcount_invalidate - invalidate in-progress read-side seq operations - * @s: pointer to seqcount_t + * write_seqcount_invalidate() - invalidate in-progress seqcount_t read + * side operations + * @s: Pointer to seqcount_t * - * After write_seqcount_invalidate, no read-side seq operations will complete - * successfully and see data older than this. + * After write_seqcount_invalidate, no seqcount_t read side operations + * will complete successfully and see data older than this. */ static inline void write_seqcount_invalidate(seqcount_t *s) { @@ -330,6 +373,21 @@ static inline void write_seqcount_invalidate(seqcount_t *s) kcsan_nestable_atomic_end(); } +/** + * raw_read_seqcount_latch() - pick even/odd seqcount_t latch data copy + * @s: Pointer to seqcount_t + * + * Use seqcount_t latching to switch between two storage places protected + * by a sequence counter. Doing so allows having interruptible, preemptible, + * seqcount_t write side critical sections. + * + * Check raw_write_seqcount_latch() for more details and a full reader and + * writer usage example. + * + * Return: sequence counter raw value. Use the lowest bit as an index for + * picking which data copy to read. The full counter value must then be + * checked with read_seqcount_retry(). + */ static inline int raw_read_seqcount_latch(seqcount_t *s) { /* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */ @@ -338,8 +396,8 @@ static inline int raw_read_seqcount_latch(seqcount_t *s) } /** - * raw_write_seqcount_latch - redirect readers to even/odd copy - * @s: pointer to seqcount_t + * raw_write_seqcount_latch() - redirect readers to even/odd copy + * @s: Pointer to seqcount_t * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never @@ -446,17 +504,28 @@ typedef struct { .lock = __SPIN_LOCK_UNLOCKED(lockname) \ } -#define seqlock_init(x) \ +/** + * seqlock_init() - dynamic initializer for seqlock_t + * @sl: Pointer to the seqlock_t instance + */ +#define seqlock_init(sl) \ do { \ - seqcount_init(&(x)->seqcount); \ - spin_lock_init(&(x)->lock); \ + seqcount_init(&(sl)->seqcount); \ + spin_lock_init(&(sl)->lock); \ } while (0) -#define DEFINE_SEQLOCK(x) \ - seqlock_t x = __SEQLOCK_UNLOCKED(x) +/** + * DEFINE_SEQLOCK() - Define a statically allocated seqlock_t + * @sl: Name of the seqlock_t instance + */ +#define DEFINE_SEQLOCK(sl) \ + seqlock_t sl = __SEQLOCK_UNLOCKED(sl) -/* - * Read side functions for starting and finalizing a read side section. +/** + * read_seqbegin() - start a seqlock_t read side critical section + * @sl: Pointer to seqlock_t + * + * Return: count, to be passed to read_seqretry() */ static inline unsigned read_seqbegin(const seqlock_t *sl) { @@ -467,6 +536,17 @@ static inline unsigned read_seqbegin(const seqlock_t *sl) return ret; } +/** + * read_seqretry() - end a seqlock_t read side section + * @sl: Pointer to seqlock_t + * @start: count, from read_seqbegin() + * + * read_seqretry closes the read side critical section of given seqlock_t. + * If the critical section was invalid, it must be ignored (and typically + * retried). + * + * Return: true if a read section retry is required, else false + */ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { /* @@ -478,10 +558,18 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) return read_seqcount_retry(&sl->seqcount, start); } -/* - * Lock out other writers and update the count. - * Acts like a normal spin_lock/unlock. - * Don't need preempt_disable() because that is in the spin_lock already. +/** + * write_seqlock() - start a seqlock_t write side critical section + * @sl: Pointer to seqlock_t + * + * write_seqlock opens a write side critical section for the given + * seqlock_t. It also implicitly acquires the spinlock_t embedded inside + * that sequential lock. All seqlock_t write side sections are thus + * automatically serialized and non-preemptible. + * + * Context: if the seqlock_t read section, or other write side critical + * sections, can be invoked from hardirq or softirq contexts, use the + * _irqsave or _bh variants of this function instead. */ static inline void write_seqlock(seqlock_t *sl) { @@ -489,30 +577,66 @@ static inline void write_seqlock(seqlock_t *sl) write_seqcount_begin(&sl->seqcount); } +/** + * write_sequnlock() - end a seqlock_t write side critical section + * @sl: Pointer to seqlock_t + * + * write_sequnlock closes the (serialized and non-preemptible) write side + * critical section of given seqlock_t. + */ static inline void write_sequnlock(seqlock_t *sl) { write_seqcount_end(&sl->seqcount); spin_unlock(&sl->lock); } +/** + * write_seqlock_bh() - start a softirqs-disabled seqlock_t write section + * @sl: Pointer to seqlock_t + * + * _bh variant of write_seqlock(). Use only if the read side section, or + * other write side sections, can be invoked from softirq contexts. + */ static inline void write_seqlock_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); write_seqcount_begin(&sl->seqcount); } +/** + * write_sequnlock_bh() - end a softirqs-disabled seqlock_t write section + * @sl: Pointer to seqlock_t + * + * write_sequnlock_bh closes the serialized, non-preemptible, and + * softirqs-disabled, seqlock_t write side critical section opened with + * write_seqlock_bh(). + */ static inline void write_sequnlock_bh(seqlock_t *sl) { write_seqcount_end(&sl->seqcount); spin_unlock_bh(&sl->lock); } +/** + * write_seqlock_irq() - start a non-interruptible seqlock_t write section + * @sl: Pointer to seqlock_t + * + * _irq variant of write_seqlock(). Use only if the read side section, or + * other write sections, can be invoked from hardirq contexts. + */ static inline void write_seqlock_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); write_seqcount_begin(&sl->seqcount); } +/** + * write_sequnlock_irq() - end a non-interruptible seqlock_t write section + * @sl: Pointer to seqlock_t + * + * write_sequnlock_irq closes the serialized and non-interruptible + * seqlock_t write side section opened with write_seqlock_irq(). + */ static inline void write_sequnlock_irq(seqlock_t *sl) { write_seqcount_end(&sl->seqcount); @@ -528,9 +652,28 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) return flags; } +/** + * write_seqlock_irqsave() - start a non-interruptible seqlock_t write + * section + * @lock: Pointer to seqlock_t + * @flags: Stack-allocated storage for saving caller's local interrupt + * state, to be passed to write_sequnlock_irqrestore(). + * + * _irqsave variant of write_seqlock(). Use it only if the read side + * section, or other write sections, can be invoked from hardirq context. + */ #define write_seqlock_irqsave(lock, flags) \ do { flags = __write_seqlock_irqsave(lock); } while (0) +/** + * write_sequnlock_irqrestore() - end non-interruptible seqlock_t write + * section + * @sl: Pointer to seqlock_t + * @flags: Caller's saved interrupt state, from write_seqlock_irqsave() + * + * write_sequnlock_irqrestore closes the serialized and non-interruptible + * seqlock_t write section previously opened with write_seqlock_irqsave(). + */ static inline void write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) { @@ -538,36 +681,79 @@ write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) spin_unlock_irqrestore(&sl->lock, flags); } -/* - * A locking reader exclusively locks out other writers and locking readers, - * but doesn't update the sequence number. Acts like a normal spin_lock/unlock. - * Don't need preempt_disable() because that is in the spin_lock already. +/** + * read_seqlock_excl() - begin a seqlock_t locking reader section + * @sl: Pointer to seqlock_t + * + * read_seqlock_excl opens a seqlock_t locking reader critical section. A + * locking reader exclusively locks out *both* other writers *and* other + * locking readers, but it does not update the embedded sequence number. + * + * Locking readers act like a normal spin_lock()/spin_unlock(). + * + * Context: if the seqlock_t write section, *or other read sections*, can + * be invoked from hardirq or softirq contexts, use the _irqsave or _bh + * variant of this function instead. + * + * The opened read section must be closed with read_sequnlock_excl(). */ static inline void read_seqlock_excl(seqlock_t *sl) { spin_lock(&sl->lock); } +/** + * read_sequnlock_excl() - end a seqlock_t locking reader critical section + * @sl: Pointer to seqlock_t + */ static inline void read_sequnlock_excl(seqlock_t *sl) { spin_unlock(&sl->lock); } +/** + * read_seqlock_excl_bh() - start a seqlock_t locking reader section with + * softirqs disabled + * @sl: Pointer to seqlock_t + * + * _bh variant of read_seqlock_excl(). Use this variant only if the + * seqlock_t write side section, *or other read sections*, can be invoked + * from softirq contexts. + */ static inline void read_seqlock_excl_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); } +/** + * read_sequnlock_excl_bh() - stop a seqlock_t softirq-disabled locking + * reader section + * @sl: Pointer to seqlock_t + */ static inline void read_sequnlock_excl_bh(seqlock_t *sl) { spin_unlock_bh(&sl->lock); } +/** + * read_seqlock_excl_irq() - start a non-interruptible seqlock_t locking + * reader section + * @sl: Pointer to seqlock_t + * + * _irq variant of read_seqlock_excl(). Use this only if the seqlock_t + * write side section, *or other read sections*, can be invoked from a + * hardirq context. + */ static inline void read_seqlock_excl_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); } +/** + * read_sequnlock_excl_irq() - end an interrupts-disabled seqlock_t + * locking reader section + * @sl: Pointer to seqlock_t + */ static inline void read_sequnlock_excl_irq(seqlock_t *sl) { spin_unlock_irq(&sl->lock); @@ -581,9 +767,26 @@ static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl) return flags; } +/** + * read_seqlock_excl_irqsave() - start a non-interruptible seqlock_t + * locking reader section + * @lock: Pointer to seqlock_t + * @flags: Stack-allocated storage for saving caller's local interrupt + * state, to be passed to read_sequnlock_excl_irqrestore(). + * + * _irqsave variant of read_seqlock_excl(). Use this only if the seqlock_t + * write side section, *or other read sections*, can be invoked from a + * hardirq context. + */ #define read_seqlock_excl_irqsave(lock, flags) \ do { flags = __read_seqlock_excl_irqsave(lock); } while (0) +/** + * read_sequnlock_excl_irqrestore() - end non-interruptible seqlock_t + * locking reader section + * @sl: Pointer to seqlock_t + * @flags: Caller saved interrupt state, from read_seqlock_excl_irqsave() + */ static inline void read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags) { @@ -591,14 +794,35 @@ read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags) } /** - * read_seqbegin_or_lock - begin a sequence number check or locking block - * @lock: sequence lock - * @seq : sequence number to be checked - * - * First try it once optimistically without taking the lock. If that fails, - * take the lock. The sequence number is also used as a marker for deciding - * whether to be a reader (even) or writer (odd). - * N.B. seq must be initialized to an even number to begin with. + * read_seqbegin_or_lock() - begin a seqlock_t lockless or locking reader + * @lock: Pointer to seqlock_t + * @seq : Marker and return parameter. If the passed value is even, the + * reader will become a *lockless* seqlock_t reader as in read_seqbegin(). + * If the passed value is odd, the reader will become a *locking* reader + * as in read_seqlock_excl(). In the first call to this function, the + * caller *must* initialize and pass an even value to @seq; this way, a + * lockless read can be optimistically tried first. + * + * read_seqbegin_or_lock is an API designed to optimistically try a normal + * lockless seqlock_t read section first. If an odd counter is found, the + * lockless read trial has failed, and the next read iteration transforms + * itself into a full seqlock_t locking reader. + * + * This is typically used to avoid seqlock_t lockless readers starvation + * (too much retry loops) in the case of a sharp spike in write side + * activity. + * + * Context: if the seqlock_t write section, *or other read sections*, can + * be invoked from hardirq or softirq contexts, use the _irqsave or _bh + * variant of this function instead. + * + * Check Documentation/locking/seqlock.rst for template example code. + * + * Return: the encountered sequence counter value, through the @seq + * parameter, which is overloaded as a return parameter. This returned + * value must be checked with need_seqretry(). If the read section need to + * be retried, this returned value must also be passed as the @seq + * parameter of the next read_seqbegin_or_lock() iteration. */ static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) { @@ -608,17 +832,52 @@ static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) read_seqlock_excl(lock); } +/** + * need_seqretry() - validate seqlock_t "locking or lockless" read section + * @lock: Pointer to seqlock_t + * @seq: sequence count, from read_seqbegin_or_lock() + * + * Return: true if a read section retry is required, false otherwise + */ static inline int need_seqretry(seqlock_t *lock, int seq) { return !(seq & 1) && read_seqretry(lock, seq); } +/** + * done_seqretry() - end seqlock_t "locking or lockless" reader section + * @lock: Pointer to seqlock_t + * @seq: count, from read_seqbegin_or_lock() + * + * done_seqretry finishes the seqlock_t read side critical section started + * with read_seqbegin_or_lock() and validated by need_seqretry(). + */ static inline void done_seqretry(seqlock_t *lock, int seq) { if (seq & 1) read_sequnlock_excl(lock); } +/** + * read_seqbegin_or_lock_irqsave() - begin a seqlock_t lockless reader, or + * a non-interruptible locking reader + * @lock: Pointer to seqlock_t + * @seq: Marker and return parameter. Check read_seqbegin_or_lock(). + * + * This is the _irqsave variant of read_seqbegin_or_lock(). Use it only if + * the seqlock_t write section, *or other read sections*, can be invoked + * from hardirq context. + * + * Note: Interrupts will be disabled only for "locking reader" mode. + * + * Return: + * + * 1. The saved local interrupts state in case of a locking reader, to + * be passed to done_seqretry_irqrestore(). + * + * 2. The encountered sequence counter value, returned through @seq + * overloaded as a return parameter. Check read_seqbegin_or_lock(). + */ static inline unsigned long read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq) { @@ -632,6 +891,18 @@ read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq) return flags; } +/** + * done_seqretry_irqrestore() - end a seqlock_t lockless reader, or a + * non-interruptible locking reader section + * @lock: Pointer to seqlock_t + * @seq: Count, from read_seqbegin_or_lock_irqsave() + * @flags: Caller's saved local interrupt state in case of a locking + * reader, also from read_seqbegin_or_lock_irqsave() + * + * This is the _irqrestore variant of done_seqretry(). The read section + * must've been opened with read_seqbegin_or_lock_irqsave(), and validated + * by need_seqretry(). + */ static inline void done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags) { -- cgit v1.2.3 From 932e46365226324d2cf26d8bdec8b51ceb296948 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:12 +0200 Subject: seqlock: Implement raw_seqcount_begin() in terms of raw_read_seqcount() raw_seqcount_begin() has the same code as raw_read_seqcount(), with the exception of masking the sequence counter's LSB before returning it to the caller. Note, raw_seqcount_begin() masks the counter's LSB before returning it to the caller so that read_seqcount_retry() can fail if the counter is odd -- without the overhead of an extra branching instruction. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-7-a.darwish@linutronix.de --- include/linux/seqlock.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 85fb3ac93ffb..e885702d8b82 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -199,10 +199,11 @@ static inline unsigned raw_read_seqcount(const seqcount_t *s) */ static inline unsigned raw_seqcount_begin(const seqcount_t *s) { - unsigned ret = READ_ONCE(s->sequence); - smp_rmb(); - kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); - return ret & ~1; + /* + * If the counter is odd, let read_seqcount_retry() fail + * by decrementing the counter. + */ + return raw_read_seqcount(s) & ~1; } /** -- cgit v1.2.3 From 8fd8ad5c5dfcb09cf62abadd4043eaf1afbbd0ce Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:13 +0200 Subject: lockdep: Add preemption enabled/disabled assertion APIs Asserting that preemption is enabled or disabled is a critical sanity check. Developers are usually reluctant to add such a check in a fastpath as reading the preemption count can be costly. Extend the lockdep API with macros asserting that preemption is disabled or enabled. If lockdep is disabled, or if the underlying architecture does not support kernel preemption, this assert has no runtime overhead. References: f54bb2ec02c8 ("locking/lockdep: Add IRQs disabled/enabled assertion APIs: ...") Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-8-a.darwish@linutronix.de --- include/linux/lockdep.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 7aafba0ddcf9..39a35699d0d6 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -549,6 +549,22 @@ do { \ WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirq_context)); \ } while (0) +#define lockdep_assert_preemption_enabled() \ +do { \ + WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ + debug_locks && \ + (preempt_count() != 0 || \ + !this_cpu_read(hardirqs_enabled))); \ +} while (0) + +#define lockdep_assert_preemption_disabled() \ +do { \ + WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ + debug_locks && \ + (preempt_count() == 0 && \ + this_cpu_read(hardirqs_enabled))); \ +} while (0) + #else # define might_lock(lock) do { } while (0) # define might_lock_read(lock) do { } while (0) @@ -557,6 +573,9 @@ do { \ # define lockdep_assert_irqs_enabled() do { } while (0) # define lockdep_assert_irqs_disabled() do { } while (0) # define lockdep_assert_in_irq() do { } while (0) + +# define lockdep_assert_preemption_enabled() do { } while (0) +# define lockdep_assert_preemption_disabled() do { } while (0) #endif #ifdef CONFIG_PROVE_RAW_LOCK_NESTING -- cgit v1.2.3 From 859247d39fb008ea812e8f0c398a58a20c12899e Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:14 +0200 Subject: seqlock: lockdep assert non-preemptibility on seqcount_t write Preemption must be disabled before entering a sequence count write side critical section. Failing to do so, the seqcount read side can preempt the write side section and spin for the entire scheduler tick. If that reader belongs to a real-time scheduling class, it can spin forever and the kernel will livelock. Assert through lockdep that preemption is disabled for seqcount writers. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-9-a.darwish@linutronix.de --- include/linux/seqlock.h | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index e885702d8b82..54bc20496392 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -266,6 +266,12 @@ static inline void raw_write_seqcount_end(seqcount_t *s) kcsan_nestable_atomic_end(); } +static inline void __write_seqcount_begin_nested(seqcount_t *s, int subclass) +{ + raw_write_seqcount_begin(s); + seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); +} + /** * write_seqcount_begin_nested() - start a seqcount_t write section with * custom lockdep nesting level @@ -276,8 +282,19 @@ static inline void raw_write_seqcount_end(seqcount_t *s) */ static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass) { - raw_write_seqcount_begin(s); - seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); + lockdep_assert_preemption_disabled(); + __write_seqcount_begin_nested(s, subclass); +} + +/* + * A write_seqcount_begin() variant w/o lockdep non-preemptibility checks. + * + * Use for internal seqlock.h code where it's known that preemption is + * already disabled. For example, seqlock_t write side functions. + */ +static inline void __write_seqcount_begin(seqcount_t *s) +{ + __write_seqcount_begin_nested(s, 0); } /** @@ -575,7 +592,7 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) static inline void write_seqlock(seqlock_t *sl) { spin_lock(&sl->lock); - write_seqcount_begin(&sl->seqcount); + __write_seqcount_begin(&sl->seqcount); } /** @@ -601,7 +618,7 @@ static inline void write_sequnlock(seqlock_t *sl) static inline void write_seqlock_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); - write_seqcount_begin(&sl->seqcount); + __write_seqcount_begin(&sl->seqcount); } /** @@ -628,7 +645,7 @@ static inline void write_sequnlock_bh(seqlock_t *sl) static inline void write_seqlock_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); - write_seqcount_begin(&sl->seqcount); + __write_seqcount_begin(&sl->seqcount); } /** @@ -649,7 +666,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) unsigned long flags; spin_lock_irqsave(&sl->lock, flags); - write_seqcount_begin(&sl->seqcount); + __write_seqcount_begin(&sl->seqcount); return flags; } -- cgit v1.2.3 From 55f3560df975f557c48aa6afc636808f31ecb87a Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:15 +0200 Subject: seqlock: Extend seqcount API with associated locks A sequence counter write side critical section must be protected by some form of locking to serialize writers. If the serialization primitive is not disabling preemption implicitly, preemption has to be explicitly disabled before entering the write side critical section. There is no built-in debugging mechanism to verify that the lock used for writer serialization is held and preemption is disabled. Some usage sites like dma-buf have explicit lockdep checks for the writer-side lock, but this covers only a small portion of the sequence counter usage in the kernel. Add new sequence counter types which allows to associate a lock to the sequence counter at initialization time. The seqcount API functions are extended to provide appropriate lockdep assertions depending on the seqcount/lock type. For sequence counters with associated locks that do not implicitly disable preemption, preemption protection is enforced in the sequence counter write side functions. This removes the need to explicitly add preempt_disable/enable() around the write side critical sections: the write_begin/end() functions for these new sequence counter types automatically do this. Introduce the following seqcount types with associated locks: seqcount_spinlock_t seqcount_raw_spinlock_t seqcount_rwlock_t seqcount_mutex_t seqcount_ww_mutex_t Extend the seqcount read and write functions to branch out to the specific seqcount_LOCKTYPE_t implementation at compile-time. This avoids kernel API explosion per each new seqcount_LOCKTYPE_t added. Add such compile-time type detection logic into a new, internal, seqlock header. Document the proper seqcount_LOCKTYPE_t usage, and rationale, at Documentation/locking/seqlock.rst. If lockdep is disabled, this lock association is compiled out and has neither storage size nor runtime overhead. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-10-a.darwish@linutronix.de --- include/linux/seqlock.h | 464 +++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 395 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 54bc20496392..8c16a494c968 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -10,13 +10,17 @@ * * Copyrights: * - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli + * - Sequence counters with associated locks, (C) 2020 Linutronix GmbH */ -#include -#include -#include #include #include +#include +#include +#include +#include +#include + #include /* @@ -48,6 +52,10 @@ * This mechanism can't be used if the protected data contains pointers, * as the writer can invalidate a pointer that a reader is following. * + * If the write serialization mechanism is one of the common kernel + * locking primitives, use a sequence counter with associated lock + * (seqcount_LOCKTYPE_t) instead. + * * If it's desired to automatically handle the sequence counter writer * serialization and non-preemptibility requirements, use a sequential * lock (seqlock_t) instead. @@ -108,9 +116,267 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) */ #define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) } +/* + * Sequence counters with associated locks (seqcount_LOCKTYPE_t) + * + * A sequence counter which associates the lock used for writer + * serialization at initialization time. This enables lockdep to validate + * that the write side critical section is properly serialized. + * + * For associated locks which do not implicitly disable preemption, + * preemption protection is enforced in the write side function. + * + * Lockdep is never used in any for the raw write variants. + * + * See Documentation/locking/seqlock.rst + */ + +#ifdef CONFIG_LOCKDEP +#define __SEQ_LOCKDEP(expr) expr +#else +#define __SEQ_LOCKDEP(expr) +#endif + +#define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) { \ + .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ + __SEQ_LOCKDEP(.lock = (assoc_lock)) \ +} + +#define seqcount_locktype_init(s, assoc_lock) \ +do { \ + seqcount_init(&(s)->seqcount); \ + __SEQ_LOCKDEP((s)->lock = (assoc_lock)); \ +} while (0) + +/** + * typedef seqcount_spinlock_t - sequence counter with spinlock associated + * @seqcount: The real sequence counter + * @lock: Pointer to the associated spinlock + * + * A plain sequence counter with external writer synchronization by a + * spinlock. The spinlock is associated to the sequence count in the + * static initializer or init function. This enables lockdep to validate + * that the write side critical section is properly serialized. + */ +typedef struct seqcount_spinlock { + seqcount_t seqcount; + __SEQ_LOCKDEP(spinlock_t *lock); +} seqcount_spinlock_t; + +/** + * SEQCNT_SPINLOCK_ZERO - static initializer for seqcount_spinlock_t + * @name: Name of the seqcount_spinlock_t instance + * @lock: Pointer to the associated spinlock + */ +#define SEQCNT_SPINLOCK_ZERO(name, lock) \ + SEQCOUNT_LOCKTYPE_ZERO(name, lock) + +/** + * seqcount_spinlock_init - runtime initializer for seqcount_spinlock_t + * @s: Pointer to the seqcount_spinlock_t instance + * @lock: Pointer to the associated spinlock + */ +#define seqcount_spinlock_init(s, lock) \ + seqcount_locktype_init(s, lock) + +/** + * typedef seqcount_raw_spinlock_t - sequence count with raw spinlock associated + * @seqcount: The real sequence counter + * @lock: Pointer to the associated raw spinlock + * + * A plain sequence counter with external writer synchronization by a + * raw spinlock. The raw spinlock is associated to the sequence count in + * the static initializer or init function. This enables lockdep to + * validate that the write side critical section is properly serialized. + */ +typedef struct seqcount_raw_spinlock { + seqcount_t seqcount; + __SEQ_LOCKDEP(raw_spinlock_t *lock); +} seqcount_raw_spinlock_t; + +/** + * SEQCNT_RAW_SPINLOCK_ZERO - static initializer for seqcount_raw_spinlock_t + * @name: Name of the seqcount_raw_spinlock_t instance + * @lock: Pointer to the associated raw_spinlock + */ +#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) \ + SEQCOUNT_LOCKTYPE_ZERO(name, lock) + +/** + * seqcount_raw_spinlock_init - runtime initializer for seqcount_raw_spinlock_t + * @s: Pointer to the seqcount_raw_spinlock_t instance + * @lock: Pointer to the associated raw_spinlock + */ +#define seqcount_raw_spinlock_init(s, lock) \ + seqcount_locktype_init(s, lock) + +/** + * typedef seqcount_rwlock_t - sequence count with rwlock associated + * @seqcount: The real sequence counter + * @lock: Pointer to the associated rwlock + * + * A plain sequence counter with external writer synchronization by a + * rwlock. The rwlock is associated to the sequence count in the static + * initializer or init function. This enables lockdep to validate that + * the write side critical section is properly serialized. + */ +typedef struct seqcount_rwlock { + seqcount_t seqcount; + __SEQ_LOCKDEP(rwlock_t *lock); +} seqcount_rwlock_t; + +/** + * SEQCNT_RWLOCK_ZERO - static initializer for seqcount_rwlock_t + * @name: Name of the seqcount_rwlock_t instance + * @lock: Pointer to the associated rwlock + */ +#define SEQCNT_RWLOCK_ZERO(name, lock) \ + SEQCOUNT_LOCKTYPE_ZERO(name, lock) + +/** + * seqcount_rwlock_init - runtime initializer for seqcount_rwlock_t + * @s: Pointer to the seqcount_rwlock_t instance + * @lock: Pointer to the associated rwlock + */ +#define seqcount_rwlock_init(s, lock) \ + seqcount_locktype_init(s, lock) + +/** + * typedef seqcount_mutex_t - sequence count with mutex associated + * @seqcount: The real sequence counter + * @lock: Pointer to the associated mutex + * + * A plain sequence counter with external writer synchronization by a + * mutex. The mutex is associated to the sequence counter in the static + * initializer or init function. This enables lockdep to validate that + * the write side critical section is properly serialized. + * + * The write side API functions write_seqcount_begin()/end() automatically + * disable and enable preemption when used with seqcount_mutex_t. + */ +typedef struct seqcount_mutex { + seqcount_t seqcount; + __SEQ_LOCKDEP(struct mutex *lock); +} seqcount_mutex_t; + +/** + * SEQCNT_MUTEX_ZERO - static initializer for seqcount_mutex_t + * @name: Name of the seqcount_mutex_t instance + * @lock: Pointer to the associated mutex + */ +#define SEQCNT_MUTEX_ZERO(name, lock) \ + SEQCOUNT_LOCKTYPE_ZERO(name, lock) + +/** + * seqcount_mutex_init - runtime initializer for seqcount_mutex_t + * @s: Pointer to the seqcount_mutex_t instance + * @lock: Pointer to the associated mutex + */ +#define seqcount_mutex_init(s, lock) \ + seqcount_locktype_init(s, lock) + +/** + * typedef seqcount_ww_mutex_t - sequence count with ww_mutex associated + * @seqcount: The real sequence counter + * @lock: Pointer to the associated ww_mutex + * + * A plain sequence counter with external writer synchronization by a + * ww_mutex. The ww_mutex is associated to the sequence counter in the static + * initializer or init function. This enables lockdep to validate that + * the write side critical section is properly serialized. + * + * The write side API functions write_seqcount_begin()/end() automatically + * disable and enable preemption when used with seqcount_ww_mutex_t. + */ +typedef struct seqcount_ww_mutex { + seqcount_t seqcount; + __SEQ_LOCKDEP(struct ww_mutex *lock); +} seqcount_ww_mutex_t; + +/** + * SEQCNT_WW_MUTEX_ZERO - static initializer for seqcount_ww_mutex_t + * @name: Name of the seqcount_ww_mutex_t instance + * @lock: Pointer to the associated ww_mutex + */ +#define SEQCNT_WW_MUTEX_ZERO(name, lock) \ + SEQCOUNT_LOCKTYPE_ZERO(name, lock) + +/** + * seqcount_ww_mutex_init - runtime initializer for seqcount_ww_mutex_t + * @s: Pointer to the seqcount_ww_mutex_t instance + * @lock: Pointer to the associated ww_mutex + */ +#define seqcount_ww_mutex_init(s, lock) \ + seqcount_locktype_init(s, lock) + +/* + * @preempt: Is the associated write serialization lock preemtpible? + */ +#define SEQCOUNT_LOCKTYPE(locktype, preempt, lockmember) \ +static inline seqcount_t * \ +__seqcount_##locktype##_ptr(seqcount_##locktype##_t *s) \ +{ \ + return &s->seqcount; \ +} \ + \ +static inline bool \ +__seqcount_##locktype##_preemptible(seqcount_##locktype##_t *s) \ +{ \ + return preempt; \ +} \ + \ +static inline void \ +__seqcount_##locktype##_assert(seqcount_##locktype##_t *s) \ +{ \ + __SEQ_LOCKDEP(lockdep_assert_held(lockmember)); \ +} + +/* + * Similar hooks, but for plain seqcount_t + */ + +static inline seqcount_t *__seqcount_ptr(seqcount_t *s) +{ + return s; +} + +static inline bool __seqcount_preemptible(seqcount_t *s) +{ + return false; +} + +static inline void __seqcount_assert(seqcount_t *s) +{ + lockdep_assert_preemption_disabled(); +} + +/* + * @s: Pointer to seqcount_locktype_t, generated hooks first parameter. + */ +SEQCOUNT_LOCKTYPE(raw_spinlock, false, s->lock) +SEQCOUNT_LOCKTYPE(spinlock, false, s->lock) +SEQCOUNT_LOCKTYPE(rwlock, false, s->lock) +SEQCOUNT_LOCKTYPE(mutex, true, s->lock) +SEQCOUNT_LOCKTYPE(ww_mutex, true, &s->lock->base) + +#define __seqprop_case(s, locktype, prop) \ + seqcount_##locktype##_t: __seqcount_##locktype##_##prop((void *)(s)) + +#define __seqprop(s, prop) _Generic(*(s), \ + seqcount_t: __seqcount_##prop((void *)(s)), \ + __seqprop_case((s), raw_spinlock, prop), \ + __seqprop_case((s), spinlock, prop), \ + __seqprop_case((s), rwlock, prop), \ + __seqprop_case((s), mutex, prop), \ + __seqprop_case((s), ww_mutex, prop)) + +#define __to_seqcount_t(s) __seqprop(s, ptr) +#define __associated_lock_exists_and_is_preemptible(s) __seqprop(s, preemptible) +#define __assert_write_section_is_protected(s) __seqprop(s, assert) + /** * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is @@ -122,7 +388,10 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) * * Return: count to be passed to read_seqcount_retry() */ -static inline unsigned __read_seqcount_begin(const seqcount_t *s) +#define __read_seqcount_begin(s) \ + __read_seqcount_t_begin(__to_seqcount_t(s)) + +static inline unsigned __read_seqcount_t_begin(const seqcount_t *s) { unsigned ret; @@ -138,32 +407,38 @@ repeat: /** * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * * Return: count to be passed to read_seqcount_retry() */ -static inline unsigned raw_read_seqcount_begin(const seqcount_t *s) +#define raw_read_seqcount_begin(s) \ + raw_read_seqcount_t_begin(__to_seqcount_t(s)) + +static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s) { - unsigned ret = __read_seqcount_begin(s); + unsigned ret = __read_seqcount_t_begin(s); smp_rmb(); return ret; } /** * read_seqcount_begin() - begin a seqcount_t read critical section - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * * Return: count to be passed to read_seqcount_retry() */ -static inline unsigned read_seqcount_begin(const seqcount_t *s) +#define read_seqcount_begin(s) \ + read_seqcount_t_begin(__to_seqcount_t(s)) + +static inline unsigned read_seqcount_t_begin(const seqcount_t *s) { seqcount_lockdep_reader_access(s); - return raw_read_seqcount_begin(s); + return raw_read_seqcount_t_begin(s); } /** * raw_read_seqcount() - read the raw seqcount_t counter value - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * * raw_read_seqcount opens a read critical section of the given * seqcount_t, without any lockdep checking, and without checking or @@ -172,7 +447,10 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s) * * Return: count to be passed to read_seqcount_retry() */ -static inline unsigned raw_read_seqcount(const seqcount_t *s) +#define raw_read_seqcount(s) \ + raw_read_seqcount_t(__to_seqcount_t(s)) + +static inline unsigned raw_read_seqcount_t(const seqcount_t *s) { unsigned ret = READ_ONCE(s->sequence); smp_rmb(); @@ -183,7 +461,7 @@ static inline unsigned raw_read_seqcount(const seqcount_t *s) /** * raw_seqcount_begin() - begin a seqcount_t read critical section w/o * lockdep and w/o counter stabilization - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * * raw_seqcount_begin opens a read critical section of the given * seqcount_t. Unlike read_seqcount_begin(), this function will not wait @@ -197,18 +475,21 @@ static inline unsigned raw_read_seqcount(const seqcount_t *s) * * Return: count to be passed to read_seqcount_retry() */ -static inline unsigned raw_seqcount_begin(const seqcount_t *s) +#define raw_seqcount_begin(s) \ + raw_seqcount_t_begin(__to_seqcount_t(s)) + +static inline unsigned raw_seqcount_t_begin(const seqcount_t *s) { /* * If the counter is odd, let read_seqcount_retry() fail * by decrementing the counter. */ - return raw_read_seqcount(s) & ~1; + return raw_read_seqcount_t(s) & ~1; } /** * __read_seqcount_retry() - end a seqcount_t read section w/o barrier - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * @start: count, from read_seqcount_begin() * * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb() @@ -221,7 +502,10 @@ static inline unsigned raw_seqcount_begin(const seqcount_t *s) * * Return: true if a read section retry is required, else false */ -static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start) +#define __read_seqcount_retry(s, start) \ + __read_seqcount_t_retry(__to_seqcount_t(s), start) + +static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start) { kcsan_atomic_next(0); return unlikely(READ_ONCE(s->sequence) != start); @@ -229,7 +513,7 @@ static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start) /** * read_seqcount_retry() - end a seqcount_t read critical section - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * @start: count, from read_seqcount_begin() * * read_seqcount_retry closes the read critical section of given @@ -238,17 +522,28 @@ static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start) * * Return: true if a read section retry is required, else false */ -static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) +#define read_seqcount_retry(s, start) \ + read_seqcount_t_retry(__to_seqcount_t(s), start) + +static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start) { smp_rmb(); - return __read_seqcount_retry(s, start); + return __read_seqcount_t_retry(s, start); } /** * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants */ -static inline void raw_write_seqcount_begin(seqcount_t *s) +#define raw_write_seqcount_begin(s) \ +do { \ + if (__associated_lock_exists_and_is_preemptible(s)) \ + preempt_disable(); \ + \ + raw_write_seqcount_t_begin(__to_seqcount_t(s)); \ +} while (0) + +static inline void raw_write_seqcount_t_begin(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; @@ -257,49 +552,50 @@ static inline void raw_write_seqcount_begin(seqcount_t *s) /** * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants */ -static inline void raw_write_seqcount_end(seqcount_t *s) +#define raw_write_seqcount_end(s) \ +do { \ + raw_write_seqcount_t_end(__to_seqcount_t(s)); \ + \ + if (__associated_lock_exists_and_is_preemptible(s)) \ + preempt_enable(); \ +} while (0) + +static inline void raw_write_seqcount_t_end(seqcount_t *s) { smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } -static inline void __write_seqcount_begin_nested(seqcount_t *s, int subclass) -{ - raw_write_seqcount_begin(s); - seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); -} - /** * write_seqcount_begin_nested() - start a seqcount_t write section with * custom lockdep nesting level - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * @subclass: lockdep nesting level * * See Documentation/locking/lockdep-design.rst */ -static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass) -{ - lockdep_assert_preemption_disabled(); - __write_seqcount_begin_nested(s, subclass); -} - -/* - * A write_seqcount_begin() variant w/o lockdep non-preemptibility checks. - * - * Use for internal seqlock.h code where it's known that preemption is - * already disabled. For example, seqlock_t write side functions. - */ -static inline void __write_seqcount_begin(seqcount_t *s) +#define write_seqcount_begin_nested(s, subclass) \ +do { \ + __assert_write_section_is_protected(s); \ + \ + if (__associated_lock_exists_and_is_preemptible(s)) \ + preempt_disable(); \ + \ + write_seqcount_t_begin_nested(__to_seqcount_t(s), subclass); \ +} while (0) + +static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass) { - __write_seqcount_begin_nested(s, 0); + raw_write_seqcount_t_begin(s); + seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); } /** * write_seqcount_begin() - start a seqcount_t write side critical section - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * * write_seqcount_begin opens a write side critical section of the given * seqcount_t. @@ -308,26 +604,44 @@ static inline void __write_seqcount_begin(seqcount_t *s) * non-preemptible. If readers can be invoked from hardirq or softirq * context, interrupts or bottom halves must be respectively disabled. */ -static inline void write_seqcount_begin(seqcount_t *s) +#define write_seqcount_begin(s) \ +do { \ + __assert_write_section_is_protected(s); \ + \ + if (__associated_lock_exists_and_is_preemptible(s)) \ + preempt_disable(); \ + \ + write_seqcount_t_begin(__to_seqcount_t(s)); \ +} while (0) + +static inline void write_seqcount_t_begin(seqcount_t *s) { - write_seqcount_begin_nested(s, 0); + write_seqcount_t_begin_nested(s, 0); } /** * write_seqcount_end() - end a seqcount_t write side critical section - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * * The write section must've been opened with write_seqcount_begin(). */ -static inline void write_seqcount_end(seqcount_t *s) +#define write_seqcount_end(s) \ +do { \ + write_seqcount_t_end(__to_seqcount_t(s)); \ + \ + if (__associated_lock_exists_and_is_preemptible(s)) \ + preempt_enable(); \ +} while (0) + +static inline void write_seqcount_t_end(seqcount_t *s) { seqcount_release(&s->dep_map, _RET_IP_); - raw_write_seqcount_end(s); + raw_write_seqcount_t_end(s); } /** * raw_write_seqcount_barrier() - do a seqcount_t write barrier - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * * This can be used to provide an ordering guarantee instead of the usual * consistency guarantee. It is one wmb cheaper, because it can collapse @@ -366,7 +680,10 @@ static inline void write_seqcount_end(seqcount_t *s) * WRITE_ONCE(X, false); * } */ -static inline void raw_write_seqcount_barrier(seqcount_t *s) +#define raw_write_seqcount_barrier(s) \ + raw_write_seqcount_t_barrier(__to_seqcount_t(s)) + +static inline void raw_write_seqcount_t_barrier(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; @@ -378,12 +695,15 @@ static inline void raw_write_seqcount_barrier(seqcount_t *s) /** * write_seqcount_invalidate() - invalidate in-progress seqcount_t read * side operations - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * * After write_seqcount_invalidate, no seqcount_t read side operations * will complete successfully and see data older than this. */ -static inline void write_seqcount_invalidate(seqcount_t *s) +#define write_seqcount_invalidate(s) \ + write_seqcount_t_invalidate(__to_seqcount_t(s)) + +static inline void write_seqcount_t_invalidate(seqcount_t *s) { smp_wmb(); kcsan_nestable_atomic_begin(); @@ -393,7 +713,7 @@ static inline void write_seqcount_invalidate(seqcount_t *s) /** * raw_read_seqcount_latch() - pick even/odd seqcount_t latch data copy - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * * Use seqcount_t latching to switch between two storage places protected * by a sequence counter. Doing so allows having interruptible, preemptible, @@ -406,7 +726,10 @@ static inline void write_seqcount_invalidate(seqcount_t *s) * picking which data copy to read. The full counter value must then be * checked with read_seqcount_retry(). */ -static inline int raw_read_seqcount_latch(seqcount_t *s) +#define raw_read_seqcount_latch(s) \ + raw_read_seqcount_t_latch(__to_seqcount_t(s)) + +static inline int raw_read_seqcount_t_latch(seqcount_t *s) { /* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */ int seq = READ_ONCE(s->sequence); /* ^^^ */ @@ -415,7 +738,7 @@ static inline int raw_read_seqcount_latch(seqcount_t *s) /** * raw_write_seqcount_latch() - redirect readers to even/odd copy - * @s: Pointer to seqcount_t + * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never @@ -494,7 +817,10 @@ static inline int raw_read_seqcount_latch(seqcount_t *s) * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. */ -static inline void raw_write_seqcount_latch(seqcount_t *s) +#define raw_write_seqcount_latch(s) \ + raw_write_seqcount_t_latch(__to_seqcount_t(s)) + +static inline void raw_write_seqcount_t_latch(seqcount_t *s) { smp_wmb(); /* prior stores before incrementing "sequence" */ s->sequence++; @@ -592,7 +918,7 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) static inline void write_seqlock(seqlock_t *sl) { spin_lock(&sl->lock); - __write_seqcount_begin(&sl->seqcount); + write_seqcount_t_begin(&sl->seqcount); } /** @@ -604,7 +930,7 @@ static inline void write_seqlock(seqlock_t *sl) */ static inline void write_sequnlock(seqlock_t *sl) { - write_seqcount_end(&sl->seqcount); + write_seqcount_t_end(&sl->seqcount); spin_unlock(&sl->lock); } @@ -618,7 +944,7 @@ static inline void write_sequnlock(seqlock_t *sl) static inline void write_seqlock_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); - __write_seqcount_begin(&sl->seqcount); + write_seqcount_t_begin(&sl->seqcount); } /** @@ -631,7 +957,7 @@ static inline void write_seqlock_bh(seqlock_t *sl) */ static inline void write_sequnlock_bh(seqlock_t *sl) { - write_seqcount_end(&sl->seqcount); + write_seqcount_t_end(&sl->seqcount); spin_unlock_bh(&sl->lock); } @@ -645,7 +971,7 @@ static inline void write_sequnlock_bh(seqlock_t *sl) static inline void write_seqlock_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); - __write_seqcount_begin(&sl->seqcount); + write_seqcount_t_begin(&sl->seqcount); } /** @@ -657,7 +983,7 @@ static inline void write_seqlock_irq(seqlock_t *sl) */ static inline void write_sequnlock_irq(seqlock_t *sl) { - write_seqcount_end(&sl->seqcount); + write_seqcount_t_end(&sl->seqcount); spin_unlock_irq(&sl->lock); } @@ -666,7 +992,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) unsigned long flags; spin_lock_irqsave(&sl->lock, flags); - __write_seqcount_begin(&sl->seqcount); + write_seqcount_t_begin(&sl->seqcount); return flags; } @@ -695,13 +1021,13 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) static inline void write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) { - write_seqcount_end(&sl->seqcount); + write_seqcount_t_end(&sl->seqcount); spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqlock_excl() - begin a seqlock_t locking reader section - * @sl: Pointer to seqlock_t + * @sl: Pointer to seqlock_t * * read_seqlock_excl opens a seqlock_t locking reader critical section. A * locking reader exclusively locks out *both* other writers *and* other -- cgit v1.2.3 From ec8702da570ebb59f38471007bf71359c51b027b Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:16 +0200 Subject: seqlock: Align multi-line macros newline escapes at 72 columns Parent commit, "seqlock: Extend seqcount API with associated locks", introduced a big number of multi-line macros that are newline-escaped at 72 columns. For overall cohesion, align the earlier-existing macros similarly. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-11-a.darwish@linutronix.de --- include/linux/seqlock.h | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 8c16a494c968..b48729988325 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -80,17 +80,18 @@ static inline void __seqcount_init(seqcount_t *s, const char *name, } #ifdef CONFIG_DEBUG_LOCK_ALLOC -# define SEQCOUNT_DEP_MAP_INIT(lockname) \ - .dep_map = { .name = #lockname } \ + +# define SEQCOUNT_DEP_MAP_INIT(lockname) \ + .dep_map = { .name = #lockname } /** * seqcount_init() - runtime initializer for seqcount_t * @s: Pointer to the seqcount_t instance */ -# define seqcount_init(s) \ - do { \ - static struct lock_class_key __key; \ - __seqcount_init((s), #s, &__key); \ +# define seqcount_init(s) \ + do { \ + static struct lock_class_key __key; \ + __seqcount_init((s), #s, &__key); \ } while (0) static inline void seqcount_lockdep_reader_access(const seqcount_t *s) @@ -842,20 +843,20 @@ typedef struct { spinlock_t lock; } seqlock_t; -#define __SEQLOCK_UNLOCKED(lockname) \ - { \ - .seqcount = SEQCNT_ZERO(lockname), \ - .lock = __SPIN_LOCK_UNLOCKED(lockname) \ +#define __SEQLOCK_UNLOCKED(lockname) \ + { \ + .seqcount = SEQCNT_ZERO(lockname), \ + .lock = __SPIN_LOCK_UNLOCKED(lockname) \ } /** * seqlock_init() - dynamic initializer for seqlock_t * @sl: Pointer to the seqlock_t instance */ -#define seqlock_init(sl) \ - do { \ - seqcount_init(&(sl)->seqcount); \ - spin_lock_init(&(sl)->lock); \ +#define seqlock_init(sl) \ + do { \ + seqcount_init(&(sl)->seqcount); \ + spin_lock_init(&(sl)->lock); \ } while (0) /** -- cgit v1.2.3 From 318ce71f3e3ae4108c1665f3860afa8a2a4c9f02 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:17 +0200 Subject: dma-buf: Remove custom seqcount lockdep class key Commit 3c3b177a9369 ("reservation: add support for read-only access using rcu") introduced a sequence counter to manage updates to reservations. Back then, the reservation object initializer reservation_object_init() was always inlined. Having the sequence counter initialization inlined meant that each of the call sites would have a different lockdep class key, which would've broken lockdep's deadlock detection. The aforementioned commit thus introduced, and exported, a custom seqcount lockdep class key and name. The commit 8735f16803f00 ("dma-buf: cleanup reservation_object_init...") transformed the reservation object initializer to a normal non-inlined C function. seqcount_init(), which automatically defines the seqcount lockdep class key and must be called non-inlined, can now be safely used. Remove the seqcount custom lockdep class key, name, and export. Use seqcount_init() inside the dma reservation object initializer. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Sebastian Andrzej Siewior Acked-by: Daniel Vetter Link: https://lkml.kernel.org/r/20200720155530.1173732-12-a.darwish@linutronix.de --- include/linux/dma-resv.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index ee50d10f052b..a6538ae7d93f 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -46,8 +46,6 @@ #include extern struct ww_class reservation_ww_class; -extern struct lock_class_key reservation_seqcount_class; -extern const char reservation_seqcount_string[]; /** * struct dma_resv_list - a list of shared fences -- cgit v1.2.3 From cd29f22019ec4ab998d2e1e8c831c7c42db4aa7d Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:18 +0200 Subject: dma-buf: Use sequence counter with associated wound/wait mutex A sequence counter write side critical section must be protected by some form of locking to serialize writers. If the serialization primitive is not disabling preemption implicitly, preemption has to be explicitly disabled before entering the sequence counter write side critical section. The dma-buf reservation subsystem uses plain sequence counters to manage updates to reservations. Writer serialization is accomplished through a wound/wait mutex. Acquiring a wound/wait mutex does not disable preemption, so this needs to be done manually before and after the write side critical section. Use the newly-added seqcount_ww_mutex_t instead: - It associates the ww_mutex with the sequence count, which enables lockdep to validate that the write side critical section is properly serialized. - It removes the need to explicitly add preempt_disable/enable() around the write side critical section because the write_begin/end() functions for this new data type automatically do this. If lockdep is disabled this ww_mutex lock association is compiled out and has neither storage size nor runtime overhead. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Acked-by: Daniel Vetter Link: https://lkml.kernel.org/r/20200720155530.1173732-13-a.darwish@linutronix.de --- include/linux/dma-resv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index a6538ae7d93f..d44a77e8a7e3 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -69,7 +69,7 @@ struct dma_resv_list { */ struct dma_resv { struct ww_mutex lock; - seqcount_t seq; + seqcount_ww_mutex_t seq; struct dma_fence __rcu *fence_excl; struct dma_resv_list __rcu *fence; -- cgit v1.2.3 From b75058614fdd3140074a640b514f6a0b4d485a2d Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:19 +0200 Subject: sched: tasks: Use sequence counter with associated spinlock A sequence counter write side critical section must be protected by some form of locking to serialize writers. A plain seqcount_t does not contain the information of which lock must be held when entering a write side critical section. Use the new seqcount_spinlock_t data type, which allows to associate a spinlock with the sequence counter. This enables lockdep to verify that the spinlock used for writer serialization is held when the write side critical section is entered. If lockdep is disabled this lock association is compiled out and has neither storage size nor runtime overhead. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-14-a.darwish@linutronix.de --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8d1de021b315..9a9d8263962d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1050,7 +1050,7 @@ struct task_struct { /* Protected by ->alloc_lock: */ nodemask_t mems_allowed; /* Seqence number to catch updates: */ - seqcount_t mems_allowed_seq; + seqcount_spinlock_t mems_allowed_seq; int cpuset_mem_spread_rotor; int cpuset_slab_spread_rotor; #endif -- cgit v1.2.3 From 26475371976c69489d3a8e6c8bbf35afbbc25055 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:24 +0200 Subject: vfs: Use sequence counter with associated spinlock A sequence counter write side critical section must be protected by some form of locking to serialize writers. A plain seqcount_t does not contain the information of which lock must be held when entering a write side critical section. Use the new seqcount_spinlock_t data type, which allows to associate a spinlock with the sequence counter. This enables lockdep to verify that the spinlock used for writer serialization is held when the write side critical section is entered. If lockdep is disabled this lock association is compiled out and has neither storage size nor runtime overhead. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-19-a.darwish@linutronix.de --- include/linux/dcache.h | 2 +- include/linux/fs_struct.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index a81f0c3cf352..65d975bf9390 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -89,7 +89,7 @@ extern struct dentry_stat_t dentry_stat; struct dentry { /* RCU lookup touched fields */ unsigned int d_flags; /* protected by d_lock */ - seqcount_t d_seq; /* per dentry seqlock */ + seqcount_spinlock_t d_seq; /* per dentry seqlock */ struct hlist_bl_node d_hash; /* lookup hash list */ struct dentry *d_parent; /* parent directory */ struct qstr d_name; diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index cf1015abfbf2..783b48dedb72 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -9,7 +9,7 @@ struct fs_struct { int users; spinlock_t lock; - seqcount_t seq; + seqcount_spinlock_t seq; int umask; int in_exec; struct path root, pwd; -- cgit v1.2.3 From 5c73b9a2b1b4ecc809a914aa64970157b3d8c936 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:29 +0200 Subject: kvm/eventfd: Use sequence counter with associated spinlock A sequence counter write side critical section must be protected by some form of locking to serialize writers. A plain seqcount_t does not contain the information of which lock must be held when entering a write side critical section. Use the new seqcount_spinlock_t data type, which allows to associate a spinlock with the sequence counter. This enables lockdep to verify that the spinlock used for writer serialization is held when the write side critical section is entered. If lockdep is disabled this lock association is compiled out and has neither storage size nor runtime overhead. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Acked-by: Paolo Bonzini Link: https://lkml.kernel.org/r/20200720155530.1173732-24-a.darwish@linutronix.de --- include/linux/kvm_irqfd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h index dc1da020305b..dac047abdba7 100644 --- a/include/linux/kvm_irqfd.h +++ b/include/linux/kvm_irqfd.h @@ -42,7 +42,7 @@ struct kvm_kernel_irqfd { wait_queue_entry_t wait; /* Update side is protected by irqfds.lock */ struct kvm_kernel_irq_routing_entry irq_entry; - seqcount_t irq_entry_sc; + seqcount_spinlock_t irq_entry_sc; /* Used for level IRQ fast-path */ int gsi; struct work_struct inject; -- cgit v1.2.3 From af5a06b582ec3d7b0160b4faaa65f73d8dcf989f Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 20 Jul 2020 17:55:30 +0200 Subject: hrtimer: Use sequence counter with associated raw spinlock A sequence counter write side critical section must be protected by some form of locking to serialize writers. A plain seqcount_t does not contain the information of which lock must be held when entering a write side critical section. Use the new seqcount_raw_spinlock_t data type, which allows to associate a raw spinlock with the sequence counter. This enables lockdep to verify that the raw spinlock used for writer serialization is held when the write side critical section is entered. If lockdep is disabled this lock association is compiled out and has neither storage size nor runtime overhead. Signed-off-by: Ahmed S. Darwish Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200720155530.1173732-25-a.darwish@linutronix.de --- include/linux/hrtimer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 15c8ac313678..25993b86ac5c 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -159,7 +159,7 @@ struct hrtimer_clock_base { struct hrtimer_cpu_base *cpu_base; unsigned int index; clockid_t clockid; - seqcount_t seq; + seqcount_raw_spinlock_t seq; struct hrtimer *running; struct timerqueue_head active; ktime_t (*get_time)(void); -- cgit v1.2.3 From e55687fe5c1e4849e5559a0a49199c9ca3fff36e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 23 Jul 2020 11:56:22 +0200 Subject: seqlock: s/__SEQ_LOCKDEP/__SEQ_LOCK/g __SEQ_LOCKDEP() is an expression gate for the seqcount_LOCKNAME_t::lock member. Rename it to be about the member, not the gate condition. Later (PREEMPT_RT) patches will make the member available for !LOCKDEP configs. Signed-off-by: Peter Zijlstra (Intel) --- include/linux/seqlock.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index b48729988325..c689abab06c8 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -133,20 +133,20 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) */ #ifdef CONFIG_LOCKDEP -#define __SEQ_LOCKDEP(expr) expr +#define __SEQ_LOCK(expr) expr #else -#define __SEQ_LOCKDEP(expr) +#define __SEQ_LOCK(expr) #endif #define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ - __SEQ_LOCKDEP(.lock = (assoc_lock)) \ + __SEQ_LOCK(.lock = (assoc_lock)) \ } #define seqcount_locktype_init(s, assoc_lock) \ do { \ seqcount_init(&(s)->seqcount); \ - __SEQ_LOCKDEP((s)->lock = (assoc_lock)); \ + __SEQ_LOCK((s)->lock = (assoc_lock)); \ } while (0) /** @@ -161,7 +161,7 @@ do { \ */ typedef struct seqcount_spinlock { seqcount_t seqcount; - __SEQ_LOCKDEP(spinlock_t *lock); + __SEQ_LOCK(spinlock_t *lock); } seqcount_spinlock_t; /** @@ -192,7 +192,7 @@ typedef struct seqcount_spinlock { */ typedef struct seqcount_raw_spinlock { seqcount_t seqcount; - __SEQ_LOCKDEP(raw_spinlock_t *lock); + __SEQ_LOCK(raw_spinlock_t *lock); } seqcount_raw_spinlock_t; /** @@ -223,7 +223,7 @@ typedef struct seqcount_raw_spinlock { */ typedef struct seqcount_rwlock { seqcount_t seqcount; - __SEQ_LOCKDEP(rwlock_t *lock); + __SEQ_LOCK(rwlock_t *lock); } seqcount_rwlock_t; /** @@ -257,7 +257,7 @@ typedef struct seqcount_rwlock { */ typedef struct seqcount_mutex { seqcount_t seqcount; - __SEQ_LOCKDEP(struct mutex *lock); + __SEQ_LOCK(struct mutex *lock); } seqcount_mutex_t; /** @@ -291,7 +291,7 @@ typedef struct seqcount_mutex { */ typedef struct seqcount_ww_mutex { seqcount_t seqcount; - __SEQ_LOCKDEP(struct ww_mutex *lock); + __SEQ_LOCK(struct ww_mutex *lock); } seqcount_ww_mutex_t; /** @@ -329,7 +329,7 @@ __seqcount_##locktype##_preemptible(seqcount_##locktype##_t *s) \ static inline void \ __seqcount_##locktype##_assert(seqcount_##locktype##_t *s) \ { \ - __SEQ_LOCKDEP(lockdep_assert_held(lockmember)); \ + __SEQ_LOCK(lockdep_assert_held(lockmember)); \ } /* -- cgit v1.2.3 From a8772dccb2ec7b139db1b3ba782ecb12ed92d7c3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 23 Jul 2020 11:56:49 +0200 Subject: seqlock: Fold seqcount_LOCKNAME_t definition Manual repetition is boring and error prone. Signed-off-by: Peter Zijlstra (Intel) --- include/linux/seqlock.h | 142 +++++++++++++----------------------------------- 1 file changed, 39 insertions(+), 103 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index c689abab06c8..4b259bb4d4b9 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -149,21 +149,6 @@ do { \ __SEQ_LOCK((s)->lock = (assoc_lock)); \ } while (0) -/** - * typedef seqcount_spinlock_t - sequence counter with spinlock associated - * @seqcount: The real sequence counter - * @lock: Pointer to the associated spinlock - * - * A plain sequence counter with external writer synchronization by a - * spinlock. The spinlock is associated to the sequence count in the - * static initializer or init function. This enables lockdep to validate - * that the write side critical section is properly serialized. - */ -typedef struct seqcount_spinlock { - seqcount_t seqcount; - __SEQ_LOCK(spinlock_t *lock); -} seqcount_spinlock_t; - /** * SEQCNT_SPINLOCK_ZERO - static initializer for seqcount_spinlock_t * @name: Name of the seqcount_spinlock_t instance @@ -180,21 +165,6 @@ typedef struct seqcount_spinlock { #define seqcount_spinlock_init(s, lock) \ seqcount_locktype_init(s, lock) -/** - * typedef seqcount_raw_spinlock_t - sequence count with raw spinlock associated - * @seqcount: The real sequence counter - * @lock: Pointer to the associated raw spinlock - * - * A plain sequence counter with external writer synchronization by a - * raw spinlock. The raw spinlock is associated to the sequence count in - * the static initializer or init function. This enables lockdep to - * validate that the write side critical section is properly serialized. - */ -typedef struct seqcount_raw_spinlock { - seqcount_t seqcount; - __SEQ_LOCK(raw_spinlock_t *lock); -} seqcount_raw_spinlock_t; - /** * SEQCNT_RAW_SPINLOCK_ZERO - static initializer for seqcount_raw_spinlock_t * @name: Name of the seqcount_raw_spinlock_t instance @@ -211,21 +181,6 @@ typedef struct seqcount_raw_spinlock { #define seqcount_raw_spinlock_init(s, lock) \ seqcount_locktype_init(s, lock) -/** - * typedef seqcount_rwlock_t - sequence count with rwlock associated - * @seqcount: The real sequence counter - * @lock: Pointer to the associated rwlock - * - * A plain sequence counter with external writer synchronization by a - * rwlock. The rwlock is associated to the sequence count in the static - * initializer or init function. This enables lockdep to validate that - * the write side critical section is properly serialized. - */ -typedef struct seqcount_rwlock { - seqcount_t seqcount; - __SEQ_LOCK(rwlock_t *lock); -} seqcount_rwlock_t; - /** * SEQCNT_RWLOCK_ZERO - static initializer for seqcount_rwlock_t * @name: Name of the seqcount_rwlock_t instance @@ -242,24 +197,6 @@ typedef struct seqcount_rwlock { #define seqcount_rwlock_init(s, lock) \ seqcount_locktype_init(s, lock) -/** - * typedef seqcount_mutex_t - sequence count with mutex associated - * @seqcount: The real sequence counter - * @lock: Pointer to the associated mutex - * - * A plain sequence counter with external writer synchronization by a - * mutex. The mutex is associated to the sequence counter in the static - * initializer or init function. This enables lockdep to validate that - * the write side critical section is properly serialized. - * - * The write side API functions write_seqcount_begin()/end() automatically - * disable and enable preemption when used with seqcount_mutex_t. - */ -typedef struct seqcount_mutex { - seqcount_t seqcount; - __SEQ_LOCK(struct mutex *lock); -} seqcount_mutex_t; - /** * SEQCNT_MUTEX_ZERO - static initializer for seqcount_mutex_t * @name: Name of the seqcount_mutex_t instance @@ -276,24 +213,6 @@ typedef struct seqcount_mutex { #define seqcount_mutex_init(s, lock) \ seqcount_locktype_init(s, lock) -/** - * typedef seqcount_ww_mutex_t - sequence count with ww_mutex associated - * @seqcount: The real sequence counter - * @lock: Pointer to the associated ww_mutex - * - * A plain sequence counter with external writer synchronization by a - * ww_mutex. The ww_mutex is associated to the sequence counter in the static - * initializer or init function. This enables lockdep to validate that - * the write side critical section is properly serialized. - * - * The write side API functions write_seqcount_begin()/end() automatically - * disable and enable preemption when used with seqcount_ww_mutex_t. - */ -typedef struct seqcount_ww_mutex { - seqcount_t seqcount; - __SEQ_LOCK(struct ww_mutex *lock); -} seqcount_ww_mutex_t; - /** * SEQCNT_WW_MUTEX_ZERO - static initializer for seqcount_ww_mutex_t * @name: Name of the seqcount_ww_mutex_t instance @@ -310,30 +229,50 @@ typedef struct seqcount_ww_mutex { #define seqcount_ww_mutex_init(s, lock) \ seqcount_locktype_init(s, lock) -/* - * @preempt: Is the associated write serialization lock preemtpible? +/** + * typedef seqcount_LOCKNAME_t - sequence counter with spinlock associated + * @seqcount: The real sequence counter + * @lock: Pointer to the associated spinlock + * + * A plain sequence counter with external writer synchronization by a + * spinlock. The spinlock is associated to the sequence count in the + * static initializer or init function. This enables lockdep to validate + * that the write side critical section is properly serialized. */ -#define SEQCOUNT_LOCKTYPE(locktype, preempt, lockmember) \ -static inline seqcount_t * \ -__seqcount_##locktype##_ptr(seqcount_##locktype##_t *s) \ + +/* + * SEQCOUNT_LOCKTYPE() - Instantiate seqcount_LOCKNAME_t and helpers + * @locktype: actual typename + * @lockname: name + * @preemptible: preemptibility of above locktype + * @lockmember: argument for lockdep_assert_held() + */ +#define SEQCOUNT_LOCKTYPE(locktype, lockname, preemptible, lockmember) \ +typedef struct seqcount_##lockname { \ + seqcount_t seqcount; \ + __SEQ_LOCK(locktype *lock); \ +} seqcount_##lockname##_t; \ + \ +static __always_inline seqcount_t * \ +__seqcount_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ -static inline bool \ -__seqcount_##locktype##_preemptible(seqcount_##locktype##_t *s) \ +static __always_inline bool \ +__seqcount_##lockname##_preemptible(seqcount_##lockname##_t *s) \ { \ - return preempt; \ + return preemptible; \ } \ \ -static inline void \ -__seqcount_##locktype##_assert(seqcount_##locktype##_t *s) \ +static __always_inline void \ +__seqcount_##lockname##_assert(seqcount_##lockname##_t *s) \ { \ __SEQ_LOCK(lockdep_assert_held(lockmember)); \ } /* - * Similar hooks, but for plain seqcount_t + * __seqprop() for seqcount_t */ static inline seqcount_t *__seqcount_ptr(seqcount_t *s) @@ -351,17 +290,14 @@ static inline void __seqcount_assert(seqcount_t *s) lockdep_assert_preemption_disabled(); } -/* - * @s: Pointer to seqcount_locktype_t, generated hooks first parameter. - */ -SEQCOUNT_LOCKTYPE(raw_spinlock, false, s->lock) -SEQCOUNT_LOCKTYPE(spinlock, false, s->lock) -SEQCOUNT_LOCKTYPE(rwlock, false, s->lock) -SEQCOUNT_LOCKTYPE(mutex, true, s->lock) -SEQCOUNT_LOCKTYPE(ww_mutex, true, &s->lock->base) - -#define __seqprop_case(s, locktype, prop) \ - seqcount_##locktype##_t: __seqcount_##locktype##_##prop((void *)(s)) +SEQCOUNT_LOCKTYPE(raw_spinlock_t, raw_spinlock, false, s->lock) +SEQCOUNT_LOCKTYPE(spinlock_t, spinlock, false, s->lock) +SEQCOUNT_LOCKTYPE(rwlock_t, rwlock, false, s->lock) +SEQCOUNT_LOCKTYPE(struct mutex, mutex, true, s->lock) +SEQCOUNT_LOCKTYPE(struct ww_mutex, ww_mutex, true, &s->lock->base) + +#define __seqprop_case(s, lockname, prop) \ + seqcount_##lockname##_t: __seqcount_##lockname##_##prop((void *)(s)) #define __seqprop(s, prop) _Generic(*(s), \ seqcount_t: __seqcount_##prop((void *)(s)), \ -- cgit v1.2.3 From e4e9ab3f9f91ad3b88d12363f890e8ad9b59b645 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 23 Jul 2020 12:00:53 +0200 Subject: seqlock: Fold seqcount_LOCKNAME_init() definition Manual repetition is boring and error prone. Signed-off-by: Peter Zijlstra (Intel) --- include/linux/seqlock.h | 61 ++++++++++++------------------------------------- 1 file changed, 14 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 4b259bb4d4b9..501ff47d1e8e 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -143,12 +143,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) __SEQ_LOCK(.lock = (assoc_lock)) \ } -#define seqcount_locktype_init(s, assoc_lock) \ -do { \ - seqcount_init(&(s)->seqcount); \ - __SEQ_LOCK((s)->lock = (assoc_lock)); \ -} while (0) - /** * SEQCNT_SPINLOCK_ZERO - static initializer for seqcount_spinlock_t * @name: Name of the seqcount_spinlock_t instance @@ -157,14 +151,6 @@ do { \ #define SEQCNT_SPINLOCK_ZERO(name, lock) \ SEQCOUNT_LOCKTYPE_ZERO(name, lock) -/** - * seqcount_spinlock_init - runtime initializer for seqcount_spinlock_t - * @s: Pointer to the seqcount_spinlock_t instance - * @lock: Pointer to the associated spinlock - */ -#define seqcount_spinlock_init(s, lock) \ - seqcount_locktype_init(s, lock) - /** * SEQCNT_RAW_SPINLOCK_ZERO - static initializer for seqcount_raw_spinlock_t * @name: Name of the seqcount_raw_spinlock_t instance @@ -173,14 +159,6 @@ do { \ #define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) \ SEQCOUNT_LOCKTYPE_ZERO(name, lock) -/** - * seqcount_raw_spinlock_init - runtime initializer for seqcount_raw_spinlock_t - * @s: Pointer to the seqcount_raw_spinlock_t instance - * @lock: Pointer to the associated raw_spinlock - */ -#define seqcount_raw_spinlock_init(s, lock) \ - seqcount_locktype_init(s, lock) - /** * SEQCNT_RWLOCK_ZERO - static initializer for seqcount_rwlock_t * @name: Name of the seqcount_rwlock_t instance @@ -189,14 +167,6 @@ do { \ #define SEQCNT_RWLOCK_ZERO(name, lock) \ SEQCOUNT_LOCKTYPE_ZERO(name, lock) -/** - * seqcount_rwlock_init - runtime initializer for seqcount_rwlock_t - * @s: Pointer to the seqcount_rwlock_t instance - * @lock: Pointer to the associated rwlock - */ -#define seqcount_rwlock_init(s, lock) \ - seqcount_locktype_init(s, lock) - /** * SEQCNT_MUTEX_ZERO - static initializer for seqcount_mutex_t * @name: Name of the seqcount_mutex_t instance @@ -205,14 +175,6 @@ do { \ #define SEQCNT_MUTEX_ZERO(name, lock) \ SEQCOUNT_LOCKTYPE_ZERO(name, lock) -/** - * seqcount_mutex_init - runtime initializer for seqcount_mutex_t - * @s: Pointer to the seqcount_mutex_t instance - * @lock: Pointer to the associated mutex - */ -#define seqcount_mutex_init(s, lock) \ - seqcount_locktype_init(s, lock) - /** * SEQCNT_WW_MUTEX_ZERO - static initializer for seqcount_ww_mutex_t * @name: Name of the seqcount_ww_mutex_t instance @@ -222,15 +184,7 @@ do { \ SEQCOUNT_LOCKTYPE_ZERO(name, lock) /** - * seqcount_ww_mutex_init - runtime initializer for seqcount_ww_mutex_t - * @s: Pointer to the seqcount_ww_mutex_t instance - * @lock: Pointer to the associated ww_mutex - */ -#define seqcount_ww_mutex_init(s, lock) \ - seqcount_locktype_init(s, lock) - -/** - * typedef seqcount_LOCKNAME_t - sequence counter with spinlock associated + * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPR associated * @seqcount: The real sequence counter * @lock: Pointer to the associated spinlock * @@ -240,6 +194,12 @@ do { \ * that the write side critical section is properly serialized. */ +/** + * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t + * @s: Pointer to the seqcount_LOCKNAME_t instance + * @lock: Pointer to the associated LOCKTYPE + */ + /* * SEQCOUNT_LOCKTYPE() - Instantiate seqcount_LOCKNAME_t and helpers * @locktype: actual typename @@ -253,6 +213,13 @@ typedef struct seqcount_##lockname { \ __SEQ_LOCK(locktype *lock); \ } seqcount_##lockname##_t; \ \ +static __always_inline void \ +seqcount_##lockname##_init(seqcount_##lockname##_t *s, locktype *lock) \ +{ \ + seqcount_init(&s->seqcount); \ + __SEQ_LOCK(s->lock = lock); \ +} \ + \ static __always_inline seqcount_t * \ __seqcount_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ -- cgit v1.2.3 From 0efc94c5d15c3da0a69543d86ad2180f39256ed6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 23 Jul 2020 12:03:13 +0200 Subject: seqcount: Compress SEQCNT_LOCKNAME_ZERO() Less is more. Signed-off-by: Peter Zijlstra (Intel) --- include/linux/seqlock.h | 63 ++++++++++++++----------------------------------- 1 file changed, 18 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 501ff47d1e8e..251dcd6f5cd8 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -138,51 +138,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) #define __SEQ_LOCK(expr) #endif -#define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) { \ - .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ - __SEQ_LOCK(.lock = (assoc_lock)) \ -} - -/** - * SEQCNT_SPINLOCK_ZERO - static initializer for seqcount_spinlock_t - * @name: Name of the seqcount_spinlock_t instance - * @lock: Pointer to the associated spinlock - */ -#define SEQCNT_SPINLOCK_ZERO(name, lock) \ - SEQCOUNT_LOCKTYPE_ZERO(name, lock) - -/** - * SEQCNT_RAW_SPINLOCK_ZERO - static initializer for seqcount_raw_spinlock_t - * @name: Name of the seqcount_raw_spinlock_t instance - * @lock: Pointer to the associated raw_spinlock - */ -#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) \ - SEQCOUNT_LOCKTYPE_ZERO(name, lock) - -/** - * SEQCNT_RWLOCK_ZERO - static initializer for seqcount_rwlock_t - * @name: Name of the seqcount_rwlock_t instance - * @lock: Pointer to the associated rwlock - */ -#define SEQCNT_RWLOCK_ZERO(name, lock) \ - SEQCOUNT_LOCKTYPE_ZERO(name, lock) - -/** - * SEQCNT_MUTEX_ZERO - static initializer for seqcount_mutex_t - * @name: Name of the seqcount_mutex_t instance - * @lock: Pointer to the associated mutex - */ -#define SEQCNT_MUTEX_ZERO(name, lock) \ - SEQCOUNT_LOCKTYPE_ZERO(name, lock) - -/** - * SEQCNT_WW_MUTEX_ZERO - static initializer for seqcount_ww_mutex_t - * @name: Name of the seqcount_ww_mutex_t instance - * @lock: Pointer to the associated ww_mutex - */ -#define SEQCNT_WW_MUTEX_ZERO(name, lock) \ - SEQCOUNT_LOCKTYPE_ZERO(name, lock) - /** * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPR associated * @seqcount: The real sequence counter @@ -263,6 +218,24 @@ SEQCOUNT_LOCKTYPE(rwlock_t, rwlock, false, s->lock) SEQCOUNT_LOCKTYPE(struct mutex, mutex, true, s->lock) SEQCOUNT_LOCKTYPE(struct ww_mutex, ww_mutex, true, &s->lock->base) +/** + * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t + * @name: Name of the seqcount_LOCKNAME_t instance + * @lock: Pointer to the associated LOCKTYPE + */ + +#define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) { \ + .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ + __SEQ_LOCK(.lock = (assoc_lock)) \ +} + +#define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock) +#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock) +#define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock) +#define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock) +#define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock) + + #define __seqprop_case(s, lockname, prop) \ seqcount_##lockname##_t: __seqcount_##lockname##_##prop((void *)(s)) -- cgit v1.2.3 From b5e6a027bd327daa679ca55182a920659e2cbb90 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 23 Jul 2020 12:11:49 +0200 Subject: seqcount: More consistent seqprop names Attempt uniformity and brevity. Signed-off-by: Peter Zijlstra (Intel) --- include/linux/seqlock.h | 52 ++++++++++++++++++++++++------------------------- 1 file changed, 26 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 251dcd6f5cd8..a076f783aa36 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -247,9 +247,9 @@ SEQCOUNT_LOCKTYPE(struct ww_mutex, ww_mutex, true, &s->lock->base) __seqprop_case((s), mutex, prop), \ __seqprop_case((s), ww_mutex, prop)) -#define __to_seqcount_t(s) __seqprop(s, ptr) -#define __associated_lock_exists_and_is_preemptible(s) __seqprop(s, preemptible) -#define __assert_write_section_is_protected(s) __seqprop(s, assert) +#define __seqcount_ptr(s) __seqprop(s, ptr) +#define __seqcount_lock_preemptible(s) __seqprop(s, preemptible) +#define __seqcount_assert_lock_held(s) __seqprop(s, assert) /** * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier @@ -266,7 +266,7 @@ SEQCOUNT_LOCKTYPE(struct ww_mutex, ww_mutex, true, &s->lock->base) * Return: count to be passed to read_seqcount_retry() */ #define __read_seqcount_begin(s) \ - __read_seqcount_t_begin(__to_seqcount_t(s)) + __read_seqcount_t_begin(__seqcount_ptr(s)) static inline unsigned __read_seqcount_t_begin(const seqcount_t *s) { @@ -289,7 +289,7 @@ repeat: * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount_begin(s) \ - raw_read_seqcount_t_begin(__to_seqcount_t(s)) + raw_read_seqcount_t_begin(__seqcount_ptr(s)) static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s) { @@ -305,7 +305,7 @@ static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s) * Return: count to be passed to read_seqcount_retry() */ #define read_seqcount_begin(s) \ - read_seqcount_t_begin(__to_seqcount_t(s)) + read_seqcount_t_begin(__seqcount_ptr(s)) static inline unsigned read_seqcount_t_begin(const seqcount_t *s) { @@ -325,7 +325,7 @@ static inline unsigned read_seqcount_t_begin(const seqcount_t *s) * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount(s) \ - raw_read_seqcount_t(__to_seqcount_t(s)) + raw_read_seqcount_t(__seqcount_ptr(s)) static inline unsigned raw_read_seqcount_t(const seqcount_t *s) { @@ -353,7 +353,7 @@ static inline unsigned raw_read_seqcount_t(const seqcount_t *s) * Return: count to be passed to read_seqcount_retry() */ #define raw_seqcount_begin(s) \ - raw_seqcount_t_begin(__to_seqcount_t(s)) + raw_seqcount_t_begin(__seqcount_ptr(s)) static inline unsigned raw_seqcount_t_begin(const seqcount_t *s) { @@ -380,7 +380,7 @@ static inline unsigned raw_seqcount_t_begin(const seqcount_t *s) * Return: true if a read section retry is required, else false */ #define __read_seqcount_retry(s, start) \ - __read_seqcount_t_retry(__to_seqcount_t(s), start) + __read_seqcount_t_retry(__seqcount_ptr(s), start) static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start) { @@ -400,7 +400,7 @@ static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start) * Return: true if a read section retry is required, else false */ #define read_seqcount_retry(s, start) \ - read_seqcount_t_retry(__to_seqcount_t(s), start) + read_seqcount_t_retry(__seqcount_ptr(s), start) static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start) { @@ -414,10 +414,10 @@ static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start) */ #define raw_write_seqcount_begin(s) \ do { \ - if (__associated_lock_exists_and_is_preemptible(s)) \ + if (__seqcount_lock_preemptible(s)) \ preempt_disable(); \ \ - raw_write_seqcount_t_begin(__to_seqcount_t(s)); \ + raw_write_seqcount_t_begin(__seqcount_ptr(s)); \ } while (0) static inline void raw_write_seqcount_t_begin(seqcount_t *s) @@ -433,9 +433,9 @@ static inline void raw_write_seqcount_t_begin(seqcount_t *s) */ #define raw_write_seqcount_end(s) \ do { \ - raw_write_seqcount_t_end(__to_seqcount_t(s)); \ + raw_write_seqcount_t_end(__seqcount_ptr(s)); \ \ - if (__associated_lock_exists_and_is_preemptible(s)) \ + if (__seqcount_lock_preemptible(s)) \ preempt_enable(); \ } while (0) @@ -456,12 +456,12 @@ static inline void raw_write_seqcount_t_end(seqcount_t *s) */ #define write_seqcount_begin_nested(s, subclass) \ do { \ - __assert_write_section_is_protected(s); \ + __seqcount_assert_lock_held(s); \ \ - if (__associated_lock_exists_and_is_preemptible(s)) \ + if (__seqcount_lock_preemptible(s)) \ preempt_disable(); \ \ - write_seqcount_t_begin_nested(__to_seqcount_t(s), subclass); \ + write_seqcount_t_begin_nested(__seqcount_ptr(s), subclass); \ } while (0) static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass) @@ -483,12 +483,12 @@ static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass) */ #define write_seqcount_begin(s) \ do { \ - __assert_write_section_is_protected(s); \ + __seqcount_assert_lock_held(s); \ \ - if (__associated_lock_exists_and_is_preemptible(s)) \ + if (__seqcount_lock_preemptible(s)) \ preempt_disable(); \ \ - write_seqcount_t_begin(__to_seqcount_t(s)); \ + write_seqcount_t_begin(__seqcount_ptr(s)); \ } while (0) static inline void write_seqcount_t_begin(seqcount_t *s) @@ -504,9 +504,9 @@ static inline void write_seqcount_t_begin(seqcount_t *s) */ #define write_seqcount_end(s) \ do { \ - write_seqcount_t_end(__to_seqcount_t(s)); \ + write_seqcount_t_end(__seqcount_ptr(s)); \ \ - if (__associated_lock_exists_and_is_preemptible(s)) \ + if (__seqcount_lock_preemptible(s)) \ preempt_enable(); \ } while (0) @@ -558,7 +558,7 @@ static inline void write_seqcount_t_end(seqcount_t *s) * } */ #define raw_write_seqcount_barrier(s) \ - raw_write_seqcount_t_barrier(__to_seqcount_t(s)) + raw_write_seqcount_t_barrier(__seqcount_ptr(s)) static inline void raw_write_seqcount_t_barrier(seqcount_t *s) { @@ -578,7 +578,7 @@ static inline void raw_write_seqcount_t_barrier(seqcount_t *s) * will complete successfully and see data older than this. */ #define write_seqcount_invalidate(s) \ - write_seqcount_t_invalidate(__to_seqcount_t(s)) + write_seqcount_t_invalidate(__seqcount_ptr(s)) static inline void write_seqcount_t_invalidate(seqcount_t *s) { @@ -604,7 +604,7 @@ static inline void write_seqcount_t_invalidate(seqcount_t *s) * checked with read_seqcount_retry(). */ #define raw_read_seqcount_latch(s) \ - raw_read_seqcount_t_latch(__to_seqcount_t(s)) + raw_read_seqcount_t_latch(__seqcount_ptr(s)) static inline int raw_read_seqcount_t_latch(seqcount_t *s) { @@ -695,7 +695,7 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s) * patterns to manage the lifetimes of the objects within. */ #define raw_write_seqcount_latch(s) \ - raw_write_seqcount_t_latch(__to_seqcount_t(s)) + raw_write_seqcount_t_latch(__seqcount_ptr(s)) static inline void raw_write_seqcount_t_latch(seqcount_t *s) { -- cgit v1.2.3 From 5037d368b2c2c90e9432d477e5562dce1c33d5c9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andreas=20F=C3=A4rber?= Date: Wed, 22 Jul 2020 11:06:57 +0100 Subject: nvmem: core: Add nvmem_cell_read_u8() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Complement the u16, u32 and u64 helpers with a u8 variant to ease accessing byte-sized values. This helper will be useful for Realtek Digital Home Center platforms, which store some byte and sub-byte sized values in non-volatile memory. Signed-off-by: Andreas Färber Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20200722100705.7772-7-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 1b311d27c9b8..052293f4cbdb 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -61,6 +61,7 @@ void nvmem_cell_put(struct nvmem_cell *cell); void devm_nvmem_cell_put(struct device *dev, struct nvmem_cell *cell); void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len); int nvmem_cell_write(struct nvmem_cell *cell, void *buf, size_t len); +int nvmem_cell_read_u8(struct device *dev, const char *cell_id, u8 *val); int nvmem_cell_read_u16(struct device *dev, const char *cell_id, u16 *val); int nvmem_cell_read_u32(struct device *dev, const char *cell_id, u32 *val); int nvmem_cell_read_u64(struct device *dev, const char *cell_id, u64 *val); -- cgit v1.2.3 From 731aa3fae8137ebca83a01d20fbf3effb4798fc8 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Wed, 22 Jul 2020 11:06:58 +0100 Subject: nvmem: core: add support to auto devid For nvmem providers which have multiple instances, it is required to suffix the provider name with proper id, so that they do not confict for the same name. Currently the core does not handle this case properly eventhough core already has logic to generate the id. This patch add new devid type NVMEM_DEVID_AUTO for providers to be able to allow core to assign id and append it to provier name. Reported-by: Shawn Guo Signed-off-by: Srinivas Kandagatla Tested-by: Shawn Guo Link: https://lore.kernel.org/r/20200722100705.7772-8-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 6d6f8e5d24c9..06409a6c40bc 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -27,6 +27,9 @@ enum nvmem_type { NVMEM_TYPE_BATTERY_BACKED, }; +#define NVMEM_DEVID_NONE (-1) +#define NVMEM_DEVID_AUTO (-2) + /** * struct nvmem_config - NVMEM device configuration * -- cgit v1.2.3 From 868f3ee6e452bc2b89e68183a1700fcbbe0807b1 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Thu, 23 Jul 2020 03:33:54 +0300 Subject: serial: 8250: Add 8250 port clock update method Some platforms can be designed in a way so the UART port reference clock might be asynchronously changed at some point. In Baikal-T1 SoC this may happen due to the reference clock being shared between two UART ports, on the Allwinner SoC the reference clock is derived from the CPU clock, so any CPU frequency change should get to be known/reflected by/in the UART controller as well. But it's not enough to just update the uart_port->uartclk field of the corresponding UART port, the 8250 controller reference clock divisor should be altered so to preserve current baud rate setting. All of these things is done in a coherent way by calling the serial8250_update_uartclk() method provided in this patch. Though note that it isn't supposed to be called from within the UART port callbacks because the locks using to the protect the UART port data are already taken in there. Signed-off-by: Serge Semin Link: https://lore.kernel.org/r/20200723003357.26897-2-Sergey.Semin@baikalelectronics.ru Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 6545f8cfc8fa..2b70f736b091 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -155,6 +155,8 @@ extern int early_serial_setup(struct uart_port *port); extern int early_serial8250_setup(struct earlycon_device *device, const char *options); +extern void serial8250_update_uartclk(struct uart_port *port, + unsigned int uartclk); extern void serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, struct ktermios *old); extern void serial8250_do_set_ldisc(struct uart_port *port, -- cgit v1.2.3 From efe9711214e6138a5a2a46ca4068bfce50c03444 Mon Sep 17 00:00:00 2001 From: Neal Liu Date: Mon, 27 Jul 2020 11:25:46 +0800 Subject: cpuidle: change enter_s2idle() prototype Control Flow Integrity(CFI) is a security mechanism that disallows changes to the original control flow graph of a compiled binary, making it significantly harder to perform such attacks. init_state_node() assign same function callback to different function pointer declarations. static int init_state_node(struct cpuidle_state *idle_state, const struct of_device_id *matches, struct device_node *state_node) { ... idle_state->enter = match_id->data; ... idle_state->enter_s2idle = match_id->data; } Function declarations: struct cpuidle_state { ... int (*enter) (struct cpuidle_device *dev, struct cpuidle_driver *drv, int index); void (*enter_s2idle) (struct cpuidle_device *dev, struct cpuidle_driver *drv, int index); }; In this case, either enter() or enter_s2idle() would cause CFI check failed since they use same callee. Align function prototype of enter() since it needs return value for some use cases. The return value of enter_s2idle() is no need currently. Signed-off-by: Neal Liu Reviewed-by: Sami Tolvanen Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index ec2ef63771f0..b65909ae4e20 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -65,10 +65,13 @@ struct cpuidle_state { * CPUs execute ->enter_s2idle with the local tick or entire timekeeping * suspended, so it must not re-enable interrupts at any point (even * temporarily) or attempt to change states of clock event devices. + * + * This callback may point to the same function as ->enter if all of + * the above requirements are met by it. */ - void (*enter_s2idle) (struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index); + int (*enter_s2idle)(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index); }; /* Idle State Flags */ -- cgit v1.2.3 From f227e3ec3b5cad859ad15666874405e8c1bbc1d4 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Fri, 10 Jul 2020 15:23:19 +0200 Subject: random32: update the net random state on interrupt and activity This modifies the first 32 bits out of the 128 bits of a random CPU's net_rand_state on interrupt or CPU activity to complicate remote observations that could lead to guessing the network RNG's internal state. Note that depending on some network devices' interrupt rate moderation or binding, this re-seeding might happen on every packet or even almost never. In addition, with NOHZ some CPUs might not even get timer interrupts, leaving their local state rarely updated, while they are running networked processes making use of the random state. For this reason, we also perform this update in update_process_times() in order to at least update the state when there is user or system activity, since it's the only case we care about. Reported-by: Amit Klein Suggested-by: Linus Torvalds Cc: Eric Dumazet Cc: "Jason A. Donenfeld" Cc: Andy Lutomirski Cc: Kees Cook Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Signed-off-by: Willy Tarreau Signed-off-by: Linus Torvalds --- include/linux/random.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index 45e1f8fa742b..39aaa1f78f9d 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -11,6 +11,7 @@ #include #include #include +#include #include @@ -119,6 +120,8 @@ struct rnd_state { __u32 s1, s2, s3, s4; }; +DECLARE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; + u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); -- cgit v1.2.3 From 2167c40657981f8a3d1ff1f04d4bda6b4a64f8e2 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Tue, 28 Jul 2020 23:03:41 +0200 Subject: PCI: Remove unused pci_lost_interrupt() 388c8c16abaf ("PCI: add routines for debugging and handling lost interrupts") added pci_lost_interrupt() that apparently never has had a single user. Remove it. Link: https://lore.kernel.org/r/e328d059-3068-6a40-28df-f81f616d15a0@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c79d83304e52..2dcd67f509a8 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1053,13 +1053,6 @@ void pci_sort_breadthfirst(void); /* Generic PCI functions exported to card drivers */ -enum pci_lost_interrupt_reason { - PCI_LOST_IRQ_NO_INFORMATION = 0, - PCI_LOST_IRQ_DISABLE_MSI, - PCI_LOST_IRQ_DISABLE_MSIX, - PCI_LOST_IRQ_DISABLE_ACPI, -}; -enum pci_lost_interrupt_reason pci_lost_interrupt(struct pci_dev *dev); int pci_find_capability(struct pci_dev *dev, int cap); int pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap); int pci_find_ext_capability(struct pci_dev *dev, int cap); -- cgit v1.2.3 From 6f24ff97e3231a5303841c5196a6f460f8485eb4 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Wed, 29 Jul 2020 13:31:43 -0500 Subject: power: supply: bq27xxx_battery: Add the BQ27Z561 Battery monitor Add the Texas Instruments BQ27Z561 battery monitor. The register address map is laid out the same as compared to other devices within the file. The battery status register has differing bits to determine if the battery is full, discharging or dead. Signed-off-by: Dan Murphy Signed-off-by: Sebastian Reichel --- include/linux/power/bq27xxx_battery.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 507c5e214c42..1f6ea5d5063d 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -30,6 +30,7 @@ enum bq27xxx_chip { BQ27426, BQ27441, BQ27621, + BQ27Z561, }; struct bq27xxx_device_info; -- cgit v1.2.3 From 707d678a5c7c5e80d1caac6c6b021171f5ecde58 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Wed, 29 Jul 2020 13:31:45 -0500 Subject: power: supply: bq27xxx_battery: Add the BQ28z610 Battery monitor Add the Texas Instruments BQ28z610 battery monitor. The register address map is laid out the same as compared to other devices within the file. The battery status register bits are similar to the bq27z561 but they are different compared to other fuel gauge devices within this file. Signed-off-by: Dan Murphy Signed-off-by: Sebastian Reichel --- include/linux/power/bq27xxx_battery.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 1f6ea5d5063d..987d9652aa4e 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -31,6 +31,7 @@ enum bq27xxx_chip { BQ27441, BQ27621, BQ27Z561, + BQ28Z610, }; struct bq27xxx_device_info; -- cgit v1.2.3 From 83bdc7275e6206f560d247be856bceba3e1ed8f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 29 Jul 2020 19:11:00 -0700 Subject: random32: remove net_rand_state from the latent entropy gcc plugin It turns out that the plugin right now ends up being really unhappy about the change from 'static' to 'extern' storage that happened in commit f227e3ec3b5c ("random32: update the net random state on interrupt and activity"). This is probably a trivial fix for the latent_entropy plugin, but for now, just remove net_rand_state from the list of things the plugin worries about. Reported-by: Stephen Rothwell Cc: Emese Revfy Cc: Kees Cook Cc: Willy Tarreau Signed-off-by: Linus Torvalds --- include/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index 39aaa1f78f9d..f310897f051d 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -120,7 +120,7 @@ struct rnd_state { __u32 s1, s2, s3, s4; }; -DECLARE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; +DECLARE_PER_CPU(struct rnd_state, net_rand_state); u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); -- cgit v1.2.3 From 3ae1f39aef08c5c584b0d0ce2186273be3f14d16 Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Sat, 6 Jun 2020 03:03:30 +0530 Subject: OPP: Add and export helper to set bandwidth Add and export 'dev_pm_opp_set_bw' to set the bandwidth levels associated with an OPP. Signed-off-by: Sibi Sankar Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index d5c4a329321d..ae68417c0ae0 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -151,6 +151,7 @@ struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names void dev_pm_opp_detach_genpd(struct opp_table *opp_table); int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); +int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); void dev_pm_opp_remove_table(struct device *dev); @@ -342,6 +343,11 @@ static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_f return -ENOTSUPP; } +static inline int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp) +{ + return -EOPNOTSUPP; +} + static inline int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask) { return -ENOTSUPP; -- cgit v1.2.3 From 292072c38768bb2321cf643b27cdf8fd8282d028 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 30 Jul 2020 08:59:40 +0530 Subject: cpufreq: cached_resolved_idx can not be negative It is not possible for cached_resolved_idx to be invalid here as the cpufreq core always sets index to a positive value. Change its type to unsigned int and fix qcom usage a bit. Signed-off-by: Viresh Kumar --- include/linux/cpufreq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 3494f6763597..540c3ea4eb3c 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -127,7 +127,7 @@ struct cpufreq_policy { /* Cached frequency lookup from cpufreq_driver_resolve_freq. */ unsigned int cached_target_freq; - int cached_resolved_idx; + unsigned int cached_resolved_idx; /* Synchronization for frequency transitions */ bool transition_ongoing; /* Tracks transition status */ -- cgit v1.2.3 From c8376994c86c4eb02b9a1032cd3a8d44c911d671 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 4 Jun 2020 10:23:14 +0200 Subject: initrd: remove support for multiple floppies Remove the special handling for multiple floppies in the initrd code. No one should be using floppies for booting these days. (famous last words..) Includes a spelling fix from Colin Ian King . Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/initrd.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/initrd.h b/include/linux/initrd.h index aa5914355728..8db6f8c8030b 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -2,12 +2,6 @@ #define INITRD_MINOR 250 /* shouldn't collide with /dev/ram* too soon ... */ -/* 1 = load ramdisk, 0 = don't load */ -extern int rd_doload; - -/* 1 = prompt for ramdisk, 0 = don't prompt */ -extern int rd_prompt; - /* starting block # of image */ extern int rd_image_start; -- cgit v1.2.3 From bef173299613404f55b11180d9a865861637f31d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 6 Jun 2020 14:49:58 +0200 Subject: initrd: switch initrd loading to struct file based APIs There is no good reason to mess with file descriptors from in-kernel code, switch the initrd loading to struct file based read and writes instead. Also Pass an explicit offset instead of ->f_pos, and to make that easier, use file scope file structs and offsets everywhere except for identify_ramdisk_image instead of the current strange mix. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/syscalls.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b951a87da987..10843a6adb77 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1246,7 +1246,6 @@ int ksys_fchown(unsigned int fd, uid_t user, gid_t group); int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, unsigned int count); int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); -off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); void ksys_sync(void); int ksys_unshare(unsigned long unshare_flags); -- cgit v1.2.3 From a787e5400a1ceeb0ef92d71ec43aeb35b1fa1334 Mon Sep 17 00:00:00 2001 From: Andrzej Hajda Date: Mon, 13 Jul 2020 16:43:21 +0200 Subject: driver core: add device probe log helper During probe every time driver gets resource it should usually check for error printk some message if it is not -EPROBE_DEFER and return the error. This pattern is simple but requires adding few lines after any resource acquisition code, as a result it is often omitted or implemented only partially. dev_err_probe helps to replace such code sequences with simple call, so code: if (err != -EPROBE_DEFER) dev_err(dev, ...); return err; becomes: return dev_err_probe(dev, err, ...); Signed-off-by: Andrzej Hajda Reviewed-by: Rafael J. Wysocki Reviewed-by: Mark Brown Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200713144324.23654-2-a.hajda@samsung.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index a120657d7587..065c24008f8b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -962,6 +962,9 @@ void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); +extern __printf(3, 4) +int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); + /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor)) -- cgit v1.2.3 From 4dc3bab8687f1ea11322611de6d4138b43eccdcd Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Thu, 2 Jul 2020 20:41:28 +0900 Subject: PM / devfreq: Add support delayed timer for polling mode Until now, the devfreq driver using polling mode like simple_ondemand governor have used only deferrable timer for reducing the redundant power consumption. It reduces the CPU wake-up from idle due to polling mode which check the status of Non-CPU device. But, it has a problem for Non-CPU device like DMC device with DMA operation. Some Non-CPU device need to do monitor continuously regardless of CPU state in order to decide the proper next status of Non-CPU device. So, add support the delayed timer for polling mode to support the repetitive monitoring. The devfreq driver and user can select the kind of timer on either deferrable and delayed timer. For example, change the timer type of DMC device based on Exynos5422-based Odroid-XU3 as following: - If want to use deferrable timer as following: echo deferrable > /sys/class/devfreq/10c20000.memory-controller/timer - If want to use delayed timer as following: echo delayed > /sys/class/devfreq/10c20000.memory-controller/timer Reviewed-by: Bartlomiej Zolnierkiewicz Reviewed-by: Lukasz Luba Signed-off-by: Chanwoo Choi --- include/linux/devfreq.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 57e871a559a9..12782fbb4c25 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -31,6 +31,13 @@ #define DEVFREQ_PRECHANGE (0) #define DEVFREQ_POSTCHANGE (1) +/* DEVFREQ work timers */ +enum devfreq_timer { + DEVFREQ_TIMER_DEFERRABLE = 0, + DEVFREQ_TIMER_DELAYED, + DEVFREQ_TIMER_NUM, +}; + struct devfreq; struct devfreq_governor; @@ -70,6 +77,7 @@ struct devfreq_dev_status { * @initial_freq: The operating frequency when devfreq_add_device() is * called. * @polling_ms: The polling interval in ms. 0 disables polling. + * @timer: Timer type is either deferrable or delayed timer. * @target: The device should set its operating frequency at * freq or lowest-upper-than-freq value. If freq is * higher than any operable frequency, set maximum. @@ -96,6 +104,7 @@ struct devfreq_dev_status { struct devfreq_dev_profile { unsigned long initial_freq; unsigned int polling_ms; + enum devfreq_timer timer; int (*target)(struct device *dev, unsigned long *freq, u32 flags); int (*get_dev_status)(struct device *dev, -- cgit v1.2.3 From 1c9df907da83812e4f33b59d3d142c864d9da57f Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Thu, 30 Jul 2020 07:59:24 +0200 Subject: random: fix circular include dependency on arm64 after addition of percpu.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Daniel Díaz and Kees Cook independently reported that commit f227e3ec3b5c ("random32: update the net random state on interrupt and activity") broke arm64 due to a circular dependency on include files since the addition of percpu.h in random.h. The correct fix would definitely be to move all the prandom32 stuff out of random.h but for backporting, a smaller solution is preferred. This one replaces linux/percpu.h with asm/percpu.h, and this fixes the problem on x86_64, arm64, arm, and mips. Note that moving percpu.h around didn't change anything and that removing it entirely broke differently. When backporting, such options might still be considered if this patch fails to help. [ It turns out that an alternate fix seems to be to just remove the troublesome remove from the arm64 that causes the circular dependency. But we might as well do the whole belt-and-suspenders thing, and minimize inclusion in too. Either will fix the problem, and both are good changes. - Linus ] Reported-by: Daniel Díaz Reported-by: Kees Cook Tested-by: Marc Zyngier Fixes: f227e3ec3b5c Cc: Stephen Rothwell Signed-off-by: Willy Tarreau Signed-off-by: Linus Torvalds --- include/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index f310897f051d..9ab7443bd91b 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include -- cgit v1.2.3 From 0de967f24e6c26fca3845e5a5970866ae59ac766 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Thu, 30 Jul 2020 17:51:17 +0100 Subject: thermal: Update power allocator and devfreq cooling to SPDX licensing Update the license to the SPDX licensing format. Signed-off-by: Lukasz Luba Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20200730165117.13998-1-lukasz.luba@arm.com --- include/linux/devfreq_cooling.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/devfreq_cooling.h b/include/linux/devfreq_cooling.h index 79a6e37a1d6f..9df2dfca68dd 100644 --- a/include/linux/devfreq_cooling.h +++ b/include/linux/devfreq_cooling.h @@ -1,17 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * devfreq_cooling: Thermal cooling device implementation for devices using * devfreq * * Copyright (C) 2014-2015 ARM Limited * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __DEVFREQ_COOLING_H__ -- cgit v1.2.3 From b13fecb1c3a603c4b8e99b306fecf4f668c11b32 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 13 Jul 2020 15:01:26 -0700 Subject: treewide: Replace DECLARE_TASKLET() with DECLARE_TASKLET_OLD() This converts all the existing DECLARE_TASKLET() (and ...DISABLED) macros with DECLARE_TASKLET_OLD() in preparation for refactoring the tasklet callback type. All existing DECLARE_TASKLET() users had a "0" data argument, it has been removed here as well. Reviewed-by: Greg Kroah-Hartman Acked-by: Thomas Gleixner Signed-off-by: Kees Cook --- include/linux/interrupt.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 5db970b6615a..b911196f03eb 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -612,12 +612,17 @@ struct tasklet_struct unsigned long data; }; -#define DECLARE_TASKLET(name, func, data) \ -struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(0), func, data } - -#define DECLARE_TASKLET_DISABLED(name, func, data) \ -struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(1), func, data } +#define DECLARE_TASKLET_OLD(name, _func) \ +struct tasklet_struct name = { \ + .count = ATOMIC_INIT(0), \ + .func = _func, \ +} +#define DECLARE_TASKLET_DISABLED_OLD(name, _func) \ +struct tasklet_struct name = { \ + .count = ATOMIC_INIT(1), \ + .func = _func, \ +} enum { -- cgit v1.2.3 From 12cc923f1ccc1df467e046b02a72c2b3b321b6a2 Mon Sep 17 00:00:00 2001 From: Romain Perier Date: Sun, 29 Sep 2019 18:30:13 +0200 Subject: tasklet: Introduce new initialization API Nowadays, modern kernel subsystems that use callbacks pass the data structure associated with a given callback as argument to the callback. The tasklet subsystem remains one which passes an arbitrary unsigned long to the callback function. This has several problems: - This keeps an extra field for storing the argument in each tasklet data structure, it bloats the tasklet_struct structure with a redundant .data field - No type checking can be performed on this argument. Instead of using container_of() like other callback subsystems, it forces callbacks to do explicit type cast of the unsigned long argument into the required object type. - Buffer overflows can overwrite the .func and the .data field, so an attacker can easily overwrite the function and its first argument to whatever it wants. Add a new tasklet initialization API, via DECLARE_TASKLET() and tasklet_setup(), which will replace the existing ones. This work is greatly inspired by the timer_struct conversion series, see commit e99e88a9d2b0 ("treewide: setup_timer() -> timer_setup()") To avoid problems with both -Wcast-function-type (which is enabled in the kernel via -Wextra is several subsystems), and with mismatched function prototypes when build with Control Flow Integrity enabled, this adds the "use_callback" member to let the tasklet caller choose which union member to call through. Once all old API uses are removed, this and the .data member will be removed as well. (On 64-bit this does not grow the struct size as the new member fills the hole after atomic_t, which is also "int" sized.) Signed-off-by: Romain Perier Co-developed-by: Allen Pais Signed-off-by: Allen Pais Reviewed-by: Greg Kroah-Hartman Acked-by: Thomas Gleixner Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/interrupt.h | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index b911196f03eb..f9aee3538461 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -585,6 +585,9 @@ static inline struct task_struct *this_cpu_ksoftirqd(void) /* Tasklets --- multithreaded analogue of BHs. + This API is deprecated. Please consider using threaded IRQs instead: + https://lore.kernel.org/lkml/20200716081538.2sivhkj4hcyrusem@linutronix.de + Main feature differing them of generic softirqs: tasklet is running only on one CPU simultaneously. @@ -608,10 +611,31 @@ struct tasklet_struct struct tasklet_struct *next; unsigned long state; atomic_t count; - void (*func)(unsigned long); + bool use_callback; + union { + void (*func)(unsigned long data); + void (*callback)(struct tasklet_struct *t); + }; unsigned long data; }; +#define DECLARE_TASKLET(name, _callback) \ +struct tasklet_struct name = { \ + .count = ATOMIC_INIT(0), \ + .callback = _callback, \ + .use_callback = true, \ +} + +#define DECLARE_TASKLET_DISABLED(name, _callback) \ +struct tasklet_struct name = { \ + .count = ATOMIC_INIT(1), \ + .callback = _callback, \ + .use_callback = true, \ +} + +#define from_tasklet(var, callback_tasklet, tasklet_fieldname) \ + container_of(callback_tasklet, typeof(*var), tasklet_fieldname) + #define DECLARE_TASKLET_OLD(name, _func) \ struct tasklet_struct name = { \ .count = ATOMIC_INIT(0), \ @@ -691,6 +715,8 @@ extern void tasklet_kill(struct tasklet_struct *t); extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); extern void tasklet_init(struct tasklet_struct *t, void (*func)(unsigned long), unsigned long data); +extern void tasklet_setup(struct tasklet_struct *t, + void (*callback)(struct tasklet_struct *)); /* * Autoprobing for irqs: -- cgit v1.2.3 From 63bb76de4aeec833ae7ba05d85a7819ac4558126 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Wed, 15 Jul 2020 08:33:39 +0300 Subject: mm: pgtable: Make generic pgprot_* macros available for no-MMU The header defines some generic pgprot_* implementations, but they are only available when CONFIG_MMU is enabled. The RISC-V architecture, for example, therefore defines some of these pgprot_* macros for !NOMMU. Let's make the pgprot_* generic available even for !NOMMU so we can remove the RISC-V specific definitions. Compile-tested with x86 defconfig, and riscv defconfig and !MMU defconfig. Suggested-by: Palmer Dabbelt Reviewed-by: Mike Rapoport Acked-by: David Rientjes Signed-off-by: Pekka Enberg Signed-off-by: Palmer Dabbelt --- include/linux/pgtable.h | 71 ++++++++++++++++++++++++++----------------------- 1 file changed, 37 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 56c1e8eb7bb0..53e97da1e8e2 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -647,40 +647,6 @@ static inline int arch_unmap_one(struct mm_struct *mm, #define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) #endif -#ifndef pgprot_nx -#define pgprot_nx(prot) (prot) -#endif - -#ifndef pgprot_noncached -#define pgprot_noncached(prot) (prot) -#endif - -#ifndef pgprot_writecombine -#define pgprot_writecombine pgprot_noncached -#endif - -#ifndef pgprot_writethrough -#define pgprot_writethrough pgprot_noncached -#endif - -#ifndef pgprot_device -#define pgprot_device pgprot_noncached -#endif - -#ifndef pgprot_modify -#define pgprot_modify pgprot_modify -static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) -{ - if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot))) - newprot = pgprot_noncached(newprot); - if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot))) - newprot = pgprot_writecombine(newprot); - if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot))) - newprot = pgprot_device(newprot); - return newprot; -} -#endif - /* * When walking page tables, get the address of the next boundary, * or the end address of the range if that comes earlier. Although no @@ -840,6 +806,43 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, * No-op macros that just return the current protection value. Defined here * because these macros can be used used even if CONFIG_MMU is not defined. */ + +#ifndef pgprot_nx +#define pgprot_nx(prot) (prot) +#endif + +#ifndef pgprot_noncached +#define pgprot_noncached(prot) (prot) +#endif + +#ifndef pgprot_writecombine +#define pgprot_writecombine pgprot_noncached +#endif + +#ifndef pgprot_writethrough +#define pgprot_writethrough pgprot_noncached +#endif + +#ifndef pgprot_device +#define pgprot_device pgprot_noncached +#endif + +#ifdef CONFIG_MMU +#ifndef pgprot_modify +#define pgprot_modify pgprot_modify +static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) +{ + if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot))) + newprot = pgprot_noncached(newprot); + if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot))) + newprot = pgprot_writecombine(newprot); + if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot))) + newprot = pgprot_device(newprot); + return newprot; +} +#endif +#endif /* CONFIG_MMU */ + #ifndef pgprot_encrypted #define pgprot_encrypted(prot) (prot) #endif -- cgit v1.2.3 From fb2da16cd70a5140acdd7a102e5cd3b697c3404f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Jul 2020 09:02:07 +0200 Subject: fs: remove ksys_getdents64 Just open code it in the only caller. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/syscalls.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 10843a6adb77..a998651629c7 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1243,8 +1243,6 @@ ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); int ksys_fchmod(unsigned int fd, umode_t mode); int ksys_fchown(unsigned int fd, uid_t user, gid_t group); -int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, - unsigned int count); int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); void ksys_sync(void); -- cgit v1.2.3 From 166e07c37c6417c9713666268fc0eb89a9ce48b9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 6 Jun 2020 15:03:21 +0200 Subject: fs: remove ksys_open Just open code it in the two callers. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/syscalls.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a998651629c7..363baaadf8e1 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1374,17 +1374,6 @@ static inline int ksys_close(unsigned int fd) return __close_fd(current->files, fd); } -extern long do_sys_open(int dfd, const char __user *filename, int flags, - umode_t mode); - -static inline long ksys_open(const char __user *filename, int flags, - umode_t mode) -{ - if (force_o_largefile()) - flags |= O_LARGEFILE; - return do_sys_open(AT_FDCWD, filename, flags, mode); -} - extern long do_sys_truncate(const char __user *pathname, loff_t length); static inline long ksys_truncate(const char __user *pathname, loff_t length) -- cgit v1.2.3 From bc1cd99a9ad7e2c768e7ea92ae9c6ad4a4e0f7f7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Jul 2020 08:58:49 +0200 Subject: fs: remove ksys_dup Fold it into the only remaining caller. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/syscalls.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 363baaadf8e1..b6d900574762 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1237,7 +1237,6 @@ asmlinkage long sys_ni_syscall(void); */ int ksys_umount(char __user *name, int flags); -int ksys_dup(unsigned int fildes); int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); -- cgit v1.2.3 From b25ba7c3c9acdc4cf69f5bd69989819cabfc4e3b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Jul 2020 08:59:57 +0200 Subject: fs: remove ksys_fchmod Fold it into the only remaining caller. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/syscalls.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b6d900574762..39ff738997a1 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1240,7 +1240,6 @@ int ksys_umount(char __user *name, int flags); int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); -int ksys_fchmod(unsigned int fd, umode_t mode); int ksys_fchown(unsigned int fd, uid_t user, gid_t group); int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); -- cgit v1.2.3 From 863b67e15177a7cd0c27b3e36e42fe7907dec9bd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Jul 2020 09:00:51 +0200 Subject: fs: remove ksys_ioctl Fold it into the only remaining caller. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/syscalls.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 39ff738997a1..5b0f1fca4cfb 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1241,7 +1241,6 @@ int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); int ksys_fchown(unsigned int fd, uid_t user, gid_t group); -int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); void ksys_sync(void); int ksys_unshare(unsigned long unshare_flags); -- cgit v1.2.3 From fd5ad30c782351ab4d4a15941fc61e743a1bd66c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Jul 2020 08:19:55 +0200 Subject: fs: expose utimes_common Rename utimes_common to vfs_utimes and make it available outside of utimes.c. This will be used by the initramfs unpacking code. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 635086726f20..a1d2685a4878 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1746,6 +1746,7 @@ int vfs_mkobj(struct dentry *, umode_t, int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); +int vfs_utimes(const struct path *path, struct timespec64 *times); extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); -- cgit v1.2.3 From e24ab0ef689de43649327f54cd1088f3dad25bb3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 21 Jul 2020 10:48:15 +0200 Subject: fs: push the getname from do_rmdir into the callers This mirrors do_unlinkat and will make life a little easier for the init code to reuse the whole function with a kernel filename. Signed-off-by: Christoph Hellwig --- include/linux/syscalls.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5b0f1fca4cfb..e43816198e60 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1281,11 +1281,11 @@ static inline long ksys_unlink(const char __user *pathname) return do_unlinkat(AT_FDCWD, getname(pathname)); } -extern long do_rmdir(int dfd, const char __user *pathname); +long do_rmdir(int dfd, struct filename *name); static inline long ksys_rmdir(const char __user *pathname) { - return do_rmdir(AT_FDCWD, pathname); + return do_rmdir(AT_FDCWD, getname(pathname)); } extern long do_mkdirat(int dfd, const char __user *pathname, umode_t mode); -- cgit v1.2.3 From c60166f04283ffba7b88b45d824bbfb2bfccee24 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 21 Jul 2020 11:12:08 +0200 Subject: init: add an init_mount helper Like do_mount, but takes a kernel pointer for the destination path. Switch over the mounts in the init code and devtmpfs to it, which just happen to work due to the implicit set_fs(KERNEL_DS) during early init right now. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 4 ++++ 1 file changed, 4 insertions(+) create mode 100644 include/linux/init_syscalls.h (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h new file mode 100644 index 000000000000..af9ea88a60e0 --- /dev/null +++ b/include/linux/init_syscalls.h @@ -0,0 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +int __init init_mount(const char *dev_name, const char *dir_name, + const char *type_page, unsigned long flags, void *data_page); -- cgit v1.2.3 From 09267defa36aaff6ff829bd2fc8b043ec151cc3e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:23:08 +0200 Subject: init: add an init_umount helper Like ksys_umount, but takes a kernel pointer for the destination path. Switch over the umount in the init code, which just happen to work due to the implicit set_fs(KERNEL_DS) during early init right now. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index af9ea88a60e0..a5a2e7f19916 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -2,3 +2,4 @@ int __init init_mount(const char *dev_name, const char *dir_name, const char *type_page, unsigned long flags, void *data_page); +int __init init_umount(const char *name, int flags); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e43816198e60..1a4f5d8ee704 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1236,7 +1236,6 @@ asmlinkage long sys_ni_syscall(void); * the ksys_xyzyyz() functions prototyped below. */ -int ksys_umount(char __user *name, int flags); int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); -- cgit v1.2.3 From 8fb9f73e5a539ab3aa4785f30fb52c65fa98600c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:23:40 +0200 Subject: init: add an init_unlink helper Add a simple helper to unlink with a kernel space file name and switch the early init code over to it. Remove the now unused ksys_unlink. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 7 ------- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index a5a2e7f19916..00d597249549 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -3,3 +3,4 @@ int __init init_mount(const char *dev_name, const char *dir_name, const char *type_page, unsigned long flags, void *data_page); int __init init_umount(const char *name, int flags); +int __init init_unlink(const char *pathname); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1a4f5d8ee704..26f9738e5ab8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1273,13 +1273,6 @@ int compat_ksys_ipc(u32 call, int first, int second, * The following kernel syscall equivalents are just wrappers to fs-internal * functions. Therefore, provide stubs to be inlined at the callsites. */ -extern long do_unlinkat(int dfd, struct filename *name); - -static inline long ksys_unlink(const char __user *pathname) -{ - return do_unlinkat(AT_FDCWD, getname(pathname)); -} - long do_rmdir(int dfd, struct filename *name); static inline long ksys_rmdir(const char __user *pathname) -- cgit v1.2.3 From 20cce026c3e0972017b9cb4a7cccfb8cacf187d5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:11:45 +0200 Subject: init: add an init_rmdir helper Add a simple helper to rmdir with a kernel space file name and switch the early init code over to it. Remove the now unused ksys_rmdir. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 7 ------- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index 00d597249549..abf3af563c0b 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -4,3 +4,4 @@ int __init init_mount(const char *dev_name, const char *dir_name, const char *type_page, unsigned long flags, void *data_page); int __init init_umount(const char *name, int flags); int __init init_unlink(const char *pathname); +int __init init_rmdir(const char *pathname); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 26f9738e5ab8..a7b14258d245 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1273,13 +1273,6 @@ int compat_ksys_ipc(u32 call, int first, int second, * The following kernel syscall equivalents are just wrappers to fs-internal * functions. Therefore, provide stubs to be inlined at the callsites. */ -long do_rmdir(int dfd, struct filename *name); - -static inline long ksys_rmdir(const char __user *pathname) -{ - return do_rmdir(AT_FDCWD, getname(pathname)); -} - extern long do_mkdirat(int dfd, const char __user *pathname, umode_t mode); static inline long ksys_mkdir(const char __user *pathname, umode_t mode) -- cgit v1.2.3 From db63f1e315384590b979f8f74abd1b5363b69894 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:25:21 +0200 Subject: init: add an init_chdir helper Add a simple helper to chdir with a kernel space file name and switch the early init code over to it. Remove the now unused ksys_chdir. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index abf3af563c0b..1e845910ae56 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -3,5 +3,6 @@ int __init init_mount(const char *dev_name, const char *dir_name, const char *type_page, unsigned long flags, void *data_page); int __init init_umount(const char *name, int flags); +int __init init_chdir(const char *filename); int __init init_unlink(const char *pathname); int __init init_rmdir(const char *pathname); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a7b14258d245..31fa67fb9894 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1238,7 +1238,6 @@ asmlinkage long sys_ni_syscall(void); int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); -int ksys_chdir(const char __user *filename); int ksys_fchown(unsigned int fd, uid_t user, gid_t group); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); void ksys_sync(void); -- cgit v1.2.3 From 4b7ca5014cbef51cdb99fd644eae4f3773747a05 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:26:13 +0200 Subject: init: add an init_chroot helper Add a simple helper to chroot with a kernel space file name and switch the early init code over to it. Remove the now unused ksys_chroot. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index 1e845910ae56..e07099a14b91 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -4,5 +4,6 @@ int __init init_mount(const char *dev_name, const char *dir_name, const char *type_page, unsigned long flags, void *data_page); int __init init_umount(const char *name, int flags); int __init init_chdir(const char *filename); +int __init init_chroot(const char *filename); int __init init_unlink(const char *pathname); int __init init_rmdir(const char *pathname); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 31fa67fb9894..e89d62e944dc 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1235,8 +1235,6 @@ asmlinkage long sys_ni_syscall(void); * Instead, use one of the functions which work equivalently, such as * the ksys_xyzyyz() functions prototyped below. */ - -int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_fchown(unsigned int fd, uid_t user, gid_t group); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); -- cgit v1.2.3 From b873498f99c77e7b5be3aa5ffe9ca67437232fe0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:13:26 +0200 Subject: init: add an init_chown helper Add a simple helper to chown with a kernel space file name and switch the early init code over to it. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index e07099a14b91..0da59d76133e 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -5,5 +5,6 @@ int __init init_mount(const char *dev_name, const char *dir_name, int __init init_umount(const char *name, int flags); int __init init_chdir(const char *filename); int __init init_chroot(const char *filename); +int __init init_chown(const char *filename, uid_t user, gid_t group, int flags); int __init init_unlink(const char *pathname); int __init init_rmdir(const char *pathname); -- cgit v1.2.3 From 1097742efc643ffc667c5c6684635b2663145a7d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:41:02 +0200 Subject: init: add an init_chmod helper Add a simple helper to chmod with a kernel space file name and switch the early init code over to it. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 7 ------- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index 0da59d76133e..2b1b4dc58682 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -6,5 +6,6 @@ int __init init_umount(const char *name, int flags); int __init init_chdir(const char *filename); int __init init_chroot(const char *filename); int __init init_chown(const char *filename, uid_t user, gid_t group, int flags); +int __init init_chmod(const char *filename, umode_t mode); int __init init_unlink(const char *pathname); int __init init_rmdir(const char *pathname); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e89d62e944dc..8b71fa321ca2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1304,13 +1304,6 @@ static inline long ksys_link(const char __user *oldname, return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } -extern int do_fchmodat(int dfd, const char __user *filename, umode_t mode); - -static inline int ksys_chmod(const char __user *filename, umode_t mode) -{ - return do_fchmodat(AT_FDCWD, filename, mode); -} - long do_faccessat(int dfd, const char __user *filename, int mode, int flags); static inline long ksys_access(const char __user *filename, int mode) -- cgit v1.2.3 From eb9d7d390e51108b4c6a9a7993ed9be92548c8f7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:14:02 +0200 Subject: init: add an init_eaccess helper Add a simple helper to check if a file exists based on kernel space file name and switch the early init code over to it. Note that this theoretically changes behavior as it always is based on the effective permissions. But during early init that doesn't make a difference. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 7 ------- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index 2b1b4dc58682..7031c0934bee 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -7,5 +7,6 @@ int __init init_chdir(const char *filename); int __init init_chroot(const char *filename); int __init init_chown(const char *filename, uid_t user, gid_t group, int flags); int __init init_chmod(const char *filename, umode_t mode); +int __init init_eaccess(const char *filename); int __init init_unlink(const char *pathname); int __init init_rmdir(const char *pathname); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 8b71fa321ca2..a2779638e414 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1304,13 +1304,6 @@ static inline long ksys_link(const char __user *oldname, return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } -long do_faccessat(int dfd, const char __user *filename, int mode, int flags); - -static inline long ksys_access(const char __user *filename, int mode) -{ - return do_faccessat(AT_FDCWD, filename, mode, 0); -} - extern int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag); -- cgit v1.2.3 From 812931d693da58cc24d2bb8dec01c2b4a7f4668f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:14:19 +0200 Subject: init: add an init_link helper Add a simple helper to link with a kernel space file name and switch the early init code over to it. Remove the now unused ksys_link. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 9 --------- 2 files changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index 7031c0934bee..5ca15a5b55b7 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -8,5 +8,6 @@ int __init init_chroot(const char *filename); int __init init_chown(const char *filename, uid_t user, gid_t group, int flags); int __init init_chmod(const char *filename, umode_t mode); int __init init_eaccess(const char *filename); +int __init init_link(const char *oldname, const char *newname); int __init init_unlink(const char *pathname); int __init init_rmdir(const char *pathname); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a2779638e414..4b18b91ce465 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1295,15 +1295,6 @@ static inline long ksys_mknod(const char __user *filename, umode_t mode, return do_mknodat(AT_FDCWD, filename, mode, dev); } -extern int do_linkat(int olddfd, const char __user *oldname, int newdfd, - const char __user *newname, int flags); - -static inline long ksys_link(const char __user *oldname, - const char __user *newname) -{ - return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); -} - extern int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag); -- cgit v1.2.3 From cd3acb6a79349f346714ab3d26d203a0c6ca5ab0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:14:36 +0200 Subject: init: add an init_symlink helper Add a simple helper to symlink with a kernel space file name and switch the early init code over to it. Remove the now unused ksys_symlink. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 9 --------- 2 files changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index 5ca15a5b55b7..125f55ae3f80 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -9,5 +9,6 @@ int __init init_chown(const char *filename, uid_t user, gid_t group, int flags); int __init init_chmod(const char *filename, umode_t mode); int __init init_eaccess(const char *filename); int __init init_link(const char *oldname, const char *newname); +int __init init_symlink(const char *oldname, const char *newname); int __init init_unlink(const char *pathname); int __init init_rmdir(const char *pathname); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 4b18b91ce465..7cdc0d749a04 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1277,15 +1277,6 @@ static inline long ksys_mkdir(const char __user *pathname, umode_t mode) return do_mkdirat(AT_FDCWD, pathname, mode); } -extern long do_symlinkat(const char __user *oldname, int newdfd, - const char __user *newname); - -static inline long ksys_symlink(const char __user *oldname, - const char __user *newname) -{ - return do_symlinkat(oldname, AT_FDCWD, newname); -} - extern long do_mknodat(int dfd, const char __user *filename, umode_t mode, unsigned int dev); -- cgit v1.2.3 From 83ff98c3e9cd2b82b4289e185f2ce7d635a9cbd3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:14:59 +0200 Subject: init: add an init_mkdir helper Add a simple helper to mkdir with a kernel space file name and switch the early init code over to it. Remove the now unused ksys_mkdir. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 7 ------- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index 125f55ae3f80..d808985231f8 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -11,4 +11,5 @@ int __init init_eaccess(const char *filename); int __init init_link(const char *oldname, const char *newname); int __init init_symlink(const char *oldname, const char *newname); int __init init_unlink(const char *pathname); +int __init init_mkdir(const char *pathname, umode_t mode); int __init init_rmdir(const char *pathname); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7cdc0d749a04..5ef77a91382a 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1270,13 +1270,6 @@ int compat_ksys_ipc(u32 call, int first, int second, * The following kernel syscall equivalents are just wrappers to fs-internal * functions. Therefore, provide stubs to be inlined at the callsites. */ -extern long do_mkdirat(int dfd, const char __user *pathname, umode_t mode); - -static inline long ksys_mkdir(const char __user *pathname, umode_t mode) -{ - return do_mkdirat(AT_FDCWD, pathname, mode); -} - extern long do_mknodat(int dfd, const char __user *filename, umode_t mode, unsigned int dev); -- cgit v1.2.3 From 5fee64fcde0770c41e926ff981022eaa512d8980 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:41:20 +0200 Subject: init: add an init_mknod helper Add a simple helper to mknod with a kernel space file name and switch the early init code over to it. Remove the now unused ksys_mknod. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + include/linux/syscalls.h | 9 --------- 2 files changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index d808985231f8..fa1fe7a87779 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -8,6 +8,7 @@ int __init init_chroot(const char *filename); int __init init_chown(const char *filename, uid_t user, gid_t group, int flags); int __init init_chmod(const char *filename, umode_t mode); int __init init_eaccess(const char *filename); +int __init init_mknod(const char *filename, umode_t mode, unsigned int dev); int __init init_link(const char *oldname, const char *newname); int __init init_symlink(const char *oldname, const char *newname); int __init init_unlink(const char *pathname); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5ef77a91382a..63046c5e9fc5 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1270,15 +1270,6 @@ int compat_ksys_ipc(u32 call, int first, int second, * The following kernel syscall equivalents are just wrappers to fs-internal * functions. Therefore, provide stubs to be inlined at the callsites. */ -extern long do_mknodat(int dfd, const char __user *filename, umode_t mode, - unsigned int dev); - -static inline long ksys_mknod(const char __user *filename, umode_t mode, - unsigned int dev) -{ - return do_mknodat(AT_FDCWD, filename, mode, dev); -} - extern int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag); -- cgit v1.2.3 From 716308a5331bf907b819f9db8dc942b19568f925 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Jul 2020 11:15:40 +0200 Subject: init: add an init_stat helper Add a simple helper to stat with a kernel space file name and switch the early init code over to it. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index fa1fe7a87779..b2fda50daca6 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -8,6 +8,7 @@ int __init init_chroot(const char *filename); int __init init_chown(const char *filename, uid_t user, gid_t group, int flags); int __init init_chmod(const char *filename, umode_t mode); int __init init_eaccess(const char *filename); +int __init init_stat(const char *filename, struct kstat *stat, int flags); int __init init_mknod(const char *filename, umode_t mode, unsigned int dev); int __init init_link(const char *oldname, const char *newname); int __init init_symlink(const char *oldname, const char *newname); -- cgit v1.2.3 From 235e57935bf328c4cce371ffc4dd1d8fab4885cd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 21 Jul 2020 16:05:31 +0200 Subject: init: add an init_utimes helper Add a simple helper to set timestamps with a kernel space file name and switch the early init code over to it. Signed-off-by: Christoph Hellwig --- include/linux/init_syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index b2fda50daca6..3654b525ac0b 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -15,3 +15,4 @@ int __init init_symlink(const char *oldname, const char *newname); int __init init_unlink(const char *pathname); int __init init_mkdir(const char *pathname, umode_t mode); int __init init_rmdir(const char *pathname); +int __init init_utimes(char *filename, struct timespec64 *ts); -- cgit v1.2.3 From 4278e9d99e38938a7611b927fa4d73e6c86cb4fc Mon Sep 17 00:00:00 2001 From: Marcelo Henrique Cerri Date: Mon, 20 Jul 2020 19:08:09 +0200 Subject: lib/mpi: Add mpi_sub_ui() Add mpi_sub_ui() based on Gnu MP mpz_sub_ui() function from file mpz/aors_ui.h[1] from change id 510b83519d1c adapting the code to the kernel's data structures, helper functions and coding style and also removing the defines used to produce mpz_sub_ui() and mpz_add_ui() from the same code. [1] https://gmplib.org/repo/gmp-6.2/file/510b83519d1c/mpz/aors.h Signed-off-by: Marcelo Henrique Cerri Signed-off-by: Stephan Mueller Signed-off-by: Herbert Xu --- include/linux/mpi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mpi.h b/include/linux/mpi.h index 7bd6d8af0004..5d906dfbf3ed 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -63,6 +63,9 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod); int mpi_cmp_ui(MPI u, ulong v); int mpi_cmp(MPI u, MPI v); +/*-- mpi-sub-ui.c --*/ +int mpi_sub_ui(MPI w, MPI u, unsigned long vval); + /*-- mpi-bit.c --*/ void mpi_normalize(MPI a); unsigned mpi_get_nbits(MPI a); -- cgit v1.2.3 From 4963bb2b89884bbdb7e33e6a09c159551e9627aa Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Thu, 30 Jul 2020 12:08:35 -0700 Subject: lib: Add zstd support to decompress - Add unzstd() and the zstd decompress interface. - Add zstd support to decompress_method(). The decompress_method() and unzstd() functions are used to decompress the initramfs and the initrd. The __decompress() function is used in the preboot environment to decompress a zstd compressed kernel. The zstd decompression function allows the input and output buffers to overlap because that is used by x86 kernel decompression. Signed-off-by: Nick Terrell Signed-off-by: Ingo Molnar Tested-by: Sedat Dilek Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20200730190841.2071656-3-nickrterrell@gmail.com --- include/linux/decompress/unzstd.h | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 include/linux/decompress/unzstd.h (limited to 'include/linux') diff --git a/include/linux/decompress/unzstd.h b/include/linux/decompress/unzstd.h new file mode 100644 index 000000000000..56d539ae880f --- /dev/null +++ b/include/linux/decompress/unzstd.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_DECOMPRESS_UNZSTD_H +#define LINUX_DECOMPRESS_UNZSTD_H + +int unzstd(unsigned char *inbuf, long len, + long (*fill)(void*, unsigned long), + long (*flush)(void*, unsigned long), + unsigned char *output, + long *pos, + void (*error_fn)(char *x)); +#endif -- cgit v1.2.3 From 0584df9c12f449124d0bfef9899e5365604ee7a9 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 29 Jul 2020 13:09:15 +0200 Subject: lockdep: Refactor IRQ trace events fields into struct Refactor the IRQ trace events fields, used for printing information about the IRQ trace events, into a separate struct 'irqtrace_events'. This improves readability by separating the information only used in reporting, as well as enables (simplified) storing/restoring of irqtrace_events snapshots. No functional change intended. Signed-off-by: Marco Elver Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200729110916.3920464-1-elver@google.com Signed-off-by: Ingo Molnar --- include/linux/irqflags.h | 13 +++++++++++++ include/linux/sched.h | 11 ++--------- 2 files changed, 15 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 5811ee8a5cd8..bd5c55755447 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -33,6 +33,19 @@ #ifdef CONFIG_TRACE_IRQFLAGS +/* Per-task IRQ trace events information. */ +struct irqtrace_events { + unsigned int irq_events; + unsigned long hardirq_enable_ip; + unsigned long hardirq_disable_ip; + unsigned int hardirq_enable_event; + unsigned int hardirq_disable_event; + unsigned long softirq_disable_ip; + unsigned long softirq_enable_ip; + unsigned int softirq_disable_event; + unsigned int softirq_enable_event; +}; + DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); diff --git a/include/linux/sched.h b/include/linux/sched.h index 8d1de021b315..52e0fdd6a555 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -980,17 +981,9 @@ struct task_struct { #endif #ifdef CONFIG_TRACE_IRQFLAGS - unsigned int irq_events; + struct irqtrace_events irqtrace; unsigned int hardirq_threaded; - unsigned long hardirq_enable_ip; - unsigned long hardirq_disable_ip; - unsigned int hardirq_enable_event; - unsigned int hardirq_disable_event; u64 hardirq_chain_key; - unsigned long softirq_disable_ip; - unsigned long softirq_enable_ip; - unsigned int softirq_disable_event; - unsigned int softirq_enable_event; int softirqs_enabled; int softirq_context; int irq_config; -- cgit v1.2.3 From 92c209ac6d3d35783c16c8a717547183e6e11162 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 29 Jul 2020 13:09:16 +0200 Subject: kcsan: Improve IRQ state trace reporting To improve the general usefulness of the IRQ state trace events with KCSAN enabled, save and restore the trace information when entering and exiting the KCSAN runtime as well as when generating a KCSAN report. Without this, reporting the IRQ trace events (whether via a KCSAN report or outside of KCSAN via a lockdep report) is rather useless due to continuously being touched by KCSAN. This is because if KCSAN is enabled, every instrumented memory access causes changes to IRQ trace events (either by KCSAN disabling/enabling interrupts or taking report_lock when generating a report). Before "lockdep: Prepare for NMI IRQ state tracking", KCSAN avoided touching the IRQ trace events via raw_local_irq_save/restore() and lockdep_off/on(). Fixes: 248591f5d257 ("kcsan: Make KCSAN compatible with new IRQ state tracking") Signed-off-by: Marco Elver Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200729110916.3920464-2-elver@google.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 52e0fdd6a555..060e9214c8b5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1184,8 +1184,12 @@ struct task_struct { #ifdef CONFIG_KASAN unsigned int kasan_depth; #endif + #ifdef CONFIG_KCSAN struct kcsan_ctx kcsan_ctx; +#ifdef CONFIG_TRACE_IRQFLAGS + struct irqtrace_events kcsan_save_irqtrace; +#endif #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER -- cgit v1.2.3 From 46cbd0b05799e8234b719d18f3a4b27679c4c92e Mon Sep 17 00:00:00 2001 From: Crag Wang Date: Thu, 30 Jul 2020 11:26:09 +0800 Subject: power: supply: wilco_ec: Add long life charging mode This is a long life mode set in the factory for extended warranty battery, the power charging rate is customized so that battery at work last longer. Presently switching to a different battery charging mode is through EC PID 0x0710 to configure the battery firmware, this operation will be blocked by EC with failure code 0x01 when PLL mode is already in use. Signed-off-by: Crag Wang Reviewed-by: Mario Limonciello Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index b5ee35d3c304..97cc4b85bf61 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -48,6 +48,7 @@ enum { POWER_SUPPLY_CHARGE_TYPE_STANDARD, /* normal speed */ POWER_SUPPLY_CHARGE_TYPE_ADAPTIVE, /* dynamically adjusted speed */ POWER_SUPPLY_CHARGE_TYPE_CUSTOM, /* use CHARGE_CONTROL_* props */ + POWER_SUPPLY_CHARGE_TYPE_LONGLIFE, /* slow speed, longer life */ }; enum { -- cgit v1.2.3 From 48040793fa6003d211f021c6ad273477bcd90d91 Mon Sep 17 00:00:00 2001 From: Yousuk Seung Date: Thu, 30 Jul 2020 15:44:40 -0700 Subject: tcp: add earliest departure time to SCM_TIMESTAMPING_OPT_STATS This change adds TCP_NLA_EDT to SCM_TIMESTAMPING_OPT_STATS that reports the earliest departure time(EDT) of the timestamped skb. By tracking EDT values of the skb from different timestamps, we can observe when and how much the value changed. This allows to measure the precise delay injected on the sender host e.g. by a bpf-base throttler. Signed-off-by: Yousuk Seung Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 527d668a5275..14b62d7df942 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -484,7 +484,8 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp) tp->saved_syn = NULL; } -struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk); +struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, + const struct sk_buff *orig_skb); static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) { -- cgit v1.2.3 From 829eb208e80d6db95c0201cb8fa00c2f9ad87faf Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Fri, 31 Jul 2020 17:34:01 -0700 Subject: rtnetlink: add support for protodown reason netdev protodown is a mechanism that allows protocols to hold an interface down. It was initially introduced in the kernel to hold links down by a multihoming protocol. There was also an attempt to introduce protodown reason at the time but was rejected. protodown and protodown reason is supported by almost every switching and routing platform. It was ok for a while to live without a protodown reason. But, its become more critical now given more than one protocol may need to keep a link down on a system at the same time. eg: vrrp peer node, port security, multihoming protocol. Its common for Network operators and protocol developers to look for such a reason on a networking box (Its also known as errDisable by most networking operators) This patch adds support for link protodown reason attribute. There are two ways to maintain protodown reasons. (a) enumerate every possible reason code in kernel - A protocol developer has to make a request and have that appear in a certain kernel version (b) provide the bits in the kernel, and allow user-space (sysadmin or NOS distributions) to manage the bit-to-reasonname map. - This makes extending reason codes easier (kind of like the iproute2 table to vrf-name map /etc/iproute2/rt_tables.d/) This patch takes approach (b). a few things about the patch: - It treats the protodown reason bits as counter to indicate active protodown users - Since protodown attribute is already an exposed UAPI, the reason is not enforced on a protodown set. Its a no-op if not used. the patch follows the below algorithm: - presence of reason bits set indicates protodown is in use - user can set protodown and protodown reason in a single or multiple setlink operations - setlink operation to clear protodown, will return -EBUSY if there are active protodown reason bits - reason is not included in link dumps if not used example with patched iproute2: $cat /etc/iproute2/protodown_reasons.d/r.conf 0 mlag 1 evpn 2 vrrp 3 psecurity $ip link set dev vxlan0 protodown on protodown_reason vrrp on $ip link set dev vxlan0 protodown_reason mlag on $ip link show 14: vxlan0: mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000 link/ether f6:06:be:17:91:e7 brd ff:ff:ff:ff:ff:ff protodown on $ip link set dev vxlan0 protodown_reason mlag off $ip link set dev vxlan0 protodown off protodown_reason vrrp off Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ac2cd3f49aba..ba0fa6b22787 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2058,6 +2058,8 @@ struct net_device { struct timer_list watchdog_timer; int watchdog_timeo; + u32 proto_down_reason; + struct list_head todo_list; int __percpu *pcpu_refcnt; @@ -3810,6 +3812,8 @@ int dev_get_port_parent_id(struct net_device *dev, bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); int dev_change_proto_down(struct net_device *dev, bool proto_down); int dev_change_proto_down_generic(struct net_device *dev, bool proto_down); +void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, + u32 value); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); -- cgit v1.2.3 From f4470cdf108f00533e8079b19434e6cb48c17fa3 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Fri, 31 Jul 2020 20:20:14 +0100 Subject: sched: Document arch_scale_*_capacity() Rather that hide their purpose in some dark, damp corner of Documentation/, add some documentation to the default implementations. Signed-off-by: Valentin Schneider Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200731192016.7484-2-valentin.schneider@arm.com --- include/linux/sched/topology.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 764222d637b7..820511289857 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -217,6 +217,16 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu) #endif /* !CONFIG_SMP */ #ifndef arch_scale_cpu_capacity +/** + * arch_scale_cpu_capacity - get the capacity scale factor of a given CPU. + * @cpu: the CPU in question. + * + * Return: the CPU scale factor normalized against SCHED_CAPACITY_SCALE, i.e. + * + * max_perf(cpu) + * ----------------------------- * SCHED_CAPACITY_SCALE + * max(max_perf(c) : c \in CPUs) + */ static __always_inline unsigned long arch_scale_cpu_capacity(int cpu) { -- cgit v1.2.3 From f369bc3f9096f5d355e8b80540bc30ac9a602912 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 1 Aug 2020 08:17:13 +0200 Subject: vgaarb: mark vga_tryget static This symbols isn't used anywhere outside of vgaarb.c. Signed-off-by: Christoph Hellwig Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20200801061713.307434-1-hch@lst.de --- include/linux/vgaarb.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index 553b34c8b5f7..977caf96c8d2 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -109,12 +109,6 @@ static inline int vga_get_uninterruptible(struct pci_dev *pdev, return vga_get(pdev, rsrc, 0); } -#if defined(CONFIG_VGA_ARB) -extern int vga_tryget(struct pci_dev *pdev, unsigned int rsrc); -#else -static inline int vga_tryget(struct pci_dev *pdev, unsigned int rsrc) { return 0; } -#endif - #if defined(CONFIG_VGA_ARB) extern void vga_put(struct pci_dev *pdev, unsigned int rsrc); #else -- cgit v1.2.3 From 7ef5264de773279b9f23b6cc8afb5addb30e970b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 30 Jul 2020 08:10:20 +0200 Subject: modules: mark ref_module static ref_module isn't used anywhere outside of module.c. Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/module.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 2e6670860d27..f1fdbeef2153 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -657,7 +657,6 @@ static inline void __module_get(struct module *module) #define symbol_put_addr(p) do { } while (0) #endif /* CONFIG_MODULE_UNLOAD */ -int ref_module(struct module *a, struct module *b); /* This is a #define so the string doesn't get put in every .o file */ #define module_name(mod) \ -- cgit v1.2.3 From 773110470e2fa3839523384ae014f8a723c4d178 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 30 Jul 2020 08:10:21 +0200 Subject: modules: mark find_symbol static find_symbol is only used in module.c. Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/module.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index f1fdbeef2153..90bdc362be36 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -590,17 +590,6 @@ struct symsearch { bool unused; }; -/* - * Search for an exported symbol by name. - * - * Must be called with module_mutex held or preemption disabled. - */ -const struct kernel_symbol *find_symbol(const char *name, - struct module **owner, - const s32 **crc, - bool gplok, - bool warn); - /* * Walk the exported symbol table * -- cgit v1.2.3 From a54e04914c211b5678602a46b3ede5d82ec1327d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 30 Jul 2020 08:10:22 +0200 Subject: modules: mark each_symbol_section static each_symbol_section is only used inside of module.c. Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/module.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 90bdc362be36..b79219eed83c 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -590,15 +590,6 @@ struct symsearch { bool unused; }; -/* - * Walk the exported symbol table - * - * Must be called with module_mutex held or preemption disabled. - */ -bool each_symbol_section(bool (*fn)(const struct symsearch *arr, - struct module *owner, - void *data), void *data); - /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if symnum out of range. */ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, -- cgit v1.2.3 From cd8732cdcc37d7077c4fa2c966b748c0662b607e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 30 Jul 2020 08:10:25 +0200 Subject: modules: rename the licence field in struct symsearch to license Use the same spelling variant as the rest of the file. Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index b79219eed83c..be04ba2f881d 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -586,7 +586,7 @@ struct symsearch { NOT_GPL_ONLY, GPL_ONLY, WILL_BE_GPL_ONLY, - } licence; + } license; bool unused; }; -- cgit v1.2.3 From ef1dac6021cc8ec5de02ce31722bf26ac4ed5523 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 30 Jul 2020 08:10:26 +0200 Subject: modules: return licensing information from find_symbol Report the GPLONLY status through a new argument. Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index be04ba2f881d..30b0f5fcdb3c 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -582,7 +582,7 @@ struct module *find_module(const char *name); struct symsearch { const struct kernel_symbol *start, *stop; const s32 *crcs; - enum { + enum mod_license { NOT_GPL_ONLY, GPL_ONLY, WILL_BE_GPL_ONLY, -- cgit v1.2.3 From 1752f0adea98ef859978c090e0726844348758f9 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 1 Aug 2020 13:36:33 +0300 Subject: fs: optimise kiocb_set_rw_flags() Use a local var to collect flags in kiocb_set_rw_flags(). That spares some memory writes and allows to replace most of the jumps with MOVEcc. Signed-off-by: Pavel Begunkov Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Jens Axboe --- include/linux/fs.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4090320360f4..e535543d31d9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3446,22 +3446,28 @@ static inline int iocb_flags(struct file *file) static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) { + int kiocb_flags = 0; + + if (!flags) + return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; - ki->ki_flags |= IOCB_NOWAIT; + kiocb_flags |= IOCB_NOWAIT; } if (flags & RWF_HIPRI) - ki->ki_flags |= IOCB_HIPRI; + kiocb_flags |= IOCB_HIPRI; if (flags & RWF_DSYNC) - ki->ki_flags |= IOCB_DSYNC; + kiocb_flags |= IOCB_DSYNC; if (flags & RWF_SYNC) - ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC); + kiocb_flags |= (IOCB_DSYNC | IOCB_SYNC); if (flags & RWF_APPEND) - ki->ki_flags |= IOCB_APPEND; + kiocb_flags |= IOCB_APPEND; + + ki->ki_flags |= kiocb_flags; return 0; } -- cgit v1.2.3 From 73b11c2ab072d5b0599d1e12cc126f55ee306daf Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 31 Jul 2020 11:28:26 -0700 Subject: bpf: Add support for forced LINK_DETACH command Add LINK_DETACH command to force-detach bpf_link without destroying it. It has the same behavior as auto-detaching of bpf_link due to cgroup dying for bpf_cgroup_link or net_device being destroyed for bpf_xdp_link. In such case, bpf_link is still a valid kernel object, but is defuncts and doesn't hold BPF program attached to corresponding BPF hook. This functionality allows users with enough access rights to manually force-detach attached bpf_link without killing respective owner process. This patch implements LINK_DETACH for cgroup, xdp, and netns links, mostly re-using existing link release handling code. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200731182830.286260-2-andriin@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 40c5e206ecf2..cef4ef0d2b4e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -793,6 +793,7 @@ struct bpf_link { struct bpf_link_ops { void (*release)(struct bpf_link *link); void (*dealloc)(struct bpf_link *link); + int (*detach)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); -- cgit v1.2.3 From c83e2a6e2fbbb7d47ea46fd7cb1f01292f2d0b6e Mon Sep 17 00:00:00 2001 From: Ajay Singh Date: Fri, 17 Jul 2020 05:11:38 +0000 Subject: wilc1000: Move wilc1000 SDIO ID's from driver source to common header file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Moved macros used for Vendor/Device ID from wilc1000 driver to common header file and changed macro name for consistency with other macros. Signed-off-by: Ajay Singh Acked-by: Ulf Hansson Acked-by: Pali Rohár Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20200717051134.19160-1-ajay.kathat@microchip.com --- include/linux/mmc/sdio_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 15ed8ce9d394..519820d18e62 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -105,6 +105,9 @@ #define SDIO_DEVICE_ID_MEDIATEK_MT7663 0x7663 #define SDIO_DEVICE_ID_MEDIATEK_MT7668 0x7668 +#define SDIO_VENDOR_ID_MICROCHIP_WILC 0x0296 +#define SDIO_DEVICE_ID_MICROCHIP_WILC1000 0x5347 + #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 #define SDIO_DEVICE_ID_SIANO_NICE 0x0202 -- cgit v1.2.3 From 614a895fc69497d99cc02c076fa712c75194eab3 Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Thu, 9 Jul 2020 20:07:33 +0200 Subject: mtd: hyperbus: Replace HTTP links with HTTPS ones Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. Signed-off-by: Alexander A. Klimov Signed-off-by: Richard Weinberger --- include/linux/mtd/hyperbus.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/hyperbus.h b/include/linux/mtd/hyperbus.h index 2dfe65964f6e..2129f7d3b6eb 100644 --- a/include/linux/mtd/hyperbus.h +++ b/include/linux/mtd/hyperbus.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 * - * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com/ */ #ifndef __LINUX_MTD_HYPERBUS_H__ -- cgit v1.2.3 From 0c84b7fc973f9220ef8732c430ccc7c92d083184 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:29:54 -0700 Subject: MTD: pfow.h: drop a duplicated word Drop the repeated word "can" in a comment. Signed-off-by: Randy Dunlap Cc: Miquel Raynal Cc: Richard Weinberger Cc: Vignesh Raghavendra Cc: linux-mtd@lists.infradead.org Signed-off-by: Richard Weinberger --- include/linux/mtd/pfow.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/pfow.h b/include/linux/mtd/pfow.h index 122f3439e1af..6166e7c60869 100644 --- a/include/linux/mtd/pfow.h +++ b/include/linux/mtd/pfow.h @@ -19,7 +19,7 @@ /* Identification info for LPDDR chip */ #define PFOW_MANUFACTURER_ID 0x0020 #define PFOW_DEVICE_ID 0x0022 -/* Address in PFOW where prog buffer can can be found */ +/* Address in PFOW where prog buffer can be found */ #define PFOW_PROGRAM_BUFFER_OFFSET 0x0040 /* Size of program buffer in words */ #define PFOW_PROGRAM_BUFFER_SIZE 0x0042 -- cgit v1.2.3 From c6fe44d96fc1536af5b11cd859686453d1b7bfd1 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 23 Jul 2020 12:33:41 -0700 Subject: list: add "list_del_init_careful()" to go with "list_empty_careful()" That gives us ordering guarantees around the pair. Signed-off-by: Linus Torvalds --- include/linux/list.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index aff44d34f4e4..0d0d17a10d25 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -282,6 +282,24 @@ static inline int list_empty(const struct list_head *head) return READ_ONCE(head->next) == head; } +/** + * list_del_init_careful - deletes entry from list and reinitialize it. + * @entry: the element to delete from the list. + * + * This is the same as list_del_init(), except designed to be used + * together with list_empty_careful() in a way to guarantee ordering + * of other memory operations. + * + * Any memory operations done before a list_del_init_careful() are + * guaranteed to be visible after a list_empty_careful() test. + */ +static inline void list_del_init_careful(struct list_head *entry) +{ + __list_del_entry(entry); + entry->prev = entry; + smp_store_release(&entry->next, entry); +} + /** * list_empty_careful - tests whether a list is empty and not being modified * @head: the list to test @@ -297,7 +315,7 @@ static inline int list_empty(const struct list_head *head) */ static inline int list_empty_careful(const struct list_head *head) { - struct list_head *next = head->next; + struct list_head *next = smp_load_acquire(&head->next); return (next == head) && (next == head->prev); } -- cgit v1.2.3 From 4e56cde15f7d68cf86ff8efff8504497de152475 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Fri, 31 Jul 2020 21:38:30 +0300 Subject: mac80211: Handle special status codes in SAE commit SAE authentication has been extended with H2E (IEEE 802.11 REVmd) and PK (WFA) options. Those extensions use special status code values in the SAE commit messages (Authentication frame with transaction sequence number 1) to identify which extension is in use. mac80211 was interpreting those new values as the AP denying authentication and that resulted in failure to complete SAE authentication in some cases. Fix this by adding exceptions for the new status code values 126 and 127. Signed-off-by: Jouni Malinen Link: https://lore.kernel.org/r/20200731183830.18735-1-jouni@codeaurora.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 9f732499ea88..c47f43e65a2f 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2561,6 +2561,8 @@ enum ieee80211_statuscode { /* 802.11ai */ WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 108, WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 109, + WLAN_STATUS_SAE_HASH_TO_ELEMENT = 126, + WLAN_STATUS_SAE_PK = 127, }; -- cgit v1.2.3 From 042f649810f61c4a834f3d6d866c567f7f6b3f8c Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 1 Jul 2020 11:54:43 -0400 Subject: libceph: just have osd_req_op_init() return a pointer The caller can just ignore the return. No need for this wrapper that just casts the other function to void. [ idryomov: argument alignment ] Signed-off-by: Jeff Layton Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index c60b59e9291b..83fa08a06507 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -404,7 +404,7 @@ void ceph_osdc_clear_abort_err(struct ceph_osd_client *osdc); &__oreq->r_ops[__whch].typ.fld; \ }) -extern void osd_req_op_init(struct ceph_osd_request *osd_req, +struct ceph_osd_req_op *osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u32 flags); extern void osd_req_op_raw_data_in_pages(struct ceph_osd_request *, -- cgit v1.2.3 From 94f17c00d6687993101372f996cf6690ec9adf83 Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Wed, 8 Jul 2020 08:53:28 +0200 Subject: libceph: replace HTTP links with HTTPS ones Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. [ idryomov: Do the same for the CRUSH paper and replace ceph.newdream.net with ceph.io. ] Signed-off-by: Alexander A. Klimov Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/crush/crush.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 33c16f2de7f6..2f811baf78d2 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -17,7 +17,7 @@ * The algorithm was originally described in detail in this paper * (although the algorithm has evolved somewhat since then): * - * http://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf + * https://www.ssrc.ucsc.edu/Papers/weil-sc06.pdf * * LGPL2 */ -- cgit v1.2.3 From 18f473b384a64cef69f166a3e2b73d3d2eca82c6 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 16 Jul 2020 10:05:57 -0400 Subject: ceph: periodically send perf metrics to MDSes This will send the caps/read/write/metadata metrics to any available MDS once per second, which will be the same as the userland client. It will skip the MDS sessions which don't support the metric collection, as the MDSs will close socket connections when they get an unknown type message. We can disable the metric sending via the disable_send_metrics module parameter. [ jlayton: fix up endianness bug in ceph_mdsc_send_metrics() ] URL: https://tracker.ceph.com/issues/43215 Signed-off-by: Xiubo Li Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index ebf5ba62b772..455e9b9e2adf 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -130,6 +130,7 @@ struct ceph_dir_layout { #define CEPH_MSG_CLIENT_REQUEST 24 #define CEPH_MSG_CLIENT_REQUEST_FORWARD 25 #define CEPH_MSG_CLIENT_REPLY 26 +#define CEPH_MSG_CLIENT_METRICS 29 #define CEPH_MSG_CLIENT_CAPS 0x310 #define CEPH_MSG_CLIENT_LEASE 0x311 #define CEPH_MSG_CLIENT_SNAP 0x312 -- cgit v1.2.3 From f1f565a26976612121f97464f9245307422d0ce8 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 17 Jul 2020 16:36:04 -0700 Subject: ceph: delete repeated words in fs/ceph/ Drop duplicated words "down" and "the" in fs/ceph/. [ idryomov: merge into a single patch ] Signed-off-by: Randy Dunlap Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_features.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 39e6f4c57580..fcd84e8d88f4 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -58,7 +58,7 @@ * because 10.2.z (jewel) did not care if its peers advertised this * feature bit. * - * - In the second phase we stop advertising the the bit and call it + * - In the second phase we stop advertising the bit and call it * RETIRED. This can normally be done in the *next* major release * following the one in which we marked the feature DEPRECATED. In * the above example, for 12.0.z (luminous) we can say: -- cgit v1.2.3 From c9dff08485a6c11449307abde1d7bb404fcee481 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 9 Jul 2020 14:49:30 +0200 Subject: fs: Fix typo in comment The comment for function filemap_check_wb_err accidentally refers to it as filemap_check_wb_error. Signed-off-by: Andreas Gruenbacher --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f5abba86107d..f9ae45795c1a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2798,7 +2798,7 @@ static inline void filemap_set_wb_err(struct address_space *mapping, int err) } /** - * filemap_check_wb_error - has an error occurred since the mark was sampled? + * filemap_check_wb_err - has an error occurred since the mark was sampled? * @mapping: mapping to check for writeback errors * @since: previously-sampled errseq_t * -- cgit v1.2.3 From f3751ad0116fb6881f2c3c957d66a9327f69cefb Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Thu, 30 Jul 2020 15:45:54 -0700 Subject: tracepoint: Mark __tracepoint_string's __used __tracepoint_string's have their string data stored in .rodata, and an address to that data stored in the "__tracepoint_str" section. Functions that refer to those strings refer to the symbol of the address. Compiler optimization can replace those address references with references directly to the string data. If the address doesn't appear to have other uses, then it appears dead to the compiler and is removed. This can break the /tracing/printk_formats sysfs node which iterates the addresses stored in the "__tracepoint_str" section. Like other strings stored in custom sections in this header, mark these __used to inform the compiler that there are other non-obvious users of the address, so they should still be emitted. Link: https://lkml.kernel.org/r/20200730224555.2142154-2-ndesaulniers@google.com Cc: Ingo Molnar Cc: Miguel Ojeda Cc: stable@vger.kernel.org Fixes: 102c9323c35a8 ("tracing: Add __tracepoint_string() to export string pointers") Reported-by: Tim Murray Reported-by: Simon MacMullen Suggested-by: Greg Hackmann Signed-off-by: Nick Desaulniers Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index a1fecf311621..3a5b717d92e8 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -361,7 +361,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) static const char *___tp_str __tracepoint_string = str; \ ___tp_str; \ }) -#define __tracepoint_string __attribute__((section("__tracepoint_str"))) +#define __tracepoint_string __attribute__((section("__tracepoint_str"), used)) #else /* * tracepoint_string() is used to save the string address for userspace -- cgit v1.2.3 From 1c39d761ff5c90227fc582c45018d5922efaa253 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Thu, 30 Jul 2020 15:45:55 -0700 Subject: tracepoint: Use __used attribute definitions from compiler_attributes.h Just a small cleanup while I was touching this header. compiler_attributes.h does feature detection of these __attributes__(()) and provides more concise ways to invoke them. Link: https://lkml.kernel.org/r/20200730224555.2142154-3-ndesaulniers@google.com Acked-by: Miguel Ojeda Signed-off-by: Nick Desaulniers Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 3a5b717d92e8..598fec9f9dbf 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -116,8 +116,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #define __TRACEPOINT_ENTRY(name) \ static tracepoint_ptr_t __tracepoint_ptr_##name __used \ - __attribute__((section("__tracepoints_ptrs"))) = \ - &__tracepoint_##name + __section(__tracepoints_ptrs) = &__tracepoint_##name #endif #endif /* _LINUX_TRACEPOINT_H */ @@ -280,9 +279,9 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) */ #define DEFINE_TRACE_FN(name, reg, unreg) \ static const char __tpstrtab_##name[] \ - __attribute__((section("__tracepoints_strings"))) = #name; \ - struct tracepoint __tracepoint_##name \ - __attribute__((section("__tracepoints"), used)) = \ + __section(__tracepoints_strings) = #name; \ + struct tracepoint __tracepoint_##name __used \ + __section(__tracepoints) = \ { __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL };\ __TRACEPOINT_ENTRY(name); @@ -361,7 +360,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) static const char *___tp_str __tracepoint_string = str; \ ___tp_str; \ }) -#define __tracepoint_string __attribute__((section("__tracepoint_str"), used)) +#define __tracepoint_string __used __section(__tracepoint_str) #else /* * tracepoint_string() is used to save the string address for userspace -- cgit v1.2.3 From 321bd212619a7269308696e4ddc446930ea73fad Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 24 Jun 2020 18:24:33 -0400 Subject: virtio: VIRTIO_F_IOMMU_PLATFORM -> VIRTIO_F_ACCESS_PLATFORM Rename the bit to match latest virtio spec. Add a compat macro to avoid breaking existing userspace. Signed-off-by: Michael S. Tsirkin Reviewed-by: David Hildenbrand --- include/linux/virtio_config.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index bb4cc4910750..f2cc2a0df174 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -171,7 +171,7 @@ static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev) * Note the reverse polarity of the quirk feature (compared to most * other features), this is for compatibility with legacy systems. */ - return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM); + return !virtio_has_feature(vdev, VIRTIO_F_ACCESS_PLATFORM); } static inline -- cgit v1.2.3 From 24b6842ade6925199e182988259761504aacfbc0 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 24 Jun 2020 19:17:04 -0400 Subject: virtio: virtio_has_iommu_quirk -> virtio_has_dma_quirk Now that the corresponding feature bit has been renamed, rename the quirk too - it's about special ways to do DMA, not necessarily about the IOMMU. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index f2cc2a0df174..3b4eae5ac5e3 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -162,10 +162,10 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev, } /** - * virtio_has_iommu_quirk - determine whether this device has the iommu quirk + * virtio_has_dma_quirk - determine whether this device has the DMA quirk * @vdev: the device */ -static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev) +static inline bool virtio_has_dma_quirk(const struct virtio_device *vdev) { /* * Note the reverse polarity of the quirk feature (compared to most -- cgit v1.2.3 From 80a6e707dd9742390776a9306b400b1fbe405b4a Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 17 Jul 2020 17:42:55 +0900 Subject: kprobes: Remove show_registers() function prototype Remove show_registers() function prototype because this function has been renamed by commit 57da8b960b9a ("x86: Avoid double stack traces with show_regs()"), and commit 80006dbee674 ("kprobes/x86: Remove jprobe implementation") has removed the caller in kprobes. So this doesn't exist anymore. Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 6adf90f248d7..81cb7e00ccdc 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -227,7 +227,6 @@ extern int arch_prepare_kprobe(struct kprobe *p); extern void arch_arm_kprobe(struct kprobe *p); extern void arch_disarm_kprobe(struct kprobe *p); extern int arch_init_kprobes(void); -extern void show_registers(struct pt_regs *regs); extern void kprobes_inc_nmissed_count(struct kprobe *p); extern bool arch_within_kprobe_blacklist(unsigned long addr); extern int arch_populate_kprobe_blacklist(void); -- cgit v1.2.3 From 6cfde88418fe95240e32d2955b51988360ee0942 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 1 Aug 2020 10:53:42 +0200 Subject: clk: drop unused function __clk_get_flags The function __clk_get_flags has not been used since the April 2019 commit a348f05361c9 ("ARM: omap2+: hwmod: drop CLK_IS_BASIC flag usage"). Other uses were removed in June 2015, eg by commit 98d8a60eccee ("clk: Convert __clk_get_flags() to clk_hw_get_flags()"), which shows how clk_hw_get_flags can easily be used instead. Signed-off-by: Julia Lawall Link: https://lore.kernel.org/r/1596272022-14173-1-git-send-email-Julia.Lawall@inria.fr Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index bd1ee9039558..93a78a5256d1 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1096,7 +1096,6 @@ int clk_hw_get_parent_index(struct clk_hw *hw); int clk_hw_set_parent(struct clk_hw *hw, struct clk_hw *new_parent); unsigned int __clk_get_enable_count(struct clk *clk); unsigned long clk_hw_get_rate(const struct clk_hw *hw); -unsigned long __clk_get_flags(struct clk *clk); unsigned long clk_hw_get_flags(const struct clk_hw *hw); #define clk_hw_can_set_rate_parent(hw) \ (clk_hw_get_flags((hw)) & CLK_SET_RATE_PARENT) -- cgit v1.2.3 From bb3831294cd50750806f2ce8d73317dc8feeda09 Mon Sep 17 00:00:00 2001 From: Bruno Thomsen Date: Thu, 30 Jul 2020 21:57:48 +0200 Subject: net: mdiobus: add reset-post-delay-us handling Load new "reset-post-delay-us" value from MDIO properties, and if configured to a greater then zero delay do a flexible sleeping delay after MDIO bus reset deassert. This allows devices to exit reset state before start bus communication. Signed-off-by: Bruno Thomsen Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 0403eb799913..3a09d2bf69ea 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -293,6 +293,8 @@ struct mii_bus { /* GPIO reset pulse width in microseconds */ int reset_delay_us; + /* GPIO reset deassert delay in microseconds */ + int reset_post_delay_us; /* RESET GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; -- cgit v1.2.3 From 038ebb1a713d114d54dbf14868a73181c0c92758 Mon Sep 17 00:00:00 2001 From: wenxu Date: Fri, 31 Jul 2020 10:45:01 +0800 Subject: net/sched: act_ct: fix miss set mru for ovs after defrag in act_ct When openvswitch conntrack offload with act_ct action. Fragment packets defrag in the ingress tc act_ct action and miss the next chain. Then the packet pass to the openvswitch datapath without the mru. The over mtu packet will be dropped in output action in openvswitch for over mtu. "kernel: net2: dropped over-mtu packet: 1528 > 1500" This patch add mru in the tc_skb_ext for adefrag and miss next chain situation. And also add mru in the qdisc_skb_cb. The act_ct set the mru to the qdisc_skb_cb when the packet defrag. And When the chain miss, The mru is set to tc_skb_ext which can be got by ovs datapath. Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct") Signed-off-by: wenxu Reviewed-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fa817a105517..3ad65d4ce085 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -283,6 +283,7 @@ struct nf_bridge_info { */ struct tc_skb_ext { __u32 chain; + __u16 mru; }; #endif -- cgit v1.2.3 From 5f402bb17533113c21d61c2d4bc4ef4a6fa1c9a5 Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Fri, 31 Jul 2020 14:38:36 +0200 Subject: gpio: don't use same lockdep class for all devm_gpiochip_add_data users Commit 959bc7b22bd2 ("gpio: Automatically add lockdep keys") documents in its commits message its intention to "create a unique class key for each driver". It does so by having gpiochip_add_data add in-place the definition of two static lockdep classes for LOCKDEP use. That way, every caller of the macro adds their gpiochip with unique lockdep classes. There are many indirect callers of gpiochip_add_data, however, via use of devm_gpiochip_add_data. devm_gpiochip_add_data has external linkage and all its users will share the same lockdep classes, which probably is not intended. Fix this by replicating the gpio_chip_add_data statics-in-macro for the devm_ version as well. Fixes: 959bc7b22bd2 ("gpio: Automatically add lockdep keys") Signed-off-by: Ahmad Fatoum Reviewed-by: Andy Shevchenko Reviewed-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20200731123835.8003-1-a.fatoum@pengutronix.de Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 6e9f1826ecd7..d1cef5c2715c 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -525,8 +525,16 @@ extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, gpiochip_add_data_with_key(gc, data, &lock_key, \ &request_key); \ }) +#define devm_gpiochip_add_data(dev, gc, data) ({ \ + static struct lock_class_key lock_key; \ + static struct lock_class_key request_key; \ + devm_gpiochip_add_data_with_key(dev, gc, data, &lock_key, \ + &request_key); \ + }) #else #define gpiochip_add_data(gc, data) gpiochip_add_data_with_key(gc, data, NULL, NULL) +#define devm_gpiochip_add_data(dev, gc, data) \ + devm_gpiochip_add_data_with_key(dev, gc, data, NULL, NULL) #endif /* CONFIG_LOCKDEP */ static inline int gpiochip_add(struct gpio_chip *gc) @@ -534,8 +542,9 @@ static inline int gpiochip_add(struct gpio_chip *gc) return gpiochip_add_data(gc, NULL); } extern void gpiochip_remove(struct gpio_chip *gc); -extern int devm_gpiochip_add_data(struct device *dev, struct gpio_chip *gc, - void *data); +extern int devm_gpiochip_add_data_with_key(struct device *dev, struct gpio_chip *gc, void *data, + struct lock_class_key *lock_key, + struct lock_class_key *request_key); extern struct gpio_chip *gpiochip_find(void *data, int (*match)(struct gpio_chip *gc, void *data)); -- cgit v1.2.3 From 6c84a589972f6458da3168a68e7d65f6ca8687f8 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 3 Aug 2020 13:03:52 -0700 Subject: net: dsa: loop: Move data structures to header In preparation for adding support for a mockup data path, move the driver data structures to include/linux/dsa/loop.h such that we can share them between net/dsa/ and drivers/net/dsa/ later on. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/loop.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) create mode 100644 include/linux/dsa/loop.h (limited to 'include/linux') diff --git a/include/linux/dsa/loop.h b/include/linux/dsa/loop.h new file mode 100644 index 000000000000..bb39401a8056 --- /dev/null +++ b/include/linux/dsa/loop.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef DSA_LOOP_H +#define DSA_LOOP_H + +#include +#include +#include + +struct dsa_loop_vlan { + u16 members; + u16 untagged; +}; + +struct dsa_loop_mib_entry { + char name[ETH_GSTRING_LEN]; + unsigned long val; +}; + +enum dsa_loop_mib_counters { + DSA_LOOP_PHY_READ_OK, + DSA_LOOP_PHY_READ_ERR, + DSA_LOOP_PHY_WRITE_OK, + DSA_LOOP_PHY_WRITE_ERR, + __DSA_LOOP_CNT_MAX, +}; + +struct dsa_loop_port { + struct dsa_loop_mib_entry mib[__DSA_LOOP_CNT_MAX]; + u16 pvid; +}; + +struct dsa_loop_priv { + struct mii_bus *bus; + unsigned int port_base; + struct dsa_loop_vlan vlans[VLAN_N_VID]; + struct net_device *netdev; + struct dsa_loop_port ports[DSA_MAX_PORTS]; +}; + +#endif /* DSA_LOOP_H */ -- cgit v1.2.3 From c99194eded25deb58f606e59b3101ba05e786021 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 3 Aug 2020 13:03:53 -0700 Subject: net: dsa: loop: Wire-up MTU callbacks For now we simply store the port MTU into a per-port member. Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/dsa/loop.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dsa/loop.h b/include/linux/dsa/loop.h index bb39401a8056..5a3470bcc8a7 100644 --- a/include/linux/dsa/loop.h +++ b/include/linux/dsa/loop.h @@ -27,6 +27,7 @@ enum dsa_loop_mib_counters { struct dsa_loop_port { struct dsa_loop_mib_entry mib[__DSA_LOOP_CNT_MAX]; u16 pvid; + int mtu; }; struct dsa_loop_priv { -- cgit v1.2.3 From 0858fde496f84fff2fdae53d9e33c7b308195f74 Mon Sep 17 00:00:00 2001 From: Dennis YC Hsieh Date: Sun, 5 Jul 2020 14:37:14 +0800 Subject: mailbox: cmdq: variablize address shift in platform Some gce hardware shift pc and end address in register to support large dram addressing. Implement gce address shift when write or read pc and end register. And add shift bit in platform definition. Signed-off-by: Dennis YC Hsieh Signed-off-by: Jassi Brar --- include/linux/mailbox/mtk-cmdq-mailbox.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index a4dc45fbec0a..c342b8799be8 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -88,4 +88,6 @@ struct cmdq_pkt { void *cl; }; +u8 cmdq_get_shift_pa(struct mbox_chan *chan); + #endif /* __MTK_CMDQ_MAILBOX_H__ */ -- cgit v1.2.3 From d88ca7e1a27eb2df056bbf37ddef62e1c73d37ea Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Thu, 30 Jul 2020 19:47:14 +0900 Subject: fbmem: pull fbcon_update_vcs() out of fb_set_var() syzbot is reporting OOB read bug in vc_do_resize() [1] caused by memcpy() based on outdated old_{rows,row_size} values, for resize_screen() can recurse into vc_do_resize() which changes vc->vc_{cols,rows} that outdates old_{rows,row_size} values which were saved before calling resize_screen(). Daniel Vetter explained that resize_screen() should not recurse into fbcon_update_vcs() path due to FBINFO_MISC_USEREVENT being still set when calling resize_screen(). Instead of masking FBINFO_MISC_USEREVENT before calling fbcon_update_vcs(), we can remove FBINFO_MISC_USEREVENT by calling fbcon_update_vcs() only if fb_set_var() returned 0. This change assumes that it is harmless to call fbcon_update_vcs() when fb_set_var() returned 0 without reaching fb_notifier_call_chain(). [1] https://syzkaller.appspot.com/bug?id=c70c88cfd16dcf6e1d3c7f0ab8648b3144b5b25e Reported-and-tested-by: syzbot Suggested-by: Daniel Vetter Signed-off-by: Tetsuo Handa Reported-by: kernel test robot for missing #include Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/075b7e37-3278-cd7d-31ab-c5073cfa8e92@i-love.sakura.ne.jp --- include/linux/fb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 2b530e6d86e4..850f79e9a7cb 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -400,8 +400,6 @@ struct fb_tile_ops { #define FBINFO_HWACCEL_YPAN 0x2000 /* optional */ #define FBINFO_HWACCEL_YWRAP 0x4000 /* optional */ -#define FBINFO_MISC_USEREVENT 0x10000 /* event request - from userspace */ #define FBINFO_MISC_TILEBLITTING 0x20000 /* use tile blitting */ /* A driver may set this flag to indicate that it does want a set_par to be -- cgit v1.2.3 From c0842fbc1b18c7a044e6ff3e8fa78bfa822c7d1a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 31 Jul 2020 07:51:14 +0200 Subject: random32: move the pseudo-random 32-bit definitions to prandom.h The addition of percpu.h to the list of includes in random.h revealed some circular dependencies on arm64 and possibly other platforms. This include was added solely for the pseudo-random definitions, which have nothing to do with the rest of the definitions in this file but are still there for legacy reasons. This patch moves the pseudo-random parts to linux/prandom.h and the percpu.h include with it, which is now guarded by _LINUX_PRANDOM_H and protected against recursive inclusion. A further cleanup step would be to remove this from entirely, and make people who use the prandom infrastructure include just the new header file. That's a bit of a churn patch, but grepping for "prandom_" and "next_pseudo_random32" "struct rnd_state" should catch most users. But it turns out that that nice cleanup step is fairly painful, because a _lot_ of code currently seems to depend on the implicit include of , which can currently come in a lot of ways, including such fairly core headfers as . So the "nice cleanup" part may or may never happen. Fixes: 1c9df907da83 ("random: fix circular include dependency on arm64 after addition of percpu.h") Tested-by: Guenter Roeck Acked-by: Willy Tarreau Signed-off-by: Linus Torvalds --- include/linux/prandom.h | 78 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/random.h | 66 +++-------------------------------------- 2 files changed, 82 insertions(+), 62 deletions(-) create mode 100644 include/linux/prandom.h (limited to 'include/linux') diff --git a/include/linux/prandom.h b/include/linux/prandom.h new file mode 100644 index 000000000000..aa16e6468f91 --- /dev/null +++ b/include/linux/prandom.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * include/linux/prandom.h + * + * Include file for the fast pseudo-random 32-bit + * generation. + */ +#ifndef _LINUX_PRANDOM_H +#define _LINUX_PRANDOM_H + +#include +#include + +u32 prandom_u32(void); +void prandom_bytes(void *buf, size_t nbytes); +void prandom_seed(u32 seed); +void prandom_reseed_late(void); + +struct rnd_state { + __u32 s1, s2, s3, s4; +}; + +DECLARE_PER_CPU(struct rnd_state, net_rand_state); + +u32 prandom_u32_state(struct rnd_state *state); +void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); +void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); + +#define prandom_init_once(pcpu_state) \ + DO_ONCE(prandom_seed_full_state, (pcpu_state)) + +/** + * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) + * @ep_ro: right open interval endpoint + * + * Returns a pseudo-random number that is in interval [0, ep_ro). Note + * that the result depends on PRNG being well distributed in [0, ~0U] + * u32 space. Here we use maximally equidistributed combined Tausworthe + * generator, that is, prandom_u32(). This is useful when requesting a + * random index of an array containing ep_ro elements, for example. + * + * Returns: pseudo-random number in interval [0, ep_ro) + */ +static inline u32 prandom_u32_max(u32 ep_ro) +{ + return (u32)(((u64) prandom_u32() * ep_ro) >> 32); +} + +/* + * Handle minimum values for seeds + */ +static inline u32 __seed(u32 x, u32 m) +{ + return (x < m) ? x + m : x; +} + +/** + * prandom_seed_state - set seed for prandom_u32_state(). + * @state: pointer to state structure to receive the seed. + * @seed: arbitrary 64-bit value to use as a seed. + */ +static inline void prandom_seed_state(struct rnd_state *state, u64 seed) +{ + u32 i = (seed >> 32) ^ (seed << 10) ^ seed; + + state->s1 = __seed(i, 2U); + state->s2 = __seed(i, 8U); + state->s3 = __seed(i, 16U); + state->s4 = __seed(i, 128U); +} + +/* Pseudo random number generator from numerical recipes. */ +static inline u32 next_pseudo_random32(u32 seed) +{ + return seed * 1664525 + 1013904223; +} + +#endif diff --git a/include/linux/random.h b/include/linux/random.h index 9ab7443bd91b..f45b8be3e3c4 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -11,7 +11,6 @@ #include #include #include -#include #include @@ -111,63 +110,12 @@ declare_get_random_var_wait(long) unsigned long randomize_page(unsigned long start, unsigned long range); -u32 prandom_u32(void); -void prandom_bytes(void *buf, size_t nbytes); -void prandom_seed(u32 seed); -void prandom_reseed_late(void); - -struct rnd_state { - __u32 s1, s2, s3, s4; -}; - -DECLARE_PER_CPU(struct rnd_state, net_rand_state); - -u32 prandom_u32_state(struct rnd_state *state); -void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); -void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); - -#define prandom_init_once(pcpu_state) \ - DO_ONCE(prandom_seed_full_state, (pcpu_state)) - -/** - * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) - * @ep_ro: right open interval endpoint - * - * Returns a pseudo-random number that is in interval [0, ep_ro). Note - * that the result depends on PRNG being well distributed in [0, ~0U] - * u32 space. Here we use maximally equidistributed combined Tausworthe - * generator, that is, prandom_u32(). This is useful when requesting a - * random index of an array containing ep_ro elements, for example. - * - * Returns: pseudo-random number in interval [0, ep_ro) - */ -static inline u32 prandom_u32_max(u32 ep_ro) -{ - return (u32)(((u64) prandom_u32() * ep_ro) >> 32); -} - /* - * Handle minimum values for seeds - */ -static inline u32 __seed(u32 x, u32 m) -{ - return (x < m) ? x + m : x; -} - -/** - * prandom_seed_state - set seed for prandom_u32_state(). - * @state: pointer to state structure to receive the seed. - * @seed: arbitrary 64-bit value to use as a seed. + * This is designed to be standalone for just prandom + * users, but for now we include it from + * for legacy reasons. */ -static inline void prandom_seed_state(struct rnd_state *state, u64 seed) -{ - u32 i = (seed >> 32) ^ (seed << 10) ^ seed; - - state->s1 = __seed(i, 2U); - state->s2 = __seed(i, 8U); - state->s3 = __seed(i, 16U); - state->s4 = __seed(i, 128U); -} +#include #ifdef CONFIG_ARCH_RANDOM # include @@ -210,10 +158,4 @@ static inline bool __init arch_get_random_long_early(unsigned long *v) } #endif -/* Pseudo random number generator from numerical recipes. */ -static inline u32 next_pseudo_random32(u32 seed) -{ - return seed * 1664525 + 1013904223; -} - #endif /* _LINUX_RANDOM_H */ -- cgit v1.2.3 From 403d2d116ec011942a8505068b943c5c6cd91176 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 31 Jul 2020 19:03:26 +0200 Subject: PM: runtime: Add kerneldoc comments to multiple helpers Add kerneldoc comments to multiple PM-runtime helper functions defined as static inline wrappers around lower-level routines to provide quick reference decumentation of their behavior. Some of them are similar to each other with subtle differences only and the behavior of some of them may appear as counter-intuitive, so clarify all that to avoid confusion. Signed-off-by: Rafael J. Wysocki Acked-by: Alan Stern Reviewed-by: Sakari Ailus --- include/linux/pm_runtime.h | 246 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 246 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 3dbc207bff53..6245caa18034 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -60,58 +60,151 @@ extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device *dev); +/** + * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter. + * @dev: Target device. + * + * Increment the runtime PM usage counter of @dev if its runtime PM status is + * %RPM_ACTIVE and its runtime PM usage counter is greater than 0. + */ static inline int pm_runtime_get_if_in_use(struct device *dev) { return pm_runtime_get_if_active(dev, false); } +/** + * pm_suspend_ignore_children - Set runtime PM behavior regarding children. + * @dev: Target device. + * @enable: Whether or not to ignore possible dependencies on children. + * + * The dependencies of @dev on its children will not be taken into account by + * the runtime PM framework going forward if @enable is %true, or they will + * be taken into account otherwise. + */ static inline void pm_suspend_ignore_children(struct device *dev, bool enable) { dev->power.ignore_children = enable; } +/** + * pm_runtime_get_noresume - Bump up runtime PM usage counter of a device. + * @dev: Target device. + */ static inline void pm_runtime_get_noresume(struct device *dev) { atomic_inc(&dev->power.usage_count); } +/** + * pm_runtime_put_noidle - Drop runtime PM usage counter of a device. + * @dev: Target device. + * + * Decrement the runtime PM usage counter of @dev unless it is 0 already. + */ static inline void pm_runtime_put_noidle(struct device *dev) { atomic_add_unless(&dev->power.usage_count, -1, 0); } +/** + * pm_runtime_suspended - Check whether or not a device is runtime-suspended. + * @dev: Target device. + * + * Return %true if runtime PM is enabled for @dev and its runtime PM status is + * %RPM_SUSPENDED, or %false otherwise. + * + * Note that the return value of this function can only be trusted if it is + * called under the runtime PM lock of @dev or under conditions in which + * runtime PM cannot be either disabled or enabled for @dev and its runtime PM + * status cannot change. + */ static inline bool pm_runtime_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED && !dev->power.disable_depth; } +/** + * pm_runtime_active - Check whether or not a device is runtime-active. + * @dev: Target device. + * + * Return %true if runtime PM is enabled for @dev and its runtime PM status is + * %RPM_ACTIVE, or %false otherwise. + * + * Note that the return value of this function can only be trusted if it is + * called under the runtime PM lock of @dev or under conditions in which + * runtime PM cannot be either disabled or enabled for @dev and its runtime PM + * status cannot change. + */ static inline bool pm_runtime_active(struct device *dev) { return dev->power.runtime_status == RPM_ACTIVE || dev->power.disable_depth; } +/** + * pm_runtime_status_suspended - Check if runtime PM status is "suspended". + * @dev: Target device. + * + * Return %true if the runtime PM status of @dev is %RPM_SUSPENDED, or %false + * otherwise, regardless of whether or not runtime PM has been enabled for @dev. + * + * Note that the return value of this function can only be trusted if it is + * called under the runtime PM lock of @dev or under conditions in which the + * runtime PM status of @dev cannot change. + */ static inline bool pm_runtime_status_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED; } +/** + * pm_runtime_enabled - Check if runtime PM is enabled. + * @dev: Target device. + * + * Return %true if runtime PM is enabled for @dev or %false otherwise. + * + * Note that the return value of this function can only be trusted if it is + * called under the runtime PM lock of @dev or under conditions in which + * runtime PM cannot be either disabled or enabled for @dev. + */ static inline bool pm_runtime_enabled(struct device *dev) { return !dev->power.disable_depth; } +/** + * pm_runtime_has_no_callbacks - Check if runtime PM callbacks may be present. + * @dev: Target device. + * + * Return %true if @dev is a special device without runtime PM callbacks or + * %false otherwise. + */ static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return dev->power.no_callbacks; } +/** + * pm_runtime_mark_last_busy - Update the last access time of a device. + * @dev: Target device. + * + * Update the last access time of @dev used by the runtime PM autosuspend + * mechanism to the current time as returned by ktime_get_mono_fast_ns(). + */ static inline void pm_runtime_mark_last_busy(struct device *dev) { WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns()); } +/** + * pm_runtime_is_irq_safe - Check if runtime PM can work in interrupt context. + * @dev: Target device. + * + * Return %true if @dev has been marked as an "IRQ-safe" device (with respect + * to runtime PM), in which case its runtime PM callabcks can be expected to + * work correctly when invoked from interrupt handlers. + */ static inline bool pm_runtime_is_irq_safe(struct device *dev) { return dev->power.irq_safe; @@ -191,97 +284,250 @@ static inline void pm_runtime_drop_link(struct device *dev) {} #endif /* !CONFIG_PM */ +/** + * pm_runtime_idle - Conditionally set up autosuspend of a device or suspend it. + * @dev: Target device. + * + * Invoke the "idle check" callback of @dev and, depending on its return value, + * set up autosuspend of @dev or suspend it (depending on whether or not + * autosuspend has been enabled for it). + */ static inline int pm_runtime_idle(struct device *dev) { return __pm_runtime_idle(dev, 0); } +/** + * pm_runtime_suspend - Suspend a device synchronously. + * @dev: Target device. + */ static inline int pm_runtime_suspend(struct device *dev) { return __pm_runtime_suspend(dev, 0); } +/** + * pm_runtime_autosuspend - Set up autosuspend of a device or suspend it. + * @dev: Target device. + * + * Set up autosuspend of @dev or suspend it (depending on whether or not + * autosuspend is enabled for it) without engaging its "idle check" callback. + */ static inline int pm_runtime_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_AUTO); } +/** + * pm_runtime_resume - Resume a device synchronously. + * @dev: Target device. + */ static inline int pm_runtime_resume(struct device *dev) { return __pm_runtime_resume(dev, 0); } +/** + * pm_request_idle - Queue up "idle check" execution for a device. + * @dev: Target device. + * + * Queue up a work item to run an equivalent of pm_runtime_idle() for @dev + * asynchronously. + */ static inline int pm_request_idle(struct device *dev) { return __pm_runtime_idle(dev, RPM_ASYNC); } +/** + * pm_request_resume - Queue up runtime-resume of a device. + * @dev: Target device. + */ static inline int pm_request_resume(struct device *dev) { return __pm_runtime_resume(dev, RPM_ASYNC); } +/** + * pm_request_autosuspend - Queue up autosuspend of a device. + * @dev: Target device. + * + * Queue up a work item to run an equivalent pm_runtime_autosuspend() for @dev + * asynchronously. + */ static inline int pm_request_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_ASYNC | RPM_AUTO); } +/** + * pm_runtime_get - Bump up usage counter and queue up resume of a device. + * @dev: Target device. + * + * Bump up the runtime PM usage counter of @dev and queue up a work item to + * carry out runtime-resume of it. + */ static inline int pm_runtime_get(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT | RPM_ASYNC); } +/** + * pm_runtime_get_sync - Bump up usage counter of a device and resume it. + * @dev: Target device. + * + * Bump up the runtime PM usage counter of @dev and carry out runtime-resume of + * it synchronously. + * + * The possible return values of this function are the same as for + * pm_runtime_resume() and the runtime PM usage counter of @dev remains + * incremented in all cases, even if it returns an error code. + */ static inline int pm_runtime_get_sync(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT); } +/** + * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0. + * @dev: Target device. + * + * Decrement the runtime PM usage counter of @dev and if it turns out to be + * equal to 0, queue up a work item for @dev like in pm_request_idle(). + */ static inline int pm_runtime_put(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); } +/** + * pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. + * @dev: Target device. + * + * Decrement the runtime PM usage counter of @dev and if it turns out to be + * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). + */ static inline int pm_runtime_put_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); } +/** + * pm_runtime_put_sync - Drop device usage counter and run "idle check" if 0. + * @dev: Target device. + * + * Decrement the runtime PM usage counter of @dev and if it turns out to be + * equal to 0, invoke the "idle check" callback of @dev and, depending on its + * return value, set up autosuspend of @dev or suspend it (depending on whether + * or not autosuspend has been enabled for it). + * + * The possible return values of this function are the same as for + * pm_runtime_idle() and the runtime PM usage counter of @dev remains + * decremented in all cases, even if it returns an error code. + */ static inline int pm_runtime_put_sync(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT); } +/** + * pm_runtime_put_sync_suspend - Drop device usage counter and suspend if 0. + * @dev: Target device. + * + * Decrement the runtime PM usage counter of @dev and if it turns out to be + * equal to 0, carry out runtime-suspend of @dev synchronously. + * + * The possible return values of this function are the same as for + * pm_runtime_suspend() and the runtime PM usage counter of @dev remains + * decremented in all cases, even if it returns an error code. + */ static inline int pm_runtime_put_sync_suspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT); } +/** + * pm_runtime_put_sync_autosuspend - Drop device usage counter and autosuspend if 0. + * @dev: Target device. + * + * Decrement the runtime PM usage counter of @dev and if it turns out to be + * equal to 0, set up autosuspend of @dev or suspend it synchronously (depending + * on whether or not autosuspend has been enabled for it). + * + * The possible return values of this function are the same as for + * pm_runtime_autosuspend() and the runtime PM usage counter of @dev remains + * decremented in all cases, even if it returns an error code. + */ static inline int pm_runtime_put_sync_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_AUTO); } +/** + * pm_runtime_set_active - Set runtime PM status to "active". + * @dev: Target device. + * + * Set the runtime PM status of @dev to %RPM_ACTIVE and ensure that dependencies + * of it will be taken into account. + * + * It is not valid to call this function for devices with runtime PM enabled. + */ static inline int pm_runtime_set_active(struct device *dev) { return __pm_runtime_set_status(dev, RPM_ACTIVE); } +/** + * pm_runtime_set_suspended - Set runtime PM status to "active". + * @dev: Target device. + * + * Set the runtime PM status of @dev to %RPM_SUSPENDED and ensure that + * dependencies of it will be taken into account. + * + * It is not valid to call this function for devices with runtime PM enabled. + */ static inline int pm_runtime_set_suspended(struct device *dev) { return __pm_runtime_set_status(dev, RPM_SUSPENDED); } +/** + * pm_runtime_disable - Disable runtime PM for a device. + * @dev: Target device. + * + * Prevent the runtime PM framework from working with @dev (by incrementing its + * "blocking" counter). + * + * For each invocation of this function for @dev there must be a matching + * pm_runtime_enable() call in order for runtime PM to be enabled for it. + */ static inline void pm_runtime_disable(struct device *dev) { __pm_runtime_disable(dev, true); } +/** + * pm_runtime_use_autosuspend - Allow autosuspend to be used for a device. + * @dev: Target device. + * + * Allow the runtime PM autosuspend mechanism to be used for @dev whenever + * requested (or "autosuspend" will be handled as direct runtime-suspend for + * it). + */ static inline void pm_runtime_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, true); } +/** + * pm_runtime_dont_use_autosuspend - Prevent autosuspend from being used. + * @dev: Target device. + * + * Prevent the runtime PM autosuspend mechanism from being used for @dev which + * means that "autosuspend" will be handled as direct runtime-suspend for it + * going forward. + */ static inline void pm_runtime_dont_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, false); -- cgit v1.2.3 From 669cbc708122fc7a02282058a09f096200cee090 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 21 Jul 2020 20:25:13 -0600 Subject: PCI: Move DT resource setup into devm_pci_alloc_host_bridge() Now that pci_parse_request_of_pci_ranges() callers just setup pci_host_bridge.windows and dma_ranges directly and don't need the bus range returned, we can just initialize them when allocating the pci_host_bridge struct. With this, pci_parse_request_of_pci_ranges() becomes a static function. Link: https://lore.kernel.org/r/20200722022514.1283916-19-robh@kernel.org Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi Acked-by: Bjorn Helgaas Cc: Lorenzo Pieralisi Cc: Bjorn Helgaas --- include/linux/pci.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c79d83304e52..2830799208fd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2303,10 +2303,6 @@ int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, struct device_node; struct irq_domain; struct irq_domain *pci_host_bridge_of_msi_domain(struct pci_bus *bus); -int pci_parse_request_of_pci_ranges(struct device *dev, - struct list_head *resources, - struct list_head *ib_resources, - struct resource **bus_range); /* Arch may override this (weak) */ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus); @@ -2314,14 +2310,6 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus); #else /* CONFIG_OF */ static inline struct irq_domain * pci_host_bridge_of_msi_domain(struct pci_bus *bus) { return NULL; } -static inline int -pci_parse_request_of_pci_ranges(struct device *dev, - struct list_head *resources, - struct list_head *ib_resources, - struct resource **bus_range) -{ - return -EINVAL; -} #endif /* CONFIG_OF */ static inline struct device_node * -- cgit v1.2.3 From a0102bda5bc0991c5c8c7c07770b236894a810fd Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 30 Jul 2020 11:03:55 -0400 Subject: ceph: move sb->wb_pagevec_pool to be a global mempool When doing some testing recently, I hit some page allocation failures on mount, when creating the wb_pagevec_pool for the mount. That requires 128k (32 contiguous pages), and after thrashing the memory during an xfstests run, sometimes that would fail. 128k for each mount seems like a lot to hold in reserve for a rainy day, so let's change this to a global mempool that gets allocated when the module is plugged in. Signed-off-by: Jeff Layton Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index e5ed1c541e7f..c8645f0b797d 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -282,6 +282,7 @@ extern struct kmem_cache *ceph_dentry_cachep; extern struct kmem_cache *ceph_file_cachep; extern struct kmem_cache *ceph_dir_file_cachep; extern struct kmem_cache *ceph_mds_request_cachep; +extern mempool_t *ceph_wb_pagevec_pool; /* ceph_common.c */ extern bool libceph_compatible(void *data); -- cgit v1.2.3 From df23bb18b44b9a1f2b54358201730e710a9df57f Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Tue, 4 Aug 2020 07:53:42 +0200 Subject: ipv4: route: Ignore output interface in FIB lookup for PMTU route Currently, processes sending traffic to a local bridge with an encapsulation device as a port don't get ICMP errors if they exceed the PMTU of the encapsulated link. David Ahern suggested this as a hack, but it actually looks like the correct solution: when we update the PMTU for a given destination by means of updating or creating a route exception, the encapsulation might trigger this because of PMTU discovery happening either on the encapsulation device itself, or its lower layer. This happens on bridged encapsulations only. The output interface shouldn't matter, because we already have a valid destination. Drop the output interface restriction from the associated route lookup. For UDP tunnels, we will now have a route exception created for the encapsulation itself, with a MTU value reflecting its headroom, which allows a bridge forwarding IP packets originated locally to deliver errors back to the sending socket. The behaviour is now consistent with IPv6 and verified with selftests pmtu_ipv{4,6}_br_{geneve,vxlan}{4,6}_exception introduced later in this series. v2: - reset output interface only for bridge ports (David Ahern) - add and use netif_is_any_bridge_port() helper (David Ahern) Suggested-by: David Ahern Signed-off-by: Stefano Brivio Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 88d40b9abaa1..90444622b703 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4840,6 +4840,11 @@ static inline bool netif_is_ovs_port(const struct net_device *dev) return dev->priv_flags & IFF_OVS_DATAPATH; } +static inline bool netif_is_any_bridge_port(const struct net_device *dev) +{ + return netif_is_bridge_port(dev) || netif_is_ovs_port(dev); +} + static inline bool netif_is_team_master(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM; -- cgit v1.2.3 From f073531070d24bbb82cb2658952d949f4851024b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 28 Jul 2020 17:49:47 +0200 Subject: init: add an init_dup helper Add a simple helper to grab a reference to a file and install it at the next available fd, and switch the early init code over to it. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/init_syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/init_syscalls.h b/include/linux/init_syscalls.h index 3654b525ac0b..92045d18cbfc 100644 --- a/include/linux/init_syscalls.h +++ b/include/linux/init_syscalls.h @@ -16,3 +16,4 @@ int __init init_unlink(const char *pathname); int __init init_mkdir(const char *pathname, umode_t mode); int __init init_rmdir(const char *pathname); int __init init_utimes(char *filename, struct timespec64 *ts); +int __init init_dup(struct file *file); -- cgit v1.2.3 From 4476770881d7ac647e3bcae0943f37e00b9c3f3c Mon Sep 17 00:00:00 2001 From: Siddharth Gupta Date: Wed, 29 Jul 2020 10:40:00 -0700 Subject: remoteproc: Add remoteproc character device interface Add the character device interface into remoteproc framework. This interface can be used in order to boot/shutdown remote subsystems and provides a basic ioctl based interface to implement supplementary functionality. An ioctl call is implemented to enable the shutdown on release feature which will allow remote processors to be shutdown when the controlling userspace application crashes or hangs. Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Signed-off-by: Rishabh Bhatnagar Signed-off-by: Siddharth Gupta Link: https://lore.kernel.org/r/1596044401-22083-2-git-send-email-sidgup@codeaurora.org [bjorn: s/int32_t/s32/ per checkpatch] Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 0e8d2ff575b4..2fa68bf5aa4f 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -38,6 +38,7 @@ #include #include #include +#include #include #include #include @@ -509,6 +510,8 @@ struct rproc_dump_segment { * @autonomous: true if an external entity has booted the remote processor * @dump_segments: list of segments in the firmware * @nb_vdev: number of vdev currently handled by rproc + * @char_dev: character device of the rproc + * @cdev_put_on_release: flag to indicate if remoteproc should be shutdown on @char_dev release */ struct rproc { struct list_head node; @@ -546,6 +549,8 @@ struct rproc { int nb_vdev; u8 elf_class; u16 elf_machine; + struct cdev cdev; + bool cdev_put_on_release; }; /** -- cgit v1.2.3 From 7de62bc09fe6d100ebd6c931c3f9a6fa7e6ed10f Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 15 Jul 2020 13:17:52 -0400 Subject: SUNRPC dont update timeout value on connection reset Current behaviour: every time a v3 operation is re-sent to the server we update (double) the timeout. There is no distinction between whether or not the previous timer had expired before the re-sent happened. Here's the scenario: 1. Client sends a v3 operation 2. Server RST-s the connection (prior to the timeout) (eg., connection is immediately reset) 3. Client re-sends a v3 operation but the timeout is now 120sec. As a result, an application sees 2mins pause before a retry in case server again does not reply. Instead, this patch proposes to keep track off when the minor timeout should happen and if it didn't, then don't update the new timeout. Value is updated based on the previous value to make timeouts predictable. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index e64bd8222f55..a603d48d2b2c 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -101,6 +101,7 @@ struct rpc_rqst { * used in the softirq. */ unsigned long rq_majortimeo; /* major timeout alarm */ + unsigned long rq_minortimeo; /* minor timeout alarm */ unsigned long rq_timeout; /* Current timeout value */ ktime_t rq_rtt; /* round-trip time */ unsigned int rq_retries; /* # of retries */ -- cgit v1.2.3 From 262e6ae7081df304fc625cf368d5c2cbba2bb991 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 28 Jul 2020 23:33:33 +0200 Subject: modules: inherit TAINT_PROPRIETARY_MODULE If a TAINT_PROPRIETARY_MODULE exports symbol, inherit the taint flag for all modules importing these symbols, and don't allow loading symbols from TAINT_PROPRIETARY_MODULE modules if the module previously imported gplonly symbols. Add a anti-circumvention devices so people don't accidentally get themselves into trouble this way. Comment from Greg: "Ah, the proven-to-be-illegal "GPL Condom" defense :)" [jeyu: pr_info -> pr_err and pr_warn as per discussion] Link: http://lore.kernel.org/r/20200730162957.GA22469@lst.de Acked-by: Daniel Vetter Reviewed-by: Greg Kroah-Hartman Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/module.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 30b0f5fcdb3c..e30ed5fa33a7 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -389,6 +389,7 @@ struct module { unsigned int num_gpl_syms; const struct kernel_symbol *gpl_syms; const s32 *gpl_crcs; + bool using_gplonly_symbols; #ifdef CONFIG_UNUSED_SYMBOLS /* unused exported symbols. */ -- cgit v1.2.3 From 75820314de26b00aaea0d0e79269c0d17914c5c4 Mon Sep 17 00:00:00 2001 From: Codrin Ciubotariu Date: Tue, 4 Aug 2020 12:59:24 +0300 Subject: i2c: core: add generic I2C GPIO recovery Multiple I2C bus drivers use similar bindings to obtain information needed for I2C recovery. For example, for platforms using device-tree, the properties look something like this: &i2c { ... pinctrl-names = "default", "gpio"; pinctrl-0 = <&pinctrl_i2c_default>; pinctrl-1 = <&pinctrl_i2c_gpio>; sda-gpios = <&pio 0 GPIO_ACTIVE_HIGH>; scl-gpios = <&pio 1 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; ... } For this reason, we can add this common initialization in the core. This way, other I2C bus drivers will be able to support GPIO recovery just by providing a pointer to platform's pinctrl and calling i2c_recover_bus() when SDA is stuck low. Signed-off-by: Codrin Ciubotariu [wsa: inverted one logic for better readability, minor update to kdoc] Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 8ea9c3f86dba..d387d3786429 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -606,6 +606,14 @@ struct i2c_timings { * may configure padmux here for SDA/SCL line or something else they want. * @scl_gpiod: gpiod of the SCL line. Only required for GPIO recovery. * @sda_gpiod: gpiod of the SDA line. Only required for GPIO recovery. + * @pinctrl: pinctrl used by GPIO recovery to change the state of the I2C pins. + * Optional. + * @pins_default: default pinctrl state of SCL/SDA lines, when they are assigned + * to the I2C bus. Optional. Populated internally for GPIO recovery, if + * state with the name PINCTRL_STATE_DEFAULT is found and pinctrl is valid. + * @pins_gpio: recovery pinctrl state of SCL/SDA lines, when they are used as + * GPIOs. Optional. Populated internally for GPIO recovery, if this state + * is called "gpio" or "recovery" and pinctrl is valid. */ struct i2c_bus_recovery_info { int (*recover_bus)(struct i2c_adapter *adap); @@ -622,6 +630,9 @@ struct i2c_bus_recovery_info { /* gpio recovery */ struct gpio_desc *scl_gpiod; struct gpio_desc *sda_gpiod; + struct pinctrl *pinctrl; + struct pinctrl_state *pins_default; + struct pinctrl_state *pins_gpio; }; int i2c_recover_bus(struct i2c_adapter *adap); -- cgit v1.2.3 From 5487196878bc926a1ee15069c13aa48b9a894fab Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 06:46:04 -0400 Subject: virtio_ring: sparse warning fixup virtio_store_mb was built with split ring in mind so it accepts __virtio16 arguments. Packed ring uses __le16 values, so sparse complains. It's just a store with some barriers so let's convert it to a macro, we don't loose too much type safety by doing that. Signed-off-by: Michael S. Tsirkin Acked-by: Cornelia Huck --- include/linux/virtio_ring.h | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 3dc70adfe5f5..b485b13fa50b 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -46,16 +46,15 @@ static inline void virtio_wmb(bool weak_barriers) dma_wmb(); } -static inline void virtio_store_mb(bool weak_barriers, - __virtio16 *p, __virtio16 v) -{ - if (weak_barriers) { - virt_store_mb(*p, v); - } else { - WRITE_ONCE(*p, v); - mb(); - } -} +#define virtio_store_mb(weak_barriers, p, v) \ +do { \ + if (weak_barriers) { \ + virt_store_mb(*p, v); \ + } else { \ + WRITE_ONCE(*p, v); \ + mb(); \ + } \ +} while (0) \ struct virtio_device; struct virtqueue; -- cgit v1.2.3 From a4235ec06acf05c58081700cda02dcd480d9e9cb Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 03:20:21 -0400 Subject: virtio: allow __virtioXX, __leXX in config space Currently all config space fields are of the type __uXX. This confuses people and some drivers (notably vdpa) access them using CPU endian-ness - which only works well for legacy or LE platforms. Update virtio_cread/virtio_cwrite macros to allow __virtioXX and __leXX field types. Follow-up patches will convert config space to use these types. Signed-off-by: Michael S. Tsirkin Acked-by: Cornelia Huck --- include/linux/virtio_config.h | 50 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 48 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 3b4eae5ac5e3..64da491936f7 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -6,6 +6,7 @@ #include #include #include +#include #include struct irq_affinity; @@ -287,12 +288,57 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) return __cpu_to_virtio64(virtio_is_little_endian(vdev), val); } +/* + * Only the checker differentiates between __virtioXX and __uXX types. But we + * try to share as much code as we can with the regular GCC build. + */ +#if !defined(CONFIG_CC_IS_GCC) && !defined(__CHECKER__) + +/* Not a checker - we can keep things simple */ +#define __virtio_native_typeof(x) typeof(x) + +#else + +/* + * We build this out of a couple of helper macros in a vain attempt to + * help you keep your lunch down while reading it. + */ +#define __virtio_pick_value(x, type, then, otherwise) \ + __builtin_choose_expr(__same_type(x, type), then, otherwise) + +#define __virtio_pick_type(x, type, then, otherwise) \ + __virtio_pick_value(x, type, (then)0, otherwise) + +#define __virtio_pick_endian(x, x16, x32, x64, otherwise) \ + __virtio_pick_type(x, x16, __u16, \ + __virtio_pick_type(x, x32, __u32, \ + __virtio_pick_type(x, x64, __u64, \ + otherwise))) + +#define __virtio_native_typeof(x) typeof( \ + __virtio_pick_type(x, __u8, __u8, \ + __virtio_pick_endian(x, __virtio16, __virtio32, __virtio64, \ + __virtio_pick_endian(x, __le16, __le32, __le64, \ + __virtio_pick_endian(x, __u16, __u32, __u64, \ + /* No other type allowed */ \ + (void)0))))) + +#endif + +#define __virtio_native_type(structname, member) \ + __virtio_native_typeof(((structname*)0)->member) + +#define __virtio_typecheck(structname, member, val) \ + /* Must match the member's type, and be integer */ \ + typecheck(__virtio_native_type(structname, member), (val)) + + /* Config space accessors. */ #define virtio_cread(vdev, structname, member, ptr) \ do { \ might_sleep(); \ /* Must match the member's type, and be integer */ \ - if (!typecheck(typeof((((structname*)0)->member)), *(ptr))) \ + if (!__virtio_typecheck(structname, member, *(ptr))) \ (*ptr) = 1; \ \ switch (sizeof(*ptr)) { \ @@ -322,7 +368,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) do { \ might_sleep(); \ /* Must match the member's type, and be integer */ \ - if (!typecheck(typeof((((structname*)0)->member)), *(ptr))) \ + if (!__virtio_typecheck(structname, member, *(ptr))) \ BUG_ON((*ptr) == 1); \ \ switch (sizeof(*ptr)) { \ -- cgit v1.2.3 From 4a04cfb0eb5e00432f9ff978f2b81bd1736e85db Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:55:52 -0400 Subject: virtio_config: disallow native type fields Transitional devices should all use __virtioXX types (and __leXX for fields not present in legacy devices). Modern ones should use __leXX. _uXX type would be a bug. Let's prevent that. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 64da491936f7..c68f58f3bf34 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -319,9 +319,8 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) __virtio_pick_type(x, __u8, __u8, \ __virtio_pick_endian(x, __virtio16, __virtio32, __virtio64, \ __virtio_pick_endian(x, __le16, __le32, __le64, \ - __virtio_pick_endian(x, __u16, __u32, __u64, \ - /* No other type allowed */ \ - (void)0))))) + /* No other type allowed */ \ + (void)0)))) #endif -- cgit v1.2.3 From 452639a64ad880792652b6d20cc5c8dd4ecf27d9 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 27 Jul 2020 10:51:55 -0400 Subject: vdpa: make sure set_features is invoked for legacy Some legacy guests just assume features are 0 after reset. We detect that config space is accessed before features are set and set features to 0 automatically. Note: some legacy guests might not even access config space, if this is reported in the field we might need to catch a kick to handle these. Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 239db794357c..29b8296f1414 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -33,12 +33,14 @@ struct vdpa_notification_area { * @dma_dev: the actual device that is performing DMA * @config: the configuration ops for this device. * @index: device index + * @features_valid: were features initialized? for legacy guests */ struct vdpa_device { struct device dev; struct device *dma_dev; const struct vdpa_config_ops *config; unsigned int index; + bool features_valid; }; /** @@ -266,4 +268,36 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev) { return vdev->dma_dev; } + +static inline void vdpa_reset(struct vdpa_device *vdev) +{ + const struct vdpa_config_ops *ops = vdev->config; + + vdev->features_valid = false; + ops->set_status(vdev, 0); +} + +static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) +{ + const struct vdpa_config_ops *ops = vdev->config; + + vdev->features_valid = true; + return ops->set_features(vdev, features); +} + + +static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset, + void *buf, unsigned int len) +{ + const struct vdpa_config_ops *ops = vdev->config; + + /* + * Config accesses aren't supposed to trigger before features are set. + * If it does happen we assume a legacy guest. + */ + if (!vdev->features_valid) + vdpa_set_features(vdev, 0); + ops->get_config(vdev, offset, buf, len); +} + #endif /* _LINUX_VDPA_H */ -- cgit v1.2.3 From cacaf775c699e9e8473491197587535f1c10ac8f Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 30 Jul 2020 16:12:40 -0400 Subject: virtio_config: cread/write cleanup Use vars of the correct type instead of casting. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index c68f58f3bf34..5c3b02245ecd 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -444,53 +444,60 @@ static inline void virtio_cwrite8(struct virtio_device *vdev, static inline u16 virtio_cread16(struct virtio_device *vdev, unsigned int offset) { - u16 ret; + __virtio16 ret; might_sleep(); vdev->config->get(vdev, offset, &ret, sizeof(ret)); - return virtio16_to_cpu(vdev, (__force __virtio16)ret); + return virtio16_to_cpu(vdev, ret); } static inline void virtio_cwrite16(struct virtio_device *vdev, unsigned int offset, u16 val) { + __virtio16 v; + might_sleep(); - val = (__force u16)cpu_to_virtio16(vdev, val); - vdev->config->set(vdev, offset, &val, sizeof(val)); + v = cpu_to_virtio16(vdev, val); + vdev->config->set(vdev, offset, &v, sizeof(v)); } static inline u32 virtio_cread32(struct virtio_device *vdev, unsigned int offset) { - u32 ret; + __virtio32 ret; might_sleep(); vdev->config->get(vdev, offset, &ret, sizeof(ret)); - return virtio32_to_cpu(vdev, (__force __virtio32)ret); + return virtio32_to_cpu(vdev, ret); } static inline void virtio_cwrite32(struct virtio_device *vdev, unsigned int offset, u32 val) { + __virtio32 v; + might_sleep(); - val = (__force u32)cpu_to_virtio32(vdev, val); - vdev->config->set(vdev, offset, &val, sizeof(val)); + v = cpu_to_virtio32(vdev, val); + vdev->config->set(vdev, offset, &v, sizeof(v)); } static inline u64 virtio_cread64(struct virtio_device *vdev, unsigned int offset) { - u64 ret; + __virtio64 ret; + __virtio_cread_many(vdev, offset, &ret, 1, sizeof(ret)); - return virtio64_to_cpu(vdev, (__force __virtio64)ret); + return virtio64_to_cpu(vdev, ret); } static inline void virtio_cwrite64(struct virtio_device *vdev, unsigned int offset, u64 val) { + __virtio64 v; + might_sleep(); - val = (__force u64)cpu_to_virtio64(vdev, val); - vdev->config->set(vdev, offset, &val, sizeof(val)); + v = cpu_to_virtio64(vdev, val); + vdev->config->set(vdev, offset, &v, sizeof(v)); } /* Conditional config space accessors. */ -- cgit v1.2.3 From a5b90f2db8e0ef6504695cbd36a65fd8296338ee Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 3 Aug 2020 16:08:11 -0400 Subject: virtio_config: rewrite using _Generic Min compiler version has been raised, so that's ok now. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 161 ++++++++++++++++++++---------------------- 1 file changed, 76 insertions(+), 85 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 5c3b02245ecd..7fa000f02721 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -288,112 +288,103 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) return __cpu_to_virtio64(virtio_is_little_endian(vdev), val); } -/* - * Only the checker differentiates between __virtioXX and __uXX types. But we - * try to share as much code as we can with the regular GCC build. - */ -#if !defined(CONFIG_CC_IS_GCC) && !defined(__CHECKER__) - -/* Not a checker - we can keep things simple */ -#define __virtio_native_typeof(x) typeof(x) - -#else - -/* - * We build this out of a couple of helper macros in a vain attempt to - * help you keep your lunch down while reading it. - */ -#define __virtio_pick_value(x, type, then, otherwise) \ - __builtin_choose_expr(__same_type(x, type), then, otherwise) - -#define __virtio_pick_type(x, type, then, otherwise) \ - __virtio_pick_value(x, type, (then)0, otherwise) - -#define __virtio_pick_endian(x, x16, x32, x64, otherwise) \ - __virtio_pick_type(x, x16, __u16, \ - __virtio_pick_type(x, x32, __u32, \ - __virtio_pick_type(x, x64, __u64, \ - otherwise))) - -#define __virtio_native_typeof(x) typeof( \ - __virtio_pick_type(x, __u8, __u8, \ - __virtio_pick_endian(x, __virtio16, __virtio32, __virtio64, \ - __virtio_pick_endian(x, __le16, __le32, __le64, \ - /* No other type allowed */ \ - (void)0)))) - -#endif +#define virtio_to_cpu(vdev, x) \ + _Generic((x), \ + __u8: (x), \ + __virtio16: virtio16_to_cpu((vdev), (x)), \ + __virtio32: virtio32_to_cpu((vdev), (x)), \ + __virtio64: virtio64_to_cpu((vdev), (x)), \ + /* + * Why define a default? checker can distinguish between + * e.g. __u16, __le16 and __virtio16, but GCC can't so + * attempts to define variants for both look like a duplicate + * variant to it. + */ \ + default: _Generic((x), \ + __u8: (x), \ + __le16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \ + __le32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \ + __le64: virtio64_to_cpu((vdev), (__force __virtio64)(x)), \ + default: _Generic((x), \ + __u8: (x), \ + __u16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \ + __u32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \ + __u64: virtio64_to_cpu((vdev), (__force __virtio64)(x)) \ + ) \ + ) \ + ) + +#define cpu_to_virtio(vdev, x, m) \ + _Generic((m), \ + __u8: (x), \ + __virtio16: cpu_to_virtio16((vdev), (x)), \ + __virtio32: cpu_to_virtio32((vdev), (x)), \ + __virtio64: cpu_to_virtio64((vdev), (x)), \ + /* + * Why define a default? checker can distinguish between + * e.g. __u16, __le16 and __virtio16, but GCC can't so + * attempts to define variants for both look like a duplicate + * variant to it. + */ \ + default: _Generic((m), \ + __u8: (x), \ + __le16: (__force __le16)cpu_to_virtio16((vdev), (x)), \ + __le32: (__force __le32)cpu_to_virtio32((vdev), (x)), \ + __le64: (__force __le64)cpu_to_virtio64((vdev), (x)), \ + default: _Generic((m), \ + __u8: (x), \ + __u16: (__force __u16)cpu_to_virtio16((vdev), (x)), \ + __u32: (__force __u32)cpu_to_virtio32((vdev), (x)), \ + __u64: (__force __u64)cpu_to_virtio64((vdev), (x)) \ + ) \ + ) \ + ) #define __virtio_native_type(structname, member) \ - __virtio_native_typeof(((structname*)0)->member) - -#define __virtio_typecheck(structname, member, val) \ - /* Must match the member's type, and be integer */ \ - typecheck(__virtio_native_type(structname, member), (val)) - + typeof(virtio_to_cpu(NULL, ((structname*)0)->member)) /* Config space accessors. */ #define virtio_cread(vdev, structname, member, ptr) \ do { \ + typeof(((structname*)0)->member) virtio_cread_v; \ + \ might_sleep(); \ - /* Must match the member's type, and be integer */ \ - if (!__virtio_typecheck(structname, member, *(ptr))) \ - (*ptr) = 1; \ + /* Sanity check: must match the member's type */ \ + typecheck(typeof(virtio_to_cpu((vdev), virtio_cread_v)), *(ptr)); \ \ - switch (sizeof(*ptr)) { \ + switch (sizeof(virtio_cread_v)) { \ case 1: \ - *(ptr) = virtio_cread8(vdev, \ - offsetof(structname, member)); \ - break; \ case 2: \ - *(ptr) = virtio_cread16(vdev, \ - offsetof(structname, member)); \ - break; \ case 4: \ - *(ptr) = virtio_cread32(vdev, \ - offsetof(structname, member)); \ - break; \ - case 8: \ - *(ptr) = virtio_cread64(vdev, \ - offsetof(structname, member)); \ + vdev->config->get((vdev), \ + offsetof(structname, member), \ + &virtio_cread_v, \ + sizeof(virtio_cread_v)); \ break; \ default: \ - BUG(); \ + __virtio_cread_many((vdev), \ + offsetof(structname, member), \ + &virtio_cread_v, \ + 1, \ + sizeof(virtio_cread_v)); \ + break; \ } \ + *(ptr) = virtio_to_cpu(vdev, virtio_cread_v); \ } while(0) /* Config space accessors. */ #define virtio_cwrite(vdev, structname, member, ptr) \ do { \ + typeof(((structname*)0)->member) virtio_cwrite_v = \ + cpu_to_virtio(vdev, *(ptr), ((structname*)0)->member); \ + \ might_sleep(); \ - /* Must match the member's type, and be integer */ \ - if (!__virtio_typecheck(structname, member, *(ptr))) \ - BUG_ON((*ptr) == 1); \ + /* Sanity check: must match the member's type */ \ + typecheck(typeof(virtio_to_cpu((vdev), virtio_cwrite_v)), *(ptr)); \ \ - switch (sizeof(*ptr)) { \ - case 1: \ - virtio_cwrite8(vdev, \ - offsetof(structname, member), \ - *(ptr)); \ - break; \ - case 2: \ - virtio_cwrite16(vdev, \ - offsetof(structname, member), \ - *(ptr)); \ - break; \ - case 4: \ - virtio_cwrite32(vdev, \ - offsetof(structname, member), \ - *(ptr)); \ - break; \ - case 8: \ - virtio_cwrite64(vdev, \ - offsetof(structname, member), \ - *(ptr)); \ - break; \ - default: \ - BUG(); \ - } \ + vdev->config->set((vdev), offsetof(structname, member), \ + &virtio_cwrite_v, \ + sizeof(virtio_cwrite_v)); \ } while(0) /* Read @count fields, @bytes each. */ -- cgit v1.2.3 From 14191c15ab9d87e60d2ebbfbf6df83d546152af1 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:55:52 -0400 Subject: virtio_config: disallow native type fields (again) _Generic version allowed __uXX types but that is no longer necessary: Transitional devices should all use __virtioXX types (and __leXX for fields not present in the legacy devices). Modern ones should use __leXX. _uXX type would be a bug. Let's prevent that. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 7fa000f02721..441fd6dd42ab 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -304,13 +304,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) __u8: (x), \ __le16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \ __le32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \ - __le64: virtio64_to_cpu((vdev), (__force __virtio64)(x)), \ - default: _Generic((x), \ - __u8: (x), \ - __u16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \ - __u32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \ - __u64: virtio64_to_cpu((vdev), (__force __virtio64)(x)) \ - ) \ + __le64: virtio64_to_cpu((vdev), (__force __virtio64)(x)) \ ) \ ) @@ -330,13 +324,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) __u8: (x), \ __le16: (__force __le16)cpu_to_virtio16((vdev), (x)), \ __le32: (__force __le32)cpu_to_virtio32((vdev), (x)), \ - __le64: (__force __le64)cpu_to_virtio64((vdev), (x)), \ - default: _Generic((m), \ - __u8: (x), \ - __u16: (__force __u16)cpu_to_virtio16((vdev), (x)), \ - __u32: (__force __u32)cpu_to_virtio32((vdev), (x)), \ - __u64: (__force __u64)cpu_to_virtio64((vdev), (x)) \ - ) \ + __le64: (__force __le64)cpu_to_virtio64((vdev), (x)) \ ) \ ) -- cgit v1.2.3 From e598960ff5e511b76a0eb8dff25207d35c2442c8 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 4 Aug 2020 17:33:08 -0400 Subject: virtio_config: LE config space accessors To be used by modern code, as well as to handle LE only fields such as balloon. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 65 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 441fd6dd42ab..5b5196fec899 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -375,6 +375,71 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) sizeof(virtio_cwrite_v)); \ } while(0) +/* + * Nothing virtio-specific about these, but let's worry about generalizing + * these later. + */ +#define virtio_le_to_cpu(x) \ + _Generic((x), \ + __u8: (x), \ + __le16: le16_to_cpu(x), \ + __le32: le32_to_cpu(x), \ + __le64: le64_to_cpu(x) \ + ) + +#define virtio_cpu_to_le(x, m) \ + _Generic((m), \ + __u8: (x), \ + __le16: cpu_to_le16(x), \ + __le32: cpu_to_le32(x), \ + __le64: cpu_to_le64(x) \ + ) + +/* LE (e.g. modern) Config space accessors. */ +#define virtio_cread_le(vdev, structname, member, ptr) \ + do { \ + typeof(((structname*)0)->member) virtio_cread_v; \ + \ + might_sleep(); \ + /* Sanity check: must match the member's type */ \ + typecheck(typeof(virtio_le_to_cpu(virtio_cread_v)), *(ptr)); \ + \ + switch (sizeof(virtio_cread_v)) { \ + case 1: \ + case 2: \ + case 4: \ + vdev->config->get((vdev), \ + offsetof(structname, member), \ + &virtio_cread_v, \ + sizeof(virtio_cread_v)); \ + break; \ + default: \ + __virtio_cread_many((vdev), \ + offsetof(structname, member), \ + &virtio_cread_v, \ + 1, \ + sizeof(virtio_cread_v)); \ + break; \ + } \ + *(ptr) = virtio_le_to_cpu(virtio_cread_v); \ + } while(0) + +/* Config space accessors. */ +#define virtio_cwrite_le(vdev, structname, member, ptr) \ + do { \ + typeof(((structname*)0)->member) virtio_cwrite_v = \ + virtio_cpu_to_le(*(ptr), ((structname*)0)->member); \ + \ + might_sleep(); \ + /* Sanity check: must match the member's type */ \ + typecheck(typeof(virtio_le_to_cpu(virtio_cwrite_v)), *(ptr)); \ + \ + vdev->config->set((vdev), offsetof(structname, member), \ + &virtio_cwrite_v, \ + sizeof(virtio_cwrite_v)); \ + } while(0) + + /* Read @count fields, @bytes each. */ static inline void __virtio_cread_many(struct virtio_device *vdev, unsigned int offset, -- cgit v1.2.3 From e3e7994d53082e48d2a6a248376683d3be3dff9d Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 4 Aug 2020 18:02:39 -0400 Subject: virtio_caif: correct tags for config space fields Tag config space fields as having virtio endian-ness. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_caif.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_caif.h b/include/linux/virtio_caif.h index 5d2d3124ca3d..ea722479510c 100644 --- a/include/linux/virtio_caif.h +++ b/include/linux/virtio_caif.h @@ -11,9 +11,9 @@ #include struct virtio_caif_transf_config { - u16 headroom; - u16 tailroom; - u32 mtu; + __virtio16 headroom; + __virtio16 tailroom; + __virtio32 mtu; u8 reserved[4]; }; -- cgit v1.2.3 From 035ce4210be1257dd417785ff7818b5c0f2205fb Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 09:17:38 -0400 Subject: virtio_config: add virtio_cread_le_feature Mirrors virtio_cread_feature but for LE fields. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 5b5196fec899..cc7a2b1fd7b2 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -555,4 +555,14 @@ static inline void virtio_cwrite64(struct virtio_device *vdev, _r; \ }) +/* Conditional config space accessors. */ +#define virtio_cread_le_feature(vdev, fbit, structname, member, ptr) \ + ({ \ + int _r = 0; \ + if (!virtio_has_feature(vdev, fbit)) \ + _r = -ENOENT; \ + else \ + virtio_cread_le((vdev), structname, member, ptr); \ + _r; \ + }) #endif /* _LINUX_VIRTIO_CONFIG_H */ -- cgit v1.2.3 From 83eb9db95eb453f1db651909ad4598c3d44ef1e1 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 07:29:12 -0400 Subject: virtio_config: drop LE option from config space All drivers now use virtio_cread/write_le for LE config space fields. Drop LE option from virtio_cread/write, only leaving the option to access transitional fields. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 28 ++-------------------------- 1 file changed, 2 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index cc7a2b1fd7b2..ecb166c824bb 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -293,19 +293,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) __u8: (x), \ __virtio16: virtio16_to_cpu((vdev), (x)), \ __virtio32: virtio32_to_cpu((vdev), (x)), \ - __virtio64: virtio64_to_cpu((vdev), (x)), \ - /* - * Why define a default? checker can distinguish between - * e.g. __u16, __le16 and __virtio16, but GCC can't so - * attempts to define variants for both look like a duplicate - * variant to it. - */ \ - default: _Generic((x), \ - __u8: (x), \ - __le16: virtio16_to_cpu((vdev), (__force __virtio16)(x)), \ - __le32: virtio32_to_cpu((vdev), (__force __virtio32)(x)), \ - __le64: virtio64_to_cpu((vdev), (__force __virtio64)(x)) \ - ) \ + __virtio64: virtio64_to_cpu((vdev), (x)) \ ) #define cpu_to_virtio(vdev, x, m) \ @@ -313,19 +301,7 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) __u8: (x), \ __virtio16: cpu_to_virtio16((vdev), (x)), \ __virtio32: cpu_to_virtio32((vdev), (x)), \ - __virtio64: cpu_to_virtio64((vdev), (x)), \ - /* - * Why define a default? checker can distinguish between - * e.g. __u16, __le16 and __virtio16, but GCC can't so - * attempts to define variants for both look like a duplicate - * variant to it. - */ \ - default: _Generic((m), \ - __u8: (x), \ - __le16: (__force __le16)cpu_to_virtio16((vdev), (x)), \ - __le32: (__force __le32)cpu_to_virtio32((vdev), (x)), \ - __le64: (__force __le64)cpu_to_virtio64((vdev), (x)) \ - ) \ + __virtio64: cpu_to_virtio64((vdev), (x)) \ ) #define __virtio_native_type(structname, member) \ -- cgit v1.2.3 From 7164675ab5caf46867d6a5448f4ff3af92d80a30 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Fri, 31 Jul 2020 14:55:30 +0800 Subject: vDPA: add get_vq_irq() in vdpa_config_ops This commit adds a new function get_vq_irq() in struct vdpa_config_ops, which will return the irq number of a virtqueue. Signed-off-by: Zhu Lingshan Suggested-by: Jason Wang Link: https://lore.kernel.org/r/20200731065533.4144-4-lingshan.zhu@intel.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 29b8296f1414..5c530a64aa06 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -89,6 +89,12 @@ struct vdpa_device { * @vdev: vdpa device * @idx: virtqueue index * Returns the notifcation area + * @get_vq_irq: Get the irq number of a virtqueue (optional, + * but must implemented if require vq irq offloading) + * @vdev: vdpa device + * @idx: virtqueue index + * Returns int: irq number of a virtqueue, + * negative number if no irq assigned. * @get_vq_align: Get the virtqueue align requirement * for the device * @vdev: vdpa device @@ -180,6 +186,7 @@ struct vdpa_config_ops { u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx); struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); + int (*get_vq_irq)(struct vdpa_device *vdv, u16 idx); /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); -- cgit v1.2.3 From 4c05433bc6fb4ae172270f0279be8ba89a3da64f Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Tue, 4 Aug 2020 18:21:23 +0800 Subject: vDPA: dont change vq irq after DRIVER_OK IRQ of a vq is not expected to be changed in a DRIVER_OK ~ !DRIVER_OK period for irq offloading purposes. Place this comment at the side of bus ops get_vq_irq than in set_status in vhost_vdpa. Signed-off-by: Zhu Lingshan Link: https://lore.kernel.org/r/20200804102123.69978-1-lingshan.zhu@intel.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 5c530a64aa06..565298cb45d2 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -186,6 +186,7 @@ struct vdpa_config_ops { u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx); struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); + /* vq irq is not expected to be changed once DRIVER_OK is set */ int (*get_vq_irq)(struct vdpa_device *vdv, u16 idx); /* Device ops */ -- cgit v1.2.3 From 923a3a863ae0c26876d704fb3453069e11ebdcb6 Mon Sep 17 00:00:00 2001 From: Michael Shych Date: Mon, 4 May 2020 17:14:24 +0300 Subject: platform_data/mlxreg: support new watchdog type with longer timeout period Add new watchdog type 3 with longer timeout period. Extend size of health_cntr field that that can be used to init watchdog timeout period. Signed-off-by: Michael Shych Reviewed-by: Vadim Pasternak Acked-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200504141427.17685-2-michaelsh@mellanox.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/linux/platform_data/mlxreg.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index b8da8aef2446..2c5e58d1d77b 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -43,10 +43,13 @@ * * TYPE1 HW watchdog implementation exist in old systems. * All new systems have TYPE2 HW watchdog. + * TYPE3 HW watchdog can exist on all systems with new CPLD. + * TYPE3 is selected by WD capability bit. */ enum mlxreg_wdt_type { MLX_WDT_TYPE1, MLX_WDT_TYPE2, + MLX_WDT_TYPE3, }; /** @@ -90,7 +93,7 @@ struct mlxreg_core_data { umode_t mode; struct device_node *np; struct mlxreg_hotplug_device hpdev; - u8 health_cntr; + u32 health_cntr; bool attached; }; -- cgit v1.2.3 From cef9572e9af373cefd1adc9e771e89670da5da3c Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 17 Jul 2020 16:29:56 +0300 Subject: watchdog: add support for adjusting last known HW keepalive time Certain watchdogs require the watchdog only to be pinged within a specific time window, pinging too early or too late cause the watchdog to fire. In cases where this sort of watchdog has been started before kernel comes up, we must adjust the watchdog keepalive window to match the actually running timer, so add a new driver API for this purpose. Signed-off-by: Tero Kristo Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20200717132958.14304-3-t-kristo@ti.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/linux/watchdog.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 1464ce6ffa31..9b19e6bb68b5 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -210,6 +210,8 @@ extern int watchdog_init_timeout(struct watchdog_device *wdd, extern int watchdog_register_device(struct watchdog_device *); extern void watchdog_unregister_device(struct watchdog_device *); +int watchdog_set_last_hw_keepalive(struct watchdog_device *, unsigned int); + /* devres register variant */ int devm_watchdog_register_device(struct device *dev, struct watchdog_device *); -- cgit v1.2.3 From a9974489b61c09c702c85c6cba3d1a3fd1be7a15 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Tue, 4 Aug 2020 19:20:42 +0300 Subject: vdpa: remove hard coded virtq num This will enable vdpa providers to add support for multi queue feature and publish it to upper layers (vhost and virtio). Signed-off-by: Max Gurtovoy Reviewed-by: Jason Wang Link: https://lore.kernel.org/r/20200804162048.22587-7-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 565298cb45d2..b5901cde73e0 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -41,6 +41,7 @@ struct vdpa_device { const struct vdpa_config_ops *config; unsigned int index; bool features_valid; + int nvqs; }; /** @@ -218,11 +219,12 @@ struct vdpa_config_ops { struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, + int nvqs, size_t size); -#define vdpa_alloc_device(dev_struct, member, parent, config) \ +#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs) \ container_of(__vdpa_alloc_device( \ - parent, config, \ + parent, config, nvqs, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ dev_struct, member))), \ -- cgit v1.2.3 From aac50c0bd434794b9950181349099e709ca4edad Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 4 Aug 2020 19:20:43 +0300 Subject: net/vdpa: Use struct for set/get vq state For now VQ state involves 16 bit available index value encoded in u64 variable. In the future it will be extended to contain more fields. Use struct to contain the state, now containing only a single u16 for the available index. In the future we can add fields to this struct. Reviewed-by: Parav Pandit Acked-by: Jason Wang Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20200804162048.22587-8-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index b5901cde73e0..d7399c983734 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -27,6 +27,14 @@ struct vdpa_notification_area { resource_size_t size; }; +/** + * vDPA vq_state definition + * @avail_index: available index + */ +struct vdpa_vq_state { + u16 avail_index; +}; + /** * vDPA device - representation of a vDPA device * @dev: underlying device @@ -80,12 +88,12 @@ struct vdpa_device { * @set_vq_state: Set the state for a virtqueue * @vdev: vdpa device * @idx: virtqueue index - * @state: virtqueue state (last_avail_idx) + * @state: pointer to set virtqueue state (last_avail_idx) * Returns integer: success (0) or error (< 0) * @get_vq_state: Get the state for a virtqueue * @vdev: vdpa device * @idx: virtqueue index - * Returns virtqueue state (last_avail_idx) + * @state: pointer to returned state (last_avail_idx) * @get_vq_notification: Get the notification area for a virtqueue * @vdev: vdpa device * @idx: virtqueue index @@ -183,8 +191,10 @@ struct vdpa_config_ops { struct vdpa_callback *cb); void (*set_vq_ready)(struct vdpa_device *vdev, u16 idx, bool ready); bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx); - int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, u64 state); - u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx); + int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, + const struct vdpa_vq_state *state); + void (*get_vq_state)(struct vdpa_device *vdev, u16 idx, + struct vdpa_vq_state *state); struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* vq irq is not expected to be changed once DRIVER_OK is set */ -- cgit v1.2.3 From 23750e39d57433d0e3d89658f0bc448f9c42ff49 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 4 Aug 2020 19:20:44 +0300 Subject: vdpa: Modify get_vq_state() to return error code Modify get_vq_state() so it returns an error code. In case of hardware acceleration, the available index may be retrieved from the device, an operation that can possibly fail. Reviewed-by: Parav Pandit Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20200804162048.22587-9-eli@mellanox.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/linux/vdpa.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index d7399c983734..eae0bfd87d91 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -193,8 +193,8 @@ struct vdpa_config_ops { bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx); int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, const struct vdpa_vq_state *state); - void (*get_vq_state)(struct vdpa_device *vdev, u16 idx, - struct vdpa_vq_state *state); + int (*get_vq_state)(struct vdpa_device *vdev, u16 idx, + struct vdpa_vq_state *state); struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* vq irq is not expected to be changed once DRIVER_OK is set */ -- cgit v1.2.3 From c84f91e2622235bb742f9f20b8675cf095157026 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 19:55:50 -0400 Subject: virtio_config: fix up warnings on parisc Apparently, on parisc le16_to_cpu returns an int. virtio_cread_le is very strict about type sizes so it causes a warning. Fix it up by casting to the correct type. Reported-by: kernel test robot Signed-off-by: Michael S. Tsirkin Link: https://lore.kernel.org/r/20200805235550.1451637-1-mst@redhat.com --- include/linux/virtio_config.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index ecb166c824bb..8fe857e27ef3 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -357,10 +357,10 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) */ #define virtio_le_to_cpu(x) \ _Generic((x), \ - __u8: (x), \ - __le16: le16_to_cpu(x), \ - __le32: le32_to_cpu(x), \ - __le64: le64_to_cpu(x) \ + __u8: (u8)(x), \ + __le16: (u16)le16_to_cpu(x), \ + __le32: (u32)le32_to_cpu(x), \ + __le64: (u64)le64_to_cpu(x) \ ) #define virtio_cpu_to_le(x, m) \ @@ -400,7 +400,6 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) *(ptr) = virtio_le_to_cpu(virtio_cread_v); \ } while(0) -/* Config space accessors. */ #define virtio_cwrite_le(vdev, structname, member, ptr) \ do { \ typeof(((structname*)0)->member) virtio_cwrite_v = \ -- cgit v1.2.3 From 0cd39f4600ed4de859383018eb10f0f724900e1b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 6 Aug 2020 14:35:11 +0200 Subject: locking/seqlock, headers: Untangle the spaghetti monster By using lockdep_assert_*() from seqlock.h, the spaghetti monster attacked. Attack back by reducing seqlock.h dependencies from two key high level headers: - : -Remove - : -Remove - : +Add The price was to add it to sched.h ... Core header fallout, we add direct header dependencies instead of gaining them parasitically from higher level headers: - : +Add - : +Add - : +Add - : +Add - : +Add - : +Add Arch headers fallout: - PARISC: : +Add - SH: : +Add - SPARC: : +Add - SPARC: : +Add , -Remove - X86: : +Add -Remove There's also a bunch of parasitic header dependency fallout in .c files, not listed separately. [ mingo: Extended the changelog, split up & fixed the original patch. ] Co-developed-by: Ingo Molnar Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200804133438.GK2674@hirez.programming.kicks-ass.net --- include/linux/dynamic_queue_limits.h | 2 ++ include/linux/hrtimer.h | 1 + include/linux/ktime.h | 1 + include/linux/lockdep.h | 1 + include/linux/mutex.h | 11 +++++++++++ include/linux/sched.h | 1 + include/linux/seqlock.h | 1 - include/linux/time.h | 1 - include/linux/videodev2.h | 1 + include/linux/ww_mutex.h | 8 -------- 10 files changed, 18 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index 99fc06f0afc1..407c2f281b64 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -38,6 +38,8 @@ #ifdef __KERNEL__ +#include + struct dql { /* Fields accessed in enqueue path (dql_queued) */ unsigned int num_queued; /* Total ever queued */ diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 25993b86ac5c..107cedd7019a 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 42d2e6ac35f2..a12b5523cc18 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -23,6 +23,7 @@ #include #include +#include /* Nanosecond scalar representation for kernel time values */ typedef s64 ktime_t; diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 39a35699d0d6..62a382d1845b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -11,6 +11,7 @@ #define __LINUX_LOCKDEP_H #include +#include #include struct task_struct; diff --git a/include/linux/mutex.h b/include/linux/mutex.h index ae197cc00cc8..dcd185cbfe79 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -65,6 +65,17 @@ struct mutex { #endif }; +struct ww_class; +struct ww_acquire_ctx; + +struct ww_mutex { + struct mutex base; + struct ww_acquire_ctx *ctx; +#ifdef CONFIG_DEBUG_MUTEXES + struct ww_class *ww_class; +#endif +}; + /* * This is the control structure for tasks blocked on mutex, * which resides on the blocked task's kernel stack: diff --git a/include/linux/sched.h b/include/linux/sched.h index 9a9d8263962d..7c7a9499d7bc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -31,6 +31,7 @@ #include #include #include +#include #include /* task_struct member predeclarations (sorted alphabetically): */ diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index a076f783aa36..962d9768945f 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -19,7 +19,6 @@ #include #include #include -#include #include diff --git a/include/linux/time.h b/include/linux/time.h index 4c325bf44ce0..b142cb5f5a53 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -3,7 +3,6 @@ #define _LINUX_TIME_H # include -# include # include # include diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 16c0ed6c50a7..219037f4c08d 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -57,6 +57,7 @@ #define __LINUX_VIDEODEV2_H #include /* need struct timeval */ +#include #include #endif /* __LINUX_VIDEODEV2_H */ diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index d7554252404c..850424e5d030 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -48,14 +48,6 @@ struct ww_acquire_ctx { #endif }; -struct ww_mutex { - struct mutex base; - struct ww_acquire_ctx *ctx; -#ifdef CONFIG_DEBUG_MUTEXES - struct ww_class *ww_class; -#endif -}; - #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) \ , .ww_class = class -- cgit v1.2.3 From 1fb497dd003009be95ce67689ac800c446b7acc5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 30 Jul 2020 12:14:06 +0200 Subject: posix-cpu-timers: Provide mechanisms to defer timer handling to task_work Running posix CPU timers in hard interrupt context has a few downsides: - For PREEMPT_RT it cannot work as the expiry code needs to take sighand lock, which is a 'sleeping spinlock' in RT. The original RT approach of offloading the posix CPU timer handling into a high priority thread was clumsy and provided no real benefit in general. - For fine grained accounting it's just wrong to run this in context of the timer interrupt because that way a process specific CPU time is accounted to the timer interrupt. - Long running timer interrupts caused by a large amount of expiring timers which can be created and armed by unpriviledged user space. There is no hard requirement to expire them in interrupt context. If the signal is targeted at the task itself then it won't be delivered before the task returns to user space anyway. If the signal is targeted at a supervisor process then it might be slightly delayed, but posix CPU timers are inaccurate anyway due to the fact that they are tied to the tick. Provide infrastructure to schedule task work which allows splitting the posix CPU timer code into a quick check in interrupt context and a thread context expiry and signal delivery function. This has to be enabled by architectures as it requires that the architecture specific KVM implementation handles pending task work before exiting to guest mode. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Reviewed-by: Oleg Nesterov Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20200730102337.783470146@linutronix.de --- include/linux/posix-timers.h | 17 +++++++++++++++++ include/linux/sched.h | 4 ++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index e3f0f8585da4..896c16d2c5fb 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -6,6 +6,7 @@ #include #include #include +#include struct kernel_siginfo; struct task_struct; @@ -125,6 +126,16 @@ struct posix_cputimers { unsigned int expiry_active; }; +/** + * posix_cputimers_work - Container for task work based posix CPU timer expiry + * @work: The task work to be scheduled + * @scheduled: @work has been scheduled already, no further processing + */ +struct posix_cputimers_work { + struct callback_head work; + unsigned int scheduled; +}; + static inline void posix_cputimers_init(struct posix_cputimers *pct) { memset(pct, 0, sizeof(*pct)); @@ -165,6 +176,12 @@ static inline void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { } #endif +#ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK +void posix_cputimers_init_work(void); +#else +static inline void posix_cputimers_init_work(void) { } +#endif + #define REQUEUE_PENDING 1 /** diff --git a/include/linux/sched.h b/include/linux/sched.h index 06ec60462af0..e9942ce07ef1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -889,6 +889,10 @@ struct task_struct { /* Empty if CONFIG_POSIX_CPUTIMERS=n */ struct posix_cputimers posix_cputimers; +#ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK + struct posix_cputimers_work posix_cputimers_work; +#endif + /* Process credentials: */ /* Tracer's credentials at attach: */ -- cgit v1.2.3 From 09fc67b500c7f0bb1b5ed774197ac7f2c5285655 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 17 Jul 2020 17:42:55 +0900 Subject: kprobes: Remove show_registers() function prototype Remove show_registers() function prototype because this function has been renamed by commit: 57da8b960b9a ("x86: Avoid double stack traces with show_regs()") and this commit has removed the caller in kprobes altogether: 80006dbee674 ("kprobes/x86: Remove jprobe implementation") So this doesn't exist anymore - remove the orphan prototype. Signed-off-by: Masami Hiramatsu Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 45b8cdc9fad7..9be1bff4f586 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -227,7 +227,6 @@ extern int arch_prepare_kprobe(struct kprobe *p); extern void arch_arm_kprobe(struct kprobe *p); extern void arch_disarm_kprobe(struct kprobe *p); extern int arch_init_kprobes(void); -extern void show_registers(struct pt_regs *regs); extern void kprobes_inc_nmissed_count(struct kprobe *p); extern bool arch_within_kprobe_blacklist(unsigned long addr); extern int arch_populate_kprobe_blacklist(void); -- cgit v1.2.3 From b55b3fdce3e554a6bbe8f8ca6a01a892d720e64e Mon Sep 17 00:00:00 2001 From: Bhupesh Sharma Date: Fri, 17 Jul 2020 13:01:00 +0530 Subject: hw_breakpoint: Remove unused __register_perf_hw_breakpoint() declaration Commit: b326e9560a28 ("hw-breakpoints: Use overflow handler instead of the event callback") removed __register_perf_hw_breakpoint() function usage and replaced it with register_perf_hw_breakpoint() function. Remove the left-over unused __register_perf_hw_breakpoint() declaration from as well. Signed-off-by: Bhupesh Sharma Signed-off-by: Ingo Molnar Acked-by: Mark Rutland Link: https://lore.kernel.org/r/1594971060-14180-1-git-send-email-bhsharma@redhat.com --- include/linux/hw_breakpoint.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index d7d4250cd1e4..78dd7035d1e5 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -72,7 +72,6 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr, void *context); extern int register_perf_hw_breakpoint(struct perf_event *bp); -extern int __register_perf_hw_breakpoint(struct perf_event *bp); extern void unregister_hw_breakpoint(struct perf_event *bp); extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events); @@ -119,8 +118,6 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr, void *context) { return NULL; } static inline int register_perf_hw_breakpoint(struct perf_event *bp) { return -ENOSYS; } -static inline int -__register_perf_hw_breakpoint(struct perf_event *bp) { return -ENOSYS; } static inline void unregister_hw_breakpoint(struct perf_event *bp) { } static inline void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events) { } -- cgit v1.2.3 From bb22d80b47d5dd641d09d31946c4be0f610f3f45 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 17 Jul 2020 16:36:40 -0700 Subject: LSM: drop duplicated words in header file comments Drop the doubled words "the" and "and" in comments. Signed-off-by: Randy Dunlap Acked-by: Serge Hallyn Cc: linux-security-module@vger.kernel.org Signed-off-by: James Morris --- include/linux/lsm_hook_defs.h | 2 +- include/linux/lsm_hooks.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 5616b2567aa7..dec0e5186834 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -15,7 +15,7 @@ */ /* - * The macro LSM_HOOK is used to define the data structures required by the + * The macro LSM_HOOK is used to define the data structures required by * the LSM framework using the pattern: * * LSM_HOOK(, , , args...) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 988ca0df7824..afd2c5becec5 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -798,7 +798,7 @@ * structure. Note that the security field was not added directly to the * socket structure, but rather, the socket security information is stored * in the associated inode. Typically, the inode alloc_security hook will - * allocate and and attach security information to + * allocate and attach security information to * SOCK_INODE(sock)->i_security. This hook may be used to update the * SOCK_INODE(sock)->i_security field with additional information that * wasn't available when the inode was allocated. -- cgit v1.2.3 From 5e7b30205cef80f6bb922e61834437ca7bff5837 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 4 Aug 2020 22:50:56 -0700 Subject: bpf: Change uapi for bpf iterator map elements Commit a5cbe05a6673 ("bpf: Implement bpf iterator for map elements") added bpf iterator support for map elements. The map element bpf iterator requires info to identify a particular map. In the above commit, the attr->link_create.target_fd is used to carry map_fd and an enum bpf_iter_link_info is added to uapi to specify the target_fd actually representing a map_fd: enum bpf_iter_link_info { BPF_ITER_LINK_UNSPEC = 0, BPF_ITER_LINK_MAP_FD = 1, MAX_BPF_ITER_LINK_INFO, }; This is an extensible approach as we can grow enumerator for pid, cgroup_id, etc. and we can unionize target_fd for pid, cgroup_id, etc. But in the future, there are chances that more complex customization may happen, e.g., for tasks, it could be filtered based on both cgroup_id and user_id. This patch changed the uapi to have fields __aligned_u64 iter_info; __u32 iter_info_len; for additional iter_info for link_create. The iter_info is defined as union bpf_iter_link_info { struct { __u32 map_fd; } map; }; So future extension for additional customization will be easier. The bpf_iter_link_info will be passed to target callback to validate and generic bpf_iter framework does not need to deal it any more. Note that map_fd = 0 will be considered invalid and -EBADF will be returned to user space. Fixes: a5cbe05a6673 ("bpf: Implement bpf iterator for map elements") Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200805055056.1457463-1-yhs@fb.com --- include/linux/bpf.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cef4ef0d2b4e..55f694b63164 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1214,15 +1214,17 @@ struct bpf_iter_aux_info { struct bpf_map *map; }; -typedef int (*bpf_iter_check_target_t)(struct bpf_prog *prog, - struct bpf_iter_aux_info *aux); +typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, + union bpf_iter_link_info *linfo, + struct bpf_iter_aux_info *aux); +typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux); #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; - bpf_iter_check_target_t check_target; + bpf_iter_attach_target_t attach_target; + bpf_iter_detach_target_t detach_target; u32 ctx_arg_info_size; - enum bpf_iter_link_info req_linfo; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; }; -- cgit v1.2.3 From d58669b093997e4e5f98c38a54f99761657c19d2 Mon Sep 17 00:00:00 2001 From: Akshu Agrawal Date: Fri, 31 Jul 2020 19:06:01 +0530 Subject: ACPI: APD: Change name from ST to FCH AMD SoC general pupose clk is present in new platforms with same MMIO mappings. We can reuse the same clk handler support for other platforms. Hence, changing name from ST(SoC) to FCH(IP) Signed-off-by: Akshu Agrawal Acked-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki --- include/linux/platform_data/clk-fch.h | 17 +++++++++++++++++ include/linux/platform_data/clk-st.h | 17 ----------------- 2 files changed, 17 insertions(+), 17 deletions(-) create mode 100644 include/linux/platform_data/clk-fch.h delete mode 100644 include/linux/platform_data/clk-st.h (limited to 'include/linux') diff --git a/include/linux/platform_data/clk-fch.h b/include/linux/platform_data/clk-fch.h new file mode 100644 index 000000000000..850ca776156d --- /dev/null +++ b/include/linux/platform_data/clk-fch.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: MIT */ +/* + * clock framework for AMD misc clocks + * + * Copyright 2018 Advanced Micro Devices, Inc. + */ + +#ifndef __CLK_FCH_H +#define __CLK_FCH_H + +#include + +struct fch_clk_data { + void __iomem *base; +}; + +#endif /* __CLK_FCH_H */ diff --git a/include/linux/platform_data/clk-st.h b/include/linux/platform_data/clk-st.h deleted file mode 100644 index 7cdb6a402b35..000000000000 --- a/include/linux/platform_data/clk-st.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * clock framework for AMD Stoney based clock - * - * Copyright 2018 Advanced Micro Devices, Inc. - */ - -#ifndef __CLK_ST_H -#define __CLK_ST_H - -#include - -struct st_clk_data { - void __iomem *base; -}; - -#endif /* __CLK_ST_H */ -- cgit v1.2.3 From 7f8802f2d2ed67ffbac9264f946a52507f749e19 Mon Sep 17 00:00:00 2001 From: Akshu Agrawal Date: Fri, 31 Jul 2020 19:06:03 +0530 Subject: ACPI: APD: Add a fmw property is_raven Since there is slight difference in AMD RV based soc in misc clk architecture. The fmw property will help in differentiating the SoCs. Signed-off-by: Akshu Agrawal Signed-off-by: Rafael J. Wysocki --- include/linux/platform_data/clk-fch.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/clk-fch.h b/include/linux/platform_data/clk-fch.h index 850ca776156d..b9f682459f08 100644 --- a/include/linux/platform_data/clk-fch.h +++ b/include/linux/platform_data/clk-fch.h @@ -12,6 +12,7 @@ struct fch_clk_data { void __iomem *base; + u32 is_rv; }; #endif /* __CLK_FCH_H */ -- cgit v1.2.3 From 529a781ee07aaa58be8164d75ba5998eb7dd216c Mon Sep 17 00:00:00 2001 From: "zhangyi (F)" Date: Sat, 20 Jun 2020 10:54:27 +0800 Subject: jbd2: remove unused parameter in jbd2_journal_try_to_free_buffers() Parameter gfp_mask in jbd2_journal_try_to_free_buffers() is no longer used after commit <536fc240e7147> ("jbd2: clean up jbd2_journal_try_to_free_buffers()"), so just remove it. Signed-off-by: zhangyi (F) Link: https://lore.kernel.org/r/20200620025427.1756360-6-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d56128df2aff..a756a4cdf939 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1380,7 +1380,7 @@ extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); extern int jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned int, unsigned int); -extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); +extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush (journal_t *); extern void jbd2_journal_lock_updates (journal_t *); -- cgit v1.2.3 From c1a06df6ebf6ca98fb7a672fe447c7469d6c1968 Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Thu, 6 Aug 2020 23:17:09 -0700 Subject: mm/migrate: fix migrate_pgmap_owner w/o CONFIG_MMU_NOTIFIER On x86_64, when CONFIG_MMU_NOTIFIER is not set/enabled, there is a compiler error: mm/migrate.c: In function 'migrate_vma_collect': mm/migrate.c:2481:7: error: 'struct mmu_notifier_range' has no member named 'migrate_pgmap_owner' range.migrate_pgmap_owner = migrate->pgmap_owner; ^ Fixes: 998427b3ad2c ("mm/notifier: add migration invalidation type") Reported-by: Randy Dunlap Signed-off-by: Ralph Campbell Signed-off-by: Andrew Morton Tested-by: Randy Dunlap Acked-by: Randy Dunlap Cc: Jerome Glisse Cc: John Hubbard Cc: Christoph Hellwig Cc: "Jason Gunthorpe" Link: http://lkml.kernel.org/r/20200806193353.7124-1-rcampbell@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index c6f0708195cd..b8200782dede 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -521,6 +521,16 @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, range->flags = flags; } +static inline void mmu_notifier_range_init_migrate( + struct mmu_notifier_range *range, unsigned int flags, + struct vm_area_struct *vma, struct mm_struct *mm, + unsigned long start, unsigned long end, void *pgmap) +{ + mmu_notifier_range_init(range, MMU_NOTIFY_MIGRATE, flags, vma, mm, + start, end); + range->migrate_pgmap_owner = pgmap; +} + #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ @@ -645,6 +655,9 @@ static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range, #define mmu_notifier_range_init(range,event,flags,vma,mm,start,end) \ _mmu_notifier_range_init(range, start, end) +#define mmu_notifier_range_init_migrate(range, flags, vma, mm, start, end, \ + pgmap) \ + _mmu_notifier_range_init(range, start, end) static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) -- cgit v1.2.3 From 453431a54934d917153c65211b2dabf45562ca88 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 6 Aug 2020 23:18:13 -0700 Subject: mm, treewide: rename kzfree() to kfree_sensitive() As said by Linus: A symmetric naming is only helpful if it implies symmetries in use. Otherwise it's actively misleading. In "kzalloc()", the z is meaningful and an important part of what the caller wants. In "kzfree()", the z is actively detrimental, because maybe in the future we really _might_ want to use that "memfill(0xdeadbeef)" or something. The "zero" part of the interface isn't even _relevant_. The main reason that kzfree() exists is to clear sensitive information that should not be leaked to other future users of the same memory objects. Rename kzfree() to kfree_sensitive() to follow the example of the recently added kvfree_sensitive() and make the intention of the API more explicit. In addition, memzero_explicit() is used to clear the memory to make sure that it won't get optimized away by the compiler. The renaming is done by using the command sequence: git grep -w --name-only kzfree |\ xargs sed -i 's/kzfree/kfree_sensitive/' followed by some editing of the kfree_sensitive() kerneldoc and adding a kzfree backward compatibility macro in slab.h. [akpm@linux-foundation.org: fs/crypto/inline_crypt.c needs linux/slab.h] [akpm@linux-foundation.org: fix fs/crypto/inline_crypt.c some more] Suggested-by: Joe Perches Signed-off-by: Waiman Long Signed-off-by: Andrew Morton Acked-by: David Howells Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Jarkko Sakkinen Cc: James Morris Cc: "Serge E. Hallyn" Cc: Joe Perches Cc: Matthew Wilcox Cc: David Rientjes Cc: Dan Carpenter Cc: "Jason A . Donenfeld" Link: http://lkml.kernel.org/r/20200616154311.12314-3-longman@redhat.com Signed-off-by: Linus Torvalds --- include/linux/slab.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 6d454886bcaf..0884d82c55ee 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -186,10 +186,12 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *, struct mem_cgroup *); */ void * __must_check krealloc(const void *, size_t, gfp_t); void kfree(const void *); -void kzfree(const void *); +void kfree_sensitive(const void *); size_t __ksize(const void *); size_t ksize(const void *); +#define kzfree(x) kfree_sensitive(x) /* For backward compatibility */ + #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR void __check_heap_object(const void *ptr, unsigned long n, struct page *page, bool to_user); -- cgit v1.2.3 From 6dc5ea16c86f753951f53085aa04df49cf17cb50 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 6 Aug 2020 23:19:51 -0700 Subject: mm, dump_page: do not crash with bad compound_mapcount() If a compound page is being split while dump_page() is being run on that page, we can end up calling compound_mapcount() on a page that is no longer compound. This leads to a crash (already seen at least once in the field), due to the VM_BUG_ON_PAGE() assertion inside compound_mapcount(). (The above is from Matthew Wilcox's analysis of Qian Cai's bug report.) A similar problem is possible, via compound_pincount() instead of compound_mapcount(). In order to avoid this kind of crash, make dump_page() slightly more robust, by providing a pair of simpler routines that don't contain assertions: head_mapcount() and head_pincount(). For debug tools, we don't want to go *too* far in this direction, but this is a simple small fix, and the crash has already been seen, so it's a good trade-off. Reported-by: Qian Cai Suggested-by: Matthew Wilcox Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Acked-by: Vlastimil Babka Cc: Kirill A. Shutemov Cc: Mike Rapoport Cc: William Kucharski Link: http://lkml.kernel.org/r/20200804214807.169256-1-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index dc7b87310c10..303a47a9769d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -779,6 +779,11 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) extern void kvfree(const void *addr); extern void kvfree_sensitive(const void *addr, size_t len); +static inline int head_mapcount(struct page *head) +{ + return atomic_read(compound_mapcount_ptr(head)) + 1; +} + /* * Mapcount of compound page as a whole, does not include mapped sub-pages. * @@ -788,7 +793,7 @@ static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); page = compound_head(page); - return atomic_read(compound_mapcount_ptr(page)) + 1; + return head_mapcount(page); } /* @@ -901,11 +906,16 @@ static inline bool hpage_pincount_available(struct page *page) return PageCompound(page) && compound_order(page) > 1; } +static inline int head_pincount(struct page *head) +{ + return atomic_read(compound_pincount_ptr(head)); +} + static inline int compound_pincount(struct page *page) { VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); page = compound_head(page); - return atomic_read(compound_pincount_ptr(page)); + return head_pincount(page); } static inline void set_compound_order(struct page *page, unsigned int order) -- cgit v1.2.3 From e809d5f0b5c912fe981dce738f3283b2010665f0 Mon Sep 17 00:00:00 2001 From: Chris Down Date: Thu, 6 Aug 2020 23:20:20 -0700 Subject: tmpfs: per-superblock i_ino support Patch series "tmpfs: inode: Reduce risk of inum overflow", v7. In Facebook production we are seeing heavy i_ino wraparounds on tmpfs. On affected tiers, in excess of 10% of hosts show multiple files with different content and the same inode number, with some servers even having as many as 150 duplicated inode numbers with differing file content. This causes actual, tangible problems in production. For example, we have complaints from those working on remote caches that their application is reporting cache corruptions because it uses (device, inodenum) to establish the identity of a particular cache object, but because it's not unique any more, the application refuses to continue and reports cache corruption. Even worse, sometimes applications may not even detect the corruption but may continue anyway, causing phantom and hard to debug behaviour. In general, userspace applications expect that (device, inodenum) should be enough to be uniquely point to one inode, which seems fair enough. One might also need to check the generation, but in this case: 1. That's not currently exposed to userspace (ioctl(...FS_IOC_GETVERSION...) returns ENOTTY on tmpfs); 2. Even with generation, there shouldn't be two live inodes with the same inode number on one device. In order to mitigate this, we take a two-pronged approach: 1. Moving inum generation from being global to per-sb for tmpfs. This itself allows some reduction in i_ino churn. This works on both 64- and 32- bit machines. 2. Adding inode{64,32} for tmpfs. This fix is supported on machines with 64-bit ino_t only: we allow users to mount tmpfs with a new inode64 option that uses the full width of ino_t, or CONFIG_TMPFS_INODE64. You can see how this compares to previous related patches which didn't implement this per-superblock: - https://patchwork.kernel.org/patch/11254001/ - https://patchwork.kernel.org/patch/11023915/ This patch (of 2): get_next_ino has a number of problems: - It uses and returns a uint, which is susceptible to become overflowed if a lot of volatile inodes that use get_next_ino are created. - It's global, with no specificity per-sb or even per-filesystem. This means it's not that difficult to cause inode number wraparounds on a single device, which can result in having multiple distinct inodes with the same inode number. This patch adds a per-superblock counter that mitigates the second case. This design also allows us to later have a specific i_ino size per-device, for example, allowing users to choose whether to use 32- or 64-bit inodes for each tmpfs mount. This is implemented in the next commit. For internal shmem mounts which may be less tolerant to spinlock delays, we implement a percpu batching scheme which only takes the stat_lock at each batch boundary. Signed-off-by: Chris Down Signed-off-by: Andrew Morton Acked-by: Hugh Dickins Cc: Amir Goldstein Cc: Al Viro Cc: Matthew Wilcox Cc: Jeff Layton Cc: Johannes Weiner Cc: Tejun Heo Link: http://lkml.kernel.org/r/cover.1594661218.git.chris@chrisdown.name Link: http://lkml.kernel.org/r/1986b9d63b986f08ec07a4aa4b2275e718e47d8a.1594661218.git.chris@chrisdown.name Signed-off-by: Linus Torvalds --- include/linux/fs.h | 15 +++++++++++++++ include/linux/shmem_fs.h | 2 ++ 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 488c3ef93601..b1c3a14f12e8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2946,6 +2946,21 @@ extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); +/* + * Userspace may rely on the the inode number being non-zero. For example, glibc + * simply ignores files with zero i_ino in unlink() and other places. + * + * As an additional complication, if userspace was compiled with + * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the + * lower 32 bits, so we need to check that those aren't zero explicitly. With + * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but + * better safe than sorry. + */ +static inline bool is_zero_ino(ino_t ino) +{ + return (u32)ino == 0; +} + extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 7a35a6901221..eb628696ec66 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -36,6 +36,8 @@ struct shmem_sb_info { unsigned char huge; /* Whether to try for hugepages */ kuid_t uid; /* Mount uid for root directory */ kgid_t gid; /* Mount gid for root directory */ + ino_t next_ino; /* The next per-sb inode number to use */ + ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */ struct mempolicy *mpol; /* default memory policy for mappings */ spinlock_t shrinklist_lock; /* Protects shrinklist */ struct list_head shrinklist; /* List of shinkable inodes */ -- cgit v1.2.3 From ea3271f7196c65ae5d3e1c7b3f733892c017dbd6 Mon Sep 17 00:00:00 2001 From: Chris Down Date: Thu, 6 Aug 2020 23:20:25 -0700 Subject: tmpfs: support 64-bit inums per-sb The default is still set to inode32 for backwards compatibility, but system administrators can opt in to the new 64-bit inode numbers by either: 1. Passing inode64 on the command line when mounting, or 2. Configuring the kernel with CONFIG_TMPFS_INODE64=y The inode64 and inode32 names are used based on existing precedent from XFS. [hughd@google.com: Kconfig fixes] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.2008011928010.13320@eggly.anvils Signed-off-by: Chris Down Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Reviewed-by: Amir Goldstein Acked-by: Hugh Dickins Cc: Al Viro Cc: Matthew Wilcox Cc: Jeff Layton Cc: Johannes Weiner Cc: Tejun Heo Link: http://lkml.kernel.org/r/8b23758d0c66b5e2263e08baf9c4b6a7565cbd8f.1594661218.git.chris@chrisdown.name Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index eb628696ec66..a5a5d1d4d7b1 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -36,6 +36,7 @@ struct shmem_sb_info { unsigned char huge; /* Whether to try for hugepages */ kuid_t uid; /* Mount uid for root directory */ kgid_t gid; /* Mount gid for root directory */ + bool full_inums; /* If i_ino should be uint or ino_t */ ino_t next_ino; /* The next per-sb inode number to use */ ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */ struct mempolicy *mpol; /* default memory policy for mappings */ -- cgit v1.2.3 From eedc4e5a142cc33fbb54f8d72b929a0e123c48c4 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:20:32 -0700 Subject: mm: memcg: factor out memcg- and lruvec-level changes out of __mod_lruvec_state() Patch series "The new cgroup slab memory controller", v7. The patchset moves the accounting from the page level to the object level. It allows to share slab pages between memory cgroups. This leads to a significant win in the slab utilization (up to 45%) and the corresponding drop in the total kernel memory footprint. The reduced number of unmovable slab pages should also have a positive effect on the memory fragmentation. The patchset makes the slab accounting code simpler: there is no more need in the complicated dynamic creation and destruction of per-cgroup slab caches, all memory cgroups use a global set of shared slab caches. The lifetime of slab caches is not more connected to the lifetime of memory cgroups. The more precise accounting does require more CPU, however in practice the difference seems to be negligible. We've been using the new slab controller in Facebook production for several months with different workloads and haven't seen any noticeable regressions. What we've seen were memory savings in order of 1 GB per host (it varied heavily depending on the actual workload, size of RAM, number of CPUs, memory pressure, etc). The third version of the patchset added yet another step towards the simplification of the code: sharing of slab caches between accounted and non-accounted allocations. It comes with significant upsides (most noticeable, a complete elimination of dynamic slab caches creation) but not without some regression risks, so this change sits on top of the patchset and is not completely merged in. So in the unlikely event of a noticeable performance regression it can be reverted separately. The slab memory accounting works in exactly the same way for SLAB and SLUB. With both allocators the new controller shows significant memory savings, with SLUB the difference is bigger. On my 16-core desktop machine running Fedora 32 the size of the slab memory measured after the start of the system was lower by 58% and 38% with SLUB and SLAB correspondingly. As an estimation of a potential CPU overhead, below are results of slab_bulk_test01 test, kindly provided by Jesper D. Brouer. He also helped with the evaluation of results. The test can be found here: https://github.com/netoptimizer/prototype-kernel/ The smallest number in each row should be picked for a comparison. SLUB-patched - bulk-API - SLUB-patched : bulk_quick_reuse objects=1 : 187 - 90 - 224 cycles(tsc) - SLUB-patched : bulk_quick_reuse objects=2 : 110 - 53 - 133 cycles(tsc) - SLUB-patched : bulk_quick_reuse objects=3 : 88 - 95 - 42 cycles(tsc) - SLUB-patched : bulk_quick_reuse objects=4 : 91 - 85 - 36 cycles(tsc) - SLUB-patched : bulk_quick_reuse objects=8 : 32 - 66 - 32 cycles(tsc) SLUB-original - bulk-API - SLUB-original: bulk_quick_reuse objects=1 : 87 - 87 - 142 cycles(tsc) - SLUB-original: bulk_quick_reuse objects=2 : 52 - 53 - 53 cycles(tsc) - SLUB-original: bulk_quick_reuse objects=3 : 42 - 42 - 91 cycles(tsc) - SLUB-original: bulk_quick_reuse objects=4 : 91 - 37 - 37 cycles(tsc) - SLUB-original: bulk_quick_reuse objects=8 : 31 - 79 - 76 cycles(tsc) SLAB-patched - bulk-API - SLAB-patched : bulk_quick_reuse objects=1 : 67 - 67 - 140 cycles(tsc) - SLAB-patched : bulk_quick_reuse objects=2 : 55 - 46 - 46 cycles(tsc) - SLAB-patched : bulk_quick_reuse objects=3 : 93 - 94 - 39 cycles(tsc) - SLAB-patched : bulk_quick_reuse objects=4 : 35 - 88 - 85 cycles(tsc) - SLAB-patched : bulk_quick_reuse objects=8 : 30 - 30 - 30 cycles(tsc) SLAB-original- bulk-API - SLAB-original: bulk_quick_reuse objects=1 : 143 - 136 - 67 cycles(tsc) - SLAB-original: bulk_quick_reuse objects=2 : 45 - 46 - 46 cycles(tsc) - SLAB-original: bulk_quick_reuse objects=3 : 38 - 39 - 39 cycles(tsc) - SLAB-original: bulk_quick_reuse objects=4 : 35 - 87 - 87 cycles(tsc) - SLAB-original: bulk_quick_reuse objects=8 : 29 - 66 - 30 cycles(tsc) This patch (of 19): To convert memcg and lruvec slab counters to bytes there must be a way to change these counters without touching node counters. Factor out __mod_memcg_lruvec_state() out of __mod_lruvec_state(). Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Christoph Lameter Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200623174037.3951353-1-guro@fb.com Link: http://lkml.kernel.org/r/20200623174037.3951353-2-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e77197a62809..b250f8197710 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -679,11 +679,23 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, return x; } +void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, + int val); void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val); void mod_memcg_obj_state(void *p, int idx, int val); +static inline void mod_memcg_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, int val) +{ + unsigned long flags; + + local_irq_save(flags); + __mod_memcg_lruvec_state(lruvec, idx, val); + local_irq_restore(flags); +} + static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { @@ -1057,6 +1069,11 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, return node_page_state(lruvec_pgdat(lruvec), idx); } +static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, int val) +{ +} + static inline void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { -- cgit v1.2.3 From ea426c2a7de8e575108b7cecd3374e0c15a9f25e Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:20:35 -0700 Subject: mm: memcg: prepare for byte-sized vmstat items To implement per-object slab memory accounting, we need to convert slab vmstat counters to bytes. Actually, out of 4 levels of counters: global, per-node, per-memcg and per-lruvec only two last levels will require byte-sized counters. It's because global and per-node counters will be counting the number of slab pages, and per-memcg and per-lruvec will be counting the amount of memory taken by charged slab objects. Converting all vmstat counters to bytes or even all slab counters to bytes would introduce an additional overhead. So instead let's store global and per-node counters in pages, and memcg and lruvec counters in bytes. To make the API clean all access helpers (both on the read and write sides) are dealing with bytes. To avoid back-and-forth conversions a new flavor of read-side helpers is introduced, which always returns values in pages: node_page_state_pages() and global_node_page_state_pages(). Actually new helpers are just reading raw values. Old helpers are simple wrappers, which will complain on an attempt to read byte value, because at the moment no one actually needs bytes. Thanks to Johannes Weiner for the idea of having the byte-sized API on top of the page-sized internal storage. Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Christoph Lameter Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200623174037.3951353-3-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 10 ++++++++++ include/linux/vmstat.h | 14 +++++++++++++- 2 files changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f6f884970511..f16306e15b98 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -206,6 +206,16 @@ enum node_stat_item { NR_VM_NODE_STAT_ITEMS }; +/* + * Returns true if the value is measured in bytes (most vmstat values are + * measured in pages). This defines the API part, the internal representation + * might be different. + */ +static __always_inline bool vmstat_item_in_bytes(int idx) +{ + return false; +} + /* * We do arithmetic on the LRU lists in various places in the code, * so it is important to keep the active lists LRU_ACTIVE higher in diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index aa961088c551..91220ace31da 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -8,6 +8,7 @@ #include #include #include +#include extern int sysctl_stat_interval; @@ -192,7 +193,8 @@ static inline unsigned long global_zone_page_state(enum zone_stat_item item) return x; } -static inline unsigned long global_node_page_state(enum node_stat_item item) +static inline +unsigned long global_node_page_state_pages(enum node_stat_item item) { long x = atomic_long_read(&vm_node_stat[item]); #ifdef CONFIG_SMP @@ -202,6 +204,13 @@ static inline unsigned long global_node_page_state(enum node_stat_item item) return x; } +static inline unsigned long global_node_page_state(enum node_stat_item item) +{ + VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); + + return global_node_page_state_pages(item); +} + static inline unsigned long zone_page_state(struct zone *zone, enum zone_stat_item item) { @@ -242,9 +251,12 @@ extern unsigned long sum_zone_node_page_state(int node, extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); +extern unsigned long node_page_state_pages(struct pglist_data *pgdat, + enum node_stat_item item); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) +#define node_page_state_pages(node, item) global_node_page_state_pages(item) #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP -- cgit v1.2.3 From d42f3245c7e299e017213fa028c319316bcdb7f4 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:20:39 -0700 Subject: mm: memcg: convert vmstat slab counters to bytes In order to prepare for per-object slab memory accounting, convert NR_SLAB_RECLAIMABLE and NR_SLAB_UNRECLAIMABLE vmstat items to bytes. To make it obvious, rename them to NR_SLAB_RECLAIMABLE_B and NR_SLAB_UNRECLAIMABLE_B (similar to NR_KERNEL_STACK_KB). Internally global and per-node counters are stored in pages, however memcg and lruvec counters are stored in bytes. This scheme may look weird, but only for now. As soon as slab pages will be shared between multiple cgroups, global and node counters will reflect the total number of slab pages. However memcg and lruvec counters will be used for per-memcg slab memory tracking, which will take separate kernel objects in the account. Keeping global and node counters in pages helps to avoid additional overhead. The size of slab memory shouldn't exceed 4Gb on 32-bit machines, so it will fit into atomic_long_t we use for vmstats. Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Christoph Lameter Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200623174037.3951353-4-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f16306e15b98..b79100edd228 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -174,8 +174,8 @@ enum node_stat_item { NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ - NR_SLAB_RECLAIMABLE, - NR_SLAB_UNRECLAIMABLE, + NR_SLAB_RECLAIMABLE_B, + NR_SLAB_UNRECLAIMABLE_B, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, @@ -213,7 +213,17 @@ enum node_stat_item { */ static __always_inline bool vmstat_item_in_bytes(int idx) { - return false; + /* + * Global and per-node slab counters track slab pages. + * It's expected that changes are multiples of PAGE_SIZE. + * Internally values are stored in pages. + * + * Per-memcg and per-lruvec counters track memory, consumed + * by individual slab objects. These counters are actually + * byte-precise. + */ + return (idx == NR_SLAB_RECLAIMABLE_B || + idx == NR_SLAB_UNRECLAIMABLE_B); } /* -- cgit v1.2.3 From 4138fdfc8b5db5a7a4b9b50c69d475fb2ac351b7 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:20:42 -0700 Subject: mm: slub: implement SLUB version of obj_to_index() This commit implements SLUB version of the obj_to_index() function, which will be required to calculate the offset of obj_cgroup in the obj_cgroups vector to store/obtain the objcg ownership data. To make it faster, let's repeat the SLAB's trick introduced by commit 6a2d7a955d8d ("SLAB: use a multiply instead of a divide in obj_to_index()") and avoid an expensive division. Vlastimil Babka noticed, that SLUB does have already a similar function called slab_index(), which is defined only if SLUB_DEBUG is enabled. The function does a similar math, but with a division, and it also takes a page address instead of a page pointer. Let's remove slab_index() and replace it with the new helper __obj_to_index(), which takes a page address. obj_to_index() will be a simple wrapper taking a page pointer and passing page_address(page) into __obj_to_index(). Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Christoph Lameter Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200623174037.3951353-5-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/slub_def.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index d2153789bd9f..30e91c83d401 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -8,6 +8,7 @@ * (C) 2007 SGI, Christoph Lameter */ #include +#include enum stat_item { ALLOC_FASTPATH, /* Allocation from cpu slab */ @@ -86,6 +87,7 @@ struct kmem_cache { unsigned long min_partial; unsigned int size; /* The size of an object including metadata */ unsigned int object_size;/* The size of an object without metadata */ + struct reciprocal_value reciprocal_size; unsigned int offset; /* Free pointer offset */ #ifdef CONFIG_SLUB_CPU_PARTIAL /* Number of per cpu partial objects to keep around */ @@ -182,4 +184,18 @@ static inline void *nearest_obj(struct kmem_cache *cache, struct page *page, return result; } +/* Determine object index from a given position */ +static inline unsigned int __obj_to_index(const struct kmem_cache *cache, + void *addr, void *obj) +{ + return reciprocal_divide(kasan_reset_tag(obj) - addr, + cache->reciprocal_size); +} + +static inline unsigned int obj_to_index(const struct kmem_cache *cache, + const struct page *page, void *obj) +{ + return __obj_to_index(cache, page_address(page), obj); +} + #endif /* _LINUX_SLUB_DEF_H */ -- cgit v1.2.3 From bf4f059954dcb221384b2f784677e19a13cd4bdb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:20:49 -0700 Subject: mm: memcg/slab: obj_cgroup API Obj_cgroup API provides an ability to account sub-page sized kernel objects, which potentially outlive the original memory cgroup. The top-level API consists of the following functions: bool obj_cgroup_tryget(struct obj_cgroup *objcg); void obj_cgroup_get(struct obj_cgroup *objcg); void obj_cgroup_put(struct obj_cgroup *objcg); int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg); struct obj_cgroup *get_obj_cgroup_from_current(void); Object cgroup is basically a pointer to a memory cgroup with a per-cpu reference counter. It substitutes a memory cgroup in places where it's necessary to charge a custom amount of bytes instead of pages. All charged memory rounded down to pages is charged to the corresponding memory cgroup using __memcg_kmem_charge(). It implements reparenting: on memcg offlining it's getting reattached to the parent memory cgroup. Each online memory cgroup has an associated active object cgroup to handle new allocations and the list of all attached object cgroups. On offlining of a cgroup this list is reparented and for each object cgroup in the list the memcg pointer is swapped to the parent memory cgroup. It prevents long-living objects from pinning the original memory cgroup in the memory. The implementation is based on byte-sized per-cpu stocks. A sub-page sized leftover is stored in an atomic field, which is a part of obj_cgroup object. So on cgroup offlining the leftover is automatically reparented. memcg->objcg is rcu protected. objcg->memcg is a raw pointer, which is always pointing at a memory cgroup, but can be atomically swapped to the parent memory cgroup. So a user must ensure the lifetime of the cgroup, e.g. grab rcu_read_lock or css_set_lock. Suggested-by: Johannes Weiner Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Cc: Christoph Lameter Cc: Michal Hocko Cc: Tejun Heo Cc: Vlastimil Babka Link: http://lkml.kernel.org/r/20200623174037.3951353-7-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 51 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b250f8197710..f2f9d5d6b7d1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -23,6 +23,7 @@ #include struct mem_cgroup; +struct obj_cgroup; struct page; struct mm_struct; struct kmem_cache; @@ -192,6 +193,22 @@ struct memcg_cgwb_frn { struct wb_completion done; /* tracks in-flight foreign writebacks */ }; +/* + * Bucket for arbitrarily byte-sized objects charged to a memory + * cgroup. The bucket can be reparented in one piece when the cgroup + * is destroyed, without having to round up the individual references + * of all live memory objects in the wild. + */ +struct obj_cgroup { + struct percpu_ref refcnt; + struct mem_cgroup *memcg; + atomic_t nr_charged_bytes; + union { + struct list_head list; + struct rcu_head rcu; + }; +}; + /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide @@ -301,6 +318,8 @@ struct mem_cgroup { int kmemcg_id; enum memcg_kmem_state kmem_state; struct list_head kmem_caches; + struct obj_cgroup __rcu *objcg; + struct list_head objcg_list; /* list of inherited objcgs */ #endif #ifdef CONFIG_CGROUP_WRITEBACK @@ -416,6 +435,33 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } +static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg) +{ + return percpu_ref_tryget(&objcg->refcnt); +} + +static inline void obj_cgroup_get(struct obj_cgroup *objcg) +{ + percpu_ref_get(&objcg->refcnt); +} + +static inline void obj_cgroup_put(struct obj_cgroup *objcg) +{ + percpu_ref_put(&objcg->refcnt); +} + +/* + * After the initialization objcg->memcg is always pointing at + * a valid memcg, but can be atomically swapped to the parent memcg. + * + * The caller must ensure that the returned memcg won't be released: + * e.g. acquire the rcu_read_lock or css_set_lock. + */ +static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) +{ + return READ_ONCE(objcg->memcg); +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { if (memcg) @@ -1368,6 +1414,11 @@ void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); +struct obj_cgroup *get_obj_cgroup_from_current(void); + +int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); +void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); + extern struct static_key_false memcg_kmem_enabled_key; extern struct workqueue_struct *memcg_kmem_cache_wq; -- cgit v1.2.3 From 286e04b8ed7a04279ae277f0f024430246ea5eec Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:20:52 -0700 Subject: mm: memcg/slab: allocate obj_cgroups for non-root slab pages Allocate and release memory to store obj_cgroup pointers for each non-root slab page. Reuse page->mem_cgroup pointer to store a pointer to the allocated space. This commit temporarily increases the memory footprint of the kernel memory accounting. To store obj_cgroup pointers we'll need a place for an objcg_pointer for each allocated object. However, the following patches in the series will enable sharing of slab pages between memory cgroups, which will dramatically increase the total slab utilization. And the final memory footprint will be significantly smaller than before. To distinguish between obj_cgroups and memcg pointers in case when it's not obvious which one is used (as in page_cgroup_ino()), let's always set the lowest bit in the obj_cgroup case. The original obj_cgroups pointer is marked to be ignored by kmemleak, which otherwise would report a memory leak for each allocated vector. Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Shakeel Butt Cc: Christoph Lameter Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200623174037.3951353-8-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 5 ++++- include/linux/slab_def.h | 6 ++++++ include/linux/slub_def.h | 5 +++++ 3 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 64ede5f150dc..0277fbab7c93 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -198,7 +198,10 @@ struct page { atomic_t _refcount; #ifdef CONFIG_MEMCG - struct mem_cgroup *mem_cgroup; + union { + struct mem_cgroup *mem_cgroup; + struct obj_cgroup **obj_cgroups; + }; #endif /* diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index abc7de77b988..ccda7b9669a5 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -114,4 +114,10 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache, return reciprocal_divide(offset, cache->reciprocal_buffer_size); } +static inline int objs_per_slab_page(const struct kmem_cache *cache, + const struct page *page) +{ + return cache->num; +} + #endif /* _LINUX_SLAB_DEF_H */ diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 30e91c83d401..f87302dcfe8c 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -198,4 +198,9 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache, return __obj_to_index(cache, page_address(page), obj); } +static inline int objs_per_slab_page(const struct kmem_cache *cache, + const struct page *page) +{ + return page->objects; +} #endif /* _LINUX_SLUB_DEF_H */ -- cgit v1.2.3 From 964d4bd370d559d9bd8e4abc139e85d2753956fb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:20:56 -0700 Subject: mm: memcg/slab: save obj_cgroup for non-root slab objects Store the obj_cgroup pointer in the corresponding place of page->obj_cgroups for each allocated non-root slab object. Make sure that each allocated object holds a reference to obj_cgroup. Objcg pointer is obtained from the memcg->objcg dereferencing in memcg_kmem_get_cache() and passed from pre_alloc_hook to post_alloc_hook. Then in case of successful allocation(s) it's getting stored in the page->obj_cgroups vector. The objcg obtaining part look a bit bulky now, but it will be simplified by next commits in the series. Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Shakeel Butt Cc: Christoph Lameter Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200623174037.3951353-9-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f2f9d5d6b7d1..b845e908e76e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1404,7 +1404,8 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, } #endif -struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); +struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep, + struct obj_cgroup **objcgp); void memcg_kmem_put_cache(struct kmem_cache *cachep); #ifdef CONFIG_MEMCG_KMEM -- cgit v1.2.3 From 0f876e4dc55db5fafef774917fd66e1373c0f390 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:21:06 -0700 Subject: mm: memcg/slab: move memcg_kmem_bypass() to memcontrol.h To make the memcg_kmem_bypass() function available outside of the memcontrol.c, let's move it to memcontrol.h. The function is small and nicely fits into static inline sort of functions. It will be used from the slab code. Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Shakeel Butt Cc: Christoph Lameter Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200623174037.3951353-12-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b845e908e76e..83e2858aecf2 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1440,6 +1440,18 @@ static inline bool memcg_kmem_enabled(void) return static_branch_unlikely(&memcg_kmem_enabled_key); } +static inline bool memcg_kmem_bypass(void) +{ + if (in_interrupt()) + return true; + + /* Allow remote memcg charging in kthread contexts. */ + if ((!current->mm || (current->flags & PF_KTHREAD)) && + !current->active_memcg) + return true; + return false; +} + static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { -- cgit v1.2.3 From 9855609bde03e2472b99a95e869d29ee1e78a751 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:21:10 -0700 Subject: mm: memcg/slab: use a single set of kmem_caches for all accounted allocations This is fairly big but mostly red patch, which makes all accounted slab allocations use a single set of kmem_caches instead of creating a separate set for each memory cgroup. Because the number of non-root kmem_caches is now capped by the number of root kmem_caches, there is no need to shrink or destroy them prematurely. They can be perfectly destroyed together with their root counterparts. This allows to dramatically simplify the management of non-root kmem_caches and delete a ton of code. This patch performs the following changes: 1) introduces memcg_params.memcg_cache pointer to represent the kmem_cache which will be used for all non-root allocations 2) reuses the existing memcg kmem_cache creation mechanism to create memcg kmem_cache on the first allocation attempt 3) memcg kmem_caches are named -memcg, e.g. dentry-memcg 4) simplifies memcg_kmem_get_cache() to just return memcg kmem_cache or schedule it's creation and return the root cache 5) removes almost all non-root kmem_cache management code (separate refcounter, reparenting, shrinking, etc) 6) makes slab debugfs to display root_mem_cgroup css id and never show :dead and :deact flags in the memcg_slabinfo attribute. Following patches in the series will simplify the kmem_cache creation. Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Shakeel Butt Cc: Christoph Lameter Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200623174037.3951353-13-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +---- include/linux/slab.h | 5 +---- 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 83e2858aecf2..11fd18b3d6c6 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -317,7 +317,6 @@ struct mem_cgroup { /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; enum memcg_kmem_state kmem_state; - struct list_head kmem_caches; struct obj_cgroup __rcu *objcg; struct list_head objcg_list; /* list of inherited objcgs */ #endif @@ -1404,9 +1403,7 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, } #endif -struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep, - struct obj_cgroup **objcgp); -void memcg_kmem_put_cache(struct kmem_cache *cachep); +struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); #ifdef CONFIG_MEMCG_KMEM int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, diff --git a/include/linux/slab.h b/include/linux/slab.h index 0884d82c55ee..8b1f91e320f9 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -155,8 +155,7 @@ struct kmem_cache *kmem_cache_create_usercopy(const char *name, void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); -void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *); -void memcg_deactivate_kmem_caches(struct mem_cgroup *, struct mem_cgroup *); +void memcg_create_kmem_cache(struct kmem_cache *cachep); /* * Please use this macro to create slab caches. Simply specify the @@ -580,8 +579,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) return __kmalloc_node(size, flags, node); } -int memcg_update_all_caches(int num_memcgs); - /** * kmalloc_array - allocate memory for an array. * @n: number of elements. -- cgit v1.2.3 From d797b7d05405c519f7b62ea69a75cea1883863b2 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:21:14 -0700 Subject: mm: memcg/slab: simplify memcg cache creation Because the number of non-root kmem_caches doesn't depend on the number of memory cgroups anymore and is generally not very big, there is no more need for a dedicated workqueue. Also, as there is no more need to pass any arguments to the memcg_create_kmem_cache() except the root kmem_cache, it's possible to just embed the work structure into the kmem_cache and avoid the dynamic allocation of the work structure. This will also simplify the synchronization: for each root kmem_cache there is only one work. So there will be no more concurrent attempts to create a non-root kmem_cache for a root kmem_cache: the second and all following attempts to queue the work will fail. On the kmem_cache destruction path there is no more need to call the expensive flush_workqueue() and wait for all pending works to be finished. Instead, cancel_work_sync() can be used to cancel/wait for only one work. Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Shakeel Butt Cc: Christoph Lameter Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200623174037.3951353-14-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 11fd18b3d6c6..2ac84dcfc9e5 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1418,7 +1418,6 @@ int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); extern struct static_key_false memcg_kmem_enabled_key; -extern struct workqueue_struct *memcg_kmem_cache_wq; extern int memcg_nr_cache_ids; void memcg_get_cache_ids(void); -- cgit v1.2.3 From 272911a4ad18c48f8bc449a5db945a54987dd687 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:21:17 -0700 Subject: mm: memcg/slab: remove memcg_kmem_get_cache() The memcg_kmem_get_cache() function became really trivial, so let's just inline it into the single call point: memcg_slab_pre_alloc_hook(). It will make the code less bulky and can also help the compiler to generate a better code. Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Shakeel Butt Cc: Christoph Lameter Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Link: http://lkml.kernel.org/r/20200623174037.3951353-15-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2ac84dcfc9e5..5a8b62d075e6 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1403,8 +1403,6 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, } #endif -struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); - #ifdef CONFIG_MEMCG_KMEM int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, unsigned int nr_pages); -- cgit v1.2.3 From 10befea91b61c4e2c2d1df06a2e978d182fcf792 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:21:27 -0700 Subject: mm: memcg/slab: use a single set of kmem_caches for all allocations Instead of having two sets of kmem_caches: one for system-wide and non-accounted allocations and the second one shared by all accounted allocations, we can use just one. The idea is simple: space for obj_cgroup metadata can be allocated on demand and filled only for accounted allocations. It allows to remove a bunch of code which is required to handle kmem_cache clones for accounted allocations. There is no more need to create them, accumulate statistics, propagate attributes, etc. It's a quite significant simplification. Also, because the total number of slab_caches is reduced almost twice (not all kmem_caches have a memcg clone), some additional memory savings are expected. On my devvm it additionally saves about 3.5% of slab memory. [guro@fb.com: fix build on MIPS] Link: http://lkml.kernel.org/r/20200717214810.3733082-1-guro@fb.com Suggested-by: Johannes Weiner Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Shakeel Butt Cc: Christoph Lameter Cc: Michal Hocko Cc: Tejun Heo Cc: Naresh Kamboju Link: http://lkml.kernel.org/r/20200623174037.3951353-18-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 -- include/linux/slab_def.h | 3 --- include/linux/slub_def.h | 10 ---------- 3 files changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 8b1f91e320f9..24df2393ec03 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -155,8 +155,6 @@ struct kmem_cache *kmem_cache_create_usercopy(const char *name, void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); -void memcg_create_kmem_cache(struct kmem_cache *cachep); - /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index ccda7b9669a5..9eb430c163c2 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -72,9 +72,6 @@ struct kmem_cache { int obj_offset; #endif /* CONFIG_DEBUG_SLAB */ -#ifdef CONFIG_MEMCG - struct memcg_cache_params memcg_params; -#endif #ifdef CONFIG_KASAN struct kasan_cache kasan_info; #endif diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index f87302dcfe8c..1be0ed5befa1 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -108,17 +108,7 @@ struct kmem_cache { struct list_head list; /* List of slab caches */ #ifdef CONFIG_SYSFS struct kobject kobj; /* For sysfs */ - struct work_struct kobj_remove_work; #endif -#ifdef CONFIG_MEMCG - struct memcg_cache_params memcg_params; - /* For propagation, maximum size of a stored attr */ - unsigned int max_attr_size; -#ifdef CONFIG_SYSFS - struct kset *memcg_kset; -#endif -#endif - #ifdef CONFIG_SLAB_FREELIST_HARDENED unsigned long random; #endif -- cgit v1.2.3 From 991e7673859ed41e7ba83c8c4e57afe8cfebe314 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 6 Aug 2020 23:21:37 -0700 Subject: mm: memcontrol: account kernel stack per node Currently the kernel stack is being accounted per-zone. There is no need to do that. In addition due to being per-zone, memcg has to keep a separate MEMCG_KERNEL_STACK_KB. Make the stat per-node and deprecate MEMCG_KERNEL_STACK_KB as memcg_stat_item is an extension of node_stat_item. In addition localize the kernel stack stats updates to account_kernel_stack(). Signed-off-by: Shakeel Butt Signed-off-by: Andrew Morton Reviewed-by: Roman Gushchin Cc: Johannes Weiner Cc: Michal Hocko Link: http://lkml.kernel.org/r/20200630161539.1759185-1-shakeelb@google.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 21 +++++++++++++++++++-- include/linux/mmzone.h | 8 ++++---- 2 files changed, 23 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5a8b62d075e6..624400c27eba 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -32,8 +32,6 @@ struct kmem_cache; enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, - /* XXX: why are these zone and not node counters? */ - MEMCG_KERNEL_STACK_KB, MEMCG_NR_STAT, }; @@ -729,8 +727,19 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val); + void mod_memcg_obj_state(void *p, int idx, int val); +static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx, + int val) +{ + unsigned long flags; + + local_irq_save(flags); + __mod_lruvec_slab_state(p, idx, val); + local_irq_restore(flags); +} + static inline void mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { @@ -1151,6 +1160,14 @@ static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, __mod_node_page_state(page_pgdat(page), idx, val); } +static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx, + int val) +{ + struct page *page = virt_to_head_page(p); + + mod_node_page_state(page_pgdat(page), idx, val); +} + static inline void mod_memcg_obj_state(void *p, int idx, int val) { } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b79100edd228..a3bd54139a30 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -155,10 +155,6 @@ enum zone_stat_item { NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ NR_PAGETABLE, /* used for pagetables */ - NR_KERNEL_STACK_KB, /* measured in KiB */ -#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) - NR_KERNEL_SCS_KB, /* measured in KiB */ -#endif /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) @@ -203,6 +199,10 @@ enum node_stat_item { NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ + NR_KERNEL_STACK_KB, /* measured in KiB */ +#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) + NR_KERNEL_SCS_KB, /* measured in KiB */ +#endif NR_VM_NODE_STAT_ITEMS }; -- cgit v1.2.3 From eda330e57b26df8fabce184736ae3d11e7a104bd Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 6 Aug 2020 23:21:47 -0700 Subject: mm: kmem: switch to static_branch_likely() in memcg_kmem_enabled() Currently memcg_kmem_enabled() is optimized for the kernel memory accounting being off. It was so for a long time, and arguably the reason behind was that the kernel memory accounting was initially an opt-in feature. However, now it's on by default on both cgroup v1 and cgroup v2, and it's on for all cgroups. So let's switch over to static_branch_likely() to reflect this fact. Unlikely there is a significant performance difference, as the cost of a memory allocation and its accounting significantly exceeds the cost of a jump. However, the conversion makes the code look more logically. Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Vlastimil Babka Cc: Johannes Weiner Cc: Michal Hocko Cc: Christoph Lameter Cc: David Rientjes Cc: Joonsoo Kim Cc: Pekka Enberg Link: http://lkml.kernel.org/r/20200707173612.124425-3-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 624400c27eba..3f8ff6519c9d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1448,7 +1448,7 @@ void memcg_put_cache_ids(void); static inline bool memcg_kmem_enabled(void) { - return static_branch_unlikely(&memcg_kmem_enabled_key); + return static_branch_likely(&memcg_kmem_enabled_key); } static inline bool memcg_kmem_bypass(void) -- cgit v1.2.3 From 22f7496f0b901249f23c5251eb8a10aae126b909 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Thu, 6 Aug 2020 23:22:01 -0700 Subject: mm, memcg: avoid stale protection values when cgroup is above protection Patch series "mm, memcg: memory.{low,min} reclaim fix & cleanup", v4. This series contains a fix for a edge case in my earlier protection calculation patches, and a patch to make the area overall a little more robust to hopefully help avoid this in future. This patch (of 2): A cgroup can have both memory protection and a memory limit to isolate it from its siblings in both directions - for example, to prevent it from being shrunk below 2G under high pressure from outside, but also from growing beyond 4G under low pressure. Commit 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim") implemented proportional scan pressure so that multiple siblings in excess of their protection settings don't get reclaimed equally but instead in accordance to their unprotected portion. During limit reclaim, this proportionality shouldn't apply of course: there is no competition, all pressure is from within the cgroup and should be applied as such. Reclaim should operate at full efficiency. However, mem_cgroup_protected() never expected anybody to look at the effective protection values when it indicated that the cgroup is above its protection. As a result, a query during limit reclaim may return stale protection values that were calculated by a previous reclaim cycle in which the cgroup did have siblings. When this happens, reclaim is unnecessarily hesitant and potentially slow to meet the desired limit. In theory this could lead to premature OOM kills, although it's not obvious this has occurred in practice. Workaround the problem by special casing reclaim roots in mem_cgroup_protection. These memcgs are never participating in the reclaim protection because the reclaim is internal. We have to ignore effective protection values for reclaim roots because mem_cgroup_protected might be called from racing reclaim contexts with different roots. Calculation is relying on root -> leaf tree traversal therefore top-down reclaim protection invariants should hold. The only exception is the reclaim root which should have effective protection set to 0 but that would be problematic for the following setup: Let's have global and A's reclaim in parallel: | A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G) |\ | C (low = 1G, usage = 2.5G) B (low = 1G, usage = 0.5G) for A reclaim we have B.elow = B.low C.elow = C.low For the global reclaim A.elow = A.low B.elow = min(B.usage, B.low) because children_low_usage <= A.elow C.elow = min(C.usage, C.low) With the effective values resetting we have A reclaim A.elow = 0 B.elow = B.low C.elow = C.low and global reclaim could see the above and then B.elow = C.elow = 0 because children_low_usage > A.elow Which means that protected memcgs would get reclaimed. In future we would like to make mem_cgroup_protected more robust against racing reclaim contexts but that is likely more complex solution than this simple workaround. [hannes@cmpxchg.org - large part of the changelog] [mhocko@suse.com - workaround explanation] [chris@chrisdown.name - retitle] Fixes: 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim") Signed-off-by: Yafang Shao Signed-off-by: Chris Down Signed-off-by: Andrew Morton Acked-by: Michal Hocko Acked-by: Johannes Weiner Acked-by: Chris Down Acked-by: Roman Gushchin Link: http://lkml.kernel.org/r/cover.1594638158.git.chris@chrisdown.name Link: http://lkml.kernel.org/r/044fb8ecffd001c7905d27c0c2ad998069fdc396.1594638158.git.chris@chrisdown.name Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 42 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 40 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3f8ff6519c9d..0301b231fd02 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -355,12 +355,49 @@ static inline bool mem_cgroup_disabled(void) return !cgroup_subsys_enabled(memory_cgrp_subsys); } -static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, +static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg, bool in_low_reclaim) { if (mem_cgroup_disabled()) return 0; + /* + * There is no reclaim protection applied to a targeted reclaim. + * We are special casing this specific case here because + * mem_cgroup_protected calculation is not robust enough to keep + * the protection invariant for calculated effective values for + * parallel reclaimers with different reclaim target. This is + * especially a problem for tail memcgs (as they have pages on LRU) + * which would want to have effective values 0 for targeted reclaim + * but a different value for external reclaim. + * + * Example + * Let's have global and A's reclaim in parallel: + * | + * A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G) + * |\ + * | C (low = 1G, usage = 2.5G) + * B (low = 1G, usage = 0.5G) + * + * For the global reclaim + * A.elow = A.low + * B.elow = min(B.usage, B.low) because children_low_usage <= A.elow + * C.elow = min(C.usage, C.low) + * + * With the effective values resetting we have A reclaim + * A.elow = 0 + * B.elow = B.low + * C.elow = C.low + * + * If the global reclaim races with A's reclaim then + * B.elow = C.elow = 0 because children_low_usage > A.elow) + * is possible and reclaiming B would be violating the protection. + * + */ + if (root == memcg) + return 0; + if (in_low_reclaim) return READ_ONCE(memcg->memory.emin); @@ -891,7 +928,8 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, { } -static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, +static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg, bool in_low_reclaim) { return 0; -- cgit v1.2.3 From 45c7f7e1ef17f09fe70bad4b705ce43772153fd7 Mon Sep 17 00:00:00 2001 From: Chris Down Date: Thu, 6 Aug 2020 23:22:05 -0700 Subject: mm, memcg: decouple e{low,min} state mutations from protection checks mem_cgroup_protected currently is both used to set effective low and min and return a mem_cgroup_protection based on the result. As a user, this can be a little unexpected: it appears to be a simple predicate function, if not for the big warning in the comment above about the order in which it must be executed. This change makes it so that we separate the state mutations from the actual protection checks, which makes it more obvious where we need to be careful mutating internal state, and where we are simply checking and don't need to worry about that. [mhocko@suse.com - don't check protection on root memcgs] Suggested-by: Johannes Weiner Signed-off-by: Chris Down Signed-off-by: Andrew Morton Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Roman Gushchin Cc: Yafang Shao Link: http://lkml.kernel.org/r/ff3f915097fcee9f6d7041c084ef92d16aaeb56a.1594638158.git.chris@chrisdown.name Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 53 ++++++++++++++++++++++++++++++++++++---------- 1 file changed, 42 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0301b231fd02..1bb49b600310 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -47,12 +47,6 @@ enum memcg_memory_event { MEMCG_NR_MEMORY_EVENTS, }; -enum mem_cgroup_protection { - MEMCG_PROT_NONE, - MEMCG_PROT_LOW, - MEMCG_PROT_MIN, -}; - struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; unsigned int generation; @@ -405,8 +399,36 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, READ_ONCE(memcg->memory.elow)); } -enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, - struct mem_cgroup *memcg); +void mem_cgroup_calculate_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg); + +static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg) +{ + /* + * The root memcg doesn't account charges, and doesn't support + * protection. + */ + return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg); + +} + +static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg) +{ + if (!mem_cgroup_supports_protection(memcg)) + return false; + + return READ_ONCE(memcg->memory.elow) >= + page_counter_read(&memcg->memory); +} + +static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) +{ + if (!mem_cgroup_supports_protection(memcg)) + return false; + + return READ_ONCE(memcg->memory.emin) >= + page_counter_read(&memcg->memory); +} int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); @@ -935,10 +957,19 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, return 0; } -static inline enum mem_cgroup_protection mem_cgroup_protected( - struct mem_cgroup *root, struct mem_cgroup *memcg) +static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg) { - return MEMCG_PROT_NONE; +} + +static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg) +{ + return false; +} + +static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) +{ + return false; } static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, -- cgit v1.2.3 From 2a681cfa5bb41e78e7bfafbb748b581374ce9b1d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 6 Aug 2020 23:22:55 -0700 Subject: mm: move p?d_alloc_track to separate header file The functions are only used in two source files, so there is no need for them to be in the global header. Move them to the new header and include it only where needed. Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Reviewed-by: Pekka Enberg Cc: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Abdul Haleem Cc: Satheesh Rajendran Cc: Stephen Rothwell Cc: Steven Rostedt (VMware) Cc: Mike Rapoport Cc: Christophe Leroy Cc: Arnd Bergmann Cc: Max Filippov Cc: Stafford Horne Cc: Geert Uytterhoeven Cc: Matthew Wilcox Link: http://lkml.kernel.org/r/20200609120533.25867-1-joro@8bytes.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 45 --------------------------------------------- 1 file changed, 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 303a47a9769d..2830f1c0fdc3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2103,51 +2103,11 @@ static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, NULL : pud_offset(p4d, address); } -static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, - unsigned long address, - pgtbl_mod_mask *mod_mask) - -{ - if (unlikely(pgd_none(*pgd))) { - if (__p4d_alloc(mm, pgd, address)) - return NULL; - *mod_mask |= PGTBL_PGD_MODIFIED; - } - - return p4d_offset(pgd, address); -} - -static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, - unsigned long address, - pgtbl_mod_mask *mod_mask) -{ - if (unlikely(p4d_none(*p4d))) { - if (__pud_alloc(mm, p4d, address)) - return NULL; - *mod_mask |= PGTBL_P4D_MODIFIED; - } - - return pud_offset(p4d, address); -} - static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } - -static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, - unsigned long address, - pgtbl_mod_mask *mod_mask) -{ - if (unlikely(pud_none(*pud))) { - if (__pmd_alloc(mm, pud, address)) - return NULL; - *mod_mask |= PGTBL_PUD_MODIFIED; - } - - return pmd_offset(pud, address); -} #endif /* CONFIG_MMU */ #if USE_SPLIT_PTE_PTLOCKS @@ -2263,11 +2223,6 @@ static inline void pgtable_pte_page_dtor(struct page *page) ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) -#define pte_alloc_kernel_track(pmd, address, mask) \ - ((unlikely(pmd_none(*(pmd))) && \ - (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ - NULL: pte_offset_kernel(pmd, address)) - #if USE_SPLIT_PMD_PTLOCKS static struct page *pmd_to_page(pmd_t *pmd) -- cgit v1.2.3 From 0a4954a850b0c4d0a5d18b1a55d6e5a653e362b5 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Thu, 6 Aug 2020 23:23:11 -0700 Subject: percpu_counter: add percpu_counter_sync() percpu_counter's accuracy is related to its batch size. For a percpu_counter with a big batch, its deviation could be big, so when the counter's batch is runtime changed to a smaller value for better accuracy, there could also be requirment to reduce the big deviation. So add a percpu-counter sync function to be run on each CPU. Reported-by: kernel test robot Signed-off-by: Feng Tang Signed-off-by: Andrew Morton Cc: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Cc: Michal Hocko Cc: Qian Cai Cc: Andi Kleen Cc: Huang Ying Cc: Dave Hansen Cc: Haiyang Zhang Cc: Johannes Weiner Cc: Kees Cook Cc: "K. Y. Srinivasan" Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Tim Chen Link: http://lkml.kernel.org/r/1594389708-60781-4-git-send-email-feng.tang@intel.com Signed-off-by: Linus Torvalds --- include/linux/percpu_counter.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 0a4f54dd4737..01861eebed79 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -44,6 +44,7 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); +void percpu_counter_sync(struct percpu_counter *fbc); static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { @@ -172,6 +173,9 @@ static inline bool percpu_counter_initialized(struct percpu_counter *fbc) return true; } +static inline void percpu_counter_sync(struct percpu_counter *fbc) +{ +} #endif /* CONFIG_SMP */ static inline void percpu_counter_inc(struct percpu_counter *fbc) -- cgit v1.2.3 From 56f3547bfa4d361148aa748ccb86073bc57f5e6c Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Thu, 6 Aug 2020 23:23:15 -0700 Subject: mm: adjust vm_committed_as_batch according to vm overcommit policy When checking a performance change for will-it-scale scalability mmap test [1], we found very high lock contention for spinlock of percpu counter 'vm_committed_as': 94.14% 0.35% [kernel.kallsyms] [k] _raw_spin_lock_irqsave 48.21% _raw_spin_lock_irqsave;percpu_counter_add_batch;__vm_enough_memory;mmap_region;do_mmap; 45.91% _raw_spin_lock_irqsave;percpu_counter_add_batch;__do_munmap; Actually this heavy lock contention is not always necessary. The 'vm_committed_as' needs to be very precise when the strict OVERCOMMIT_NEVER policy is set, which requires a rather small batch number for the percpu counter. So keep 'batch' number unchanged for strict OVERCOMMIT_NEVER policy, and lift it to 64X for OVERCOMMIT_ALWAYS and OVERCOMMIT_GUESS policies. Also add a sysctl handler to adjust it when the policy is reconfigured. Benchmark with the same testcase in [1] shows 53% improvement on a 8C/16T desktop, and 2097%(20X) on a 4S/72C/144T server. We tested with test platforms in 0day (server, desktop and laptop), and 80%+ platforms shows improvements with that test. And whether it shows improvements depends on if the test mmap size is bigger than the batch number computed. And if the lift is 16X, 1/3 of the platforms will show improvements, though it should help the mmap/unmap usage generally, as Michal Hocko mentioned: : I believe that there are non-synthetic worklaods which would benefit from : a larger batch. E.g. large in memory databases which do large mmaps : during startups from multiple threads. [1] https://lore.kernel.org/lkml/20200305062138.GI5972@shao2-debian/ Signed-off-by: Feng Tang Signed-off-by: Andrew Morton Acked-by: Michal Hocko Cc: Matthew Wilcox (Oracle) Cc: Johannes Weiner Cc: Mel Gorman Cc: Qian Cai Cc: Kees Cook Cc: Andi Kleen Cc: Tim Chen Cc: Dave Hansen Cc: Huang Ying Cc: Christoph Lameter Cc: Dennis Zhou Cc: Haiyang Zhang Cc: kernel test robot Cc: "K. Y. Srinivasan" Cc: Tejun Heo Link: http://lkml.kernel.org/r/1589611660-89854-4-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1592725000-73486-4-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1594389708-60781-5-git-send-email-feng.tang@intel.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ include/linux/mman.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2830f1c0fdc3..1c3470550395 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -206,6 +206,8 @@ int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, loff_t *); +int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) diff --git a/include/linux/mman.h b/include/linux/mman.h index 4b08e9c9c538..6f34c33075f9 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -57,8 +57,12 @@ extern struct percpu_counter vm_committed_as; #ifdef CONFIG_SMP extern s32 vm_committed_as_batch; +extern void mm_compute_batch(int overcommit_policy); #else #define vm_committed_as_batch 0 +static inline void mm_compute_batch(int overcommit_policy) +{ +} #endif unsigned long vm_memory_committed(void); -- cgit v1.2.3 From 1d9cfee7535c213038a615f112c900c2d0ba8f54 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 6 Aug 2020 23:23:19 -0700 Subject: mm/sparsemem: enable vmem_altmap support in vmemmap_populate_basepages() Patch series "arm64: Enable vmemmap mapping from device memory", v4. This series enables vmemmap backing memory allocation from device memory ranges on arm64. But before that, it enables vmemmap_populate_basepages() and vmemmap_alloc_block_buf() to accommodate struct vmem_altmap based alocation requests. This patch (of 3): vmemmap_populate_basepages() is used across platforms to allocate backing memory for vmemmap mapping. This is used as a standard default choice or as a fallback when intended huge pages allocation fails. This just creates entire vmemmap mapping with base pages (PAGE_SIZE). On arm64 platforms, vmemmap_populate_basepages() is called instead of the platform specific vmemmap_populate() when ARM64_SWAPPER_USES_SECTION_MAPS is not enabled as in case for ARM64_16K_PAGES and ARM64_64K_PAGES configs. At present vmemmap_populate_basepages() does not support allocating from driver defined struct vmem_altmap while trying to create vmemmap mapping for a device memory range. It prevents ARM64_16K_PAGES and ARM64_64K_PAGES configs on arm64 from supporting device memory with vmemap_altmap request. This enables vmem_altmap support in vmemmap_populate_basepages() unlocking device memory allocation for vmemap mapping on arm64 platforms with 16K or 64K base page configs. Each architecture should evaluate and decide on subscribing device memory based base page allocation through vmemmap_populate_basepages(). Hence lets keep it disabled on all archs in order to preserve the existing semantics. A subsequent patch enables it on arm64. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Tested-by: Jia He Reviewed-by: David Hildenbrand Acked-by: Will Deacon Acked-by: Catalin Marinas Cc: Mark Rutland Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Tony Luck Cc: Fenghua Yu Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Mike Rapoport Cc: Michal Hocko Cc: "Matthew Wilcox (Oracle)" Cc: "Kirill A. Shutemov" Cc: Dan Williams Cc: Pavel Tatashin Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Hsin-Yi Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: Paul Mackerras Cc: Robin Murphy Cc: Steve Capper Cc: Yu Zhao Link: http://lkml.kernel.org/r/1594004178-8861-1-git-send-email-anshuman.khandual@arm.com Link: http://lkml.kernel.org/r/1594004178-8861-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1c3470550395..a7ff98738126 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2978,14 +2978,15 @@ pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); -pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); +pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, + struct vmem_altmap *altmap); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node); void *altmap_alloc_block_buf(unsigned long size, struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(unsigned long start, unsigned long end, - int node); + int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); void vmemmap_populate_print_last(void); -- cgit v1.2.3 From 56993b4e147e9f2ba91ac15ef9ae5ee0626a6850 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 6 Aug 2020 23:23:24 -0700 Subject: mm/sparsemem: enable vmem_altmap support in vmemmap_alloc_block_buf() There are many instances where vmemap allocation is often switched between regular memory and device memory just based on whether altmap is available or not. vmemmap_alloc_block_buf() is used in various platforms to allocate vmemmap mappings. Lets also enable it to handle altmap based device memory allocation along with existing regular memory allocations. This will help in avoiding the altmap based allocation switch in many places. To summarize there are two different methods to call vmemmap_alloc_block_buf(). vmemmap_alloc_block_buf(size, node, NULL) /* Allocate from system RAM */ vmemmap_alloc_block_buf(size, node, altmap) /* Allocate from altmap */ This converts altmap_alloc_block_buf() into a static function, drops it's entry from the header and updates Documentation/vm/memory-model.rst. Suggested-by: Robin Murphy Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Tested-by: Jia He Reviewed-by: Catalin Marinas Cc: Jonathan Corbet Cc: Will Deacon Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Dan Williams Cc: David Hildenbrand Cc: Fenghua Yu Cc: Hsin-Yi Wang Cc: "Kirill A. Shutemov" Cc: Mark Rutland Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Rapoport Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Pavel Tatashin Cc: Steve Capper Cc: Tony Luck Cc: Yu Zhao Link: http://lkml.kernel.org/r/1594004178-8861-3-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a7ff98738126..98e35df8d88e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2982,8 +2982,8 @@ pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, struct vmem_altmap *altmap); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; -void *vmemmap_alloc_block_buf(unsigned long size, int node); -void *altmap_alloc_block_buf(unsigned long size, struct vmem_altmap *altmap); +void *vmemmap_alloc_block_buf(unsigned long size, int node, + struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); -- cgit v1.2.3 From 45e55300f11495ed58c53427da7f0d958800a30f Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 6 Aug 2020 23:23:37 -0700 Subject: mm: remove unnecessary wrapper function do_mmap_pgoff() The current split between do_mmap() and do_mmap_pgoff() was introduced in commit 1fcfd8db7f82 ("mm, mpx: add "vm_flags_t vm_flags" arg to do_mmap_pgoff()") to support MPX. The wrapper function do_mmap_pgoff() always passed 0 as the value of the vm_flags argument to do_mmap(). However, MPX support has subsequently been removed from the kernel and there were no more direct callers of do_mmap(); all calls were going via do_mmap_pgoff(). Simplify the code by removing do_mmap_pgoff() and changing all callers to directly call do_mmap(), which now no longer takes a vm_flags argument. Signed-off-by: Peter Collingbourne Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Reviewed-by: David Hildenbrand Link: http://lkml.kernel.org/r/20200727194109.1371462-1-pcc@google.com Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- include/linux/mm.h | 12 +----------- 2 files changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b1c3a14f12e8..f5da33bcaaae 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -528,7 +528,7 @@ static inline int mapping_mapped(struct address_space *mapping) /* * Might pages of this file have been modified in userspace? - * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff + * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * diff --git a/include/linux/mm.h b/include/linux/mm.h index 98e35df8d88e..cf7e4605ff3f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2546,23 +2546,13 @@ extern unsigned long mmap_region(struct file *file, unsigned long addr, struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, - vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, - struct list_head *uf); + unsigned long pgoff, unsigned long *populate, struct list_head *uf); extern int __do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(unsigned long start, size_t len_in, int behavior); -static inline unsigned long -do_mmap_pgoff(struct file *file, unsigned long addr, - unsigned long len, unsigned long prot, unsigned long flags, - unsigned long pgoff, unsigned long *populate, - struct list_head *uf) -{ - return do_mmap(file, addr, len, prot, flags, 0, pgoff, populate, uf); -} - #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); -- cgit v1.2.3 From b8aa9d9d95b3b4b60d42ac95f65d33a92527aef3 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 6 Aug 2020 23:23:40 -0700 Subject: mm/mremap: it is sure to have enough space when extent meets requirement Patch series "mm/mremap: cleanup move_page_tables() a little", v5. move_page_tables() tries to move page table by PMD or PTE. The root reason is if it tries to move PMD, both old and new range should be PMD aligned. But current code calculate old range and new range separately. This leads to some redundant check and calculation. This cleanup tries to consolidate the range check in one place to reduce some extra range handling. This patch (of 3): old_end is passed to these two functions to check whether there is enough space to do the move, while this check is done before invoking these functions. These two functions only would be invoked when extent meets the requirement and there is one check before invoking these functions: if (extent > old_end - old_addr) extent = old_end - old_addr; This implies (old_end - old_addr) won't fail the check in these two functions. Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Tested-by: Dmitry Osipenko Acked-by: Kirill A. Shutemov Cc: Vlastimil Babka Cc: Yang Shi Cc: Thomas Hellstrom (VMware) Cc: Anshuman Khandual Cc: Sean Christopherson Cc: Wei Yang Cc: Peter Xu Cc: Aneesh Kumar K.V Cc: Matthew Wilcox Cc: Thomas Hellstrom Link: http://lkml.kernel.org/r/20200710092835.56368-1-richard.weiyang@linux.alibaba.com Link: http://lkml.kernel.org/r/20200710092835.56368-2-richard.weiyang@linux.alibaba.com Link: http://lkml.kernel.org/r/20200708095028.41706-1-richard.weiyang@linux.alibaba.com Link: http://lkml.kernel.org/r/20200708095028.41706-2-richard.weiyang@linux.alibaba.com Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 71f20776b06c..17c4c4975145 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -42,7 +42,7 @@ extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned char *vec); extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, - unsigned long new_addr, unsigned long old_end, + unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, -- cgit v1.2.3 From c89ab04febf97d2db8ca4ef8e2866fadc474351b Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 6 Aug 2020 23:24:02 -0700 Subject: mm/sparse: cleanup the code surrounding memory_present() After removal of CONFIG_HAVE_MEMBLOCK_NODE_MAP we have two equivalent functions that call memory_present() for each region in memblock.memory: sparse_memory_present_with_active_regions() and membocks_present(). Moreover, all architectures have a call to either of these functions preceding the call to sparse_init() and in the most cases they are called one after the other. Mark the regions from memblock.memory as present during sparce_init() by making sparse_init() call memblocks_present(), make memblocks_present() and memory_present() functions static and remove redundant sparse_memory_present_with_active_regions() function. Also remove no longer required HAVE_MEMORY_PRESENT configuration option. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Link: http://lkml.kernel.org/r/20200712083130.22919-1-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ---- include/linux/mmzone.h | 14 -------------- 2 files changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index cf7e4605ff3f..392016ce5878 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2382,9 +2382,6 @@ static inline unsigned long get_num_physpages(void) * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid) * free_area_init(max_zone_pfns); - * - * sparse_memory_present_with_active_regions() calls memory_present() for - * each range when SPARSEMEM is enabled. */ void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); @@ -2395,7 +2392,6 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn, extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); -extern void sparse_memory_present_with_active_regions(int nid); #ifndef CONFIG_NEED_MULTIPLE_NODES static inline int early_pfn_to_nid(unsigned long pfn) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index a3bd54139a30..2eef8afd3a0f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -839,18 +839,6 @@ static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx); -#ifdef CONFIG_HAVE_MEMORY_PRESENT -void memory_present(int nid, unsigned long start, unsigned long end); -#else -static inline void memory_present(int nid, unsigned long start, unsigned long end) {} -#endif - -#if defined(CONFIG_SPARSEMEM) -void memblocks_present(void); -#else -static inline void memblocks_present(void) {} -#endif - #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else @@ -1407,8 +1395,6 @@ struct mminit_pfnnid_cache { #define early_pfn_valid(pfn) (1) #endif -void memory_present(int nid, unsigned long start, unsigned long end); - /* * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we * need to check pfn validity within that MAX_ORDER_NR_PAGES block. -- cgit v1.2.3 From 26e760c9a7c8ec31fa1a6bfbbce3f63f189ccef0 Mon Sep 17 00:00:00 2001 From: Walter Wu Date: Thu, 6 Aug 2020 23:24:35 -0700 Subject: rcu: kasan: record and print call_rcu() call stack Patch series "kasan: memorize and print call_rcu stack", v8. This patchset improves KASAN reports by making them to have call_rcu() call stack information. It is useful for programmers to solve use-after-free or double-free memory issue. The KASAN report was as follows(cleaned up slightly): BUG: KASAN: use-after-free in kasan_rcu_reclaim+0x58/0x60 Freed by task 0: kasan_save_stack+0x24/0x50 kasan_set_track+0x24/0x38 kasan_set_free_info+0x18/0x20 __kasan_slab_free+0x10c/0x170 kasan_slab_free+0x10/0x18 kfree+0x98/0x270 kasan_rcu_reclaim+0x1c/0x60 Last call_rcu(): kasan_save_stack+0x24/0x50 kasan_record_aux_stack+0xbc/0xd0 call_rcu+0x8c/0x580 kasan_rcu_uaf+0xf4/0xf8 Generic KASAN will record the last two call_rcu() call stacks and print up to 2 call_rcu() call stacks in KASAN report. it is only suitable for generic KASAN. This feature considers the size of struct kasan_alloc_meta and kasan_free_meta, we try to optimize the structure layout and size, lets it get better memory consumption. [1]https://bugzilla.kernel.org/show_bug.cgi?id=198437 [2]https://groups.google.com/forum/#!searchin/kasan-dev/better$20stack$20traces$20for$20rcu%7Csort:date/kasan-dev/KQsjT_88hDE/7rNUZprRBgAJ This patch (of 4): This feature will record the last two call_rcu() call stacks and prints up to 2 call_rcu() call stacks in KASAN report. When call_rcu() is called, we store the call_rcu() call stack into slub alloc meta-data, so that the KASAN report can print rcu stack. [1]https://bugzilla.kernel.org/show_bug.cgi?id=198437 [2]https://groups.google.com/forum/#!searchin/kasan-dev/better$20stack$20traces$20for$20rcu%7Csort:date/kasan-dev/KQsjT_88hDE/7rNUZprRBgAJ [walter-zh.wu@mediatek.com: build fix] Link: http://lkml.kernel.org/r/20200710162401.23816-1-walter-zh.wu@mediatek.com Suggested-by: Dmitry Vyukov Signed-off-by: Walter Wu Signed-off-by: Andrew Morton Tested-by: Dmitry Vyukov Reviewed-by: Dmitry Vyukov Reviewed-by: Andrey Konovalov Acked-by: Paul E. McKenney Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Josh Triplett Cc: Mathieu Desnoyers Cc: Lai Jiangshan Cc: Joel Fernandes Cc: Jonathan Corbet Cc: Matthias Brugger Link: http://lkml.kernel.org/r/20200710162123.23713-1-walter-zh.wu@mediatek.com Link: http://lkml.kernel.org/r/20200601050847.1096-1-walter-zh.wu@mediatek.com Link: http://lkml.kernel.org/r/20200601050927.1153-1-walter-zh.wu@mediatek.com Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 82522e996c76..18452e35e7b2 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -174,11 +174,13 @@ static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); +void kasan_record_aux_stack(void *ptr); #else /* CONFIG_KASAN_GENERIC */ static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} +static inline void kasan_record_aux_stack(void *ptr) {} #endif /* CONFIG_KASAN_GENERIC */ -- cgit v1.2.3 From c0e16ab3b5887e86cd45b95e28cf66498b161ee1 Mon Sep 17 00:00:00 2001 From: Vincenzo Frascino Date: Thu, 6 Aug 2020 23:24:50 -0700 Subject: kasan: remove kasan_unpoison_stack_above_sp_to() kasan_unpoison_stack_above_sp_to() is defined in kasan code but never used. The function was introduced as part of the commit: commit 9f7d416c36124667 ("kprobes: Unpoison stack in jprobe_return() for KASAN") ... where it was necessary because x86's jprobe_return() would leave stale shadow on the stack, and was an oddity in that regard. Since then, jprobes were removed entirely, and as of commit: commit 80006dbee674f9fa ("kprobes/x86: Remove jprobe implementation") ... there have been no callers of this function. Remove the declaration and the implementation. Signed-off-by: Vincenzo Frascino Signed-off-by: Andrew Morton Reviewed-by: Mark Rutland Reviewed-by: Andrey Konovalov Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Link: http://lkml.kernel.org/r/20200706143505.23299-1-vincenzo.frascino@arm.com Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 18452e35e7b2..087fba34b209 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -38,7 +38,6 @@ extern void kasan_disable_current(void); void kasan_unpoison_shadow(const void *address, size_t size); void kasan_unpoison_task_stack(struct task_struct *task); -void kasan_unpoison_stack_above_sp_to(const void *watermark); void kasan_alloc_pages(struct page *page, unsigned int order); void kasan_free_pages(struct page *page, unsigned int order); @@ -101,7 +100,6 @@ void kasan_restore_multi_shot(bool enabled); static inline void kasan_unpoison_shadow(const void *address, size_t size) {} static inline void kasan_unpoison_task_stack(struct task_struct *task) {} -static inline void kasan_unpoison_stack_above_sp_to(const void *watermark) {} static inline void kasan_enable_current(void) {} static inline void kasan_disable_current(void) {} -- cgit v1.2.3 From 2c547f9da0539ad1f7ef7f08c8c82036d61b011a Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 6 Aug 2020 23:25:01 -0700 Subject: efi: provide empty efi_enter_virtual_mode implementation When CONFIG_EFI is not enabled, we might get an undefined reference to efi_enter_virtual_mode() error, if this efi_enabled() call isn't inlined into start_kernel(). This happens in particular, if start_kernel() is annodated with __no_sanitize_address. Reported-by: kernel test robot Signed-off-by: Andrey Konovalov Signed-off-by: Andrew Morton Acked-by: Ard Biesheuvel Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Elena Petrova Cc: Marco Elver Cc: Vincenzo Frascino Cc: Walter Wu Link: http://lkml.kernel.org/r/6514652d3a32d3ed33d6eb5c91d0af63bf0d1a0c.1596544734.git.andreyknvl@google.com Signed-off-by: Linus Torvalds --- include/linux/efi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 05c47f857383..73db1ae04cef 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -606,7 +606,11 @@ extern void *efi_get_pal_addr (void); extern void efi_map_pal_code (void); extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg); extern void efi_gettimeofday (struct timespec64 *ts); +#ifdef CONFIG_EFI extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if possible */ +#else +static inline void efi_enter_virtual_mode (void) {} +#endif #ifdef CONFIG_X86 extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size, -- cgit v1.2.3 From 0a18e60788d6a39436e8b5e91001b790043fc29c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 6 Aug 2020 23:25:27 -0700 Subject: mm: remove vm_total_pages The global variable "vm_total_pages" is a relic from older days. There is only a single user that reads the variable - build_all_zonelists() - and the first thing it does is update it. Use a local variable in build_all_zonelists() instead and remove the global variable. Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Reviewed-by: Wei Yang Reviewed-by: Pankaj Gupta Reviewed-by: Mike Rapoport Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Huang Ying Cc: Minchan Kim Link: http://lkml.kernel.org/r/20200619132410.23859-2-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 5b3216ba39a9..4ab236692e05 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -372,7 +372,6 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; extern int remove_mapping(struct address_space *mapping, struct page *page); -extern unsigned long vm_total_pages; extern unsigned long reclaim_pages(struct list_head *page_list); #ifdef CONFIG_NUMA -- cgit v1.2.3 From 56b9413bcb369f1329a438c7b61d235b4123e794 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 6 Aug 2020 23:25:30 -0700 Subject: mm/page_alloc: remove nr_free_pagecache_pages() nr_free_pagecache_pages() isn't used outside page_alloc.c anymore - and the name does not really help to understand what's going on. Let's open-code it instead and add a comment. Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Reviewed-by: Wei Yang Reviewed-by: Pankaj Gupta Reviewed-by: Mike Rapoport Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Minchan Kim Cc: Huang Ying Link: http://lkml.kernel.org/r/20200619132410.23859-3-david@redhat.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 4ab236692e05..7eb59bc552a5 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -328,7 +328,6 @@ void workingset_update_node(struct xa_node *node); /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; extern unsigned long nr_free_buffer_pages(void); -extern unsigned long nr_free_pagecache_pages(void); /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) -- cgit v1.2.3 From d38ac97f8a7c4519ba141bbd7c2f7a8da8c9ff8d Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 6 Aug 2020 23:25:41 -0700 Subject: mm/page_alloc.c: replace the definition of NR_MIGRATETYPE_BITS with PB_migratetype_bits We already have the definition of PB_migratetype_bits and current NR_MIGRATETYPE_BITS looks like a cyclic definition. Just use PB_migratetype_bits is enough. Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Cc: Mel Gorman Link: http://lkml.kernel.org/r/20200623124201.8199-1-richard.weiyang@linux.alibaba.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2eef8afd3a0f..f509ede317b5 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -88,8 +88,7 @@ static inline bool is_migrate_movable(int mt) extern int page_group_by_mobility_disabled; -#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1) -#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1) +#define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1) #define get_pageblock_migratetype(page) \ get_pfnblock_flags_mask(page, page_to_pfn(page), \ -- cgit v1.2.3 From d93d5ab9ca01e24efc6add60371b0d5684b5c146 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 6 Aug 2020 23:25:48 -0700 Subject: mm/page_alloc.c: simplify pageblock bitmap access Due to commit e58469bafd05 ("mm: page_alloc: use word-based accesses for get/set pageblock bitmaps"), pageblock bitmap is accessed with word-based access. This operation could be simplified a little. Intuitively, if we want to get a bit range [start_idx, end_idx] in a word, we can do like this: mask = (1 << (end_bitidx - start_bitidx + 1)) - 1; ret = (word >> start_idx) & mask; And also if we want to set a bit range [start_idx, end_idx] with flags, we can do the same by just shift start_bitidx. By doing so we reduce some instructions for these two helper functions: Before Patched set_pfnblock_flags_mask 209 198(-5%) get_pfnblock_flags_mask 101 87(-13%) Since the syntax is changed a little, we need to check the whole 4-bit migrate_type instead of part of it. Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Cc: Mel Gorman Link: http://lkml.kernel.org/r/20200623124201.8199-3-richard.weiyang@linux.alibaba.com Signed-off-by: Linus Torvalds --- include/linux/pageblock-flags.h | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index c066fec5b74b..6556e4474409 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -66,25 +66,17 @@ void set_pfnblock_flags_mask(struct page *page, unsigned long mask); /* Declarations for getting and setting flags. See mm/page_alloc.c */ -#define get_pageblock_flags_group(page, start_bitidx, end_bitidx) \ - get_pfnblock_flags_mask(page, page_to_pfn(page), \ - end_bitidx, \ - (1 << (end_bitidx - start_bitidx + 1)) - 1) -#define set_pageblock_flags_group(page, flags, start_bitidx, end_bitidx) \ - set_pfnblock_flags_mask(page, flags, page_to_pfn(page), \ - end_bitidx, \ - (1 << (end_bitidx - start_bitidx + 1)) - 1) - #ifdef CONFIG_COMPACTION #define get_pageblock_skip(page) \ - get_pageblock_flags_group(page, PB_migrate_skip, \ - PB_migrate_skip) + get_pfnblock_flags_mask(page, page_to_pfn(page), \ + PB_migrate_skip, (1 << (PB_migrate_skip))) #define clear_pageblock_skip(page) \ - set_pageblock_flags_group(page, 0, PB_migrate_skip, \ - PB_migrate_skip) + set_pfnblock_flags_mask(page, 0, page_to_pfn(page), \ + PB_migrate_skip, (1 << PB_migrate_skip)) #define set_pageblock_skip(page) \ - set_pageblock_flags_group(page, 1, PB_migrate_skip, \ - PB_migrate_skip) + set_pfnblock_flags_mask(page, (1 << PB_migrate_skip), \ + page_to_pfn(page), \ + PB_migrate_skip, (1 << PB_migrate_skip)) #else static inline bool get_pageblock_skip(struct page *page) { -- cgit v1.2.3 From 535b81e209219e03f815379746bfd1eeb82d68e5 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 6 Aug 2020 23:25:51 -0700 Subject: mm/page_alloc.c: remove unnecessary end_bitidx for [set|get]_pfnblock_flags_mask() After previous cleanup, the end_bitidx is not necessary any more. Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Cc: Mel Gorman Link: http://lkml.kernel.org/r/20200623124201.8199-4-richard.weiyang@linux.alibaba.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 +-- include/linux/pageblock-flags.h | 8 +++----- 2 files changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f509ede317b5..635a96cd9b1f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -91,8 +91,7 @@ extern int page_group_by_mobility_disabled; #define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1) #define get_pageblock_migratetype(page) \ - get_pfnblock_flags_mask(page, page_to_pfn(page), \ - PB_migrate_end, MIGRATETYPE_MASK) + get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK) struct free_area { struct list_head free_list[MIGRATE_TYPES]; diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 6556e4474409..fff52ad370c1 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -56,27 +56,25 @@ struct page; unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, - unsigned long end_bitidx, unsigned long mask); void set_pfnblock_flags_mask(struct page *page, unsigned long flags, unsigned long pfn, - unsigned long end_bitidx, unsigned long mask); /* Declarations for getting and setting flags. See mm/page_alloc.c */ #ifdef CONFIG_COMPACTION #define get_pageblock_skip(page) \ get_pfnblock_flags_mask(page, page_to_pfn(page), \ - PB_migrate_skip, (1 << (PB_migrate_skip))) + (1 << (PB_migrate_skip))) #define clear_pageblock_skip(page) \ set_pfnblock_flags_mask(page, 0, page_to_pfn(page), \ - PB_migrate_skip, (1 << PB_migrate_skip)) + (1 << PB_migrate_skip)) #define set_pageblock_skip(page) \ set_pfnblock_flags_mask(page, (1 << PB_migrate_skip), \ page_to_pfn(page), \ - PB_migrate_skip, (1 << PB_migrate_skip)) + (1 << PB_migrate_skip)) #else static inline bool get_pageblock_skip(struct page *page) { -- cgit v1.2.3 From 8510e69c8efef82f2b37ea3e8ea19a27122c533e Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Thu, 6 Aug 2020 23:26:04 -0700 Subject: mm/page_alloc: fix memalloc_nocma_{save/restore} APIs Currently, memalloc_nocma_{save/restore} API that prevents CMA area in page allocation is implemented by using current_gfp_context(). However, there are two problems of this implementation. First, this doesn't work for allocation fastpath. In the fastpath, original gfp_mask is used since current_gfp_context() is introduced in order to control reclaim and it is on slowpath. So, CMA area can be allocated through the allocation fastpath even if memalloc_nocma_{save/restore} APIs are used. Currently, there is just one user for these APIs and it has a fallback method to prevent actual problem. Second, clearing __GFP_MOVABLE in current_gfp_context() has a side effect to exclude the memory on the ZONE_MOVABLE for allocation target. To fix these problems, this patch changes the implementation to exclude CMA area in page allocation. Main point of this change is using the alloc_flags. alloc_flags is mainly used to control allocation so it fits for excluding CMA area in allocation. Fixes: d7fefcc8de91 (mm/cma: add PF flag to force non cma alloc) Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Cc: Christoph Hellwig Cc: Roman Gushchin Cc: Mike Kravetz Cc: Naoya Horiguchi Cc: Michal Hocko Cc: "Aneesh Kumar K . V" Link: http://lkml.kernel.org/r/1595468942-29687-1-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/sched/mm.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 6be66f52a2ad..85023ddc2dc2 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -175,12 +175,10 @@ static inline bool in_vfork(struct task_struct *tsk) * Applies per-task gfp context to the given allocation flags. * PF_MEMALLOC_NOIO implies GFP_NOIO * PF_MEMALLOC_NOFS implies GFP_NOFS - * PF_MEMALLOC_NOCMA implies no allocation from CMA region. */ static inline gfp_t current_gfp_context(gfp_t flags) { - if (unlikely(current->flags & - (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) { + if (unlikely(current->flags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) { /* * NOIO implies both NOIO and NOFS and it is a weaker context * so always make sure it makes precedence @@ -189,10 +187,6 @@ static inline gfp_t current_gfp_context(gfp_t flags) flags &= ~(__GFP_IO | __GFP_FS); else if (current->flags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; -#ifdef CONFIG_CMA - if (current->flags & PF_MEMALLOC_NOCMA) - flags &= ~__GFP_MOVABLE; -#endif } return flags; } -- cgit v1.2.3 From 38ce2a9e33db61a3041840310077072d6210ead4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 6 Aug 2020 12:46:49 -0400 Subject: tracing: Add trace_array_init_printk() to initialize instance trace_printk() buffers As trace_array_printk() used with not global instances will not add noise to the main buffer, they are OK to have in the kernel (unlike trace_printk()). This require the subsystem to create their own tracing instance, and the trace_array_printk() only writes into those instances. Add trace_array_init_printk() to initialize the trace_printk() buffers without printing out the WARNING message. Reported-by: Sean Paul Reviewed-by: Sean Paul Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/trace.h b/include/linux/trace.h index 7fd86d3c691f..36d255d66f88 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -29,6 +29,7 @@ struct trace_array; void trace_printk_init_buffers(void); int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...); +int trace_array_init_printk(struct trace_array *tr); void trace_array_put(struct trace_array *tr); struct trace_array *trace_array_get_by_name(const char *name); int trace_array_destroy(struct trace_array *tr); -- cgit v1.2.3 From 519a8a6cf91dda095be2d36216fc4ebc525270a1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Aug 2020 18:42:14 +0200 Subject: net: Revert "net: optimize the sockptr_t for unified kernel/user address spaces" This reverts commits 6d04fe15f78acdf8e32329e208552e226f7a8ae6 and a31edb2059ed4e498f9aa8230c734b59d0ad797a. It turns out the idea to share a single pointer for both kernel and user space address causes various kinds of problems. So use the slightly less optimal version that uses an extra bit, but which is guaranteed to be safe everywhere. Fixes: 6d04fe15f78a ("net: optimize the sockptr_t for unified kernel/user address spaces") Reported-by: Eric Dumazet Reported-by: John Stultz Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/sockptr.h | 26 ++------------------------ 1 file changed, 2 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 96840def9d69..ea193414298b 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -8,26 +8,9 @@ #ifndef _LINUX_SOCKPTR_H #define _LINUX_SOCKPTR_H -#include #include #include -#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE -typedef union { - void *kernel; - void __user *user; -} sockptr_t; - -static inline bool sockptr_is_kernel(sockptr_t sockptr) -{ - return (unsigned long)sockptr.kernel >= TASK_SIZE; -} - -static inline sockptr_t KERNEL_SOCKPTR(void *p) -{ - return (sockptr_t) { .kernel = p }; -} -#else /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ typedef struct { union { void *kernel; @@ -45,15 +28,10 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p, .is_kernel = true }; } -#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ -static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p, - size_t size) +static inline sockptr_t USER_SOCKPTR(void __user *p) { - if (!access_ok(p, size)) - return -EFAULT; - *sp = (sockptr_t) { .user = p }; - return 0; + return (sockptr_t) { .user = p }; } static inline bool sockptr_is_null(sockptr_t sockptr) -- cgit v1.2.3 From 444da3f52407d74c9aa12187ac6b01f76ee47d62 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 10 Aug 2020 11:21:11 -0700 Subject: bitfield.h: don't compile-time validate _val in FIELD_FIT When ur_load_imm_any() is inlined into jeq_imm(), it's possible for the compiler to deduce a case where _val can only have the value of -1 at compile time. Specifically, /* struct bpf_insn: _s32 imm */ u64 imm = insn->imm; /* sign extend */ if (imm >> 32) { /* non-zero only if insn->imm is negative */ /* inlined from ur_load_imm_any */ u32 __imm = imm >> 32; /* therefore, always 0xffffffff */ if (__builtin_constant_p(__imm) && __imm > 255) compiletime_assert_XXX() This can result in tripping a BUILD_BUG_ON() in __BF_FIELD_CHECK() that checks that a given value is representable in one byte (interpreted as unsigned). FIELD_FIT() should return true or false at runtime for whether a value can fit for not. Don't break the build over a value that's too large for the mask. We'd prefer to keep the inlining and compiler optimizations though we know this case will always return false. Cc: stable@vger.kernel.org Fixes: 1697599ee301a ("bitfield.h: add FIELD_FIT() helper") Link: https://lore.kernel.org/kernel-hardening/CAK7LNASvb0UDJ0U5wkYYRzTAdnEs64HjXpEUL7d=V0CXiAXcNw@mail.gmail.com/ Reported-by: Masahiro Yamada Debugged-by: Sami Tolvanen Signed-off-by: Jakub Kicinski Signed-off-by: Nick Desaulniers Signed-off-by: David S. Miller --- include/linux/bitfield.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 48ea093ff04c..4e035aca6f7e 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -77,7 +77,7 @@ */ #define FIELD_FIT(_mask, _val) \ ({ \ - __BF_FIELD_CHECK(_mask, 0ULL, _val, "FIELD_FIT: "); \ + __BF_FIELD_CHECK(_mask, 0ULL, 0ULL, "FIELD_FIT: "); \ !((((typeof(_mask))_val) << __bf_shf(_mask)) & ~(_mask)); \ }) -- cgit v1.2.3 From efa8480a831673bb52400df9dbe5da0aacda97bf Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 10 Aug 2020 18:44:24 -0600 Subject: fs: RWF_NOWAIT should imply IOCB_NOIO With the change allowing read-ahead for IOCB_NOWAIT, we changed the RWF_NOWAIT semantics of only doing cached reads. Since we know have IOCB_NOIO to manage that specific side of it, just make RWF_NOWAIT imply IOCB_NOIO as well to restore the previous behavior. Fixes: 2e85abf053b9 ("mm: allow read-ahead with IOCB_NOWAIT set") Reported-by: Dave Chinner Reviewed-by: Dave Chinner Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index bd7ec3eaeed0..f1cca4bfdd7b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3293,7 +3293,7 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; - kiocb_flags |= IOCB_NOWAIT; + kiocb_flags |= IOCB_NOWAIT | IOCB_NOIO; } if (flags & RWF_HIPRI) kiocb_flags |= IOCB_HIPRI; -- cgit v1.2.3 From f6ebbcf08f37b01827c51309a188e85165e498e7 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 6 Aug 2020 14:03:55 +0200 Subject: cpufreq: intel_pstate: Implement passive mode with HWP enabled Allow intel_pstate to work in the passive mode with HWP enabled and make it set the HWP minimum performance limit (HWP floor) to the P-state value given by the target frequency supplied by the cpufreq governor, so as to prevent the HWP algorithm and the CPU scheduler from working against each other, at least when the schedutil governor is in use, and update the intel_pstate documentation accordingly. Among other things, this allows utilization clamps to be taken into account, at least to a certain extent, when intel_pstate is in use and makes it more likely that sufficient capacity for deadline tasks will be provided. After this change, the resulting behavior of an HWP system with intel_pstate in the passive mode should be close to the behavior of the analogous non-HWP system with intel_pstate in the passive mode, except that the HWP algorithm is generally allowed to make the CPU run at a frequency above the floor P-state set by intel_pstate in the entire available range of P-states, while without HWP a CPU can run in a P-state above the requested one if the latter falls into the range of turbo P-states (referred to as the turbo range) or if the P-states of all CPUs in one package are coordinated with each other at the hardware level. [Note that in principle the HWP floor may not be taken into account by the processor if it falls into the turbo range, in which case the processor has a license to choose any P-state, either below or above the HWP floor, just like a non-HWP processor in the case when the target P-state falls into the turbo range.] With this change applied, intel_pstate in the passive mode assumes complete control over the HWP request MSR and concurrent changes of that MSR (eg. via the direct MSR access interface) are overridden by it. Signed-off-by: Rafael J. Wysocki Acked-by: Srinivas Pandruvada Reviewed-by: Francisco Jerez --- include/linux/cpufreq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 58687a5bf9c8..8f141d4c859c 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -576,6 +576,8 @@ unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy, unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy); int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); +int cpufreq_start_governor(struct cpufreq_policy *policy); +void cpufreq_stop_governor(struct cpufreq_policy *policy); #define cpufreq_governor_init(__governor) \ static int __init __governor##_init(void) \ -- cgit v1.2.3 From 772616b031f06e05846488b01dab46a7c832da13 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 11 Aug 2020 18:30:21 -0700 Subject: mm: memcg/percpu: per-memcg percpu memory statistics MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Percpu memory can represent a noticeable chunk of the total memory consumption, especially on big machines with many CPUs. Let's track percpu memory usage for each memcg and display it in memory.stat. A percpu allocation is usually scattered over multiple pages (and nodes), and can be significantly smaller than a page. So let's add a byte-sized counter on the memcg level: MEMCG_PERCPU_B. Byte-sized vmstat infra created for slabs can be perfectly reused for percpu case. [guro@fb.com: v3] Link: http://lkml.kernel.org/r/20200623184515.4132564-4-guro@fb.com Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Dennis Zhou Acked-by: Johannes Weiner Cc: Christoph Lameter Cc: David Rientjes Cc: Joonsoo Kim Cc: Mel Gorman Cc: Michal Hocko Cc: Pekka Enberg Cc: Tejun Heo Cc: Tobin C. Harding Cc: Vlastimil Babka Cc: Waiman Long Cc: Bixuan Cui Cc: Michal Koutný Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200608230819.832349-4-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1bb49b600310..2c2d301eac33 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -32,6 +32,7 @@ struct kmem_cache; enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, + MEMCG_PERCPU_B, MEMCG_NR_STAT, }; @@ -339,6 +340,13 @@ struct mem_cgroup { extern struct mem_cgroup *root_mem_cgroup; +static __always_inline bool memcg_stat_item_in_bytes(int idx) +{ + if (idx == MEMCG_PERCPU_B) + return true; + return vmstat_item_in_bytes(idx); +} + static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); -- cgit v1.2.3 From 8ca39e6874f812a393bb66d9fdbb7598d5f0451c Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 11 Aug 2020 18:30:32 -0700 Subject: mm/hugetlb: add mempolicy check in the reservation routine In the reservation routine, we only check whether the cpuset meets the memory allocation requirements. But we ignore the mempolicy of MPOL_BIND case. If someone mmap hugetlb succeeds, but the subsequent memory allocation may fail due to mempolicy restrictions and receives the SIGBUS signal. This can be reproduced by the follow steps. 1) Compile the test case. cd tools/testing/selftests/vm/ gcc map_hugetlb.c -o map_hugetlb 2) Pre-allocate huge pages. Suppose there are 2 numa nodes in the system. Each node will pre-allocate one huge page. echo 2 > /proc/sys/vm/nr_hugepages 3) Run test case(mmap 4MB). We receive the SIGBUS signal. numactl --membind=3D0 ./map_hugetlb 4 With this patch applied, the mmap will fail in the step 3) and throw "mmap: Cannot allocate memory". [akpm@linux-foundation.org: include sched.h for `current'] Reported-by: Jianchao Guo Suggested-by: Michal Hocko Signed-off-by: Muchun Song Signed-off-by: Andrew Morton Reviewed-by: Mike Kravetz Cc: David Rientjes Cc: Mel Gorman Cc: Michel Lespinasse Cc: Baoquan He Link: http://lkml.kernel.org/r/20200728034938.14993-1-songmuchun@bytedance.com Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index ea9c15b60a96..5f1648c23e29 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -6,7 +6,7 @@ #ifndef _LINUX_MEMPOLICY_H #define _LINUX_MEMPOLICY_H 1 - +#include #include #include #include @@ -152,6 +152,15 @@ extern int huge_node(struct vm_area_struct *vma, extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern bool mempolicy_nodemask_intersects(struct task_struct *tsk, const nodemask_t *mask); +extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy); + +static inline nodemask_t *policy_nodemask_current(gfp_t gfp) +{ + struct mempolicy *mpol = get_task_policy(current); + + return policy_nodemask(gfp, mpol); +} + extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; @@ -281,5 +290,10 @@ static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma, static inline void mpol_put_task_policy(struct task_struct *task) { } + +static inline nodemask_t *policy_nodemask_current(gfp_t gfp) +{ + return NULL; +} #endif /* CONFIG_NUMA */ #endif -- cgit v1.2.3 From b518154e59aab3ad0780a169c5cc84bd4ee4357e Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 11 Aug 2020 18:30:40 -0700 Subject: mm/vmscan: protect the workingset on anonymous LRU In current implementation, newly created or swap-in anonymous page is started on active list. Growing active list results in rebalancing active/inactive list so old pages on active list are demoted to inactive list. Hence, the page on active list isn't protected at all. Following is an example of this situation. Assume that 50 hot pages on active list. Numbers denote the number of pages on active/inactive list (active | inactive). 1. 50 hot pages on active list 50(h) | 0 2. workload: 50 newly created (used-once) pages 50(uo) | 50(h) 3. workload: another 50 newly created (used-once) pages 50(uo) | 50(uo), swap-out 50(h) This patch tries to fix this issue. Like as file LRU, newly created or swap-in anonymous pages will be inserted to the inactive list. They are promoted to active list if enough reference happens. This simple modification changes the above example as following. 1. 50 hot pages on active list 50(h) | 0 2. workload: 50 newly created (used-once) pages 50(h) | 50(uo) 3. workload: another 50 newly created (used-once) pages 50(h) | 50(uo), swap-out 50(uo) As you can see, hot pages on active list would be protected. Note that, this implementation has a drawback that the page cannot be promoted and will be swapped-out if re-access interval is greater than the size of inactive list but less than the size of total(active+inactive). To solve this potential issue, following patch will apply workingset detection similar to the one that's already applied to file LRU. Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Hugh Dickins Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Link: http://lkml.kernel.org/r/1595490560-15117-3-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 7eb59bc552a5..51ec9cdb92c0 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -352,7 +352,7 @@ extern void deactivate_page(struct page *page); extern void mark_page_lazyfree(struct page *page); extern void swap_setup(void); -extern void lru_cache_add_active_or_unevictable(struct page *page, +extern void lru_cache_add_inactive_or_unevictable(struct page *page, struct vm_area_struct *vma); /* linux/mm/vmscan.c */ -- cgit v1.2.3 From 170b04b7ae49634df103810dad67b22cf8a99aa6 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 11 Aug 2020 18:30:43 -0700 Subject: mm/workingset: prepare the workingset detection infrastructure for anon LRU To prepare the workingset detection for anon LRU, this patch splits workingset event counters for refault, activate and restore into anon and file variants, as well as the refaults counter in struct lruvec. Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Hugh Dickins Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Link: http://lkml.kernel.org/r/1595490560-15117-4-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 635a96cd9b1f..efbd95dd3bbf 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -173,9 +173,15 @@ enum node_stat_item { NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, - WORKINGSET_REFAULT, - WORKINGSET_ACTIVATE, - WORKINGSET_RESTORE, + WORKINGSET_REFAULT_BASE, + WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE, + WORKINGSET_REFAULT_FILE, + WORKINGSET_ACTIVATE_BASE, + WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE, + WORKINGSET_ACTIVATE_FILE, + WORKINGSET_RESTORE_BASE, + WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE, + WORKINGSET_RESTORE_FILE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. @@ -277,8 +283,8 @@ struct lruvec { unsigned long file_cost; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; - /* Refaults at the time of last reclaim cycle */ - unsigned long refaults; + /* Refaults at the time of last reclaim cycle, anon=0, file=1 */ + unsigned long refaults[2]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; #ifdef CONFIG_MEMCG -- cgit v1.2.3 From 3852f6768ede542ed48b9077bedf482c7ecb6327 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 11 Aug 2020 18:30:47 -0700 Subject: mm/swapcache: support to handle the shadow entries Workingset detection for anonymous page will be implemented in the following patch and it requires to store the shadow entries into the swapcache. This patch implements an infrastructure to store the shadow entry in the swapcache. Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Acked-by: Johannes Weiner Cc: Hugh Dickins Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Vlastimil Babka Link: http://lkml.kernel.org/r/1595490560-15117-5-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 51ec9cdb92c0..8a4c592698a9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -414,9 +414,13 @@ extern struct address_space *swapper_spaces[]; extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); extern int add_to_swap(struct page *page); -extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); -extern void __delete_from_swap_cache(struct page *, swp_entry_t entry); +extern int add_to_swap_cache(struct page *page, swp_entry_t entry, + gfp_t gfp, void **shadowp); +extern void __delete_from_swap_cache(struct page *page, + swp_entry_t entry, void *shadow); extern void delete_from_swap_cache(struct page *); +extern void clear_shadow_from_swap_cache(int type, unsigned long begin, + unsigned long end); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); extern struct page *lookup_swap_cache(swp_entry_t entry, @@ -570,13 +574,13 @@ static inline int add_to_swap(struct page *page) } static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, - gfp_t gfp_mask) + gfp_t gfp_mask, void **shadowp) { return -1; } static inline void __delete_from_swap_cache(struct page *page, - swp_entry_t entry) + swp_entry_t entry, void *shadow) { } @@ -584,6 +588,11 @@ static inline void delete_from_swap_cache(struct page *page) { } +static inline void clear_shadow_from_swap_cache(int type, unsigned long begin, + unsigned long end) +{ +} + static inline int page_swapcount(struct page *page) { return 0; -- cgit v1.2.3 From aae466b0052e1888edd1d7f473d4310d64936196 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 11 Aug 2020 18:30:50 -0700 Subject: mm/swap: implement workingset detection for anonymous LRU This patch implements workingset detection for anonymous LRU. All the infrastructure is implemented by the previous patches so this patch just activates the workingset detection by installing/retrieving the shadow entry and adding refault calculation. Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Hugh Dickins Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Link: http://lkml.kernel.org/r/1595490560-15117-6-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/swap.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 8a4c592698a9..661046994db4 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -414,6 +414,7 @@ extern struct address_space *swapper_spaces[]; extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); extern int add_to_swap(struct page *page); +extern void *get_shadow_from_swap_cache(swp_entry_t entry); extern int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp, void **shadowp); extern void __delete_from_swap_cache(struct page *page, @@ -573,6 +574,11 @@ static inline int add_to_swap(struct page *page) return 0; } +static inline void *get_shadow_from_swap_cache(swp_entry_t entry) +{ + return NULL; +} + static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask, void **shadowp) { -- cgit v1.2.3 From facdaa917c4d5a376d09d25865f5a863f906234a Mon Sep 17 00:00:00 2001 From: Nitin Gupta Date: Tue, 11 Aug 2020 18:31:00 -0700 Subject: mm: proactive compaction MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For some applications, we need to allocate almost all memory as hugepages. However, on a running system, higher-order allocations can fail if the memory is fragmented. Linux kernel currently does on-demand compaction as we request more hugepages, but this style of compaction incurs very high latency. Experiments with one-time full memory compaction (followed by hugepage allocations) show that kernel is able to restore a highly fragmented memory state to a fairly compacted memory state within <1 sec for a 32G system. Such data suggests that a more proactive compaction can help us allocate a large fraction of memory as hugepages keeping allocation latencies low. For a more proactive compaction, the approach taken here is to define a new sysctl called 'vm.compaction_proactiveness' which dictates bounds for external fragmentation which kcompactd tries to maintain. The tunable takes a value in range [0, 100], with a default of 20. Note that a previous version of this patch [1] was found to introduce too many tunables (per-order extfrag{low, high}), but this one reduces them to just one sysctl. Also, the new tunable is an opaque value instead of asking for specific bounds of "external fragmentation", which would have been difficult to estimate. The internal interpretation of this opaque value allows for future fine-tuning. Currently, we use a simple translation from this tunable to [low, high] "fragmentation score" thresholds (low=100-proactiveness, high=low+10%). The score for a node is defined as weighted mean of per-zone external fragmentation. A zone's present_pages determines its weight. To periodically check per-node score, we reuse per-node kcompactd threads, which are woken up every 500 milliseconds to check the same. If a node's score exceeds its high threshold (as derived from user-provided proactiveness value), proactive compaction is started until its score reaches its low threshold value. By default, proactiveness is set to 20, which implies threshold values of low=80 and high=90. This patch is largely based on ideas from Michal Hocko [2]. See also the LWN article [3]. Performance data ================ System: x64_64, 1T RAM, 80 CPU threads. Kernel: 5.6.0-rc3 + this patch echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/enabled echo madvise | sudo tee /sys/kernel/mm/transparent_hugepage/defrag Before starting the driver, the system was fragmented from a userspace program that allocates all memory and then for each 2M aligned section, frees 3/4 of base pages using munmap. The workload is mainly anonymous userspace pages, which are easy to move around. I intentionally avoided unmovable pages in this test to see how much latency we incur when hugepage allocations hit direct compaction. 1. Kernel hugepage allocation latencies With the system in such a fragmented state, a kernel driver then allocates as many hugepages as possible and measures allocation latency: (all latency values are in microseconds) - With vanilla 5.6.0-rc3 percentile latency –––––––––– ––––––– 5 7894 10 9496 25 12561 30 15295 40 18244 50 21229 60 27556 75 30147 80 31047 90 32859 95 33799 Total 2M hugepages allocated = 383859 (749G worth of hugepages out of 762G total free => 98% of free memory could be allocated as hugepages) - With 5.6.0-rc3 + this patch, with proactiveness=20 sysctl -w vm.compaction_proactiveness=20 percentile latency –––––––––– ––––––– 5 2 10 2 25 3 30 3 40 3 50 4 60 4 75 4 80 4 90 5 95 429 Total 2M hugepages allocated = 384105 (750G worth of hugepages out of 762G total free => 98% of free memory could be allocated as hugepages) 2. JAVA heap allocation In this test, we first fragment memory using the same method as for (1). Then, we start a Java process with a heap size set to 700G and request the heap to be allocated with THP hugepages. We also set THP to madvise to allow hugepage backing of this heap. /usr/bin/time java -Xms700G -Xmx700G -XX:+UseTransparentHugePages -XX:+AlwaysPreTouch The above command allocates 700G of Java heap using hugepages. - With vanilla 5.6.0-rc3 17.39user 1666.48system 27:37.89elapsed - With 5.6.0-rc3 + this patch, with proactiveness=20 8.35user 194.58system 3:19.62elapsed Elapsed time remains around 3:15, as proactiveness is further increased. Note that proactive compaction happens throughout the runtime of these workloads. The situation of one-time compaction, sufficient to supply hugepages for following allocation stream, can probably happen for more extreme proactiveness values, like 80 or 90. In the above Java workload, proactiveness is set to 20. The test starts with a node's score of 80 or higher, depending on the delay between the fragmentation step and starting the benchmark, which gives more-or-less time for the initial round of compaction. As t he benchmark consumes hugepages, node's score quickly rises above the high threshold (90) and proactive compaction starts again, which brings down the score to the low threshold level (80). Repeat. bpftrace also confirms proactive compaction running 20+ times during the runtime of this Java benchmark. kcompactd threads consume 100% of one of the CPUs while it tries to bring a node's score within thresholds. Backoff behavior ================ Above workloads produce a memory state which is easy to compact. However, if memory is filled with unmovable pages, proactive compaction should essentially back off. To test this aspect: - Created a kernel driver that allocates almost all memory as hugepages followed by freeing first 3/4 of each hugepage. - Set proactiveness=40 - Note that proactive_compact_node() is deferred maximum number of times with HPAGE_FRAG_CHECK_INTERVAL_MSEC of wait between each check (=> ~30 seconds between retries). [1] https://patchwork.kernel.org/patch/11098289/ [2] https://lore.kernel.org/linux-mm/20161230131412.GI13301@dhcp22.suse.cz/ [3] https://lwn.net/Articles/817905/ Signed-off-by: Nitin Gupta Signed-off-by: Andrew Morton Tested-by: Oleksandr Natalenko Reviewed-by: Vlastimil Babka Reviewed-by: Khalid Aziz Reviewed-by: Oleksandr Natalenko Cc: Vlastimil Babka Cc: Khalid Aziz Cc: Michal Hocko Cc: Mel Gorman Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Joonsoo Kim Cc: David Rientjes Cc: Nitin Gupta Cc: Oleksandr Natalenko Link: http://lkml.kernel.org/r/20200616204527.19185-1-nigupta@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 6fa0eea3f530..7a242d46454e 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -85,11 +85,13 @@ static inline unsigned long compact_gap(unsigned int order) #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; +extern int sysctl_compaction_proactiveness; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); extern int sysctl_extfrag_threshold; extern int sysctl_compact_unevictable_allowed; +extern int extfrag_for_order(struct zone *zone, unsigned int order); extern int fragmentation_index(struct zone *zone, unsigned int order); extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, -- cgit v1.2.3 From d34c0a7599ea8c301bc471dfa1eb2bf2db6752d1 Mon Sep 17 00:00:00 2001 From: Nitin Gupta Date: Tue, 11 Aug 2020 18:31:07 -0700 Subject: mm: use unsigned types for fragmentation score Proactive compaction uses per-node/zone "fragmentation score" which is always in range [0, 100], so use unsigned type of these scores as well as for related constants. Signed-off-by: Nitin Gupta Signed-off-by: Andrew Morton Reviewed-by: Baoquan He Cc: Luis Chamberlain Cc: Kees Cook Cc: Iurii Zaikin Cc: Vlastimil Babka Cc: Joonsoo Kim Link: http://lkml.kernel.org/r/20200618010319.13159-1-nigupta@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 7a242d46454e..25a521d299c1 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -85,13 +85,13 @@ static inline unsigned long compact_gap(unsigned int order) #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; -extern int sysctl_compaction_proactiveness; +extern unsigned int sysctl_compaction_proactiveness; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); extern int sysctl_extfrag_threshold; extern int sysctl_compact_unevictable_allowed; -extern int extfrag_for_order(struct zone *zone, unsigned int order); +extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); extern int fragmentation_index(struct zone *zone, unsigned int order); extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, -- cgit v1.2.3 From 860b32729a21e0565585a9e2ecea2e5244d65acd Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Tue, 11 Aug 2020 18:31:10 -0700 Subject: mm/compaction: correct the comments of compact_defer_shift There is no compact_defer_limit. It should be compact_defer_shift in use. and add compact_order_failed explanation. Signed-off-by: Alex Shi Signed-off-by: Andrew Morton Reviewed-by: Alexander Duyck Link: http://lkml.kernel.org/r/3bd60e1b-a74e-050d-ade4-6e8f54e00b92@linux.alibaba.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index efbd95dd3bbf..8379432f4f2f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -536,6 +536,7 @@ struct zone { * On compaction failure, 1< Date: Tue, 11 Aug 2020 18:31:19 -0700 Subject: include/linux/mempolicy.h: fix typo Change "interlave" to "interleave". Signed-off-by: Yanfei Xu Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Link: http://lkml.kernel.org/r/20200810063454.9357-1-yanfei.xu@windriver.com Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5f1648c23e29..5f1c74df264d 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -28,7 +28,7 @@ struct mm_struct; * the process policy is used. Interrupts ignore the memory policy * of the current process. * - * Locking policy for interlave: + * Locking policy for interleave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on * mmap_lock. -- cgit v1.2.3 From 9066e5cfb73cdbcdbb49e87999482ab615e9fc76 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Tue, 11 Aug 2020 18:31:22 -0700 Subject: mm, oom: make the calculation of oom badness more accurate Recently we found an issue on our production environment that when memcg oom is triggered the oom killer doesn't chose the process with largest resident memory but chose the first scanned process. Note that all processes in this memcg have the same oom_score_adj, so the oom killer should chose the process with largest resident memory. Bellow is part of the oom info, which is enough to analyze this issue. [7516987.983223] memory: usage 16777216kB, limit 16777216kB, failcnt 52843037 [7516987.983224] memory+swap: usage 16777216kB, limit 9007199254740988kB, failcnt 0 [7516987.983225] kmem: usage 301464kB, limit 9007199254740988kB, failcnt 0 [...] [7516987.983293] [ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name [7516987.983510] [ 5740] 0 5740 257 1 32768 0 -998 pause [7516987.983574] [58804] 0 58804 4594 771 81920 0 -998 entry_point.bas [7516987.983577] [58908] 0 58908 7089 689 98304 0 -998 cron [7516987.983580] [58910] 0 58910 16235 5576 163840 0 -998 supervisord [7516987.983590] [59620] 0 59620 18074 1395 188416 0 -998 sshd [7516987.983594] [59622] 0 59622 18680 6679 188416 0 -998 python [7516987.983598] [59624] 0 59624 1859266 5161 548864 0 -998 odin-agent [7516987.983600] [59625] 0 59625 707223 9248 983040 0 -998 filebeat [7516987.983604] [59627] 0 59627 416433 64239 774144 0 -998 odin-log-agent [7516987.983607] [59631] 0 59631 180671 15012 385024 0 -998 python3 [7516987.983612] [61396] 0 61396 791287 3189 352256 0 -998 client [7516987.983615] [61641] 0 61641 1844642 29089 946176 0 -998 client [7516987.983765] [ 9236] 0 9236 2642 467 53248 0 -998 php_scanner [7516987.983911] [42898] 0 42898 15543 838 167936 0 -998 su [7516987.983915] [42900] 1000 42900 3673 867 77824 0 -998 exec_script_vr2 [7516987.983918] [42925] 1000 42925 36475 19033 335872 0 -998 python [7516987.983921] [57146] 1000 57146 3673 848 73728 0 -998 exec_script_J2p [7516987.983925] [57195] 1000 57195 186359 22958 491520 0 -998 python2 [7516987.983928] [58376] 1000 58376 275764 14402 290816 0 -998 rosmaster [7516987.983931] [58395] 1000 58395 155166 4449 245760 0 -998 rosout [7516987.983935] [58406] 1000 58406 18285584 3967322 37101568 0 -998 data_sim [7516987.984221] oom-kill:constraint=CONSTRAINT_MEMCG,nodemask=(null),cpuset=3aa16c9482ae3a6f6b78bda68a55d32c87c99b985e0f11331cddf05af6c4d753,mems_allowed=0-1,oom_memcg=/kubepods/podf1c273d3-9b36-11ea-b3df-246e9693c184,task_memcg=/kubepods/podf1c273d3-9b36-11ea-b3df-246e9693c184/1f246a3eeea8f70bf91141eeaf1805346a666e225f823906485ea0b6c37dfc3d,task=pause,pid=5740,uid=0 [7516987.984254] Memory cgroup out of memory: Killed process 5740 (pause) total-vm:1028kB, anon-rss:4kB, file-rss:0kB, shmem-rss:0kB [7516988.092344] oom_reaper: reaped process 5740 (pause), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB We can find that the first scanned process 5740 (pause) was killed, but its rss is only one page. That is because, when we calculate the oom badness in oom_badness(), we always ignore the negtive point and convert all of these negtive points to 1. Now as oom_score_adj of all the processes in this targeted memcg have the same value -998, the points of these processes are all negtive value. As a result, the first scanned process will be killed. The oom_socre_adj (-998) in this memcg is set by kubelet, because it is a a Guaranteed pod, which has higher priority to prevent from being killed by system oom. To fix this issue, we should make the calculation of oom point more accurate. We can achieve it by convert the chosen_point from 'unsigned long' to 'long'. [cai@lca.pw: reported a issue in the previous version] [mhocko@suse.com: fixed the issue reported by Cai] [mhocko@suse.com: add the comment in proc_oom_score()] [laoar.shao@gmail.com: v3] Link: http://lkml.kernel.org/r/1594396651-9931-1-git-send-email-laoar.shao@gmail.com Signed-off-by: Yafang Shao Signed-off-by: Andrew Morton Tested-by: Naresh Kamboju Acked-by: Michal Hocko Cc: David Rientjes Cc: Qian Cai Link: http://lkml.kernel.org/r/1594309987-9919-1-git-send-email-laoar.shao@gmail.com Signed-off-by: Linus Torvalds --- include/linux/oom.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index c696c265f019..f022f581ac29 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -48,7 +48,7 @@ struct oom_control { /* Used by oom implementation, do not set */ unsigned long totalpages; struct task_struct *chosen; - unsigned long chosen_points; + long chosen_points; /* Used to print the constraint info. */ enum oom_constraint constraint; @@ -107,7 +107,7 @@ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm) bool __oom_reap_task_mm(struct mm_struct *mm); -extern unsigned long oom_badness(struct task_struct *p, +long oom_badness(struct task_struct *p, unsigned long totalpages); extern bool out_of_memory(struct oom_control *oc); -- cgit v1.2.3 From 34ae204f18519f0920bd50a644abd6fefc8dbfcf Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Tue, 11 Aug 2020 18:31:38 -0700 Subject: hugetlbfs: remove call to huge_pte_alloc without i_mmap_rwsem Commit c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization") requires callers of huge_pte_alloc to hold i_mmap_rwsem in at least read mode. This is because the explicit locking in huge_pmd_share (called by huge_pte_alloc) was removed. When restructuring the code, the call to huge_pte_alloc in the else block at the beginning of hugetlb_fault was missed. Unfortunately, that else clause is exercised when there is no page table entry. This will likely lead to a call to huge_pmd_share. If huge_pmd_share thinks pmd sharing is possible, it will traverse the mapping tree (i_mmap) without holding i_mmap_rwsem. If someone else is modifying the tree, bad things such as addressing exceptions or worse could happen. Simply remove the else clause. It should have been removed previously. The code following the else will call huge_pte_alloc with the appropriate locking. To prevent this type of issue in the future, add routines to assert that i_mmap_rwsem is held, and call these routines in huge pmd sharing routines. Fixes: c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization") Suggested-by: Matthew Wilcox Signed-off-by: Mike Kravetz Signed-off-by: Andrew Morton Cc: Michal Hocko Cc: Hugh Dickins Cc: Naoya Horiguchi Cc: "Aneesh Kumar K.V" Cc: Andrea Arcangeli Cc: "Kirill A.Shutemov" Cc: Davidlohr Bueso Cc: Prakash Sangappa Cc: Link: http://lkml.kernel.org/r/e670f327-5cf9-1959-96e4-6dc7cc30d3d5@oracle.com Signed-off-by: Linus Torvalds --- include/linux/fs.h | 10 ++++++++++ include/linux/hugetlb.h | 8 +++++--- 2 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 011af396aa17..7c69dd7c6160 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -518,6 +518,16 @@ static inline void i_mmap_unlock_read(struct address_space *mapping) up_read(&mapping->i_mmap_rwsem); } +static inline void i_mmap_assert_locked(struct address_space *mapping) +{ + lockdep_assert_held(&mapping->i_mmap_rwsem); +} + +static inline void i_mmap_assert_write_locked(struct address_space *mapping) +{ + lockdep_assert_held_write(&mapping->i_mmap_rwsem); +} + /* * Might pages of this file be mapped into userspace? */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 50650d0d01b9..a520bf26e5d8 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -164,7 +164,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz); pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); -int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); +int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long *addr, pte_t *ptep); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, @@ -203,8 +204,9 @@ static inline struct address_space *hugetlb_page_mapping_lock_write( return NULL; } -static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, - pte_t *ptep) +static inline int huge_pmd_unshare(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long *addr, pte_t *ptep) { return 0; } -- cgit v1.2.3 From 4958e4d86ecb011a81f5d80ce2023ef9f10692d8 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Tue, 11 Aug 2020 18:31:48 -0700 Subject: mm: thp: remove debug_cow switch Since commit 3917c80280c93a7123f ("thp: change CoW semantics for anon-THP"), the CoW page fault of THP has been rewritten, debug_cow is not used anymore. So, just remove it. Signed-off-by: Yang Shi Signed-off-by: Andrew Morton Reviewed-by: Zi Yan Cc: Kirill A. Shutemov Link: http://lkml.kernel.org/r/1592270980-116062-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 17c4c4975145..467302056e17 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -181,13 +181,6 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1< Date: Tue, 11 Aug 2020 18:31:51 -0700 Subject: mm/vmstat: add events for THP migration without split Add following new vmstat events which will help in validating THP migration without split. Statistics reported through these new VM events will help in performance debugging. 1. THP_MIGRATION_SUCCESS 2. THP_MIGRATION_FAILURE 3. THP_MIGRATION_SPLIT In addition, these new events also update normal page migration statistics appropriately via PGMIGRATE_SUCCESS and PGMIGRATE_FAILURE. While here, this updates current trace event 'mm_migrate_pages' to accommodate now available THP statistics. [akpm@linux-foundation.org: s/hpage_nr_pages/thp_nr_pages/] [ziy@nvidia.com: v2] Link: http://lkml.kernel.org/r/C5E3C65C-8253-4638-9D3C-71A61858BB8B@nvidia.com [anshuman.khandual@arm.com: s/thp_nr_pages/hpage_nr_pages/] Link: http://lkml.kernel.org/r/1594287583-16568-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Signed-off-by: Zi Yan Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Cc: Hugh Dickins Cc: Matthew Wilcox Cc: Zi Yan Cc: John Hubbard Cc: Naoya Horiguchi Link: http://lkml.kernel.org/r/1594080415-27924-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 24fc7c3ae7d6..2e6ca53b9bbd 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -56,6 +56,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif #ifdef CONFIG_MIGRATION PGMIGRATE_SUCCESS, PGMIGRATE_FAIL, + THP_MIGRATION_SUCCESS, + THP_MIGRATION_FAIL, + THP_MIGRATION_SPLIT, #endif #ifdef CONFIG_COMPACTION COMPACTMIGRATE_SCANNED, COMPACTFREE_SCANNED, -- cgit v1.2.3 From af161bee93332a1ff10ba029f41936d21850ae82 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 11 Aug 2020 18:32:06 -0700 Subject: include/linux/sched/mm.h: optimize current_gfp_context() The current_gfp_context() converts a number of PF_MEMALLOC_* per-process flags into the corresponding GFP_* flags for memory allocation. In that function, current->flags is accessed 3 times. That may lead to duplicated access of the same memory location. This is not usually a problem with minimal debug config options on as the compiler can optimize away the duplicated memory accesses. With most of the debug config options on, however, that may not be the case. For example, the x86-64 object size of the __need_fs_reclaim() in a debug kernel that calls current_gfp_context() was 309 bytes. With this patch applied, the object size is reduced to 202 bytes. This is a saving of 107 bytes and will probably be slightly faster too. Use READ_ONCE() to access current->flags to prevent the compiler from possibly accessing current->flags multiple times. Signed-off-by: Waiman Long Signed-off-by: Andrew Morton Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Mathieu Desnoyers Cc: Michel Lespinasse Link: http://lkml.kernel.org/r/20200618212936.9776-1-longman@redhat.com Signed-off-by: Linus Torvalds --- include/linux/sched/mm.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 85023ddc2dc2..f889e332912f 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -178,14 +178,16 @@ static inline bool in_vfork(struct task_struct *tsk) */ static inline gfp_t current_gfp_context(gfp_t flags) { - if (unlikely(current->flags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) { + unsigned int pflags = READ_ONCE(current->flags); + + if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) { /* * NOIO implies both NOIO and NOFS and it is a weaker context * so always make sure it makes precedence */ - if (current->flags & PF_MEMALLOC_NOIO) + if (pflags & PF_MEMALLOC_NOIO) flags &= ~(__GFP_IO | __GFP_FS); - else if (current->flags & PF_MEMALLOC_NOFS) + else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; } return flags; -- cgit v1.2.3 From 1067b261cc973d68c29de54ef0587c56786e6bd5 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 11 Aug 2020 18:32:27 -0700 Subject: mm: drop duplicated words in Drop the doubled words "used" and "by". Drop the repeated acronym "TLB" and make several other fixes around it. (capital letters, spellos) Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Reviewed-by: SeongJae Park Link: http://lkml.kernel.org/r/2bb6e13e-44df-4920-52d9-4d3539945f73@infradead.org Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 53e97da1e8e2..a124c21e3204 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -804,7 +804,7 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, /* * No-op macros that just return the current protection value. Defined here - * because these macros can be used used even if CONFIG_MMU is not defined. + * because these macros can be used even if CONFIG_MMU is not defined. */ #ifndef pgprot_nx @@ -1234,7 +1234,7 @@ static inline int pmd_trans_unstable(pmd_t *pmd) * Technically a PTE can be PROTNONE even when not doing NUMA balancing but * the only case the kernel cares is for NUMA balancing and is only ever set * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked - * _PAGE_PROTNONE so by by default, implement the helper as "always no". It + * _PAGE_PROTNONE so by default, implement the helper as "always no". It * is the responsibility of the caller to distinguish between PROT_NONE * protections and NUMA hinting fault protections. */ @@ -1318,10 +1318,10 @@ static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) /* * ARCHes with special requirements for evicting THP backing TLB entries can * implement this. Otherwise also, it can help optimize normal TLB flush in - * THP regime. stock flush_tlb_range() typically has optimization to nuke the - * entire TLB TLB if flush span is greater than a threshold, which will - * likely be true for a single huge page. Thus a single thp flush will - * invalidate the entire TLB which is not desitable. + * THP regime. Stock flush_tlb_range() typically has optimization to nuke the + * entire TLB if flush span is greater than a threshold, which will + * likely be true for a single huge page. Thus a single THP flush will + * invalidate the entire TLB which is not desirable. * e.g. see arch/arc: flush_pmd_tlb_range */ #define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) -- cgit v1.2.3 From 11192337206d2211bce3ba4ec1575439b6045654 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 11 Aug 2020 18:32:30 -0700 Subject: mm: drop duplicated words in Drop the doubled words "to" and "the". Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Reviewed-by: SeongJae Park Link: http://lkml.kernel.org/r/d9fae8d6-0d60-4d52-9385-3199ee98de49@infradead.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f6a82f9bccd7..f97b10117d44 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -479,7 +479,7 @@ static inline bool fault_flag_allow_retry_first(unsigned int flags) { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" } /* - * vm_fault is filled by the the pagefault handler and passed to the vma's + * vm_fault is filled by the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * @@ -2599,7 +2599,7 @@ extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); -/* CONFIG_STACK_GROWSUP still needs to to grow downwards at some places */ +/* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */ extern int expand_downwards(struct vm_area_struct *vma, unsigned long address); #if VM_GROWSUP -- cgit v1.2.3 From 3ecabd31341fb4307f156a2bf4467c3f8fa9101b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 11 Aug 2020 18:32:33 -0700 Subject: include/linux/highmem.h: fix duplicated words in a comment Change the doubled word "is" in a comment to "it is". Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Link: http://lkml.kernel.org/r/ad605959-0083-4794-8d31-6b073300dd6f@infradead.org Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index d6e82e3de027..14e6202ce47f 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -73,7 +73,7 @@ static inline void kunmap(struct page *page) * no global lock is needed and because the kmap code must perform a global TLB * invalidation when the kmap pool wraps. * - * However when holding an atomic kmap is is not legal to sleep, so atomic + * However when holding an atomic kmap it is not legal to sleep, so atomic * kmaps are appropriate for short, tight code paths only. * * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap -- cgit v1.2.3 From c82f16b52cb3b50ac1b47e6c590e3dddefc5a97c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 11 Aug 2020 18:32:36 -0700 Subject: include/linux/frontswap.h: drop duplicated word in a comment Drop the doubled word "in" in a comment. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Konrad Rzeszutek Wilk Link: http://lkml.kernel.org/r/3af7ed91-ad62-8445-40a4-9e07a64b9523@infradead.org Signed-off-by: Linus Torvalds --- include/linux/frontswap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index 6d775984905b..b07d88c92bb2 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -10,7 +10,7 @@ /* * Return code to denote that requested number of * frontswap pages are unused(moved to page cache). - * Used in in shmem_unuse and try_to_unuse. + * Used in shmem_unuse and try_to_unuse. */ #define FRONTSWAP_PAGES_UNUSED 2 -- cgit v1.2.3 From 0845f83122d93ae3bafa7ea10209de2148a3b9bc Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 11 Aug 2020 18:32:40 -0700 Subject: include/linux/memcontrol.h: drop duplicate word and fix spello Drop the doubled word "for" in a comment. Fix spello of "incremented". Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Acked-by: Chris Down Cc: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Link: http://lkml.kernel.org/r/b04aa2e4-7c95-12f0-599d-43d07fb28134@infradead.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2c2d301eac33..385237e4cb44 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -65,8 +65,8 @@ struct mem_cgroup_id { /* * Per memcg event counter is incremented at every pagein/pageout. With THP, - * it will be incremated by the number of pages. This counter is used for - * for trigger some periodic events. This is straightforward and better + * it will be incremented by the number of pages. This counter is used + * to trigger some periodic events. This is straightforward and better * than using jiffies etc. to handle periodic memcg event. */ enum mem_cgroup_events_target { -- cgit v1.2.3 From bfe00c5bbd9ee37b99c281429556c335271d027b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Aug 2020 18:33:34 -0700 Subject: syscalls: use uaccess_kernel in addr_limit_user_check Patch series "clean up address limit helpers", v2. In preparation for eventually phasing out direct use of set_fs(), this series removes the segment_eq() arch helper that is only used to implement or duplicate the uaccess_kernel() API, and then adds descriptive helpers to force the kernel address limit. This patch (of 6): Use the uaccess_kernel helper instead of duplicating it. [hch@lst.de: arm: don't call addr_limit_user_check for nommu] Link: http://lkml.kernel.org/r/20200721045834.GA9613@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Tested-by: Guenter Roeck Acked-by: Linus Torvalds Cc: Nick Hu Cc: Greentime Hu Cc: Vincent Chen Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Geert Uytterhoeven Link: http://lkml.kernel.org/r/20200714105505.935079-1-hch@lst.de Link: http://lkml.kernel.org/r/20200710135706.537715-1-hch@lst.de Link: http://lkml.kernel.org/r/20200710135706.537715-2-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a2429d336593..dc2b827c81e5 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -263,7 +263,7 @@ static inline void addr_limit_user_check(void) return; #endif - if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS), + if (CHECK_DATA_CORRUPTION(uaccess_kernel(), "Invalid address limit on user-mode return")) force_sig(SIGKILL); -- cgit v1.2.3 From 428e2976a5bf7e7f5554286d7a5a33b8147b106a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Aug 2020 18:33:44 -0700 Subject: uaccess: remove segment_eq segment_eq is only used to implement uaccess_kernel. Just open code uaccess_kernel in the arch uaccess headers and remove one layer of indirection. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Linus Torvalds Acked-by: Greentime Hu Acked-by: Geert Uytterhoeven Cc: Nick Hu Cc: Vincent Chen Cc: Paul Walmsley Cc: Palmer Dabbelt Link: http://lkml.kernel.org/r/20200710135706.537715-5-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 0a76ddc07d59..5c62d0c6f15b 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -6,8 +6,6 @@ #include #include -#define uaccess_kernel() segment_eq(get_fs(), KERNEL_DS) - #include /* -- cgit v1.2.3 From 3d13f313ce4c34c524ccc37986fe77172f601ff3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Aug 2020 18:33:47 -0700 Subject: uaccess: add force_uaccess_{begin,end} helpers Add helpers to wrap the get_fs/set_fs magic for undoing any damange done by set_fs(KERNEL_DS). There is no real functional benefit, but this documents the intent of these calls better, and will allow stubbing the functions out easily for kernels builds that do not allow address space overrides in the future. [hch@lst.de: drop two incorrect hunks, fix a commit log typo] Link: http://lkml.kernel.org/r/20200714105505.935079-6-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Linus Torvalds Acked-by: Mark Rutland Acked-by: Greentime Hu Acked-by: Geert Uytterhoeven Cc: Nick Hu Cc: Vincent Chen Cc: Paul Walmsley Cc: Palmer Dabbelt Link: http://lkml.kernel.org/r/20200710135706.537715-6-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 5c62d0c6f15b..94b285411659 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -8,6 +8,24 @@ #include +/* + * Force the uaccess routines to be wired up for actual userspace access, + * overriding any possible set_fs(KERNEL_DS) still lingering around. Undone + * using force_uaccess_end below. + */ +static inline mm_segment_t force_uaccess_begin(void) +{ + mm_segment_t fs = get_fs(); + + set_fs(USER_DS); + return fs; +} + +static inline void force_uaccess_end(mm_segment_t oldfs) +{ + set_fs(oldfs); +} + /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and -- cgit v1.2.3 From c5f748e2f2ad970078de11bd6b12bcd81147c636 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 11 Aug 2020 18:33:57 -0700 Subject: include/linux/compiler-clang.h: drop duplicated word in a comment Drop the doubled word "the" in a comment. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Reviewed-by: Nathan Chancellor Link: http://lkml.kernel.org/r/6a18c301-3505-742f-4dd7-0f38d0e537b9@infradead.org Signed-off-by: Linus Torvalds --- include/linux/compiler-clang.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 8a072d00e688..cee0c728d39a 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -40,7 +40,7 @@ #endif /* - * Not all versions of clang implement the the type-generic versions + * Not all versions of clang implement the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements * __has_builtin allowing us to avoid awkward version * checks. Unfortunately, we don't know which version of gcc clang -- cgit v1.2.3 From cd1a406fa46f81b1a859ef874b8413a6fa6ac7e8 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 11 Aug 2020 18:34:00 -0700 Subject: include/linux/exportfs.h: drop duplicated word in a comment Drop the doubled word "a" in a comment. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Alexander Viro Link: http://lkml.kernel.org/r/c61b707a-8fd8-5b1b-aab0-679122881543@infradead.org Signed-off-by: Linus Torvalds --- include/linux/exportfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index d896b8657085..3ceb72b67a7a 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -178,7 +178,7 @@ struct fid { * get_name: * @get_name should find a name for the given @child in the given @parent * directory. The name should be stored in the @name (with the - * understanding that it is already pointing to a a %NAME_MAX+1 sized + * understanding that it is already pointing to a %NAME_MAX+1 sized * buffer. get_name() should return %0 on success, a negative error code * or error. @get_name will be called without @parent->i_mutex held. * -- cgit v1.2.3 From 121ae8da9cd49f7139bf80f26352337458e63fe1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 11 Aug 2020 18:34:04 -0700 Subject: include/linux/async_tx.h: drop duplicated word in a comment Drop the doubled word "the" in a comment. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Dan Williams Link: http://lkml.kernel.org/r/e85802f7-8f48-8b4c-29b3-ea237a2c7ae9@infradead.org Signed-off-by: Linus Torvalds --- include/linux/async_tx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 75e582b8d2d9..4c328fef403c 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -36,7 +36,7 @@ struct dma_chan_ref { /** * async_tx_flags - modifiers for the async_* calls * @ASYNC_TX_XOR_ZERO_DST: this flag must be used for xor operations where the - * the destination address is not a source. The asynchronous case handles this + * destination address is not a source. The asynchronous case handles this * implicitly, the synchronous case needs to zero the destination block. * @ASYNC_TX_XOR_DROP_DST: this flag must be used if the destination address is * also one of the source addresses. In the synchronous case the destination -- cgit v1.2.3 From f48ff83e9c1a8fc2e8bfedb4855933eb1ed159b2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 11 Aug 2020 18:34:07 -0700 Subject: include/linux/xz.h: drop duplicated word Drop the doubled word "than" in a comment. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Cc: Lasse Collin Link: http://lkml.kernel.org/r/05ebba7a-c1e4-01ae-fc7b-15c081b33f3e@infradead.org Signed-off-by: Linus Torvalds --- include/linux/xz.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xz.h b/include/linux/xz.h index 64cffa6ddfce..24ad7d875977 100644 --- a/include/linux/xz.h +++ b/include/linux/xz.h @@ -28,7 +28,7 @@ * enum xz_mode - Operation mode * * @XZ_SINGLE: Single-call mode. This uses less RAM than - * than multi-call modes, because the LZMA2 + * multi-call modes, because the LZMA2 * dictionary doesn't need to be allocated as * part of the decoder state. All required data * structures are allocated at initialization, -- cgit v1.2.3 From 8043fc147a97ec2eefc582487f344f2cbe86d12e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Aug 2020 18:34:10 -0700 Subject: kernel: add a kernel_wait helper Add a helper that waits for a pid and stores the status in the passed in kernel pointer. Use it to fix the usage of kernel_wait4 in call_usermodehelper_exec_sync that only happens to work due to the implicit set_fs(KERNEL_DS) for kernel threads. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Acked-by: "Eric W. Biederman" Cc: Luis Chamberlain Link: http://lkml.kernel.org/r/20200721130449.5008-1-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/sched/task.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index ae3060f0b0c9..a98965007eef 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -88,6 +88,7 @@ struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); +int kernel_wait(pid_t pid, int *stat); extern void free_task(struct task_struct *tsk); -- cgit v1.2.3 From 376653435dacf84a8aca87e66aff94079a817cf2 Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Tue, 11 Aug 2020 18:34:16 -0700 Subject: kernel.h: remove duplicate include of asm/div64.h This seems to have been added inadvertently in commit 72deb455b5ec ("block: remove CONFIG_LBDAF") Fixes: 72deb455b5ec ("block: remove CONFIG_LBDAF") Signed-off-by: Arvind Sankar Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Link: http://lkml.kernel.org/r/20200727034852.2813453-1-nivedita@alum.mit.edu Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7339a00c895e..e19c13616666 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -17,7 +17,6 @@ #include #include #include -#include #define STACK_MAGIC 0xdeadbeef -- cgit v1.2.3 From 7f317d34906c1033f0752fc137dda04e43979bb8 Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Tue, 11 Aug 2020 18:34:19 -0700 Subject: include/: replace HTTP links with HTTPS ones Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Signed-off-by: Alexander A. Klimov Signed-off-by: Andrew Morton Reviewed-by: Kees Cook Link: http://lkml.kernel.org/r/20200726110117.16346-1-grandmaster@al2klimov.de Signed-off-by: Linus Torvalds --- include/linux/btree.h | 2 +- include/linux/delay.h | 2 +- include/linux/dma/k3-psil.h | 2 +- include/linux/dma/k3-udma-glue.h | 2 +- include/linux/dma/ti-cppi5.h | 2 +- include/linux/irqchip/irq-omap-intc.h | 2 +- include/linux/jhash.h | 2 +- include/linux/leds-ti-lmu-common.h | 2 +- include/linux/platform_data/davinci-cpufreq.h | 2 +- include/linux/platform_data/davinci_asp.h | 2 +- include/linux/platform_data/elm.h | 2 +- include/linux/platform_data/gpio-davinci.h | 2 +- include/linux/platform_data/gpmc-omap.h | 2 +- include/linux/platform_data/mtd-davinci-aemif.h | 2 +- include/linux/platform_data/omap-twl4030.h | 2 +- include/linux/platform_data/uio_pruss.h | 2 +- include/linux/platform_data/usb-omap.h | 2 +- include/linux/soc/ti/k3-ringacc.h | 2 +- include/linux/soc/ti/knav_qmss.h | 2 +- include/linux/soc/ti/ti-msgmgr.h | 2 +- include/linux/wkup_m3_ipc.h | 2 +- include/linux/xxhash.h | 2 +- include/linux/xz.h | 2 +- include/linux/zlib.h | 2 +- 24 files changed, 24 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btree.h b/include/linux/btree.h index 68f858c831b1..243ee544397a 100644 --- a/include/linux/btree.h +++ b/include/linux/btree.h @@ -10,7 +10,7 @@ * * A B+Tree is a data structure for looking up arbitrary (currently allowing * unsigned long, u32, u64 and 2 * u64) keys into pointers. The data structure - * is described at http://en.wikipedia.org/wiki/B-tree, we currently do not + * is described at https://en.wikipedia.org/wiki/B-tree, we currently do not * use binary search to find the key on lookups. * * Each B+Tree consists of a head, that contains bookkeeping information and diff --git a/include/linux/delay.h b/include/linux/delay.h index 5e016a4029d9..1d0e2ce6b6d9 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -16,7 +16,7 @@ * 3. CPU clock rate changes. * * Please see this thread: - * http://lists.openwall.net/linux-kernel/2011/01/09/56 + * https://lists.openwall.net/linux-kernel/2011/01/09/56 */ #include diff --git a/include/linux/dma/k3-psil.h b/include/linux/dma/k3-psil.h index 61d5cc0ad601..1962f75fa2d3 100644 --- a/include/linux/dma/k3-psil.h +++ b/include/linux/dma/k3-psil.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com */ #ifndef K3_PSIL_H_ diff --git a/include/linux/dma/k3-udma-glue.h b/include/linux/dma/k3-udma-glue.h index caadbab1632a..5eb34ad973a7 100644 --- a/include/linux/dma/k3-udma-glue.h +++ b/include/linux/dma/k3-udma-glue.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com */ #ifndef K3_UDMA_GLUE_H_ diff --git a/include/linux/dma/ti-cppi5.h b/include/linux/dma/ti-cppi5.h index 579356ae447e..5896441ee604 100644 --- a/include/linux/dma/ti-cppi5.h +++ b/include/linux/dma/ti-cppi5.h @@ -2,7 +2,7 @@ /* * CPPI5 descriptors interface * - * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com */ #ifndef __TI_CPPI5_H__ diff --git a/include/linux/irqchip/irq-omap-intc.h b/include/linux/irqchip/irq-omap-intc.h index 216e5adf80ce..dca379c0d7eb 100644 --- a/include/linux/irqchip/irq-omap-intc.h +++ b/include/linux/irqchip/irq-omap-intc.h @@ -2,7 +2,7 @@ /** * irq-omap-intc.h - INTC Idle Functions * - * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com * * Author: Felipe Balbi */ diff --git a/include/linux/jhash.h b/include/linux/jhash.h index ba2f6a9776b6..19ddd43aee68 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -5,7 +5,7 @@ * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * - * http://burtleburtle.net/bob/hash/ + * https://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * diff --git a/include/linux/leds-ti-lmu-common.h b/include/linux/leds-ti-lmu-common.h index 5eb111f38803..420b61e5a213 100644 --- a/include/linux/leds-ti-lmu-common.h +++ b/include/linux/leds-ti-lmu-common.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ // TI LMU Common Core -// Copyright (C) 2018 Texas Instruments Incorporated - http://www.ti.com/ +// Copyright (C) 2018 Texas Instruments Incorporated - https://www.ti.com/ #ifndef _TI_LMU_COMMON_H_ #define _TI_LMU_COMMON_H_ diff --git a/include/linux/platform_data/davinci-cpufreq.h b/include/linux/platform_data/davinci-cpufreq.h index 3fbf9f2793b5..bc208c64e3d7 100644 --- a/include/linux/platform_data/davinci-cpufreq.h +++ b/include/linux/platform_data/davinci-cpufreq.h @@ -2,7 +2,7 @@ /* * TI DaVinci CPUFreq platform support. * - * Copyright (C) 2009 Texas Instruments, Inc. http://www.ti.com/ + * Copyright (C) 2009 Texas Instruments, Inc. https://www.ti.com/ */ #ifndef _MACH_DAVINCI_CPUFREQ_H diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h index 7fe80f1c7e08..5d1fb0d78a22 100644 --- a/include/linux/platform_data/davinci_asp.h +++ b/include/linux/platform_data/davinci_asp.h @@ -1,7 +1,7 @@ /* * TI DaVinci Audio Serial Port support * - * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/ * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h index 0f491d8abfdd..3cc78f0447b1 100644 --- a/include/linux/platform_data/elm.h +++ b/include/linux/platform_data/elm.h @@ -2,7 +2,7 @@ /* * BCH Error Location Module * - * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/ */ #ifndef __ELM_H diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index a93841bfb9f7..e182a46e609f 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -1,7 +1,7 @@ /* * DaVinci GPIO Platform Related Defines * - * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2013 Texas Instruments Incorporated - https://www.ti.com/ * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as diff --git a/include/linux/platform_data/gpmc-omap.h b/include/linux/platform_data/gpmc-omap.h index ef663e570552..c9cc4e32435d 100644 --- a/include/linux/platform_data/gpmc-omap.h +++ b/include/linux/platform_data/gpmc-omap.h @@ -2,7 +2,7 @@ /* * OMAP GPMC Platform data * - * Copyright (C) 2014 Texas Instruments, Inc. - http://www.ti.com + * Copyright (C) 2014 Texas Instruments, Inc. - https://www.ti.com * Roger Quadros */ diff --git a/include/linux/platform_data/mtd-davinci-aemif.h b/include/linux/platform_data/mtd-davinci-aemif.h index a403dd51dacc..a49826214a39 100644 --- a/include/linux/platform_data/mtd-davinci-aemif.h +++ b/include/linux/platform_data/mtd-davinci-aemif.h @@ -1,7 +1,7 @@ /* * TI DaVinci AEMIF support * - * Copyright 2010 (C) Texas Instruments, Inc. http://www.ti.com/ + * Copyright 2010 (C) Texas Instruments, Inc. https://www.ti.com/ * * This file is licensed under the terms of the GNU General Public License * version 2. This program is licensed "as is" without any warranty of any diff --git a/include/linux/platform_data/omap-twl4030.h b/include/linux/platform_data/omap-twl4030.h index 8419c8caf54e..0dd851ea1c72 100644 --- a/include/linux/platform_data/omap-twl4030.h +++ b/include/linux/platform_data/omap-twl4030.h @@ -3,7 +3,7 @@ * omap-twl4030.h - ASoC machine driver for TI SoC based boards with twl4030 * codec, header. * - * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com * All rights reserved. * * Author: Peter Ujfalusi diff --git a/include/linux/platform_data/uio_pruss.h b/include/linux/platform_data/uio_pruss.h index 3d47d219827f..31f2e22661bc 100644 --- a/include/linux/platform_data/uio_pruss.h +++ b/include/linux/platform_data/uio_pruss.h @@ -3,7 +3,7 @@ * * Platform data for uio_pruss driver * - * Copyright (C) 2010-11 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2010-11 Texas Instruments Incorporated - https://www.ti.com/ * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as diff --git a/include/linux/platform_data/usb-omap.h b/include/linux/platform_data/usb-omap.h index fa579b4c666b..5e70d667031c 100644 --- a/include/linux/platform_data/usb-omap.h +++ b/include/linux/platform_data/usb-omap.h @@ -1,7 +1,7 @@ /* * usb-omap.h - Platform data for the various OMAP USB IPs * - * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com * * This software is distributed under the terms of the GNU General Public * License ("GPL") version 2, as published by the Free Software Foundation. diff --git a/include/linux/soc/ti/k3-ringacc.h b/include/linux/soc/ti/k3-ringacc.h index 7ac115432fa1..5a472eca5ee4 100644 --- a/include/linux/soc/ti/k3-ringacc.h +++ b/include/linux/soc/ti/k3-ringacc.h @@ -2,7 +2,7 @@ /* * K3 Ring Accelerator (RA) subsystem interface * - * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com */ #ifndef __SOC_TI_K3_RINGACC_API_H_ diff --git a/include/linux/soc/ti/knav_qmss.h b/include/linux/soc/ti/knav_qmss.h index 9745df6ed9d3..c75ef99c99ca 100644 --- a/include/linux/soc/ti/knav_qmss.h +++ b/include/linux/soc/ti/knav_qmss.h @@ -1,7 +1,7 @@ /* * Keystone Navigator Queue Management Sub-System header * - * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com * Author: Sandeep Nair * Cyril Chemparathy * Santosh Shilimkar diff --git a/include/linux/soc/ti/ti-msgmgr.h b/include/linux/soc/ti/ti-msgmgr.h index eac8e0c6fe11..1f6e76d423cf 100644 --- a/include/linux/soc/ti/ti-msgmgr.h +++ b/include/linux/soc/ti/ti-msgmgr.h @@ -1,7 +1,7 @@ /* * Texas Instruments' Message Manager * - * Copyright (C) 2015-2016 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2015-2016 Texas Instruments Incorporated - https://www.ti.com/ * Nishanth Menon * * This program is free software; you can redistribute it and/or modify diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h index e497e621dbb7..3f496967b538 100644 --- a/include/linux/wkup_m3_ipc.h +++ b/include/linux/wkup_m3_ipc.h @@ -1,7 +1,7 @@ /* * TI Wakeup M3 for AMx3 SoCs Power Management Routines * - * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/ * Dave Gerlach * * This program is free software; you can redistribute it and/or diff --git a/include/linux/xxhash.h b/include/linux/xxhash.h index 52b073fea17f..df42511438d0 100644 --- a/include/linux/xxhash.h +++ b/include/linux/xxhash.h @@ -34,7 +34,7 @@ * ("BSD"). * * You can contact the author at: - * - xxHash homepage: http://cyan4973.github.io/xxHash/ + * - xxHash homepage: https://cyan4973.github.io/xxHash/ * - xxHash source repository: https://github.com/Cyan4973/xxHash */ diff --git a/include/linux/xz.h b/include/linux/xz.h index 24ad7d875977..9884c8440188 100644 --- a/include/linux/xz.h +++ b/include/linux/xz.h @@ -2,7 +2,7 @@ * XZ decompressor * * Authors: Lasse Collin - * Igor Pavlov + * Igor Pavlov * * This file has been put into the public domain. * You can do whatever you want with this file. diff --git a/include/linux/zlib.h b/include/linux/zlib.h index c757d848a758..78ede944c082 100644 --- a/include/linux/zlib.h +++ b/include/linux/zlib.h @@ -23,7 +23,7 @@ The data format used by the zlib library is described by RFCs (Request for - Comments) 1950 to 1952 in the files http://www.ietf.org/rfc/rfc1950.txt + Comments) 1950 to 1952 in the files https://www.ietf.org/rfc/rfc1950.txt (zlib format), rfc1951.txt (deflate format) and rfc1952.txt (gzip format). */ -- cgit v1.2.3 From 9e58c5e2fcd8d8d8820ea277e0f577f563eed1f1 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 11 Aug 2020 18:34:23 -0700 Subject: include/linux/poison.h: remove obsolete comment When the definition was changed, the comment became stale. Just remove it since there isn't anything useful to say here. Fixes: b8a0255db958 ("include/linux/poison.h: use POISON_POINTER_DELTA for poison pointers") Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Cc: Vasily Kulikov Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20200730174108.GJ23808@casper.infradead.org Signed-off-by: Linus Torvalds --- include/linux/poison.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/poison.h b/include/linux/poison.h index df34330b4e34..dc8ae5d8db03 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -24,10 +24,6 @@ #define LIST_POISON2 ((void *) 0x122 + POISON_POINTER_DELTA) /********** include/linux/timer.h **********/ -/* - * Magic number "tsta" to indicate a static timer initializer - * for the object debugging code. - */ #define TIMER_ENTRY_STATIC ((void *) 0x300 + POISON_POINTER_DELTA) /********** mm/page_poison.c **********/ -- cgit v1.2.3 From 25fd529c34d063d1bef23742f2e8f8341c639dc3 Mon Sep 17 00:00:00 2001 From: Luc Van Oostenryck Date: Tue, 11 Aug 2020 18:34:26 -0700 Subject: sparse: group the defines by functionality By popular demand, reorder the defines for sparse annotations and group them by functionality. Signed-off-by: Luc Van Oostenryck Signed-off-by: Andrew Morton Acked-by: Miguel Ojeda Cc: Geert Uytterhoeven Link: lore.kernel.org/r/CAMuHMdWQsirja-h3wBcZezk+H2Q_HShhAks8Hc8ps5fTAp=ObQ@mail.gmail.com Link: http://lkml.kernel.org/r/20200621143652.53798-1-luc.vanoostenryck@gmail.com Signed-off-by: Linus Torvalds --- include/linux/compiler_types.h | 44 ++++++++++++++++++++++++------------------ 1 file changed, 25 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 2e231ba8fe3f..4b33cb385f96 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -5,48 +5,54 @@ #ifndef __ASSEMBLY__ #ifdef __CHECKER__ +/* address spaces */ # define __kernel __attribute__((address_space(0))) # define __user __attribute__((noderef, address_space(__user))) -# define __safe __attribute__((safe)) -# define __force __attribute__((force)) -# define __nocast __attribute__((nocast)) # define __iomem __attribute__((noderef, address_space(__iomem))) +# define __percpu __attribute__((noderef, address_space(__percpu))) +# define __rcu __attribute__((noderef, address_space(__rcu))) +extern void __chk_user_ptr(const volatile void __user *); +extern void __chk_io_ptr(const volatile void __iomem *); +/* context/locking */ # define __must_hold(x) __attribute__((context(x,1,1))) # define __acquires(x) __attribute__((context(x,0,1))) # define __releases(x) __attribute__((context(x,1,0))) # define __acquire(x) __context__(x,1) # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) -# define __percpu __attribute__((noderef, address_space(__percpu))) -# define __rcu __attribute__((noderef, address_space(__rcu))) +/* other */ +# define __force __attribute__((force)) +# define __nocast __attribute__((nocast)) +# define __safe __attribute__((safe)) # define __private __attribute__((noderef)) -extern void __chk_user_ptr(const volatile void __user *); -extern void __chk_io_ptr(const volatile void __iomem *); # define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member)) #else /* __CHECKER__ */ +/* address spaces */ +# define __kernel # ifdef STRUCTLEAK_PLUGIN -# define __user __attribute__((user)) +# define __user __attribute__((user)) # else # define __user # endif -# define __kernel -# define __safe -# define __force -# define __nocast # define __iomem -# define __chk_user_ptr(x) (void)0 -# define __chk_io_ptr(x) (void)0 -# define __builtin_warning(x, y...) (1) +# define __percpu +# define __rcu +# define __chk_user_ptr(x) (void)0 +# define __chk_io_ptr(x) (void)0 +/* context/locking */ # define __must_hold(x) # define __acquires(x) # define __releases(x) -# define __acquire(x) (void)0 -# define __release(x) (void)0 +# define __acquire(x) (void)0 +# define __release(x) (void)0 # define __cond_lock(x,c) (c) -# define __percpu -# define __rcu +/* other */ +# define __force +# define __nocast +# define __safe # define __private # define ACCESS_PRIVATE(p, member) ((p)->member) +# define __builtin_warning(x, y...) (1) #endif /* __CHECKER__ */ /* Indirect macros required for expanded argument pasting, eg. __LINE__. */ -- cgit v1.2.3 From 0a650e472d2039a5f768acd82f2a7068bf338dfd Mon Sep 17 00:00:00 2001 From: Luc Van Oostenryck Date: Tue, 11 Aug 2020 18:34:35 -0700 Subject: lib/generic-radix-tree.c: remove unneeded __rcu struct __genradix is defined as having its member 'root' annotated as __rcu. But in the corresponding API RCU is not used. Sparse reports this type mismatch as: lib/generic-radix-tree.c:56:35: warning: incorrect type in initializer (different address spaces) lib/generic-radix-tree.c:56:35: expected struct genradix_root *r lib/generic-radix-tree.c:56:35: got struct genradix_root [noderef] *__val with 6 other ones. So, correct root's type by removing this unneeded __rcu. Signed-off-by: Luc Van Oostenryck Signed-off-by: Andrew Morton Cc: Kent Overstreet Link: http://lkml.kernel.org/r/20200621161745.55396-1-luc.vanoostenryck@gmail.com Signed-off-by: Linus Torvalds --- include/linux/generic-radix-tree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h index 02393c0c98f9..bfd00320c7f3 100644 --- a/include/linux/generic-radix-tree.h +++ b/include/linux/generic-radix-tree.h @@ -44,7 +44,7 @@ struct genradix_root; struct __genradix { - struct genradix_root __rcu *root; + struct genradix_root *root; }; /* -- cgit v1.2.3 From b642e44e8ab335868b549fe5753b783ca47bf3a3 Mon Sep 17 00:00:00 2001 From: Kars Mulder Date: Tue, 11 Aug 2020 18:34:53 -0700 Subject: kstrto*: correct documentation references to simple_strto*() The documentation of the kstrto*() functions reference the simple_strtoull function by "used as a replacement for [the obsolete] simple_strtoull". All these functions describes themselves as replacements for the function simple_strtoull, even though a function like kstrtol() would be more aptly described as a replacement of simple_strtol(). Fix these references by making the documentation of kstrto*() reference the closest simple_strto*() equivalent available. The functions kstrto[u]int() do not have direct simple_strto[u]int() equivalences, so these are made to refer to simple_strto[u]l() instead. Furthermore, add parentheses after function names, as is standard in kernel documentation. Fixes: 4c925d6031f71 ("kstrto*: add documentation") Signed-off-by: Kars Mulder Signed-off-by: Andrew Morton Reviewed-by: Andy Shevchenko Cc: Eldad Zack Cc: Miguel Ojeda Cc: Geert Uytterhoeven Cc: Mans Rullgard Cc: Petr Mladek Link: http://lkml.kernel.org/r/1ee1-5f234c00-f3-165a6440@234394593 Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e19c13616666..47b1dad63ffc 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -346,7 +346,7 @@ int __must_check kstrtoll(const char *s, unsigned int base, long long *res); * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Used as a replacement for the simple_strtoull. Return code must be checked. + * Used as a replacement for the simple_strtoul(). Return code must be checked. */ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) { @@ -374,7 +374,7 @@ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsign * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Used as a replacement for the simple_strtoull. Return code must be checked. + * Used as a replacement for the simple_strtol(). Return code must be checked. */ static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) { -- cgit v1.2.3 From ef0f2685336bbc334e8b6997ce9b155e5f7edd31 Mon Sep 17 00:00:00 2001 From: Kars Mulder Date: Tue, 11 Aug 2020 18:34:56 -0700 Subject: kstrto*: do not describe simple_strto*() as obsolete/replaced The documentation of the kstrto*() functions describes kstrto*() as "replacements" of the "obsolete" simple_strto*() functions. Both of these terms are inaccurate: they're not replacements because they have different behaviour, and the simple_strto*() are not obsolete because there are cases where they have benefits over kstrto*(). Remove usage of the terms "replacement" and "obsolete" in reference to simple_strto*(), and instead use the term "preferred over". Fixes: 4c925d6031f71 ("kstrto*: add documentation") Fixes: 885e68e8b7b13 ("kernel.h: update comment about simple_strto() functions") Signed-off-by: Kars Mulder Signed-off-by: Andrew Morton Reviewed-by: Andy Shevchenko Cc: Eldad Zack Cc: Miguel Ojeda Cc: Geert Uytterhoeven Cc: Mans Rullgard Cc: Petr Mladek Link: http://lkml.kernel.org/r/29b9-5f234c80-13-4e3aa200@244003027 Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 47b1dad63ffc..92517ae53e7c 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -346,7 +346,7 @@ int __must_check kstrtoll(const char *s, unsigned int base, long long *res); * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Used as a replacement for the simple_strtoul(). Return code must be checked. + * Preferred over simple_strtoul(). Return code must be checked. */ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) { @@ -374,7 +374,7 @@ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsign * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Used as a replacement for the simple_strtol(). Return code must be checked. + * Preferred over simple_strtol(). Return code must be checked. */ static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) { -- cgit v1.2.3 From 0935288c6e008c0682ab6171fb5605dcc049e7bd Mon Sep 17 00:00:00 2001 From: Vijay Balakrishna Date: Tue, 11 Aug 2020 18:36:33 -0700 Subject: kdump: append kernel build-id string to VMCOREINFO Make kernel GNU build-id available in VMCOREINFO. Having build-id in VMCOREINFO facilitates presenting appropriate kernel namelist image with debug information file to kernel crash dump analysis tools. Currently VMCOREINFO lacks uniquely identifiable key for crash analysis automation. Regarding if this patch is necessary or matching of linux_banner and OSRELEASE in VMCOREINFO employed by crash(8) meets the need -- IMO, build-id approach more foolproof, in most instances it is a cryptographic hash generated using internal code/ELF bits unlike kernel version string upon which linux_banner is based that is external to the code. I feel each is intended for a different purpose. Also OSRELEASE is not suitable when two different kernel builds from same version with different features enabled. Currently for most linux (and non-linux) systems build-id can be extracted using standard methods for file types such as user mode crash dumps, shared libraries, loadable kernel modules etc., This is an exception for linux kernel dump. Having build-id in VMCOREINFO brings some uniformity for automation tools. Tyler said: : I think this is a nice improvement over today's linux_banner approach for : correlating vmlinux to a kernel dump. : : The elf notes parsing in this patch lines up with what is described in in : the "Notes (Nhdr)" section of the elf(5) man page. : : BUILD_ID_MAX is sufficient to hold a sha1 build-id, which is the default : build-id type today in GNU ld(2). It is also sufficient to hold the : "fast" build-id, which is the default build-id type today in LLVM lld(2). Signed-off-by: Vijay Balakrishna Signed-off-by: Andrew Morton Reviewed-by: Tyler Hicks Acked-by: Baoquan He Cc: Dave Young Cc: Vivek Goyal Link: http://lkml.kernel.org/r/1591849672-34104-1-git-send-email-vijayb@linux.microsoft.com Signed-off-by: Linus Torvalds --- include/linux/crash_core.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 525510a9f965..6594dbc34a37 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -38,6 +38,8 @@ phys_addr_t paddr_vmcoreinfo_note(void); #define VMCOREINFO_OSRELEASE(value) \ vmcoreinfo_append_str("OSRELEASE=%s\n", value) +#define VMCOREINFO_BUILD_ID(value) \ + vmcoreinfo_append_str("BUILD-ID=%s\n", value) #define VMCOREINFO_PAGESIZE(value) \ vmcoreinfo_append_str("PAGESIZE=%ld\n", value) #define VMCOREINFO_SYMBOL(name) \ @@ -64,6 +66,10 @@ extern unsigned char *vmcoreinfo_data; extern size_t vmcoreinfo_size; extern u32 *vmcoreinfo_note; +/* raw contents of kernel .notes section */ +extern const void __start_notes __weak; +extern const void __stop_notes __weak; + Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len); void final_note(Elf_Word *buf); -- cgit v1.2.3 From 79076e1241bb3bf02d0aac7d39120d8161fe07b1 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Tue, 11 Aug 2020 18:36:46 -0700 Subject: kernel/panic.c: make oops_may_print() return bool The return value of oops_may_print() is true or false, so change its type to reflect that. Signed-off-by: Tiezhu Yang Signed-off-by: Andrew Morton Reviewed-by: Kees Cook Cc: Xuefeng Li Link: http://lkml.kernel.org/r/1591103358-32087-1-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 92517ae53e7c..211005163682 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -322,7 +322,7 @@ void nmi_panic(struct pt_regs *regs, const char *msg); extern void oops_enter(void); extern void oops_exit(void); void print_oops_end_marker(void); -extern int oops_may_print(void); +extern bool oops_may_print(void); void do_exit(long error_code) __noreturn; void complete_and_exit(struct completion *, long) __noreturn; -- cgit v1.2.3 From 63037f74725ddd8a767ed2ad0369e60a3bf1f2ce Mon Sep 17 00:00:00 2001 From: Yue Hu Date: Tue, 11 Aug 2020 18:36:53 -0700 Subject: panic: make print_oops_end_marker() static Since print_oops_end_marker() is not used externally, also remove it in kernel.h at the same time. Signed-off-by: Yue Hu Signed-off-by: Andrew Morton Cc: Kees Cook Link: http://lkml.kernel.org/r/20200724011516.12756-1-zbestahu@gmail.com Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 211005163682..500def620d8f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -321,7 +321,6 @@ void panic(const char *fmt, ...) __noreturn __cold; void nmi_panic(struct pt_regs *regs, const char *msg); extern void oops_enter(void); extern void oops_exit(void); -void print_oops_end_marker(void); extern bool oops_may_print(void); void do_exit(long error_code) __noreturn; void complete_and_exit(struct completion *, long) __noreturn; -- cgit v1.2.3 From b4b382238ed2f94f0d3860f9120b66404fa99463 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 11 Aug 2020 18:37:14 -0700 Subject: mm/migrate: move migration helper from .h to .c It's not performance sensitive function. Move it to .c. This is a preparation step for future change. Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Acked-by: Mike Kravetz Acked-by: Michal Hocko Cc: Christoph Hellwig Cc: Naoya Horiguchi Cc: Roman Gushchin Link: http://lkml.kernel.org/r/1594622517-20681-3-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 33 +++++---------------------------- 1 file changed, 5 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 540998d9810b..abeb4b15b297 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -31,34 +31,6 @@ enum migrate_reason { /* In mm/debug.c; also keep sync with include/trace/events/migrate.h */ extern const char *migrate_reason_names[MR_TYPES]; -static inline struct page *new_page_nodemask(struct page *page, - int preferred_nid, nodemask_t *nodemask) -{ - gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL; - unsigned int order = 0; - struct page *new_page = NULL; - - if (PageHuge(page)) - return alloc_huge_page_nodemask(page_hstate(compound_head(page)), - preferred_nid, nodemask); - - if (PageTransHuge(page)) { - gfp_mask |= GFP_TRANSHUGE; - order = HPAGE_PMD_ORDER; - } - - if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE)) - gfp_mask |= __GFP_HIGHMEM; - - new_page = __alloc_pages_nodemask(gfp_mask, order, - preferred_nid, nodemask); - - if (new_page && PageTransHuge(new_page)) - prep_transhuge_page(new_page); - - return new_page; -} - #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); @@ -67,6 +39,8 @@ extern int migrate_page(struct address_space *mapping, enum migrate_mode mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason); +extern struct page *new_page_nodemask(struct page *page, + int preferred_nid, nodemask_t *nodemask); extern int isolate_movable_page(struct page *page, isolate_mode_t mode); extern void putback_movable_page(struct page *page); @@ -85,6 +59,9 @@ static inline int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason) { return -ENOSYS; } +static inline struct page *new_page_nodemask(struct page *page, + int preferred_nid, nodemask_t *nodemask) + { return NULL; } static inline int isolate_movable_page(struct page *page, isolate_mode_t mode) { return -EBUSY; } -- cgit v1.2.3 From d92bbc2719bd2be237ee336113b63492a6baca3b Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 11 Aug 2020 18:37:17 -0700 Subject: mm/hugetlb: unify migration callbacks There is no difference between two migration callback functions, alloc_huge_page_node() and alloc_huge_page_nodemask(), except __GFP_THISNODE handling. It's redundant to have two almost similar functions in order to handle this flag. So, this patch tries to remove one by introducing a new argument, gfp_mask, to alloc_huge_page_nodemask(). After introducing gfp_mask argument, it's caller's job to provide correct gfp_mask. So, every callsites for alloc_huge_page_nodemask() are changed to provide gfp_mask. Note that it's safe to remove a node id check in alloc_huge_page_node() since there is no caller passing NUMA_NO_NODE as a node id. Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Reviewed-by: Mike Kravetz Reviewed-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Christoph Hellwig Cc: Naoya Horiguchi Cc: Roman Gushchin Link: http://lkml.kernel.org/r/1594622517-20681-4-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index a520bf26e5d8..3517edde681e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -10,6 +10,7 @@ #include #include #include +#include struct ctl_table; struct user_struct; @@ -506,9 +507,8 @@ struct huge_bootmem_page { struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); -struct page *alloc_huge_page_node(struct hstate *h, int nid); struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask); + nodemask_t *nmask, gfp_t gfp_mask); struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, @@ -694,6 +694,15 @@ static inline bool hugepage_movable_supported(struct hstate *h) return true; } +/* Movability of hugepages depends on migration support. */ +static inline gfp_t htlb_alloc_mask(struct hstate *h) +{ + if (hugepage_movable_supported(h)) + return GFP_HIGHUSER_MOVABLE; + else + return GFP_HIGHUSER; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { @@ -761,13 +770,9 @@ static inline struct page *alloc_huge_page(struct vm_area_struct *vma, return NULL; } -static inline struct page *alloc_huge_page_node(struct hstate *h, int nid) -{ - return NULL; -} - static inline struct page * -alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask) +alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask) { return NULL; } @@ -880,6 +885,11 @@ static inline bool hugepage_movable_supported(struct hstate *h) return false; } +static inline gfp_t htlb_alloc_mask(struct hstate *h) +{ + return 0; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { -- cgit v1.2.3 From 19fc7bed252c16ace29491e4cfa2bafb264eb505 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 11 Aug 2020 18:37:25 -0700 Subject: mm/migrate: introduce a standard migration target allocation function There are some similar functions for migration target allocation. Since there is no fundamental difference, it's better to keep just one rather than keeping all variants. This patch implements base migration target allocation function. In the following patches, variants will be converted to use this function. Changes should be mechanical, but, unfortunately, there are some differences. First, some callers' nodemask is assgined to NULL since NULL nodemask will be considered as all available nodes, that is, &node_states[N_MEMORY]. Second, for hugetlb page allocation, gfp_mask is redefined as regular hugetlb allocation gfp_mask plus __GFP_THISNODE if user provided gfp_mask has it. This is because future caller of this function requires to set this node constaint. Lastly, if provided nodeid is NUMA_NO_NODE, nodeid is set up to the node where migration source lives. It helps to remove simple wrappers for setting up the nodeid. Note that PageHighmem() call in previous function is changed to open-code "is_highmem_idx()" since it provides more readability. [akpm@linux-foundation.org: tweak patch title, per Vlastimil] [akpm@linux-foundation.org: fix typo in comment] Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Acked-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Christoph Hellwig Cc: Mike Kravetz Cc: Naoya Horiguchi Cc: Roman Gushchin Link: http://lkml.kernel.org/r/1594622517-20681-6-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 15 +++++++++++++++ include/linux/migrate.h | 9 +++++---- 2 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3517edde681e..30e1f14119c8 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -703,6 +703,16 @@ static inline gfp_t htlb_alloc_mask(struct hstate *h) return GFP_HIGHUSER; } +static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) +{ + gfp_t modified_mask = htlb_alloc_mask(h); + + /* Some callers might want to enforce node */ + modified_mask |= (gfp_mask & __GFP_THISNODE); + + return modified_mask; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { @@ -890,6 +900,11 @@ static inline gfp_t htlb_alloc_mask(struct hstate *h) return 0; } +static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) +{ + return 0; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { diff --git a/include/linux/migrate.h b/include/linux/migrate.h index abeb4b15b297..0f8d1583fa8e 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -10,6 +10,8 @@ typedef struct page *new_page_t(struct page *page, unsigned long private); typedef void free_page_t(struct page *page, unsigned long private); +struct migration_target_control; + /* * Return values from addresss_space_operations.migratepage(): * - negative errno on page migration failure; @@ -39,8 +41,7 @@ extern int migrate_page(struct address_space *mapping, enum migrate_mode mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason); -extern struct page *new_page_nodemask(struct page *page, - int preferred_nid, nodemask_t *nodemask); +extern struct page *alloc_migration_target(struct page *page, unsigned long private); extern int isolate_movable_page(struct page *page, isolate_mode_t mode); extern void putback_movable_page(struct page *page); @@ -59,8 +60,8 @@ static inline int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason) { return -ENOSYS; } -static inline struct page *new_page_nodemask(struct page *page, - int preferred_nid, nodemask_t *nodemask) +static inline struct page *alloc_migration_target(struct page *page, + unsigned long private) { return NULL; } static inline int isolate_movable_page(struct page *page, isolate_mode_t mode) { return -EBUSY; } -- cgit v1.2.3 From 41b4dc14ee807cb1bd15e67cad287534046f92dc Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 11 Aug 2020 18:37:34 -0700 Subject: mm/gup: restrict CMA region by using allocation scope API We have well defined scope API to exclude CMA region. Use it rather than manipulating gfp_mask manually. With this change, we can now restore __GFP_MOVABLE for gfp_mask like as usual migration target allocation. It would result in that the ZONE_MOVABLE is also searched by page allocator. For hugetlb, gfp_mask is redefined since it has a regular allocation mask filter for migration target. __GPF_NOWARN is added to hugetlb gfp_mask filter since a new user for gfp_mask filter, gup, want to be silent when allocation fails. Note that this can be considered as a fix for the commit 9a4e9f3b2d73 ("mm: update get_user_pages_longterm to migrate pages allocated from CMA region"). However, "Fixes" tag isn't added here since it is just suboptimal but it doesn't cause any problem. Suggested-by: Michal Hocko Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Acked-by: Vlastimil Babka Cc: Christoph Hellwig Cc: Roman Gushchin Cc: Mike Kravetz Cc: Naoya Horiguchi Cc: "Aneesh Kumar K . V" Link: http://lkml.kernel.org/r/1596180906-8442-1-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 30e1f14119c8..d86c82749836 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -710,6 +710,8 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) /* Some callers might want to enforce node */ modified_mask |= (gfp_mask & __GFP_THISNODE); + modified_mask |= (gfp_mask & __GFP_NOWARN); + return modified_mask; } -- cgit v1.2.3 From bbe88753bd42b1faf1458dde8f58ff1239990436 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 11 Aug 2020 18:37:38 -0700 Subject: mm/hugetlb: make hugetlb migration callback CMA aware new_non_cma_page() in gup.c requires to allocate the new page that is not on the CMA area. new_non_cma_page() implements it by using allocation scope APIs. However, there is a work-around for hugetlb. Normal hugetlb page allocation API for migration is alloc_huge_page_nodemask(). It consists of two steps. First is dequeing from the pool. Second is, if there is no available page on the queue, allocating by using the page allocator. new_non_cma_page() can't use this API since first step (deque) isn't aware of scope API to exclude CMA area. So, new_non_cma_page() exports hugetlb internal function for the second step, alloc_migrate_huge_page(), to global scope and uses it directly. This is suboptimal since hugetlb pages on the queue cannot be utilized. This patch tries to fix this situation by making the deque function on hugetlb CMA aware. In the deque function, CMA memory is skipped if PF_MEMALLOC_NOCMA flag is found. Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Acked-by: Mike Kravetz Acked-by: Vlastimil Babka Acked-by: Michal Hocko Cc: "Aneesh Kumar K . V" Cc: Christoph Hellwig Cc: Naoya Horiguchi Cc: Roman Gushchin Link: http://lkml.kernel.org/r/1596180906-8442-2-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d86c82749836..d5cc5f802dd4 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -511,8 +511,6 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); -struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, - int nid, nodemask_t *nmask); int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); -- cgit v1.2.3 From bce617edecada007aee8610fbe2c14d10b8de2f6 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Tue, 11 Aug 2020 18:37:44 -0700 Subject: mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds Signed-off-by: Peter Xu Signed-off-by: Andrew Morton Cc: Albert Ou Cc: Alexander Gordeev Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Brian Cain Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Chris Zankel Cc: Dave Hansen Cc: David S. Miller Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Greentime Hu Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: James E.J. Bottomley Cc: John Hubbard Cc: Jonas Bonn Cc: Ley Foon Tan Cc: "Luck, Tony" Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Nick Hu Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Richard Henderson Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vincent Chen Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f97b10117d44..ec0ffb423769 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -38,6 +38,7 @@ struct file_ra_state; struct user_struct; struct writeback_control; struct bdi_writeback; +struct pt_regs; void init_mm_internals(void); @@ -1658,7 +1659,8 @@ int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, - unsigned long address, unsigned int flags); + unsigned long address, unsigned int flags, + struct pt_regs *regs); extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); @@ -1668,7 +1670,8 @@ void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); #else static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma, - unsigned long address, unsigned int flags) + unsigned long address, unsigned int flags, + struct pt_regs *regs) { /* should never happen if there's no MMU */ BUG(); -- cgit v1.2.3 From 64019a2e467a288a16b65ab55ddcbf58c1b00187 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Tue, 11 Aug 2020 18:39:01 -0700 Subject: mm/gup: remove task_struct pointer for all gup code After the cleanup of page fault accounting, gup does not need to pass task_struct around any more. Remove that parameter in the whole gup stack. Signed-off-by: Peter Xu Signed-off-by: Andrew Morton Reviewed-by: John Hubbard Link: http://lkml.kernel.org/r/20200707225021.200906-26-peterx@redhat.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ec0ffb423769..e7602a3bcef1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1661,7 +1661,7 @@ int invalidate_inode_page(struct page *page); extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs); -extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, +extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); void unmap_mapping_pages(struct address_space *mapping, @@ -1677,8 +1677,7 @@ static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma, BUG(); return VM_FAULT_SIGBUS; } -static inline int fixup_user_fault(struct task_struct *tsk, - struct mm_struct *mm, unsigned long address, +static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ @@ -1704,11 +1703,11 @@ extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); -long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, +long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); -long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, +long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); -- cgit v1.2.3 From 2404b73c3f1a5f15726c6ecd226b56f6f992767f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 10 Aug 2020 13:52:15 +0200 Subject: netfilter: avoid ipv6 -> nf_defrag_ipv6 module dependency nf_ct_frag6_gather is part of nf_defrag_ipv6.ko, not ipv6 core. The current use of the netfilter ipv6 stub indirections causes a module dependency between ipv6 and nf_defrag_ipv6. This prevents nf_defrag_ipv6 module from being removed because ipv6 can't be unloaded. Remove the indirection and always use a direct call. This creates a depency from nf_conntrack_bridge to nf_defrag_ipv6 instead: modinfo nf_conntrack depends: nf_conntrack,nf_defrag_ipv6,bridge .. and nf_conntrack already depends on nf_defrag_ipv6 anyway. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index aac42c28fe62..9b67394471e1 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -58,7 +58,6 @@ struct nf_ipv6_ops { int (*output)(struct net *, struct sock *, struct sk_buff *)); int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); #if IS_MODULE(CONFIG_IPV6) - int (*br_defrag)(struct net *net, struct sk_buff *skb, u32 user); int (*br_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, @@ -117,23 +116,6 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, #include -static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb, - u32 user) -{ -#if IS_MODULE(CONFIG_IPV6) - const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); - - if (!v6_ops) - return 1; - - return v6_ops->br_defrag(net, skb, user); -#elif IS_BUILTIN(CONFIG_IPV6) - return nf_ct_frag6_gather(net, skb, user); -#else - return 1; -#endif -} - int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, -- cgit v1.2.3 From 466a62d7642f02f36d37d9b30c19a725538a01ca Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 11 Jun 2020 07:35:33 +0100 Subject: mfd: core: Make a best effort attempt to match devices with the correct of_nodes Currently, when a child platform device (sometimes referred to as a sub-device) is registered via the Multi-Functional Device (MFD) API, the framework attempts to match the newly registered platform device with its associated Device Tree (OF) node. Until now, the device has been allocated the first node found with an identical OF compatible string. Unfortunately, if there are, say for example '3' devices which are to be handled by the same driver and therefore have the same compatible string, each of them will be allocated a pointer to the *first* node. An example Device Tree entry might look like this: mfd_of_test { compatible = "mfd,of-test-parent"; #address-cells = <0x02>; #size-cells = <0x02>; child@aaaaaaaaaaaaaaaa { compatible = "mfd,of-test-child"; reg = <0xaaaaaaaa 0xaaaaaaaa 0 0x11>, <0xbbbbbbbb 0xbbbbbbbb 0 0x22>; }; child@cccccccc { compatible = "mfd,of-test-child"; reg = <0x00000000 0xcccccccc 0 0x33>; }; child@dddddddd00000000 { compatible = "mfd,of-test-child"; reg = <0xdddddddd 0x00000000 0 0x44>; }; }; When used with example sub-device registration like this: static const struct mfd_cell mfd_of_test_cell[] = { OF_MFD_CELL("mfd-of-test-child", NULL, NULL, 0, 0, "mfd,of-test-child"), OF_MFD_CELL("mfd-of-test-child", NULL, NULL, 0, 1, "mfd,of-test-child"), OF_MFD_CELL("mfd-of-test-child", NULL, NULL, 0, 2, "mfd,of-test-child") }; ... the current implementation will result in all devices being allocated the first OF node found containing a matching compatible string: [0.712511] mfd-of-test-child mfd-of-test-child.0: Probing platform device: 0 [0.712710] mfd-of-test-child mfd-of-test-child.0: Using OF node: child@aaaaaaaaaaaaaaaa [0.713033] mfd-of-test-child mfd-of-test-child.1: Probing platform device: 1 [0.713381] mfd-of-test-child mfd-of-test-child.1: Using OF node: child@aaaaaaaaaaaaaaaa [0.713691] mfd-of-test-child mfd-of-test-child.2: Probing platform device: 2 [0.713889] mfd-of-test-child mfd-of-test-child.2: Using OF node: child@aaaaaaaaaaaaaaaa After this patch each device will be allocated a unique OF node: [0.712511] mfd-of-test-child mfd-of-test-child.0: Probing platform device: 0 [0.712710] mfd-of-test-child mfd-of-test-child.0: Using OF node: child@aaaaaaaaaaaaaaaa [0.713033] mfd-of-test-child mfd-of-test-child.1: Probing platform device: 1 [0.713381] mfd-of-test-child mfd-of-test-child.1: Using OF node: child@cccccccc [0.713691] mfd-of-test-child mfd-of-test-child.2: Probing platform device: 2 [0.713889] mfd-of-test-child mfd-of-test-child.2: Using OF node: child@dddddddd00000000 Which is fine if all OF nodes are identical. However if we wish to apply an attribute to particular device, we really need to ensure the correct OF node will be associated with the device containing the correct address. We accomplish this by matching the device's address expressed in DT with one provided during sub-device registration. Like this: static const struct mfd_cell mfd_of_test_cell[] = { OF_MFD_CELL_REG("mfd-of-test-child", NULL, NULL, 0, 1, "mfd,of-test-child", 0xdddddddd00000000), OF_MFD_CELL_REG("mfd-of-test-child", NULL, NULL, 0, 2, "mfd,of-test-child", 0xaaaaaaaaaaaaaaaa), OF_MFD_CELL_REG("mfd-of-test-child", NULL, NULL, 0, 3, "mfd,of-test-child", 0x00000000cccccccc) }; This will ensure a specific device (designated here using the platform_ids; 1, 2 and 3) is matched with a particular OF node: [0.712511] mfd-of-test-child mfd-of-test-child.0: Probing platform device: 0 [0.712710] mfd-of-test-child mfd-of-test-child.0: Using OF node: child@dddddddd00000000 [0.713033] mfd-of-test-child mfd-of-test-child.1: Probing platform device: 1 [0.713381] mfd-of-test-child mfd-of-test-child.1: Using OF node: child@aaaaaaaaaaaaaaaa [0.713691] mfd-of-test-child mfd-of-test-child.2: Probing platform device: 2 [0.713889] mfd-of-test-child mfd-of-test-child.2: Using OF node: child@cccccccc This implementation is still not infallible, hence the mention of "best effort" in the commit subject. Since we have not *insisted* on the existence of 'reg' properties (in some scenarios they just do not make sense) and no device currently uses the new 'of_reg' attribute, we have to make an on-the-fly judgement call whether to associate the OF node anyway. Which we do in cases where parent drivers haven't specified a particular OF node to match to. So there is a *slight* possibility of the following result (note: the implementation here is convoluted, but it shows you one means by which this process can still break): /* * First entry will match to the first OF node with matching compatible * Second will fail, since the first took its OF node and is no longer available * Third will succeed */ static const struct mfd_cell mfd_of_test_cell[] = { OF_MFD_CELL("mfd-of-test-child", NULL, NULL, 0, 1, "mfd,of-test-child"), OF_MFD_CELL_REG("mfd-of-test-child", NULL, NULL, 0, 2, "mfd,of-test-child", 0xaaaaaaaaaaaaaaaa), OF_MFD_CELL_REG("mfd-of-test-child", NULL, NULL, 0, 3, "mfd,of-test-child", 0x00000000cccccccc) }; The result: [0.753869] mfd-of-test-parent mfd_of_test: Registering 3 devices [0.756597] mfd-of-test-child: Failed to locate of_node [id: 2] [0.759999] mfd-of-test-child mfd-of-test-child.1: Probing platform device: 1 [0.760314] mfd-of-test-child mfd-of-test-child.1: Using OF node: child@aaaaaaaaaaaaaaaa [0.760908] mfd-of-test-child mfd-of-test-child.2: Probing platform device: 2 [0.761183] mfd-of-test-child mfd-of-test-child.2: No OF node associated with this device [0.761621] mfd-of-test-child mfd-of-test-child.3: Probing platform device: 3 [0.761899] mfd-of-test-child mfd-of-test-child.3: Using OF node: child@cccccccc We could code around this with some pre-parsing semantics, but the added complexity required to cover each and every corner-case is not justified. Merely patching the current failing (via this patch) is already working with some pretty small corner-cases. Other issues should be patched in the parent drivers which can be achieved simply by implementing OF_MFD_CELL_REG(). Signed-off-by: Lee Jones --- include/linux/mfd/core.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index ab76cdd06199..c437a73b43a3 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -78,6 +78,16 @@ struct mfd_cell { */ const char *of_compatible; + /* + * Address as defined in Device Tree. Used to compement 'of_compatible' + * (above) when matching OF nodes with devices that have identical + * compatible strings + */ + const u64 of_reg; + + /* Set to 'true' to use 'of_reg' (above) - allows for of_reg=0 */ + bool use_of_reg; + /* Matches ACPI */ const struct mfd_cell_acpi_match *acpi_match; -- cgit v1.2.3 From d097965bb6682afe1f8481923b16c033f708923b Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 11 Jun 2020 10:18:43 +0100 Subject: mfd: core: Fix formatting of MFD helpers Remove unnecessary '\'s and leading tabs. This will help to clean-up future diffs when subsequent changes are made. Hint: The aforementioned changes follow this patch. Signed-off-by: Lee Jones --- include/linux/mfd/core.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index c437a73b43a3..da9b066e1594 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -26,20 +26,20 @@ .id = (_id), \ } -#define OF_MFD_CELL(_name, _res, _pdata, _pdsize,_id, _compat) \ - MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, NULL) \ +#define OF_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _compat) \ + MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, NULL) -#define ACPI_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _match) \ - MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, _match) \ +#define ACPI_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _match) \ + MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, _match) -#define MFD_CELL_BASIC(_name, _res, _pdata, _pdsize, _id) \ - MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, NULL) \ +#define MFD_CELL_BASIC(_name, _res, _pdata, _pdsize, _id) \ + MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, NULL) -#define MFD_CELL_RES(_name, _res) \ - MFD_CELL_ALL(_name, _res, NULL, 0, 0, NULL, NULL) \ +#define MFD_CELL_RES(_name, _res) \ + MFD_CELL_ALL(_name, _res, NULL, 0, 0, NULL, NULL) -#define MFD_CELL_NAME(_name) \ - MFD_CELL_ALL(_name, NULL, NULL, 0, 0, NULL, NULL) \ +#define MFD_CELL_NAME(_name) \ + MFD_CELL_ALL(_name, NULL, NULL, 0, 0, NULL, NULL) struct irq_domain; struct property_entry; -- cgit v1.2.3 From 44e6171ed04a0cd0378e2503f03a444ebdd4e8e3 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 11 Jun 2020 10:12:05 +0100 Subject: mfd: core: Add OF_MFD_CELL_REG() helper Extend current list of helpers to provide support for parent drivers wishing to match specific child devices to particular OF nodes. Signed-off-by: Lee Jones --- include/linux/mfd/core.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index da9b066e1594..6d68f44a26a1 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -14,7 +14,7 @@ #define MFD_RES_SIZE(arr) (sizeof(arr) / sizeof(struct resource)) -#define MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, _match)\ +#define MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, _of_reg, _use_of_reg, _match) \ { \ .name = (_name), \ .resources = (_res), \ @@ -22,24 +22,29 @@ .platform_data = (_pdata), \ .pdata_size = (_pdsize), \ .of_compatible = (_compat), \ + .of_reg = (_of_reg), \ + .use_of_reg = (_use_of_reg), \ .acpi_match = (_match), \ .id = (_id), \ } +#define OF_MFD_CELL_REG(_name, _res, _pdata, _pdsize, _id, _compat, _of_reg) \ + MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, _of_reg, true, NULL) + #define OF_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _compat) \ - MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, NULL) + MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, 0, false, NULL) #define ACPI_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _match) \ - MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, _match) + MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, 0, false, _match) #define MFD_CELL_BASIC(_name, _res, _pdata, _pdsize, _id) \ - MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, NULL) + MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, 0, false, NULL) #define MFD_CELL_RES(_name, _res) \ - MFD_CELL_ALL(_name, _res, NULL, 0, 0, NULL, NULL) + MFD_CELL_ALL(_name, _res, NULL, 0, 0, NULL, 0, false, NULL) #define MFD_CELL_NAME(_name) \ - MFD_CELL_ALL(_name, NULL, NULL, 0, 0, NULL, NULL) + MFD_CELL_ALL(_name, NULL, NULL, 0, 0, NULL, 0, false, NULL) struct irq_domain; struct property_entry; -- cgit v1.2.3 From 7d2594cd1fa0b03b2746ce811926ee150a3a14fa Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Wed, 1 Jul 2020 23:23:48 +0200 Subject: mfd: smsc-ece1099: Remove driver This MFD driver has no user. The keypad driver of this device never made it into the kernel. Therefore, this driver is useless. Remove it. Signed-off-by: Michael Walle Cc: Sourav Poddar Signed-off-by: Lee Jones --- include/linux/mfd/smsc.h | 104 ----------------------------------------------- 1 file changed, 104 deletions(-) delete mode 100644 include/linux/mfd/smsc.h (limited to 'include/linux') diff --git a/include/linux/mfd/smsc.h b/include/linux/mfd/smsc.h deleted file mode 100644 index 83944124e886..000000000000 --- a/include/linux/mfd/smsc.h +++ /dev/null @@ -1,104 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * SMSC ECE1099 - * - * Copyright 2012 Texas Instruments Inc. - * - * Author: Sourav Poddar - */ - -#ifndef __LINUX_MFD_SMSC_H -#define __LINUX_MFD_SMSC_H - -#include - -#define SMSC_ID_ECE1099 1 -#define SMSC_NUM_CLIENTS 2 - -#define SMSC_BASE_ADDR 0x38 -#define OMAP_GPIO_SMSC_IRQ 151 - -#define SMSC_MAXGPIO 32 -#define SMSC_BANK(offs) ((offs) >> 3) -#define SMSC_BIT(offs) (1u << ((offs) & 0x7)) - -struct smsc { - struct device *dev; - struct i2c_client *i2c_clients[SMSC_NUM_CLIENTS]; - struct regmap *regmap; - int clk; - /* Stored chip id */ - int id; -}; - -struct smsc_gpio; -struct smsc_keypad; - -static inline int smsc_read(struct device *child, unsigned int reg, - unsigned int *dest) -{ - struct smsc *smsc = dev_get_drvdata(child->parent); - - return regmap_read(smsc->regmap, reg, dest); -} - -static inline int smsc_write(struct device *child, unsigned int reg, - unsigned int value) -{ - struct smsc *smsc = dev_get_drvdata(child->parent); - - return regmap_write(smsc->regmap, reg, value); -} - -/* Registers for SMSC */ -#define SMSC_RESET 0xF5 -#define SMSC_GRP_INT 0xF9 -#define SMSC_CLK_CTRL 0xFA -#define SMSC_WKUP_CTRL 0xFB -#define SMSC_DEV_ID 0xFC -#define SMSC_DEV_REV 0xFD -#define SMSC_VEN_ID_L 0xFE -#define SMSC_VEN_ID_H 0xFF - -/* CLK VALUE */ -#define SMSC_CLK_VALUE 0x13 - -/* Registers for function GPIO INPUT */ -#define SMSC_GPIO_DATA_IN_START 0x00 - -/* Registers for function GPIO OUPUT */ -#define SMSC_GPIO_DATA_OUT_START 0x05 - -/* Definitions for SMSC GPIO CONFIGURATION REGISTER*/ -#define SMSC_GPIO_INPUT_LOW 0x01 -#define SMSC_GPIO_INPUT_RISING 0x09 -#define SMSC_GPIO_INPUT_FALLING 0x11 -#define SMSC_GPIO_INPUT_BOTH_EDGE 0x19 -#define SMSC_GPIO_OUTPUT_PP 0x21 -#define SMSC_GPIO_OUTPUT_OP 0x31 - -#define GRP_INT_STAT 0xf9 -#define SMSC_GPI_INT 0x0f -#define SMSC_CFG_START 0x0A - -/* Registers for SMSC GPIO INTERRUPT STATUS REGISTER*/ -#define SMSC_GPIO_INT_STAT_START 0x32 - -/* Registers for SMSC GPIO INTERRUPT MASK REGISTER*/ -#define SMSC_GPIO_INT_MASK_START 0x37 - -/* Registers for SMSC function KEYPAD*/ -#define SMSC_KP_OUT 0x40 -#define SMSC_KP_IN 0x41 -#define SMSC_KP_INT_STAT 0x42 -#define SMSC_KP_INT_MASK 0x43 - -/* Definitions for keypad */ -#define SMSC_KP_KSO 0x70 -#define SMSC_KP_KSI 0x51 -#define SMSC_KSO_ALL_LOW 0x20 -#define SMSC_KP_SET_LOW_PWR 0x0B -#define SMSC_KP_SET_HIGH 0xFF -#define SMSC_KSO_EVAL 0x00 - -#endif /* __LINUX_MFD_SMSC_H */ -- cgit v1.2.3 From 091c6110862bce4e2380e353cb062dcb6a56bcb6 Mon Sep 17 00:00:00 2001 From: Adam Thomson Date: Mon, 13 Jul 2020 10:38:57 +0100 Subject: mfd: da9063: Fix revision handling to correctly select reg tables The current implementation performs checking in the i2c_probe() function of the variant_code but does this immediately after the containing struct has been initialised as all zero. This means the check for variant code will always default to using the BB tables and will never select AD. The variant code is subsequently set by device_init() and later used by the RTC so really it's a little fortunate this mismatch works. This update adds raw I2C read access functionality to read the chip and variant/revision information (common to all revisions) so that it can subsequently correctly choose the proper regmap tables for real initialisation. Signed-off-by: Adam Thomson Signed-off-by: Lee Jones --- include/linux/mfd/da9063/registers.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/registers.h b/include/linux/mfd/da9063/registers.h index ba706b0e28c2..1dbabf1b3cb8 100644 --- a/include/linux/mfd/da9063/registers.h +++ b/include/linux/mfd/da9063/registers.h @@ -292,8 +292,10 @@ #define DA9063_BB_REG_GP_ID_19 0x134 /* Chip ID and variant */ -#define DA9063_REG_CHIP_ID 0x181 -#define DA9063_REG_CHIP_VARIANT 0x182 +#define DA9063_REG_DEVICE_ID 0x181 +#define DA9063_REG_VARIANT_ID 0x182 +#define DA9063_REG_CUSTOMER_ID 0x183 +#define DA9063_REG_CONFIG_ID 0x184 /* * PMIC registers bits @@ -929,9 +931,6 @@ #define DA9063_RTC_CLOCK 0x40 #define DA9063_OUT_32K_EN 0x80 -/* DA9063_REG_CHIP_VARIANT */ -#define DA9063_CHIP_VARIANT_SHIFT 4 - /* DA9063_REG_BUCK_ILIM_A (addr=0x9A) */ #define DA9063_BIO_ILIM_MASK 0x0F #define DA9063_BMEM_ILIM_MASK 0xF0 @@ -1065,4 +1064,10 @@ #define DA9063_MON_A10_IDX_LDO9 0x04 #define DA9063_MON_A10_IDX_LDO10 0x05 +/* DA9063_REG_VARIANT_ID (addr=0x182) */ +#define DA9063_VARIANT_ID_VRC_SHIFT 0 +#define DA9063_VARIANT_ID_VRC_MASK 0x0F +#define DA9063_VARIANT_ID_MRC_SHIFT 4 +#define DA9063_VARIANT_ID_MRC_MASK 0xF0 + #endif /* _DA9063_REG_H */ -- cgit v1.2.3 From 9ece3601aed46f7b460b79cd7d60908b47b2b0d4 Mon Sep 17 00:00:00 2001 From: Adam Thomson Date: Mon, 13 Jul 2020 10:38:59 +0100 Subject: mfd: da9063: Add support for latest DA silicon revision This update adds new regmap tables to support the latest DA silicon which will automatically be selected based on the chip and variant information read from the device. Signed-off-by: Adam Thomson Signed-off-by: Lee Jones --- include/linux/mfd/da9063/core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h index 5cd06ab26352..fa7a43f02f27 100644 --- a/include/linux/mfd/da9063/core.h +++ b/include/linux/mfd/da9063/core.h @@ -35,6 +35,7 @@ enum da9063_variant_codes { PMIC_DA9063_AD = 0x3, PMIC_DA9063_BB = 0x5, PMIC_DA9063_CA = 0x6, + PMIC_DA9063_DA = 0x7, }; /* Interrupts */ -- cgit v1.2.3 From 23ef2b642b85f03a109fbf5958134a5e40193dbd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:29:17 -0700 Subject: mfd: da9055: pdata.h: Drop a duplicated word Drop the repeated word "that" in a comment. Signed-off-by: Randy Dunlap Acked-by: Adam Thomson Signed-off-by: Lee Jones --- include/linux/mfd/da9055/pdata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9055/pdata.h b/include/linux/mfd/da9055/pdata.h index eac48e483190..d3f126990ad0 100644 --- a/include/linux/mfd/da9055/pdata.h +++ b/include/linux/mfd/da9055/pdata.h @@ -35,7 +35,7 @@ struct da9055_pdata { int *gpio_rsel; /* * Regulator mode control bits value (GPI offset) that - * that controls the regulator state, 0 if not available. + * controls the regulator state, 0 if not available. */ enum gpio_select *reg_ren; /* -- cgit v1.2.3 From e7b85500885f2a70129f5d3a72153e23b37d0fe5 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:29:31 -0700 Subject: mfd: max77693-private: Drop a duplicated word Drop the repeated word "in" in a comment. Signed-off-by: Randy Dunlap Signed-off-by: Lee Jones --- include/linux/mfd/max77693-private.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h index e798c81aec31..311f7d3d2323 100644 --- a/include/linux/mfd/max77693-private.h +++ b/include/linux/mfd/max77693-private.h @@ -131,7 +131,7 @@ enum max77693_pmic_reg { #define FLASH_INT_FLED1_SHORT BIT(3) #define FLASH_INT_OVER_CURRENT BIT(4) -/* Fast charge timer in in hours */ +/* Fast charge timer in hours */ #define DEFAULT_FAST_CHARGE_TIMER 4 /* microamps */ #define DEFAULT_TOP_OFF_THRESHOLD_CURRENT 150000 -- cgit v1.2.3 From 114294d276279d6cda81f9c685452239ea89cdb8 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Thu, 23 Jul 2020 11:54:58 +0100 Subject: mfd: mfd-core: Add mechanism for removal of a subset of children Currently, the only way to remove MFD children is with a call to mfd_remove_devices, which will remove all the children. Under some circumstances it is useful to remove only a subset of the child devices. For example if some additional clean up is required between removal of certain child devices. To accomplish this a level field is added to mfd_cell, the normal mfd_remove_devices is modified to not remove devices that are set to a higher level and a corresponding mfd_remove_devices_late function is added to remove those children. See further discussion at: https://lore.kernel.org/lkml/20200616075834.GF2608702@dell/ Suggested-by: Lee Jones Signed-off-by: Charles Keepax Signed-off-by: Lee Jones --- include/linux/mfd/core.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index 6d68f44a26a1..4b35baa14d30 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -46,6 +46,9 @@ #define MFD_CELL_NAME(_name) \ MFD_CELL_ALL(_name, NULL, NULL, 0, 0, NULL, 0, false, NULL) +#define MFD_DEP_LEVEL_NORMAL 0 +#define MFD_DEP_LEVEL_HIGH 1 + struct irq_domain; struct property_entry; @@ -63,6 +66,7 @@ struct mfd_cell_acpi_match { struct mfd_cell { const char *name; int id; + int level; int (*enable)(struct platform_device *dev); int (*disable)(struct platform_device *dev); @@ -150,6 +154,7 @@ static inline int mfd_add_hotplug_devices(struct device *parent, } extern void mfd_remove_devices(struct device *parent); +extern void mfd_remove_devices_late(struct device *parent); extern int devm_mfd_add_devices(struct device *dev, int id, const struct mfd_cell *cells, int n_devs, -- cgit v1.2.3 From 4f4ed4543e2096dc0158ff79bd6d8bc09e27fa93 Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Wed, 22 Jul 2020 21:24:54 +0200 Subject: mfd: Replace HTTP links with HTTPS ones Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. Signed-off-by: Alexander A. Klimov Acked-by: Rob Herring Signed-off-by: Lee Jones --- include/linux/mfd/hi6421-pmic.h | 2 +- include/linux/mfd/lp873x.h | 2 +- include/linux/mfd/lp87565.h | 2 +- include/linux/mfd/ti_am335x_tscadc.h | 2 +- include/linux/mfd/tps65086.h | 2 +- include/linux/mfd/tps65217.h | 2 +- include/linux/mfd/tps65218.h | 2 +- include/linux/mfd/tps65912.h | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/hi6421-pmic.h b/include/linux/mfd/hi6421-pmic.h index bbc64484c021..2cadf8897c64 100644 --- a/include/linux/mfd/hi6421-pmic.h +++ b/include/linux/mfd/hi6421-pmic.h @@ -5,7 +5,7 @@ * Copyright (c) <2011-2014> HiSilicon Technologies Co., Ltd. * http://www.hisilicon.com * Copyright (c) <2013-2014> Linaro Ltd. - * http://www.linaro.org + * https://www.linaro.org * * Author: Guodong Xu */ diff --git a/include/linux/mfd/lp873x.h b/include/linux/mfd/lp873x.h index edbec8350a49..5546688c7da7 100644 --- a/include/linux/mfd/lp873x.h +++ b/include/linux/mfd/lp873x.h @@ -1,7 +1,7 @@ /* * Functions to access LP873X power management chip. * - * Copyright (C) 2016 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2016 Texas Instruments Incorporated - https://www.ti.com/ * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as diff --git a/include/linux/mfd/lp87565.h b/include/linux/mfd/lp87565.h index ce965354bbad..43716aca46fa 100644 --- a/include/linux/mfd/lp87565.h +++ b/include/linux/mfd/lp87565.h @@ -2,7 +2,7 @@ /* * Functions to access LP87565 power management chip. * - * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2017 Texas Instruments Incorporated - https://www.ti.com/ */ #ifndef __LINUX_MFD_LP87565_H diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 483168403ae5..ffc091b77633 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -4,7 +4,7 @@ /* * TI Touch Screen / ADC MFD driver * - * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/ * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as diff --git a/include/linux/mfd/tps65086.h b/include/linux/mfd/tps65086.h index a228ae4c88d9..e0a417e53766 100644 --- a/include/linux/mfd/tps65086.h +++ b/include/linux/mfd/tps65086.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/ * Andrew F. Davis * * This program is free software; you can redistribute it and/or diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index b5dd108421c8..db7091824ed0 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -3,7 +3,7 @@ * * Functions to access TPS65217 power management chip. * - * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2011 Texas Instruments Incorporated - https://www.ti.com/ * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h index b0470c35162d..f4ca367e3473 100644 --- a/include/linux/mfd/tps65218.h +++ b/include/linux/mfd/tps65218.h @@ -3,7 +3,7 @@ * * Functions to access TPS65219 power management chip. * - * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com/ * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License version 2 as diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h index b25d0297ba88..7943e413deae 100644 --- a/include/linux/mfd/tps65912.h +++ b/include/linux/mfd/tps65912.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2015 Texas Instruments Incorporated - https://www.ti.com/ * Andrew F. Davis * * This program is free software; you can redistribute it and/or -- cgit v1.2.3 From 9420139f516d7fbc248ce17f35275cb005ed98ea Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 14 Aug 2020 12:26:24 +0200 Subject: dma-pool: fix coherent pool allocations for IOMMU mappings When allocating coherent pool memory for an IOMMU mapping we don't care about the DMA mask. Move the guess for the initial GFP mask into the dma_direct_alloc_pages and pass dma_coherent_ok as a function pointer argument so that it doesn't get applied to the IOMMU case. Signed-off-by: Christoph Hellwig Tested-by: Amit Pundir --- include/linux/dma-direct.h | 3 --- include/linux/dma-mapping.h | 5 +++-- 2 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 5a3ce2a24794..6e87225600ae 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -73,9 +73,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, } u64 dma_direct_get_required_mask(struct device *dev); -gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, - u64 *phys_mask); -bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size); void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 016b96b384bd..52635e91143b 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -522,8 +522,9 @@ void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot, const void *caller); void dma_common_free_remap(void *cpu_addr, size_t size); -void *dma_alloc_from_pool(struct device *dev, size_t size, - struct page **ret_page, gfp_t flags); +struct page *dma_alloc_from_pool(struct device *dev, size_t size, + void **cpu_addr, gfp_t flags, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)); bool dma_free_from_pool(struct device *dev, void *start, size_t size); int -- cgit v1.2.3 From 5848dc5b1b76d83599dcec1b39f188a7cbdca7e2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 14 Aug 2020 15:22:43 -0700 Subject: dma-debug: remove debug_dma_assert_idle() function This remoes the code from the COW path to call debug_dma_assert_idle(), which was added many years ago. Google shows that it hasn't caught anything in the 6+ years we've had it apart from a false positive, and Hugh just noticed how it had a very unfortunate spinlock serialization in the COW path. He fixed that issue the previous commit (a85ffd59bd36: "dma-debug: fix debug_dma_assert_idle(), use rcu_read_lock()"), but let's see if anybody even notices when we remove this function entirely. NOTE! We keep the dma tracking infrastructure that was added by the commit that introduced it. Partly to make it easier to resurrect this debug code if we ever deside to, and partly because that tracking by pfn and offset looks quite reasonable. The problem with this debug code was simply that it was expensive and didn't seem worth it, not that it was wrong per se. Acked-by: Dan Williams Acked-by: Christoph Hellwig Signed-off-by: Linus Torvalds --- include/linux/dma-debug.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index 4208f94d93f7..7b3b04ba60f3 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -67,8 +67,6 @@ extern void debug_dma_sync_sg_for_device(struct device *dev, extern void debug_dma_dump_mappings(struct device *dev); -extern void debug_dma_assert_idle(struct page *page); - #else /* CONFIG_DMA_API_DEBUG */ static inline void dma_debug_add_bus(struct bus_type *bus) @@ -157,10 +155,6 @@ static inline void debug_dma_dump_mappings(struct device *dev) { } -static inline void debug_dma_assert_idle(struct page *page) -{ -} - #endif /* CONFIG_DMA_API_DEBUG */ #endif /* __DMA_DEBUG_H */ -- cgit v1.2.3 From 1378a5ee451a5e87d0d8dd6356a0b7844db231f6 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Aug 2020 17:30:23 -0700 Subject: mm: store compound_nr as well as compound_order Patch series "THP prep patches". These are some generic cleanups and improvements, which I would like merged into mmotm soon. The first one should be a performance improvement for all users of compound pages, and the others are aimed at getting code to compile away when CONFIG_TRANSPARENT_HUGEPAGE is disabled (ie small systems). Also better documented / less confusing than the current prefix mixture of compound, hpage and thp. This patch (of 7): This removes a few instructions from functions which need to know how many pages are in a compound page. The storage used is either page->mapping on 64-bit or page->index on 32-bit. Both of these are fine to overlay on tail pages. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: William Kucharski Reviewed-by: Zi Yan Cc: David Hildenbrand Cc: Mike Kravetz Cc: "Kirill A. Shutemov" Link: http://lkml.kernel.org/r/20200629151959.15779-1-willy@infradead.org Link: http://lkml.kernel.org/r/20200629151959.15779-2-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 ++++- include/linux/mm_types.h | 1 + 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e7602a3bcef1..10b1e6e5f885 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -922,12 +922,15 @@ static inline int compound_pincount(struct page *page) static inline void set_compound_order(struct page *page, unsigned int order) { page[1].compound_order = order; + page[1].compound_nr = 1U << order; } /* Returns the number of pages in this potentially compound page. */ static inline unsigned long compound_nr(struct page *page) { - return 1UL << compound_order(page); + if (!PageHead(page)) + return 1; + return page[1].compound_nr; } /* Returns the number of bytes in this potentially compound page. */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0277fbab7c93..496c3ff97cce 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -134,6 +134,7 @@ struct page { unsigned char compound_dtor; unsigned char compound_order; atomic_t compound_mapcount; + unsigned int compound_nr; /* 1 << compound_order */ }; struct { /* Second tail page of compound page */ unsigned long _compound_pad_1; /* compound_head */ -- cgit v1.2.3 From 419015675fef6c4b28689bd2ace559564c2e106c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Aug 2020 17:30:26 -0700 Subject: mm: move page-flags include to top of file Give up on the notion that we can remove page-flags.h from mm.h. There are currently 14 inline functions which use a PageFoo function. Also, two of the files directly included by mm.h include page-flags.h themselves, and there are probably more indirect inclusions. So just include it at the top like any other header file. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: William Kucharski Reviewed-by: Zi Yan Cc: David Hildenbrand Cc: Mike Kravetz Cc: "Kirill A. Shutemov" Link: http://lkml.kernel.org/r/20200629151959.15779-3-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 10b1e6e5f885..fd0cd4e93029 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -668,11 +669,6 @@ int vma_is_stack_for_current(struct vm_area_struct *vma); struct mmu_gather; struct inode; -/* - * FIXME: take this include out, include page-flags.h in - * files which need it (119 of them) - */ -#include #include /* -- cgit v1.2.3 From 6ffbb45826f5d9ae09aa60cd88594b7816c96190 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Aug 2020 17:30:30 -0700 Subject: mm: add thp_order This function returns the order of a transparent huge page. It compiles to 0 if CONFIG_TRANSPARENT_HUGEPAGE is disabled. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: William Kucharski Reviewed-by: Zi Yan Cc: David Hildenbrand Cc: Mike Kravetz Cc: "Kirill A. Shutemov" Link: http://lkml.kernel.org/r/20200629151959.15779-4-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 467302056e17..9521cfdf18ca 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -258,6 +258,19 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, else return NULL; } + +/** + * thp_order - Order of a transparent huge page. + * @page: Head page of a transparent huge page. + */ +static inline unsigned int thp_order(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + if (PageHead(page)) + return HPAGE_PMD_ORDER; + return 0; +} + static inline int hpage_nr_pages(struct page *page) { if (unlikely(PageTransHuge(page))) @@ -317,6 +330,12 @@ static inline struct list_head *page_deferred_list(struct page *page) #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) +static inline unsigned int thp_order(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + return 0; +} + static inline int hpage_nr_pages(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); -- cgit v1.2.3 From af3bbc12df80e8c279b94c752b6edca29841f4f5 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Aug 2020 17:30:33 -0700 Subject: mm: add thp_size This function returns the number of bytes in a THP. It is like page_size(), but compiles to just PAGE_SIZE if CONFIG_TRANSPARENT_HUGEPAGE is disabled. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: William Kucharski Reviewed-by: Zi Yan Cc: David Hildenbrand Cc: Mike Kravetz Cc: "Kirill A. Shutemov" Link: http://lkml.kernel.org/r/20200629151959.15779-5-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 9521cfdf18ca..9b33ac774fdd 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -462,4 +462,15 @@ static inline bool thp_migration_supported(void) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +/** + * thp_size - Size of a transparent huge page. + * @page: Head page of a transparent huge page. + * + * Return: Number of bytes in this page. + */ +static inline unsigned long thp_size(struct page *page) +{ + return PAGE_SIZE << thp_order(page); +} + #endif /* _LINUX_HUGE_MM_H */ -- cgit v1.2.3 From 6c357848b44b4016ca422178aa368a7472245f6f Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Aug 2020 17:30:37 -0700 Subject: mm: replace hpage_nr_pages with thp_nr_pages The thp prefix is more frequently used than hpage and we should be consistent between the various functions. [akpm@linux-foundation.org: fix mm/migrate.c] Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: William Kucharski Reviewed-by: Zi Yan Cc: Mike Kravetz Cc: David Hildenbrand Cc: "Kirill A. Shutemov" Link: http://lkml.kernel.org/r/20200629151959.15779-6-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 13 +++++++++---- include/linux/mm_inline.h | 6 +++--- include/linux/pagemap.h | 6 +++--- 3 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 9b33ac774fdd..229f986d535a 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -271,9 +271,14 @@ static inline unsigned int thp_order(struct page *page) return 0; } -static inline int hpage_nr_pages(struct page *page) +/** + * thp_nr_pages - The number of regular pages in this huge page. + * @page: The head page of a huge page. + */ +static inline int thp_nr_pages(struct page *page) { - if (unlikely(PageTransHuge(page))) + VM_BUG_ON_PGFLAGS(PageTail(page), page); + if (PageHead(page)) return HPAGE_PMD_NR; return 1; } @@ -336,9 +341,9 @@ static inline unsigned int thp_order(struct page *page) return 0; } -static inline int hpage_nr_pages(struct page *page) +static inline int thp_nr_pages(struct page *page) { - VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PGFLAGS(PageTail(page), page); return 1; } diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 219bef41d87c..8fc71e9d7bb0 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -48,14 +48,14 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, static __always_inline void add_page_to_lru_list(struct page *page, struct lruvec *lruvec, enum lru_list lru) { - update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page)); + update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); list_add(&page->lru, &lruvec->lists[lru]); } static __always_inline void add_page_to_lru_list_tail(struct page *page, struct lruvec *lruvec, enum lru_list lru) { - update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page)); + update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); list_add_tail(&page->lru, &lruvec->lists[lru]); } @@ -63,7 +63,7 @@ static __always_inline void del_page_from_lru_list(struct page *page, struct lruvec *lruvec, enum lru_list lru) { list_del(&page->lru); - update_lru_size(lruvec, lru, page_zonenum(page), -hpage_nr_pages(page)); + update_lru_size(lruvec, lru, page_zonenum(page), -thp_nr_pages(page)); } /** diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d1f4eff605ad..7de11dcd534d 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -381,7 +381,7 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) if (PageHuge(head)) return head; - return head + (index & (hpage_nr_pages(head) - 1)); + return head + (index & (thp_nr_pages(head) - 1)); } struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); @@ -773,7 +773,7 @@ static inline struct page *readahead_page(struct readahead_control *rac) page = xa_load(&rac->mapping->i_pages, rac->_index); VM_BUG_ON_PAGE(!PageLocked(page), page); - rac->_batch_count = hpage_nr_pages(page); + rac->_batch_count = thp_nr_pages(page); return page; } @@ -796,7 +796,7 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; - rac->_batch_count += hpage_nr_pages(page); + rac->_batch_count += thp_nr_pages(page); /* * The page cache isn't using multi-index entries yet, -- cgit v1.2.3 From 2be1d71841b7ecfb01ce4c59f6e1d082c3c18a8a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Aug 2020 17:30:40 -0700 Subject: mm: add thp_head This is like compound_head() but compiles away when CONFIG_TRANSPARENT_HUGEPAGE is not enabled. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: William Kucharski Reviewed-by: Zi Yan Cc: David Hildenbrand Cc: Mike Kravetz Cc: "Kirill A. Shutemov" Link: http://lkml.kernel.org/r/20200629151959.15779-7-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 229f986d535a..8a8bc46a2432 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -259,6 +259,15 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, return NULL; } +/** + * thp_head - Head page of a transparent huge page. + * @page: Any page (tail, head or regular) found in the page cache. + */ +static inline struct page *thp_head(struct page *page) +{ + return compound_head(page); +} + /** * thp_order - Order of a transparent huge page. * @page: Head page of a transparent huge page. @@ -335,6 +344,12 @@ static inline struct list_head *page_deferred_list(struct page *page) #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) +static inline struct page *thp_head(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + return page; +} + static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); -- cgit v1.2.3 From ee6c400f5c05459b8c5f2884a176a1287ce2f68f Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Aug 2020 17:30:43 -0700 Subject: mm: introduce offset_in_thp Mirroring offset_in_page(), this gives you the offset within this particular page, no matter what size page it is. It optimises down to offset_in_page() if CONFIG_TRANSPARENT_HUGEPAGE is not set. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Reviewed-by: William Kucharski Reviewed-by: Zi Yan Cc: Mike Kravetz Cc: "Kirill A. Shutemov" Link: http://lkml.kernel.org/r/20200629151959.15779-8-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index fd0cd4e93029..2e7ec3ee34cf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1594,6 +1594,7 @@ static inline void clear_page_pfmemalloc(struct page *page) extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) +#define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1)) /* * Flags passed to show_mem() and show_free_areas() to suppress output in -- cgit v1.2.3 From 88db0aa2421666d2f73486d15b239a4521983d55 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 14 Aug 2020 17:31:07 -0700 Subject: all arch: remove system call sys_sysctl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 61a47c1ad3a4dc ("sysctl: Remove the sysctl system call"), sys_sysctl is actually unavailable: any input can only return an error. We have been warning about people using the sysctl system call for years and believe there are no more users. Even if there are users of this interface if they have not complained or fixed their code by now they probably are not going to, so there is no point in warning them any longer. So completely remove sys_sysctl on all architectures. [nixiaoming@huawei.com: s390: fix build error for sys_call_table_emu] Link: http://lkml.kernel.org/r/20200618141426.16884-1-nixiaoming@huawei.com Signed-off-by: Xiaoming Ni Signed-off-by: Andrew Morton Acked-by: Will Deacon [arm/arm64] Acked-by: "Eric W. Biederman" Cc: Aleksa Sarai Cc: Alexander Shishkin Cc: Al Viro Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Bin Meng Cc: Borislav Petkov Cc: Brian Gerst Cc: Catalin Marinas Cc: chenzefeng Cc: Christian Borntraeger Cc: Christian Brauner Cc: Chris Zankel Cc: David Howells Cc: David S. Miller Cc: Diego Elio Pettenò Cc: Dmitry Vyukov Cc: Dominik Brodowski Cc: Fenghua Yu Cc: Geert Uytterhoeven Cc: Heiko Carstens Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Iurii Zaikin Cc: Ivan Kokshaysky Cc: James Bottomley Cc: Jens Axboe Cc: Jiri Olsa Cc: Kars de Jong Cc: Kees Cook Cc: Krzysztof Kozlowski Cc: Luis Chamberlain Cc: Marco Elver Cc: Mark Rutland Cc: Martin K. Petersen Cc: Masahiro Yamada Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Miklos Szeredi Cc: Minchan Kim Cc: Namhyung Kim Cc: Naveen N. Rao Cc: Nick Piggin Cc: Oleg Nesterov Cc: Olof Johansson Cc: Paul Burton Cc: "Paul E. McKenney" Cc: Paul Mackerras Cc: Peter Zijlstra (Intel) Cc: Randy Dunlap Cc: Ravi Bangoria Cc: Richard Henderson Cc: Rich Felker Cc: Russell King Cc: Sami Tolvanen Cc: Sargun Dhillon Cc: Stephen Rothwell Cc: Sudeep Holla Cc: Sven Schnelle Cc: Thiago Jung Bauermann Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Tony Luck Cc: Vasily Gorbik Cc: Vlastimil Babka Cc: Yoshinori Sato Cc: Zhou Yanjie Link: http://lkml.kernel.org/r/20200616030734.87257-1-nixiaoming@huawei.com Signed-off-by: Linus Torvalds --- include/linux/compat.h | 1 - include/linux/syscalls.h | 2 -- include/linux/sysctl.h | 6 ++---- 3 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index c4255d8a4a8a..d38c4d7e83bd 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -851,7 +851,6 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len, unsigned flags); -asmlinkage long compat_sys_sysctl(struct compat_sysctl_args __user *args); /* obsolete: fs/readdir.c */ asmlinkage long compat_sys_old_readdir(unsigned int fd, diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index dc2b827c81e5..75ac7f8ae93c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -47,7 +47,6 @@ struct stat64; struct statfs; struct statfs64; struct statx; -struct __sysctl_args; struct sysinfo; struct timespec; struct __kernel_old_timeval; @@ -1117,7 +1116,6 @@ asmlinkage long sys_send(int, void __user *, size_t, unsigned); asmlinkage long sys_bdflush(int func, long data); asmlinkage long sys_oldumount(char __user *name); asmlinkage long sys_uselib(const char __user *library); -asmlinkage long sys_sysctl(struct __sysctl_args __user *args); asmlinkage long sys_sysfs(int option, unsigned long arg1, unsigned long arg2); asmlinkage long sys_fork(void); diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 50bb7f383a1b..51298a4f4623 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -74,15 +74,13 @@ int proc_do_static_key(struct ctl_table *table, int write, void *buffer, * sysctl names can be mirrored automatically under /proc/sys. The * procname supplied controls /proc naming. * - * The table's mode will be honoured both for sys_sysctl(2) and - * proc-fs access. + * The table's mode will be honoured for proc-fs access. * * Leaf nodes in the sysctl tree will be represented by a single file * under /proc; non-leaf nodes will be represented by directories. A * null procname disables /proc mirroring at this node. * - * sysctl(2) can automatically manage read and write requests through - * the sysctl table. The data and maxlen fields of the ctl_table + * The data and maxlen fields of the ctl_table * struct enable minimal validation of the values being written to be * performed, and the mode field allows minimal authentication. * -- cgit v1.2.3 From e0e3f42fd96cf830c61aa720f0abb4eef41c5ce3 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 14 Aug 2020 17:31:37 -0700 Subject: mm/memcontrol: fix a data race in scan count struct mem_cgroup_per_node mz.lru_zone_size[zone_idx][lru] could be accessed concurrently as noticed by KCSAN, BUG: KCSAN: data-race in lruvec_lru_size / mem_cgroup_update_lru_size write to 0xffff9c804ca285f8 of 8 bytes by task 50951 on cpu 12: mem_cgroup_update_lru_size+0x11c/0x1d0 mem_cgroup_update_lru_size at mm/memcontrol.c:1266 isolate_lru_pages+0x6a9/0xf30 shrink_active_list+0x123/0xcc0 shrink_lruvec+0x8fd/0x1380 shrink_node+0x317/0xd80 do_try_to_free_pages+0x1f7/0xa10 try_to_free_pages+0x26c/0x5e0 __alloc_pages_slowpath+0x458/0x1290 __alloc_pages_nodemask+0x3bb/0x450 alloc_pages_vma+0x8a/0x2c0 do_anonymous_page+0x170/0x700 __handle_mm_fault+0xc9f/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 read to 0xffff9c804ca285f8 of 8 bytes by task 50964 on cpu 95: lruvec_lru_size+0xbb/0x270 mem_cgroup_get_zone_lru_size at include/linux/memcontrol.h:536 (inlined by) lruvec_lru_size at mm/vmscan.c:326 shrink_lruvec+0x1d0/0x1380 shrink_node+0x317/0xd80 do_try_to_free_pages+0x1f7/0xa10 try_to_free_pages+0x26c/0x5e0 __alloc_pages_slowpath+0x458/0x1290 __alloc_pages_nodemask+0x3bb/0x450 alloc_pages_current+0xa6/0x120 alloc_slab_page+0x3b1/0x540 allocate_slab+0x70/0x660 new_slab+0x46/0x70 ___slab_alloc+0x4ad/0x7d0 __slab_alloc+0x43/0x70 kmem_cache_alloc+0x2c3/0x420 getname_flags+0x4c/0x230 getname+0x22/0x30 do_sys_openat2+0x205/0x3b0 do_sys_open+0x9a/0xf0 __x64_sys_openat+0x62/0x80 do_syscall_64+0x91/0xb47 entry_SYSCALL_64_after_hwframe+0x49/0xbe Reported by Kernel Concurrency Sanitizer on: CPU: 95 PID: 50964 Comm: cc1 Tainted: G W O L 5.5.0-next-20200204+ #6 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019 The write is under lru_lock, but the read is done as lockless. The scan count is used to determine how aggressively the anon and file LRU lists should be scanned. Load tearing could generate an inefficient heuristic, so fix it by adding READ_ONCE() for the read. Signed-off-by: Qian Cai Signed-off-by: Andrew Morton Cc: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Link: http://lkml.kernel.org/r/20200206034945.2481-1-cai@lca.pw Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 385237e4cb44..d0b036123c6a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -630,7 +630,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, struct mem_cgroup_per_node *mz; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - return mz->lru_zone_size[zone_idx][lru]; + return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } void mem_cgroup_handle_over_high(void); -- cgit v1.2.3 From c403f6a3a792a6601185497c12b0bdf4be880439 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 14 Aug 2020 17:31:53 -0700 Subject: mm: annotate a data race in page_zonenum() BUG: KCSAN: data-race in page_cpupid_xchg_last / put_page write (marked) to 0xfffffc0d48ec1a00 of 8 bytes by task 91442 on cpu 3: page_cpupid_xchg_last+0x51/0x80 page_cpupid_xchg_last at mm/mmzone.c:109 (discriminator 11) wp_page_reuse+0x3e/0xc0 wp_page_reuse at mm/memory.c:2453 do_wp_page+0x472/0x7b0 do_wp_page at mm/memory.c:2798 __handle_mm_fault+0xcb0/0xd00 handle_pte_fault at mm/memory.c:4049 (inlined by) __handle_mm_fault at mm/memory.c:4163 handle_mm_fault+0xfc/0x2f0 handle_mm_fault at mm/memory.c:4200 do_page_fault+0x263/0x6f9 do_user_addr_fault at arch/x86/mm/fault.c:1465 (inlined by) do_page_fault at arch/x86/mm/fault.c:1539 page_fault+0x34/0x40 read to 0xfffffc0d48ec1a00 of 8 bytes by task 94817 on cpu 69: put_page+0x15a/0x1f0 page_zonenum at include/linux/mm.h:923 (inlined by) is_zone_device_page at include/linux/mm.h:929 (inlined by) page_is_devmap_managed at include/linux/mm.h:948 (inlined by) put_page at include/linux/mm.h:1023 wp_page_copy+0x571/0x930 wp_page_copy at mm/memory.c:2615 do_wp_page+0x107/0x7b0 __handle_mm_fault+0xcb0/0xd00 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 Reported by Kernel Concurrency Sanitizer on: CPU: 69 PID: 94817 Comm: systemd-udevd Tainted: G W O L 5.5.0-next-20200204+ #6 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019 A page never changes its zone number. The zone number happens to be stored in the same word as other bits which are modified, but the zone number bits will never be modified by any other write, so it can accept a reload of the zone bits after an intervening write and it don't need to use READ_ONCE(). Thus, annotate this data race using ASSERT_EXCLUSIVE_BITS() to also assert that there are no concurrent writes to it. Suggested-by: Marco Elver Signed-off-by: Qian Cai Signed-off-by: Andrew Morton Cc: Paul E. McKenney Cc: David Hildenbrand Cc: Jan Kara Cc: John Hubbard Cc: Ira Weiny Cc: Dan Williams Link: http://lkml.kernel.org/r/1581619089-14472-1-git-send-email-cai@lca.pw Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2e7ec3ee34cf..1983e08f5906 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1067,6 +1067,7 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); static inline enum zone_type page_zonenum(const struct page *page) { + ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } -- cgit v1.2.3 From 8f28ca6bd8211214faf717677bbffe375c2a6072 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 14 Aug 2020 17:32:07 -0700 Subject: iomap: constify ioreadX() iomem argument (as in generic implementation) Patch series "iomap: Constify ioreadX() iomem argument", v3. The ioread8/16/32() and others have inconsistent interface among the architectures: some taking address as const, some not. It seems there is nothing really stopping all of them to take pointer to const. This patch (of 4): The ioreadX() and ioreadX_rep() helpers have inconsistent interface. On some architectures void *__iomem address argument is a pointer to const, on some not. Implementations of ioreadX() do not modify the memory under the address so they can be converted to a "const" version for const-safety and consistency among architectures. [krzk@kernel.org: sh: clk: fix assignment from incompatible pointer type for ioreadX()] Link: http://lkml.kernel.org/r/20200723082017.24053-1-krzk@kernel.org [akpm@linux-foundation.org: fix drivers/mailbox/bcm-pdc-mailbox.c] Link: http://lkml.kernel.org/r/202007132209.Rxmv4QyS%25lkp@intel.com Suggested-by: Geert Uytterhoeven Signed-off-by: Krzysztof Kozlowski Signed-off-by: Andrew Morton Reviewed-by: Geert Uytterhoeven Reviewed-by: Arnd Bergmann Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Yoshinori Sato Cc: Rich Felker Cc: Kalle Valo Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Dave Jiang Cc: Jon Mason Cc: Allen Hubbe Cc: "Michael S. Tsirkin" Cc: Jason Wang Link: http://lkml.kernel.org/r/20200709072837.5869-1-krzk@kernel.org Link: http://lkml.kernel.org/r/20200709072837.5869-2-krzk@kernel.org Signed-off-by: Linus Torvalds --- include/linux/io-64-nonatomic-hi-lo.h | 4 ++-- include/linux/io-64-nonatomic-lo-hi.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-64-nonatomic-hi-lo.h b/include/linux/io-64-nonatomic-hi-lo.h index ae21b72cce85..f32522bb3aa5 100644 --- a/include/linux/io-64-nonatomic-hi-lo.h +++ b/include/linux/io-64-nonatomic-hi-lo.h @@ -57,7 +57,7 @@ static inline void hi_lo_writeq_relaxed(__u64 val, volatile void __iomem *addr) #ifndef ioread64_hi_lo #define ioread64_hi_lo ioread64_hi_lo -static inline u64 ioread64_hi_lo(void __iomem *addr) +static inline u64 ioread64_hi_lo(const void __iomem *addr) { u32 low, high; @@ -79,7 +79,7 @@ static inline void iowrite64_hi_lo(u64 val, void __iomem *addr) #ifndef ioread64be_hi_lo #define ioread64be_hi_lo ioread64be_hi_lo -static inline u64 ioread64be_hi_lo(void __iomem *addr) +static inline u64 ioread64be_hi_lo(const void __iomem *addr) { u32 low, high; diff --git a/include/linux/io-64-nonatomic-lo-hi.h b/include/linux/io-64-nonatomic-lo-hi.h index faaa842dbdb9..448a21435dba 100644 --- a/include/linux/io-64-nonatomic-lo-hi.h +++ b/include/linux/io-64-nonatomic-lo-hi.h @@ -57,7 +57,7 @@ static inline void lo_hi_writeq_relaxed(__u64 val, volatile void __iomem *addr) #ifndef ioread64_lo_hi #define ioread64_lo_hi ioread64_lo_hi -static inline u64 ioread64_lo_hi(void __iomem *addr) +static inline u64 ioread64_lo_hi(const void __iomem *addr) { u32 low, high; @@ -79,7 +79,7 @@ static inline void iowrite64_lo_hi(u64 val, void __iomem *addr) #ifndef ioread64be_lo_hi #define ioread64be_lo_hi ioread64be_lo_hi -static inline u64 ioread64be_lo_hi(void __iomem *addr) +static inline u64 ioread64be_lo_hi(const void __iomem *addr) { u32 low, high; -- cgit v1.2.3 From 53bf2b0e4e4c1ff0a957474237f9dcd20036ca54 Mon Sep 17 00:00:00 2001 From: Lokesh Vutla Date: Thu, 6 Aug 2020 13:18:16 +0530 Subject: firmware: ti_sci: Add support for getting resource with subtype With SYSFW ABI 3.0 changes, interrupts coming out of an interrupt controller is identified by a type and it is consistent across SoCs. Similarly global events for Interrupt aggregator. So add an API to get resource range using a resource type. Signed-off-by: Lokesh Vutla Signed-off-by: Marc Zyngier Acked-by: Nishanth Menon Link: https://lore.kernel.org/r/20200806074826.24607-4-lokeshvutla@ti.com --- include/linux/soc/ti/ti_sci_protocol.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 49c5d29cd33c..cf27b080e148 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -220,6 +220,9 @@ struct ti_sci_rm_core_ops { u16 *range_start, u16 *range_num); }; +#define TI_SCI_RESASG_SUBTYPE_IR_OUTPUT 0 +#define TI_SCI_RESASG_SUBTYPE_IA_VINT 0xa +#define TI_SCI_RESASG_SUBTYPE_GLOBAL_EVENT_SEVT 0xd /** * struct ti_sci_rm_irq_ops: IRQ management operations * @set_irq: Set an IRQ route between the requested source @@ -556,6 +559,9 @@ u32 ti_sci_get_num_resources(struct ti_sci_resource *res); struct ti_sci_resource * devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle, struct device *dev, u32 dev_id, char *of_prop); +struct ti_sci_resource * +devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev, + u32 dev_id, u32 sub_type); #else /* CONFIG_TI_SCI_PROTOCOL */ @@ -609,6 +615,13 @@ devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle, { return ERR_PTR(-EINVAL); } + +static inline struct ti_sci_resource * +devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev, + u32 dev_id, u32 sub_type); +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_TI_SCI_PROTOCOL */ #endif /* __TISCI_PROTOCOL_H */ -- cgit v1.2.3 From 29e44f4535faa71a70827af3639b5e6762d8f02a Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 17 Aug 2020 11:07:28 +0100 Subject: watch_queue: Limit the number of watches a user can hold Impose a limit on the number of watches that a user can hold so that they can't use this mechanism to fill up all the available memory. This is done by putting a counter in user_struct that's incremented when a watch is allocated and decreased when it is released. If the number exceeds the RLIMIT_NOFILE limit, the watch is rejected with EAGAIN. This can be tested by the following means: (1) Create a watch queue and attach it to fd 5 in the program given - in this case, bash: keyctl watch_session /tmp/nlog /tmp/gclog 5 bash (2) In the shell, set the maximum number of files to, say, 99: ulimit -n 99 (3) Add 200 keyrings: for ((i=0; i<200; i++)); do keyctl newring a$i @s || break; done (4) Try to watch all of the keyrings: for ((i=0; i<200; i++)); do echo $i; keyctl watch_add 5 %:a$i || break; done This should fail when the number of watches belonging to the user hits 99. (5) Remove all the keyrings and all of those watches should go away: for ((i=0; i<200; i++)); do keyctl unlink %:a$i; done (6) Kill off the watch queue by exiting the shell spawned by watch_session. Fixes: c73be61cede5 ("pipe: Add general notification queue support") Reported-by: Linus Torvalds Signed-off-by: David Howells Reviewed-by: Jarkko Sakkinen Signed-off-by: Linus Torvalds --- include/linux/sched/user.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 917d88edb7b9..a8ec3b6093fc 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -36,6 +36,9 @@ struct user_struct { defined(CONFIG_NET) || defined(CONFIG_IO_URING) atomic_long_t locked_vm; #endif +#ifdef CONFIG_WATCH_QUEUE + atomic_t nr_watches; /* The number of watches this user currently has */ +#endif /* Miscellaneous per-user rate limit */ struct ratelimit_state ratelimit; -- cgit v1.2.3 From 0b76e642f9ad2471e899e2dd71b9543b7e85e9f6 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 16 Aug 2020 15:25:49 -0700 Subject: phylink: : fix function prototype kernel-doc warning Fix a kernel-doc warning for the pcs_config() function prototype: ../include/linux/phylink.h:406: warning: Excess function parameter 'permit_pause_to_mac' description in 'pcs_config' Fixes: 7137e18f6f88 ("net: phylink: add struct phylink_pcs") Signed-off-by: Randy Dunlap Cc: Russell King Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: David S. Miller --- include/linux/phylink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index a8e876317e25..c36fb41a7d90 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -402,7 +402,8 @@ void pcs_get_state(struct phylink_pcs *pcs, * For most 10GBASE-R, there is no advertisement. */ int pcs_config(struct phylink_pcs *pcs, unsigned int mode, - phy_interface_t interface, const unsigned long *advertising); + phy_interface_t interface, const unsigned long *advertising, + bool permit_pause_to_mac); /** * pcs_an_restart() - restart 802.3z BaseX autonegotiation -- cgit v1.2.3 From bd05220c7be3356046861c317d9c287ca50445ba Mon Sep 17 00:00:00 2001 From: Jessica Clarke Date: Tue, 11 Aug 2020 19:24:57 +0100 Subject: arch/ia64: Restore arch-specific pgd_offset_k implementation IA-64 is special and treats pgd_offset_k() differently to pgd_offset(), using different formulae to calculate the indices into the kernel and user PGDs. The index into the user PGDs takes into account the region number, but the index into the kernel (init_mm) PGD always assumes a predefined kernel region number. Commit 974b9b2c68f3 ("mm: consolidate pte_index() and pte_offset_*() definitions") made IA-64 use a generic pgd_offset_k() which incorrectly used pgd_index() for kernel page tables. As a result, the index into the kernel PGD was going out of bounds and the kernel hung during early boot. Allow overrides of pgd_offset_k() and override it on IA-64 with the old implementation that will correctly index the kernel PGD. Fixes: 974b9b2c68f3 ("mm: consolidate pte_index() and pte_offset_*() definitions") Reported-by: John Paul Adrian Glaubitz Signed-off-by: Jessica Clarke Tested-by: John Paul Adrian Glaubitz Acked-by: Tony Luck Signed-off-by: Mike Rapoport --- include/linux/pgtable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index a124c21e3204..e8cbc2e795d5 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -117,7 +117,9 @@ static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ +#ifndef pgd_offset_k #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) +#endif /* * In many cases it is known that a virtual address is mapped at PMD or PTE -- cgit v1.2.3 From cc5453a5b7e90c39f713091a7ebc53c1f87d1700 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 18 Aug 2020 16:15:58 +0200 Subject: netfilter: conntrack: allow sctp hearbeat after connection re-use If an sctp connection gets re-used, heartbeats are flagged as invalid because their vtag doesn't match. Handle this in a similar way as TCP conntrack when it suspects that the endpoints and conntrack are out-of-sync. When a HEARTBEAT request fails its vtag validation, flag this in the conntrack state and accept the packet. When a HEARTBEAT_ACK is received with an invalid vtag in the reverse direction after we allowed such a HEARTBEAT through, assume we are out-of-sync and re-set the vtag info. v2: remove left-over snippet from an older incarnation that moved new_state/old_state assignments, thats not needed so keep that as-is. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_sctp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h index 9a33f171aa82..625f491b95de 100644 --- a/include/linux/netfilter/nf_conntrack_sctp.h +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -9,6 +9,8 @@ struct ip_ct_sctp { enum sctp_conntrack state; __be32 vtag[IP_CT_DIR_MAX]; + u8 last_dir; + u8 flags; }; #endif /* _NF_CONNTRACK_SCTP_H */ -- cgit v1.2.3 From 2ac6795fcc085e8d03649f1bbd0d70aaff612cad Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Mon, 17 Aug 2020 18:12:49 +0530 Subject: clocksource/drivers: Add CLINT timer driver We add a separate CLINT timer driver for Linux RISC-V M-mode (i.e. RISC-V NoMMU kernel). The CLINT MMIO device provides three things: 1. 64bit free running counter register 2. 64bit per-CPU time compare registers 3. 32bit per-CPU inter-processor interrupt registers Unlike other timer devices, CLINT provides IPI registers along with timer registers. To use CLINT IPI registers, the CLINT timer driver provides IPI related callbacks to arch/riscv. Signed-off-by: Anup Patel Tested-by: Emil Renner Berhing Acked-by: Daniel Lezcano Reviewed-by: Atish Patra Reviewed-by: Palmer Dabbelt Signed-off-by: Palmer Dabbelt --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index a2710e654b64..3215023d4852 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -132,6 +132,7 @@ enum cpuhp_state { CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING, + CPUHP_AP_CLINT_TIMER_STARTING, CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, CPUHP_AP_KVM_STARTING, -- cgit v1.2.3 From 4d2d4ce001f283ed8127173543b4cfb65641e357 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Tue, 4 Aug 2020 19:06:01 +0200 Subject: KVM: arm64: Drop type input from kvm_put_guest We can use typeof() to avoid the need for the type input. Suggested-by: Marc Zyngier Signed-off-by: Andrew Jones Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20200804170604.42662-4-drjones@redhat.com --- include/linux/kvm_host.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a23076765b4c..84371fb06209 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -749,25 +749,26 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); -#define __kvm_put_guest(kvm, gfn, offset, value, type) \ +#define __kvm_put_guest(kvm, gfn, offset, v) \ ({ \ unsigned long __addr = gfn_to_hva(kvm, gfn); \ - type __user *__uaddr = (type __user *)(__addr + offset); \ + typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \ int __ret = -EFAULT; \ \ if (!kvm_is_error_hva(__addr)) \ - __ret = put_user(value, __uaddr); \ + __ret = put_user(v, __uaddr); \ if (!__ret) \ mark_page_dirty(kvm, gfn); \ __ret; \ }) -#define kvm_put_guest(kvm, gpa, value, type) \ +#define kvm_put_guest(kvm, gpa, v) \ ({ \ gpa_t __gpa = gpa; \ struct kvm *__kvm = kvm; \ + \ __kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT, \ - offset_in_page(__gpa), (value), type); \ + offset_in_page(__gpa), v); \ }) int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); -- cgit v1.2.3 From 53f985584e3c2ebe5f2455530fbf87a001528db8 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Tue, 4 Aug 2020 19:06:02 +0200 Subject: KVM: arm64: pvtime: Fix stolen time accounting across migration When updating the stolen time we should always read the current stolen time from the user provided memory, not from a kernel cache. If we use a cache then we'll end up resetting stolen time to zero on the first update after migration. Signed-off-by: Andrew Jones Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20200804170604.42662-5-drjones@redhat.com --- include/linux/kvm_host.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 84371fb06209..05e3c2fb3ef7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -749,6 +749,26 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); +#define __kvm_get_guest(kvm, gfn, offset, v) \ +({ \ + unsigned long __addr = gfn_to_hva(kvm, gfn); \ + typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \ + int __ret = -EFAULT; \ + \ + if (!kvm_is_error_hva(__addr)) \ + __ret = get_user(v, __uaddr); \ + __ret; \ +}) + +#define kvm_get_guest(kvm, gpa, v) \ +({ \ + gpa_t __gpa = gpa; \ + struct kvm *__kvm = kvm; \ + \ + __kvm_get_guest(__kvm, __gpa >> PAGE_SHIFT, \ + offset_in_page(__gpa), v); \ +}) + #define __kvm_put_guest(kvm, gfn, offset, v) \ ({ \ unsigned long __addr = gfn_to_hva(kvm, gfn); \ -- cgit v1.2.3 From df561f6688fef775baa341a0f5d960becd248b11 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Sun, 23 Aug 2020 17:36:59 -0500 Subject: treewide: Use fallthrough pseudo-keyword Replace the existing /* fall through */ comments and its variants with the new pseudo-keyword macro fallthrough[1]. Also, remove unnecessary fall-through markings when it is the case. [1] https://www.kernel.org/doc/html/v5.7/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-through Signed-off-by: Gustavo A. R. Silva --- include/linux/compat.h | 6 +++--- include/linux/filter.h | 2 +- include/linux/jhash.h | 26 +++++++++++++------------- include/linux/mm.h | 9 ++++++--- include/linux/signal.h | 12 ++++++------ include/linux/skbuff.h | 12 ++++++------ 6 files changed, 35 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index d38c4d7e83bd..b354ce58966e 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -429,11 +429,11 @@ put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, compat_sigset_t v; switch (_NSIG_WORDS) { case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; - /* fall through */ + fallthrough; case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; - /* fall through */ + fallthrough; case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; - /* fall through */ + fallthrough; case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; } return copy_to_user(compat, &v, size) ? -EFAULT : 0; diff --git a/include/linux/filter.h b/include/linux/filter.h index 0a355b005bf4..ebfb7cfb65f1 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1200,7 +1200,7 @@ static inline u16 bpf_anc_helper(const struct sock_filter *ftest) BPF_ANCILLARY(RANDOM); BPF_ANCILLARY(VLAN_TPID); } - /* Fallthrough. */ + fallthrough; default: return ftest->code; } diff --git a/include/linux/jhash.h b/include/linux/jhash.h index 19ddd43aee68..cfb62e9f37be 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -86,17 +86,17 @@ static inline u32 jhash(const void *key, u32 length, u32 initval) } /* Last block: affect all 32 bits of (c) */ switch (length) { - case 12: c += (u32)k[11]<<24; /* fall through */ - case 11: c += (u32)k[10]<<16; /* fall through */ - case 10: c += (u32)k[9]<<8; /* fall through */ - case 9: c += k[8]; /* fall through */ - case 8: b += (u32)k[7]<<24; /* fall through */ - case 7: b += (u32)k[6]<<16; /* fall through */ - case 6: b += (u32)k[5]<<8; /* fall through */ - case 5: b += k[4]; /* fall through */ - case 4: a += (u32)k[3]<<24; /* fall through */ - case 3: a += (u32)k[2]<<16; /* fall through */ - case 2: a += (u32)k[1]<<8; /* fall through */ + case 12: c += (u32)k[11]<<24; fallthrough; + case 11: c += (u32)k[10]<<16; fallthrough; + case 10: c += (u32)k[9]<<8; fallthrough; + case 9: c += k[8]; fallthrough; + case 8: b += (u32)k[7]<<24; fallthrough; + case 7: b += (u32)k[6]<<16; fallthrough; + case 6: b += (u32)k[5]<<8; fallthrough; + case 5: b += k[4]; fallthrough; + case 4: a += (u32)k[3]<<24; fallthrough; + case 3: a += (u32)k[2]<<16; fallthrough; + case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ @@ -132,8 +132,8 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) /* Handle the last 3 u32's */ switch (length) { - case 3: c += k[2]; /* fall through */ - case 2: b += k[1]; /* fall through */ + case 3: c += k[2]; fallthrough; + case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 1983e08f5906..97c83773b6f0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -157,11 +157,14 @@ static inline void __mm_zero_struct_page(struct page *page) switch (sizeof(struct page)) { case 80: - _pp[9] = 0; /* fallthrough */ + _pp[9] = 0; + fallthrough; case 72: - _pp[8] = 0; /* fallthrough */ + _pp[8] = 0; + fallthrough; case 64: - _pp[7] = 0; /* fallthrough */ + _pp[7] = 0; + fallthrough; case 56: _pp[6] = 0; _pp[5] = 0; diff --git a/include/linux/signal.h b/include/linux/signal.h index 6bb1a3f0258c..7bbc0e9cf084 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -137,11 +137,11 @@ static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \ b3 = b->sig[3]; b2 = b->sig[2]; \ r->sig[3] = op(a3, b3); \ r->sig[2] = op(a2, b2); \ - /* fall through */ \ + fallthrough; \ case 2: \ a1 = a->sig[1]; b1 = b->sig[1]; \ r->sig[1] = op(a1, b1); \ - /* fall through */ \ + fallthrough; \ case 1: \ a0 = a->sig[0]; b0 = b->sig[0]; \ r->sig[0] = op(a0, b0); \ @@ -171,9 +171,9 @@ static inline void name(sigset_t *set) \ switch (_NSIG_WORDS) { \ case 4: set->sig[3] = op(set->sig[3]); \ set->sig[2] = op(set->sig[2]); \ - /* fall through */ \ + fallthrough; \ case 2: set->sig[1] = op(set->sig[1]); \ - /* fall through */ \ + fallthrough; \ case 1: set->sig[0] = op(set->sig[0]); \ break; \ default: \ @@ -194,7 +194,7 @@ static inline void sigemptyset(sigset_t *set) memset(set, 0, sizeof(sigset_t)); break; case 2: set->sig[1] = 0; - /* fall through */ + fallthrough; case 1: set->sig[0] = 0; break; } @@ -207,7 +207,7 @@ static inline void sigfillset(sigset_t *set) memset(set, -1, sizeof(sigset_t)); break; case 2: set->sig[1] = -1; - /* fall through */ + fallthrough; case 1: set->sig[0] = -1; break; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 46881d902124..ab57cf787c1f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3745,19 +3745,19 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 24: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 16: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 20: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 12: diffs |= __it_diff(a, b, 64); - /* fall through */ + fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; } -- cgit v1.2.3 From 12564485ed8caac3c18572793ec01330792c7191 Mon Sep 17 00:00:00 2001 From: Shawn Anastasio Date: Fri, 21 Aug 2020 13:55:56 -0500 Subject: Revert "powerpc/64s: Remove PROT_SAO support" This reverts commit 5c9fa16e8abd342ce04dc830c1ebb2a03abf6c05. Since PROT_SAO can still be useful for certain classes of software, reintroduce it. Concerns about guest migration for LPARs using SAO will be addressed next. Signed-off-by: Shawn Anastasio Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200821185558.35561-2-shawn@anastas.io --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1983e08f5906..5abe6df4247e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -321,6 +321,8 @@ extern unsigned int kobjsize(const void *objp); #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ +#elif defined(CONFIG_PPC) +# define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_IA64) -- cgit v1.2.3 From f062f025fc3a4fae3e6a50d13fb1fafb11900fa7 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 19 Aug 2020 10:50:08 +0200 Subject: libceph: add __maybe_unused to DEFINE_CEPH_FEATURE Avoid -Wunused-const-variable warnings for "make W=1". Reported-by: Leon Romanovsky Signed-off-by: Ilya Dryomov Reviewed-by: Leon Romanovsky --- include/linux/ceph/ceph_features.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index fcd84e8d88f4..999636d53cf2 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -11,14 +11,14 @@ #define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL #define DEFINE_CEPH_FEATURE(bit, incarnation, name) \ - static const uint64_t CEPH_FEATURE_##name = (1ULL< Date: Sat, 22 Aug 2020 08:23:29 +1000 Subject: net: Get rid of consume_skb when tracing is off The function consume_skb is only meaningful when tracing is enabled. This patch makes it conditional on CONFIG_TRACEPOINTS. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 46881d902124..e8bca74857a3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1056,7 +1056,16 @@ void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); + +#ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); +#else +static inline void consume_skb(struct sk_buff *skb) +{ + return kfree_skb(skb); +} +#endif + void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); extern struct kmem_cache *skbuff_head_cache; -- cgit v1.2.3 From c94a88f341c9b8f05d8639f62bb5d95936f881cd Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 20 Aug 2020 19:20:46 +0200 Subject: sched: Use __always_inline on is_idle_task() is_idle_task() may be used from noinstr functions such as irqentry_enter(). Since the compiler is free to not inline regular inline functions, switch to using __always_inline. Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200820172046.GA177701@elver.google.com --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 93ecd930efd3..afe01e232935 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1666,7 +1666,7 @@ extern struct task_struct *idle_task(int cpu); * * Return: 1 if @p is an idle task. 0 otherwise. */ -static inline bool is_idle_task(const struct task_struct *p) +static __always_inline bool is_idle_task(const struct task_struct *p) { return !!(p->flags & PF_IDLE); } -- cgit v1.2.3 From fddf9055a60dfcc97bda5ef03c8fa4108ed555c5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 Aug 2020 09:13:30 +0200 Subject: lockdep: Use raw_cpu_*() for per-cpu variables Sven reported that commit a21ee6055c30 ("lockdep: Change hardirq{s_enabled,_context} to per-cpu variables") caused trouble on s390 because their this_cpu_*() primitives disable preemption which then lands back tracing. On the one hand, per-cpu ops should use preempt_*able_notrace() and raw_local_irq_*(), on the other hand, we can trivialy use raw_cpu_*() ops for this. Fixes: a21ee6055c30 ("lockdep: Change hardirq{s_enabled,_context} to per-cpu variables") Reported-by: Sven Schnelle Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Thomas Gleixner Acked-by: Rafael J. Wysocki Tested-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200821085348.192346882@infradead.org --- include/linux/irqflags.h | 6 +++--- include/linux/lockdep.h | 18 +++++++++++++----- 2 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index bd5c55755447..d7e50a215ea9 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -53,13 +53,13 @@ DECLARE_PER_CPU(int, hardirq_context); extern void trace_hardirqs_off_finish(void); extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); -# define lockdep_hardirq_context() (this_cpu_read(hardirq_context)) +# define lockdep_hardirq_context() (raw_cpu_read(hardirq_context)) # define lockdep_softirq_context(p) ((p)->softirq_context) # define lockdep_hardirqs_enabled() (this_cpu_read(hardirqs_enabled)) # define lockdep_softirqs_enabled(p) ((p)->softirqs_enabled) # define lockdep_hardirq_enter() \ do { \ - if (this_cpu_inc_return(hardirq_context) == 1) \ + if (__this_cpu_inc_return(hardirq_context) == 1)\ current->hardirq_threaded = 0; \ } while (0) # define lockdep_hardirq_threaded() \ @@ -68,7 +68,7 @@ do { \ } while (0) # define lockdep_hardirq_exit() \ do { \ - this_cpu_dec(hardirq_context); \ + __this_cpu_dec(hardirq_context); \ } while (0) # define lockdep_softirq_enter() \ do { \ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 62a382d1845b..6a584b3e5c74 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -535,19 +535,27 @@ do { \ DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); +/* + * The below lockdep_assert_*() macros use raw_cpu_read() to access the above + * per-cpu variables. This is required because this_cpu_read() will potentially + * call into preempt/irq-disable and that obviously isn't right. This is also + * correct because when IRQs are enabled, it doesn't matter if we accidentally + * read the value from our previous CPU. + */ + #define lockdep_assert_irqs_enabled() \ do { \ - WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirqs_enabled)); \ + WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_irqs_disabled() \ do { \ - WARN_ON_ONCE(debug_locks && this_cpu_read(hardirqs_enabled)); \ + WARN_ON_ONCE(debug_locks && raw_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_in_irq() \ do { \ - WARN_ON_ONCE(debug_locks && !this_cpu_read(hardirq_context)); \ + WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirq_context)); \ } while (0) #define lockdep_assert_preemption_enabled() \ @@ -555,7 +563,7 @@ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ debug_locks && \ (preempt_count() != 0 || \ - !this_cpu_read(hardirqs_enabled))); \ + !raw_cpu_read(hardirqs_enabled))); \ } while (0) #define lockdep_assert_preemption_disabled() \ @@ -563,7 +571,7 @@ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ debug_locks && \ (preempt_count() == 0 && \ - this_cpu_read(hardirqs_enabled))); \ + raw_cpu_read(hardirqs_enabled))); \ } while (0) #else -- cgit v1.2.3 From bf9282dc26e7fe2a0736edc568762f0f05d12416 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 12 Aug 2020 12:22:17 +0200 Subject: cpuidle: Make CPUIDLE_FLAG_TLB_FLUSHED generic This allows moving the leave_mm() call into generic code before rcu_idle_enter(). Gets rid of more trace_*_rcuidle() users. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Thomas Gleixner Acked-by: Rafael J. Wysocki Tested-by: Marco Elver Link: https://lkml.kernel.org/r/20200821085348.369441600@infradead.org --- include/linux/cpuidle.h | 13 +++++++------ include/linux/mmu_context.h | 5 +++++ 2 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index b65909ae4e20..75895e6363b8 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -75,12 +75,13 @@ struct cpuidle_state { }; /* Idle State Flags */ -#define CPUIDLE_FLAG_NONE (0x00) -#define CPUIDLE_FLAG_POLLING BIT(0) /* polling state */ -#define CPUIDLE_FLAG_COUPLED BIT(1) /* state applies to multiple cpus */ -#define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */ -#define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ -#define CPUIDLE_FLAG_OFF BIT(4) /* disable this state by default */ +#define CPUIDLE_FLAG_NONE (0x00) +#define CPUIDLE_FLAG_POLLING BIT(0) /* polling state */ +#define CPUIDLE_FLAG_COUPLED BIT(1) /* state applies to multiple cpus */ +#define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */ +#define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ +#define CPUIDLE_FLAG_OFF BIT(4) /* disable this state by default */ +#define CPUIDLE_FLAG_TLB_FLUSHED BIT(5) /* idle-state flushes TLBs */ struct cpuidle_device_kobj; struct cpuidle_state_kobj; diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index c51a84132d7c..03dee12d2b61 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -3,10 +3,15 @@ #define _LINUX_MMU_CONTEXT_H #include +#include /* Architectures that care about IRQ state in switch_mm can override this. */ #ifndef switch_mm_irqs_off # define switch_mm_irqs_off switch_mm #endif +#ifndef leave_mm +static inline void leave_mm(int cpu) { } +#endif + #endif -- cgit v1.2.3 From 00b0ed2d4997af6d0a93edef820386951fd66d94 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 12 Aug 2020 19:28:06 +0200 Subject: locking/lockdep: Cleanup Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Thomas Gleixner Acked-by: Rafael J. Wysocki Tested-by: Marco Elver Link: https://lkml.kernel.org/r/20200821085348.546087214@infradead.org --- include/linux/irqflags.h | 54 +++++++++++++++++++++++++++--------------------- 1 file changed, 30 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index d7e50a215ea9..00d553d77911 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -49,10 +49,11 @@ struct irqtrace_events { DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); - extern void trace_hardirqs_on_prepare(void); - extern void trace_hardirqs_off_finish(void); - extern void trace_hardirqs_on(void); - extern void trace_hardirqs_off(void); +extern void trace_hardirqs_on_prepare(void); +extern void trace_hardirqs_off_finish(void); +extern void trace_hardirqs_on(void); +extern void trace_hardirqs_off(void); + # define lockdep_hardirq_context() (raw_cpu_read(hardirq_context)) # define lockdep_softirq_context(p) ((p)->softirq_context) # define lockdep_hardirqs_enabled() (this_cpu_read(hardirqs_enabled)) @@ -120,17 +121,17 @@ do { \ #else # define trace_hardirqs_on_prepare() do { } while (0) # define trace_hardirqs_off_finish() do { } while (0) -# define trace_hardirqs_on() do { } while (0) -# define trace_hardirqs_off() do { } while (0) -# define lockdep_hardirq_context() 0 -# define lockdep_softirq_context(p) 0 -# define lockdep_hardirqs_enabled() 0 -# define lockdep_softirqs_enabled(p) 0 -# define lockdep_hardirq_enter() do { } while (0) -# define lockdep_hardirq_threaded() do { } while (0) -# define lockdep_hardirq_exit() do { } while (0) -# define lockdep_softirq_enter() do { } while (0) -# define lockdep_softirq_exit() do { } while (0) +# define trace_hardirqs_on() do { } while (0) +# define trace_hardirqs_off() do { } while (0) +# define lockdep_hardirq_context() 0 +# define lockdep_softirq_context(p) 0 +# define lockdep_hardirqs_enabled() 0 +# define lockdep_softirqs_enabled(p) 0 +# define lockdep_hardirq_enter() do { } while (0) +# define lockdep_hardirq_threaded() do { } while (0) +# define lockdep_hardirq_exit() do { } while (0) +# define lockdep_softirq_enter() do { } while (0) +# define lockdep_softirq_exit() do { } while (0) # define lockdep_hrtimer_enter(__hrtimer) false # define lockdep_hrtimer_exit(__context) do { } while (0) # define lockdep_posixtimer_enter() do { } while (0) @@ -181,17 +182,25 @@ do { \ * if !TRACE_IRQFLAGS. */ #ifdef CONFIG_TRACE_IRQFLAGS -#define local_irq_enable() \ - do { trace_hardirqs_on(); raw_local_irq_enable(); } while (0) -#define local_irq_disable() \ - do { raw_local_irq_disable(); trace_hardirqs_off(); } while (0) + +#define local_irq_enable() \ + do { \ + trace_hardirqs_on(); \ + raw_local_irq_enable(); \ + } while (0) + +#define local_irq_disable() \ + do { \ + raw_local_irq_disable(); \ + trace_hardirqs_off(); \ + } while (0) + #define local_irq_save(flags) \ do { \ raw_local_irq_save(flags); \ trace_hardirqs_off(); \ } while (0) - #define local_irq_restore(flags) \ do { \ if (raw_irqs_disabled_flags(flags)) { \ @@ -214,10 +223,7 @@ do { \ #define local_irq_enable() do { raw_local_irq_enable(); } while (0) #define local_irq_disable() do { raw_local_irq_disable(); } while (0) -#define local_irq_save(flags) \ - do { \ - raw_local_irq_save(flags); \ - } while (0) +#define local_irq_save(flags) do { raw_local_irq_save(flags); } while (0) #define local_irq_restore(flags) do { raw_local_irq_restore(flags); } while (0) #define safe_halt() do { raw_safe_halt(); } while (0) -- cgit v1.2.3 From 044d0d6de9f50192f9697583504a382347ee95ca Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 23 Jul 2020 20:56:14 +1000 Subject: lockdep: Only trace IRQ edges Problem: raw_local_irq_save(); // software state on local_irq_save(); // software state off ... local_irq_restore(); // software state still off, because we don't enable IRQs raw_local_irq_restore(); // software state still off, *whoopsie* existing instances: - lock_acquire() raw_local_irq_save() __lock_acquire() arch_spin_lock(&graph_lock) pv_wait() := kvm_wait() (same or worse for Xen/HyperV) local_irq_save() - trace_clock_global() raw_local_irq_save() arch_spin_lock() pv_wait() := kvm_wait() local_irq_save() - apic_retrigger_irq() raw_local_irq_save() apic->send_IPI() := default_send_IPI_single_phys() local_irq_save() Possible solutions: A) make it work by enabling the tracing inside raw_*() B) make it work by keeping tracing disabled inside raw_*() C) call it broken and clean it up now Now, given that the only reason to use the raw_* variant is because you don't want tracing. Therefore A) seems like a weird option (although it can be done). C) is tempting, but OTOH it ends up converting a _lot_ of code to raw just because there is one raw user, this strips the validation/tracing off for all the other users. So we pick B) and declare any code that ends up doing: raw_local_irq_save() local_irq_save() lockdep_assert_irqs_disabled(); broken. AFAICT this problem has existed forever, the only reason it came up is because commit: 859d069ee1dd ("lockdep: Prepare for NMI IRQ state tracking") changed IRQ tracing vs lockdep recursion and the first instance is fairly common, the other cases hardly ever happen. Signed-off-by: Nicholas Piggin [rewrote changelog] Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Thomas Gleixner Acked-by: Rafael J. Wysocki Tested-by: Marco Elver Link: https://lkml.kernel.org/r/20200723105615.1268126-1-npiggin@gmail.com --- include/linux/irqflags.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 00d553d77911..3ed4e8771b64 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -191,25 +191,24 @@ do { \ #define local_irq_disable() \ do { \ + bool was_disabled = raw_irqs_disabled();\ raw_local_irq_disable(); \ - trace_hardirqs_off(); \ + if (!was_disabled) \ + trace_hardirqs_off(); \ } while (0) #define local_irq_save(flags) \ do { \ raw_local_irq_save(flags); \ - trace_hardirqs_off(); \ + if (!raw_irqs_disabled_flags(flags)) \ + trace_hardirqs_off(); \ } while (0) #define local_irq_restore(flags) \ do { \ - if (raw_irqs_disabled_flags(flags)) { \ - raw_local_irq_restore(flags); \ - trace_hardirqs_off(); \ - } else { \ + if (!raw_irqs_disabled_flags(flags)) \ trace_hardirqs_on(); \ - raw_local_irq_restore(flags); \ - } \ + raw_local_irq_restore(flags); \ } while (0) #define safe_halt() \ -- cgit v1.2.3 From aac544c3553d98ebe150dda19a25aa253f7ad3fe Mon Sep 17 00:00:00 2001 From: Luc Van Oostenryck Date: Tue, 25 Aug 2020 01:25:11 +0200 Subject: Compiler Attributes: remove comment about sparse not supporting __has_attribute Sparse supports __has_attribute() since 2018-08-31, so the comment is not true anymore but more importantly is rather confusing. So remove it. Signed-off-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 6122efdad6ad..af7a58c19e20 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -24,12 +24,6 @@ * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. * In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute * by hand. - * - * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__ - * depending on the compiler used to build it; however, these attributes have - * no semantic effects for sparse, so it does not matter. Also note that, - * in order to avoid sparse's warnings, even the unsupported ones must be - * defined to 0. */ #ifndef __has_attribute # define __has_attribute(x) __GCC4_has_attribute_##x -- cgit v1.2.3 From 5861af92ff2a2e002449191413c35f3ec5f721fe Mon Sep 17 00:00:00 2001 From: Luc Van Oostenryck Date: Tue, 25 Aug 2020 01:25:26 +0200 Subject: Compiler Attributes: fix comment concerning GCC 4.6 GCC 4.6 is not supported anymore, so remove a reference to it, leaving just the part about version prior GCC 5. Signed-off-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index af7a58c19e20..ea7b756b1c8f 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -22,7 +22,7 @@ /* * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. - * In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute + * In the meantime, to support gcc < 5, we implement __has_attribute * by hand. */ #ifndef __has_attribute -- cgit v1.2.3 From 30b8e6b22fd0f7a56911e69c681e92532e72e3b6 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 27 Aug 2020 10:54:16 +0530 Subject: cpufreq: Use WARN_ON_ONCE() for invalid relation The relation can't be invalid here, so if it turns out to be invalid, just WARN_ON_ONCE() and return 0. Signed-off-by: Viresh Kumar [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 8f141d4c859c..a911e5d06845 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -956,8 +956,8 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, case CPUFREQ_RELATION_C: return cpufreq_table_find_index_c(policy, target_freq); default: - pr_err("%s: Invalid relation: %d\n", __func__, relation); - return -EINVAL; + WARN_ON_ONCE(1); + return 0; } } -- cgit v1.2.3 From 645f08975f49441b3e753d8dc5b740cbcb226594 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 27 Aug 2020 07:27:49 -0400 Subject: net: Fix some comments Fix some comments, including wrong function name, duplicated word and so on. Signed-off-by: Miaohe Lin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e8bca74857a3..8d9ab50b08c9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -71,7 +71,7 @@ * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or - * IPv4|UDP where the Next Header field in the IPv6 + * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with @@ -2667,7 +2667,7 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. - * get_rps_cpus() for example only access one 64 bytes aligned block : + * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD -- cgit v1.2.3 From ee921183557af39c1a0475f982d43b0fcac25e2e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 23 Aug 2020 13:55:36 +0200 Subject: netfilter: nfnetlink: nfnetlink_unicast() reports EAGAIN instead of ENOBUFS Frontend callback reports EAGAIN to nfnetlink to retry a command, this is used to signal that module autoloading is required. Unfortunately, nlmsg_unicast() reports EAGAIN in case the receiver socket buffer gets full, so it enters a busy-loop. This patch updates nfnetlink_unicast() to turn EAGAIN into ENOBUFS and to use nlmsg_unicast(). Remove the flags field in nfnetlink_unicast() since this is always MSG_DONTWAIT in the existing code which is exactly what nlmsg_unicast() passes to netlink_unicast() as parameter. Fixes: 96518518cc41 ("netfilter: add nftables") Reported-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 851425c3178f..89016d08f6a2 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -43,8 +43,7 @@ int nfnetlink_has_listeners(struct net *net, unsigned int group); int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags); int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error); -int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, - int flags); +int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid); static inline u16 nfnl_msg_type(u8 subsys, u8 msg_type) { -- cgit v1.2.3 From ef91bb196b0db1013ef8705367bc2d7944ef696b Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 28 Aug 2020 17:11:25 +1000 Subject: kernel.h: Silence sparse warning in lower_32_bits I keep getting sparse warnings in crypto such as: CHECK drivers/crypto/ccree/cc_hash.c drivers/crypto/ccree/cc_hash.c:49:9: warning: cast truncates bits from constant value (47b5481dbefa4fa4 becomes befa4fa4) drivers/crypto/ccree/cc_hash.c:49:26: warning: cast truncates bits from constant value (db0c2e0d64f98fa7 becomes 64f98fa7) [.. many more ..] This patch removes the warning by adding a mask to keep sparse happy. Signed-off-by: Herbert Xu Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 500def620d8f..c25b8e41c0ea 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -186,7 +186,7 @@ * lower_32_bits - return bits 0-31 of a number * @n: the number we're accessing */ -#define lower_32_bits(n) ((u32)(n)) +#define lower_32_bits(n) ((u32)((n) & 0xffffffff)) struct completion; struct pt_regs; -- cgit v1.2.3 From e5fc436f06eef54ef512ea55a9db8eb9f2e76959 Mon Sep 17 00:00:00 2001 From: Luc Van Oostenryck Date: Fri, 28 Aug 2020 10:53:01 +0200 Subject: sparse: use static inline for __chk_{user,io}_ptr() __chk_user_ptr() & __chk_io_ptr() are dummy extern functions which only exist to enforce the typechecking of __user or __iomem pointers in macros when using sparse. This typechecking is done by inserting a call to these functions. But the presence of these calls can inhibit some simplifications and so influence the result of sparse's analysis of context/locking. Fix this by changing these calls into static inline calls with an empty body. Signed-off-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 4b33cb385f96..6e390d58a9f8 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -11,8 +11,8 @@ # define __iomem __attribute__((noderef, address_space(__iomem))) # define __percpu __attribute__((noderef, address_space(__percpu))) # define __rcu __attribute__((noderef, address_space(__rcu))) -extern void __chk_user_ptr(const volatile void __user *); -extern void __chk_io_ptr(const volatile void __iomem *); +static inline void __chk_user_ptr(const volatile void __user *ptr) { } +static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } /* context/locking */ # define __must_hold(x) __attribute__((context(x,1,1))) # define __acquires(x) __attribute__((context(x,0,1))) -- cgit v1.2.3 From 35556bed836f8dc07ac55f69c8d17dce3e7f0e25 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 1 Sep 2020 10:52:33 +0100 Subject: HID: core: Sanitize event code and type when mapping input When calling into hid_map_usage(), the passed event code is blindly stored as is, even if it doesn't fit in the associated bitmap. This event code can come from a variety of sources, including devices masquerading as input devices, only a bit more "programmable". Instead of taking the event code at face value, check that it actually fits the corresponding bitmap, and if it doesn't: - spit out a warning so that we know which device is acting up - NULLify the bitmap pointer so that we catch unexpected uses Code paths that can make use of untrusted inputs can now check that the mapping was indeed correct and bail out if not. Cc: stable@vger.kernel.org Signed-off-by: Marc Zyngier Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 42 +++++++++++++++++++++++++++++------------- 1 file changed, 29 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 875f71132b14..c7044a14200e 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -959,34 +959,49 @@ static inline void hid_device_io_stop(struct hid_device *hid) { * @max: maximal valid usage->code to consider later (out parameter) * @type: input event type (EV_KEY, EV_REL, ...) * @c: code which corresponds to this usage and type + * + * The value pointed to by @bit will be set to NULL if either @type is + * an unhandled event type, or if @c is out of range for @type. This + * can be used as an error condition. */ static inline void hid_map_usage(struct hid_input *hidinput, struct hid_usage *usage, unsigned long **bit, int *max, - __u8 type, __u16 c) + __u8 type, unsigned int c) { struct input_dev *input = hidinput->input; - - usage->type = type; - usage->code = c; + unsigned long *bmap = NULL; + unsigned int limit = 0; switch (type) { case EV_ABS: - *bit = input->absbit; - *max = ABS_MAX; + bmap = input->absbit; + limit = ABS_MAX; break; case EV_REL: - *bit = input->relbit; - *max = REL_MAX; + bmap = input->relbit; + limit = REL_MAX; break; case EV_KEY: - *bit = input->keybit; - *max = KEY_MAX; + bmap = input->keybit; + limit = KEY_MAX; break; case EV_LED: - *bit = input->ledbit; - *max = LED_MAX; + bmap = input->ledbit; + limit = LED_MAX; break; } + + if (unlikely(c > limit || !bmap)) { + pr_warn_ratelimited("%s: Invalid code %d type %d\n", + input->name, c, type); + *bit = NULL; + return; + } + + usage->type = type; + usage->code = c; + *max = limit; + *bit = bmap; } /** @@ -1000,7 +1015,8 @@ static inline void hid_map_usage_clear(struct hid_input *hidinput, __u8 type, __u16 c) { hid_map_usage(hidinput, usage, bit, max, type, c); - clear_bit(c, *bit); + if (*bit) + clear_bit(usage->code, *bit); } /** -- cgit v1.2.3 From 3b5455636fe26ea21b4189d135a424a6da016418 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 2 Sep 2020 12:32:45 -0400 Subject: libata: implement ATA_HORKAGE_MAX_TRIM_128M and apply to Sandisks All three generations of Sandisk SSDs lock up hard intermittently. Experiments showed that disabling NCQ lowered the failure rate significantly and the kernel has been disabling NCQ for some models of SD7's and 8's, which is obviously undesirable. Karthik worked with Sandisk to root cause the hard lockups to trim commands larger than 128M. This patch implements ATA_HORKAGE_MAX_TRIM_128M which limits max trim size to 128M and applies it to all three generations of Sandisk SSDs. Signed-off-by: Tejun Heo Cc: Karthik Shivaram Cc: stable@vger.kernel.org Signed-off-by: Jens Axboe --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 77ccf040a128..5f550eb27f81 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -421,6 +421,7 @@ enum { ATA_HORKAGE_NO_DMA_LOG = (1 << 23), /* don't use DMA for log read */ ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ + ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From 7e24969022cbd61ddc586f14824fc205661bb124 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 17 Aug 2020 18:00:55 +0800 Subject: block: allow for_each_bvec to support zero len bvec Block layer usually doesn't support or allow zero-length bvec. Since commit 1bdc76aea115 ("iov_iter: use bvec iterator to implement iterate_bvec()"), iterate_bvec() switches to bvec iterator. However, Al mentioned that 'Zero-length segments are not disallowed' in iov_iter. Fixes for_each_bvec() so that it can move on after seeing one zero length bvec. Fixes: 1bdc76aea115 ("iov_iter: use bvec iterator to implement iterate_bvec()") Reported-by: syzbot Signed-off-by: Ming Lei Tested-by: Tetsuo Handa Cc: Al Viro Cc: Matthew Wilcox Cc: Link: https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg2262077.html Signed-off-by: Jens Axboe --- include/linux/bvec.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index ac0c7299d5b8..dd74503f7e5e 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -117,11 +117,18 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv, return true; } +static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter) +{ + iter->bi_bvec_done = 0; + iter->bi_idx++; +} + #define for_each_bvec(bvl, bio_vec, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ - bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len)) + (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter), \ + (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter))) /* for iterating one bio from start to end */ #define BVEC_ITER_ALL_INIT (struct bvec_iter) \ -- cgit v1.2.3 From 4533d3aed857c558d6aabd00d0cb04100c5a2258 Mon Sep 17 00:00:00 2001 From: Roger Pau Monne Date: Tue, 1 Sep 2020 10:33:25 +0200 Subject: memremap: rename MEMORY_DEVICE_DEVDAX to MEMORY_DEVICE_GENERIC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is in preparation for the logic behind MEMORY_DEVICE_DEVDAX also being used by non DAX devices. No functional change intended. Signed-off-by: Roger Pau Monné Reviewed-by: Ira Weiny Acked-by: Andrew Morton Reviewed-by: Pankaj Gupta Link: https://lore.kernel.org/r/20200901083326.21264-3-roger.pau@citrix.com Signed-off-by: Juergen Gross --- include/linux/memremap.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 5f5b2df06e61..e5862746751b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -46,11 +46,10 @@ struct vmem_altmap { * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). * - * MEMORY_DEVICE_DEVDAX: + * MEMORY_DEVICE_GENERIC: * Host memory that has similar access semantics as System RAM i.e. DMA - * coherent and supports page pinning. In contrast to - * MEMORY_DEVICE_FS_DAX, this memory is access via a device-dax - * character device. + * coherent and supports page pinning. This is for example used by DAX devices + * that expose memory using a character device. * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer @@ -60,7 +59,7 @@ enum memory_type { /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_FS_DAX, - MEMORY_DEVICE_DEVDAX, + MEMORY_DEVICE_GENERIC, MEMORY_DEVICE_PCI_P2PDMA, }; -- cgit v1.2.3 From 4facb95b7adaf77e2da73aafb9ba60996fe42a12 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 2 Sep 2020 01:50:54 +0200 Subject: x86/entry: Unbreak 32bit fast syscall Andy reported that the syscall treacing for 32bit fast syscall fails: # ./tools/testing/selftests/x86/ptrace_syscall_32 ... [RUN] SYSEMU [FAIL] Initial args are wrong (nr=224, args=10 11 12 13 14 4289172732) ... [RUN] SYSCALL [FAIL] Initial args are wrong (nr=29, args=0 0 0 0 0 4289172732) The eason is that the conversion to generic entry code moved the retrieval of the sixth argument (EBP) after the point where the syscall entry work runs, i.e. ptrace, seccomp, audit... Unbreak it by providing a split up version of syscall_enter_from_user_mode(). - syscall_enter_from_user_mode_prepare() establishes state and enables interrupts - syscall_enter_from_user_mode_work() runs the entry work Replace the call to syscall_enter_from_user_mode() in the 32bit fast syscall C-entry with the split functions and stick the EBP retrieval between them. Fixes: 27d6b4d14f5c ("x86/entry: Use generic syscall entry function") Reported-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/87k0xdjbtt.fsf@nanos.tec.linutronix.de --- include/linux/entry-common.h | 51 ++++++++++++++++++++++++++++++++++++-------- 1 file changed, 42 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index efebbffcd5cc..159c7476b11b 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -110,15 +110,30 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs #endif /** - * syscall_enter_from_user_mode - Check and handle work before invoking - * a syscall + * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts * @regs: Pointer to currents pt_regs - * @syscall: The syscall number * * Invoked from architecture specific syscall entry code with interrupts * disabled. The calling code has to be non-instrumentable. When the - * function returns all state is correct and the subsequent functions can be - * instrumented. + * function returns all state is correct, interrupts are enabled and the + * subsequent functions can be instrumented. + * + * This handles lockdep, RCU (context tracking) and tracing state. + * + * This is invoked when there is extra architecture specific functionality + * to be done between establishing state and handling user mode entry work. + */ +void syscall_enter_from_user_mode_prepare(struct pt_regs *regs); + +/** + * syscall_enter_from_user_mode_work - Check and handle work before invoking + * a syscall + * @regs: Pointer to currents pt_regs + * @syscall: The syscall number + * + * Invoked from architecture specific syscall entry code with interrupts + * enabled after invoking syscall_enter_from_user_mode_prepare() and extra + * architecture specific work. * * Returns: The original or a modified syscall number * @@ -127,12 +142,30 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs * syscall_set_return_value() first. If neither of those are called and -1 * is returned, then the syscall will fail with ENOSYS. * - * The following functionality is handled here: + * It handles the following work items: * - * 1) Establish state (lockdep, RCU (context tracking), tracing) - * 2) TIF flag dependent invocations of arch_syscall_enter_tracehook(), + * 1) TIF flag dependent invocations of arch_syscall_enter_tracehook(), * __secure_computing(), trace_sys_enter() - * 3) Invocation of audit_syscall_entry() + * 2) Invocation of audit_syscall_entry() + */ +long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall); + +/** + * syscall_enter_from_user_mode - Establish state and check and handle work + * before invoking a syscall + * @regs: Pointer to currents pt_regs + * @syscall: The syscall number + * + * Invoked from architecture specific syscall entry code with interrupts + * disabled. The calling code has to be non-instrumentable. When the + * function returns all state is correct, interrupts are enabled and the + * subsequent functions can be instrumented. + * + * This is combination of syscall_enter_from_user_mode_prepare() and + * syscall_enter_from_user_mode_work(). + * + * Returns: The original or a modified syscall number. See + * syscall_enter_from_user_mode_work() for further explanation. */ long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall); -- cgit v1.2.3 From a2d375eda771a6a4866f3717a8ed81b63acb1dbd Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Mon, 31 Aug 2020 12:22:09 -0600 Subject: dyndbg: refine export, rename to dynamic_debug_exec_queries() commit 4c0d77828d4f ("dyndbg: export ddebug_exec_queries") had a few problems: - broken non DYNAMIC_DEBUG_CORE configs, sparse warning - the exported function modifies query string, breaks on RO strings. - func name follows internal convention, shouldn't be exposed as is. 1st is fixed in header with ifdefd function prototype or stub defn. Also remove an obsolete HAVE-symbol ifdef-comment, and add others. Fix others by wrapping existing internal function with a new one, named in accordance with module-prefix naming convention, before export hits v5.9.0. In new function, copy query string to a local buffer, so users can pass hard-coded/RO queries, and internal function can be used unchanged. Fixes: 4c0d77828d4f ("dyndbg: export ddebug_exec_queries") Signed-off-by: Jim Cromie Link: https://lore.kernel.org/r/20200831182210.850852-3-jim.cromie@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/dynamic_debug.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index aa9ff9e1c0b3..8aa0c7c2608c 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -49,6 +49,10 @@ struct _ddebug { #if defined(CONFIG_DYNAMIC_DEBUG_CORE) + +/* exported for module authors to exercise >control */ +int dynamic_debug_exec_queries(const char *query, const char *modname); + int ddebug_add_module(struct _ddebug *tab, unsigned int n, const char *modname); extern int ddebug_remove_module(const char *mod_name); @@ -105,7 +109,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, static_branch_unlikely(&descriptor.key.dd_key_false) #endif -#else /* !HAVE_JUMP_LABEL */ +#else /* !CONFIG_JUMP_LABEL */ #define _DPRINTK_KEY_INIT @@ -117,7 +121,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) #endif -#endif +#endif /* CONFIG_JUMP_LABEL */ #define __dynamic_func_call(id, fmt, func, ...) do { \ DEFINE_DYNAMIC_DEBUG_METADATA(id, fmt); \ @@ -172,10 +176,11 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, KERN_DEBUG, prefix_str, prefix_type, \ rowsize, groupsize, buf, len, ascii) -#else +#else /* !CONFIG_DYNAMIC_DEBUG_CORE */ #include #include +#include static inline int ddebug_add_module(struct _ddebug *tab, unsigned int n, const char *modname) @@ -210,6 +215,13 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, \ rowsize, groupsize, buf, len, ascii); \ } while (0) -#endif + +static inline int dynamic_debug_exec_queries(const char *query, const char *modname) +{ + pr_warn("kernel not built with CONFIG_DYNAMIC_DEBUG_CORE\n"); + return 0; +} + +#endif /* !CONFIG_DYNAMIC_DEBUG_CORE */ #endif -- cgit v1.2.3 From 1a0cf26323c80e2f1c58fc04f15686de61bfab0c Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 21 Aug 2020 19:49:56 -0400 Subject: mm/ksm: Remove reuse_ksm_page() Remove the function as the last reference has gone away with the do_wp_page() changes. Signed-off-by: Peter Xu Signed-off-by: Linus Torvalds --- include/linux/ksm.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index e48b1e453ff5..161e8164abcf 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -53,8 +53,6 @@ struct page *ksm_might_need_to_copy(struct page *page, void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); void ksm_migrate_page(struct page *newpage, struct page *oldpage); -bool reuse_ksm_page(struct page *page, - struct vm_area_struct *vma, unsigned long address); #else /* !CONFIG_KSM */ @@ -88,11 +86,6 @@ static inline void rmap_walk_ksm(struct page *page, static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage) { } -static inline bool reuse_ksm_page(struct page *page, - struct vm_area_struct *vma, unsigned long address) -{ - return false; -} #endif /* CONFIG_MMU */ #endif /* !CONFIG_KSM */ -- cgit v1.2.3 From 798a6b87ecd72828a6c6b5469aaa2032a57e92b7 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 21 Aug 2020 19:49:58 -0400 Subject: mm: Add PGREUSE counter This accounts for wp_page_reuse() case, where we reused a page for COW. Signed-off-by: Peter Xu Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 24fc7c3ae7d6..58d3f91baad1 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -30,6 +30,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGFAULT, PGMAJFAULT, PGLAZYFREED, PGREFILL, + PGREUSE, PGSTEAL_KSWAPD, PGSTEAL_DIRECT, PGSCAN_KSWAPD, -- cgit v1.2.3 From 428fc0aff4e59399ec719ffcc1f7a5d29a4ee476 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 4 Sep 2020 16:36:19 -0700 Subject: include/linux/log2.h: add missing () around n in roundup_pow_of_two() Otherwise gcc generates warnings if the expression is complicated. Fixes: 312a0c170945 ("[PATCH] LOG2: Alter roundup_pow_of_two() so that it can use a ilog2() on a constant") Signed-off-by: Jason Gunthorpe Signed-off-by: Andrew Morton Link: https://lkml.kernel.org/r/0-v1-8a2697e3c003+41165-log_brackets_jgg@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/log2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/log2.h b/include/linux/log2.h index 83a4a3ca3e8a..c619ec6eff4a 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -173,7 +173,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) #define roundup_pow_of_two(n) \ ( \ __builtin_constant_p(n) ? ( \ - (n == 1) ? 1 : \ + ((n) == 1) ? 1 : \ (1UL << (ilog2((n) - 1) + 1)) \ ) : \ __roundup_pow_of_two(n) \ -- cgit v1.2.3 From 1c30474826682bc970c3200700d8bcfa2b771278 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 6 Sep 2020 20:42:52 -0700 Subject: PM: : fix @em_pd kernel-doc warning Fix kernel-doc warning in : ../include/linux/device.h:613: warning: Function parameter or member 'em_pd' not described in 'device' Fixes: 1bc138c62295 ("PM / EM: add support for other devices than CPUs in Energy Model") Signed-off-by: Randy Dunlap Cc: Rafael J. Wysocki Reviewed-by: Lukasz Luba Link: https://lore.kernel.org/r/d97f40ad-3033-703a-c3cb-2843ce0f6371@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index ca18da4768e3..9e6ea8931a52 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -454,6 +454,7 @@ struct dev_links_info { * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. + * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pinctl.rst for details. * @msi_list: Hosts MSI descriptors -- cgit v1.2.3 From eb02d39ad3099c3dcd96c5b3fdc0303541766ed1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 6 Sep 2020 20:31:16 -0700 Subject: netdevice.h: fix proto_down_reason kernel-doc warning Fix kernel-doc warning in : ../include/linux/netdevice.h:2158: warning: Function parameter or member 'proto_down_reason' not described in 'net_device' Fixes: 829eb208e80d ("rtnetlink: add support for protodown reason") Signed-off-by: Randy Dunlap Acked-by: Roopa Prabhu Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b0e303f6603f..bf0e313486be 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1784,6 +1784,7 @@ enum netdev_priv_flags { * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers * + * @proto_down_reason: reason a netdev interface is held down * @pcpu_refcnt: Number of references to this device * @todo_list: Delayed register/unregister * @link_watch_list: XXX: need comments on this one -- cgit v1.2.3 From ffa59b0b396cb2c0ea6712ff30ee05c35d4c9c8d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 6 Sep 2020 20:32:30 -0700 Subject: netdevice.h: fix xdp_state kernel-doc warning Fix kernel-doc warning in : ../include/linux/netdevice.h:2158: warning: Function parameter or member 'xdp_state' not described in 'net_device' Fixes: 7f0a838254bd ("bpf, xdp: Maintain info on attached XDP BPF programs in net_device") Signed-off-by: Randy Dunlap Cc: Andrii Nakryiko Cc: Alexei Starovoitov Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bf0e313486be..7bd4fcdd0738 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1849,6 +1849,7 @@ enum netdev_priv_flags { * @udp_tunnel_nic_info: static structure describing the UDP tunnel * offload capabilities of the device * @udp_tunnel_nic: UDP tunnel offload state + * @xdp_state: stores info on attached XDP BPF programs * * FIXME: cleanup struct net_device such that network protocol info * moves out. -- cgit v1.2.3 From 0a355aeb24081e4538d4d424cd189f16c0bbd983 Mon Sep 17 00:00:00 2001 From: Evan Nimmo Date: Wed, 9 Sep 2020 08:32:47 +1200 Subject: i2c: algo: pca: Reapply i2c bus settings after reset If something goes wrong (such as the SCL being stuck low) then we need to reset the PCA chip. The issue with this is that on reset we lose all config settings and the chip ends up in a disabled state which results in a lock up/high CPU usage. We need to re-apply any configuration that had previously been set and re-enable the chip. Signed-off-by: Evan Nimmo Reviewed-by: Chris Packham Reviewed-by: Andy Shevchenko Signed-off-by: Wolfram Sang --- include/linux/i2c-algo-pca.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c-algo-pca.h b/include/linux/i2c-algo-pca.h index d03071732db4..7c522fdd9ea7 100644 --- a/include/linux/i2c-algo-pca.h +++ b/include/linux/i2c-algo-pca.h @@ -53,6 +53,20 @@ #define I2C_PCA_CON_SI 0x08 /* Serial Interrupt */ #define I2C_PCA_CON_CR 0x07 /* Clock Rate (MASK) */ +/** + * struct pca_i2c_bus_settings - The configured PCA i2c bus settings + * @mode: Configured i2c bus mode + * @tlow: Configured SCL LOW period + * @thi: Configured SCL HIGH period + * @clock_freq: The configured clock frequency + */ +struct pca_i2c_bus_settings { + int mode; + int tlow; + int thi; + int clock_freq; +}; + struct i2c_algo_pca_data { void *data; /* private low level data */ void (*write_byte) (void *data, int reg, int val); @@ -64,6 +78,7 @@ struct i2c_algo_pca_data { * For PCA9665, use the frequency you want here. */ unsigned int i2c_clock; unsigned int chip; + struct pca_i2c_bus_settings bus_settings; }; int i2c_pca_add_bus(struct i2c_adapter *); -- cgit v1.2.3 From 4a009cb04aeca0de60b73f37b102573354214b52 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 9 Sep 2020 01:27:40 -0700 Subject: net: add __must_check to skb_put_padto() skb_put_padto() and __skb_put_padto() callers must check return values or risk use-after-free. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ed9bea924dc3..04a18e01b362 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3223,8 +3223,9 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len) * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ -static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, - bool free_on_error) +static inline int __must_check __skb_put_padto(struct sk_buff *skb, + unsigned int len, + bool free_on_error) { unsigned int size = skb->len; @@ -3247,7 +3248,7 @@ static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ -static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) +static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } -- cgit v1.2.3 From 2d2fe8433796603091ac8ea235b9165ac5a85f9a Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Wed, 9 Sep 2020 20:43:08 +0300 Subject: net: qed: Disable aRFS for NPAR and 100G In CMT and NPAR the PF is unknown when the GFS block processes the packet. Therefore cannot use searcher as it has a per PF database, and thus ARFS must be disabled. Fixes: d51e4af5c209 ("qed: aRFS infrastructure support") Signed-off-by: Manish Chopra Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: Dmitry Bogdanov Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index cd6a5c7e56eb..cdd73afc4c46 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -623,6 +623,7 @@ struct qed_dev_info { #define QED_MFW_VERSION_3_OFFSET 24 u32 flash_size; + bool b_arfs_capable; bool b_inter_pf_switch; bool tx_switching; bool rdma_supported; -- cgit v1.2.3 From baaabecfc80fad255f866563b53b8c7a3eec176e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 9 Sep 2020 15:53:54 -0700 Subject: test_firmware: Test platform fw loading on non-EFI systems On non-EFI systems, it wasn't possible to test the platform firmware loader because it will have never set "checked_fw" during __init. Instead, allow the test code to override this check. Additionally split the declarations into a private symbol namespace so there is greater enforcement of the symbol visibility. Fixes: 548193cba2a7 ("test_firmware: add support for firmware_request_platform") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Acked-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20200909225354.3118328-1-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/efi_embedded_fw.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h index 57eac5241303..a97a12bb2c9e 100644 --- a/include/linux/efi_embedded_fw.h +++ b/include/linux/efi_embedded_fw.h @@ -8,8 +8,8 @@ #define EFI_EMBEDDED_FW_PREFIX_LEN 8 /* - * This struct and efi_embedded_fw_list are private to the efi-embedded fw - * implementation they are in this header for use by lib/test_firmware.c only! + * This struct is private to the efi-embedded fw implementation. + * They are in this header for use by lib/test_firmware.c only! */ struct efi_embedded_fw { struct list_head list; @@ -18,8 +18,6 @@ struct efi_embedded_fw { size_t length; }; -extern struct list_head efi_embedded_fw_list; - /** * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw * code to search for embedded firmwares. -- cgit v1.2.3 From 95035eac763294eb4543aea9afd48d2f7c8caa5c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 6 Sep 2020 20:42:52 -0700 Subject: PM: : fix @em_pd kernel-doc warning Fix kernel-doc warning in : ../include/linux/device.h:613: warning: Function parameter or member 'em_pd' not described in 'device' Fixes: 1bc138c62295 ("PM / EM: add support for other devices than CPUs in Energy Model") Signed-off-by: Randy Dunlap Reviewed-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index ca18da4768e3..9e6ea8931a52 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -454,6 +454,7 @@ struct dev_links_info { * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. + * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pinctl.rst for details. * @msi_list: Hosts MSI descriptors -- cgit v1.2.3 From cc88b78c0870ebcab2123ba9e73689d97fbf3b14 Mon Sep 17 00:00:00 2001 From: Amit Kucheria Date: Thu, 10 Sep 2020 15:57:46 +0530 Subject: powercap: make documentation reflect code Fix up the documentation of the struct powercap_control_type members to match the code. Also fixup stray whitespace. Signed-off-by: Amit Kucheria [ rjw: Changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/powercap.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/powercap.h b/include/linux/powercap.h index 4537f57f9e42..3d557bbcd2c7 100644 --- a/include/linux/powercap.h +++ b/include/linux/powercap.h @@ -44,19 +44,18 @@ struct powercap_control_type_ops { }; /** - * struct powercap_control_type- Defines a powercap control_type - * @name: name of control_type + * struct powercap_control_type - Defines a powercap control_type * @dev: device for this control_type * @idr: idr to have unique id for its child - * @root_node: Root holding power zones for this control_type + * @nr_zones: counter for number of zones of this type * @ops: Pointer to callback struct - * @node_lock: mutex for control type + * @lock: mutex for control type * @allocated: This is possible that client owns the memory * used by this structure. In this case * this flag is set to false by framework to * prevent deallocation during release process. * Otherwise this flag is set to true. - * @ctrl_inst: link to the control_type list + * @node: linked-list node * * Defines powercap control_type. This acts as a container for power * zones, which use same method to control power. E.g. RAPL, RAPL-PCI etc. @@ -129,7 +128,7 @@ struct powercap_zone_ops { * this flag is set to false by framework to * prevent deallocation during release process. * Otherwise this flag is set to true. - * @constraint_ptr: List of constraints for this zone. + * @constraints: List of constraints for this zone. * * This defines a power zone instance. The fields of this structure are * private, and should not be used by client drivers. -- cgit v1.2.3 From 83896b0bd8223ac33bcc609bcc82a57a587002ff Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 10 Sep 2020 04:46:40 -0400 Subject: net: Fix broken NETIF_F_CSUM_MASK spell in netdev_features.h Remove the weird space inside the NETIF_F_CSUM_MASK. Signed-off-by: Miaohe Lin Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2cc3cf80b49a..0b17c4322b09 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -193,7 +193,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) #define NETIF_F_GSO_MASK (__NETIF_F_BIT(NETIF_F_GSO_LAST + 1) - \ __NETIF_F_BIT(NETIF_F_GSO_SHIFT)) -/* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be +/* List of IP checksum features. Note that NETIF_F_HW_CSUM should not be * set in features when NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM are set-- * this would be contradictory */ -- cgit v1.2.3 From 27ba3e8ff3ab86449e63d38a8d623053591e65fa Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 15 Sep 2020 16:33:46 +0900 Subject: scsi: sd: sd_zbc: Fix handling of host-aware ZBC disks When CONFIG_BLK_DEV_ZONED is disabled, allow using host-aware ZBC disks as regular disks. In this case, ensure that command completion is correctly executed by changing sd_zbc_complete() to return good_bytes instead of 0 and causing a hang during device probe (endless retries). When CONFIG_BLK_DEV_ZONED is enabled and a host-aware disk is detected to have partitions, it will be used as a regular disk. In this case, make sure to not do anything in sd_zbc_revalidate_zones() as that triggers warnings. Since all these different cases result in subtle settings of the disk queue zoned model, introduce the block layer helper function blk_queue_set_zoned() to generically implement setting up the effective zoned model according to the disk type, the presence of partitions on the disk and CONFIG_BLK_DEV_ZONED configuration. Link: https://lore.kernel.org/r/20200915073347.832424-2-damien.lemoal@wdc.com Fixes: b72053072c0b ("block: allow partitions on host aware zone devices") Cc: Reported-by: Borislav Petkov Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Damien Le Moal Signed-off-by: Martin K. Petersen --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bb5636cc17b9..868e11face00 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -352,6 +352,8 @@ struct queue_limits { typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); +void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model); + #ifdef CONFIG_BLK_DEV_ZONED #define BLK_ALL_ZONES ((unsigned int)-1) -- cgit v1.2.3 From e0830dbf71f191851ed3772d2760f007b7c5bc3a Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 9 Sep 2020 16:31:01 +0200 Subject: serial: core: fix console port-lock regression Fix the port-lock initialisation regression introduced by commit a3cb39d258ef ("serial: core: Allow detach and attach serial device for console") by making sure that the lock is again initialised during console setup. The console may be registered before the serial controller has been probed in which case the port lock needs to be initialised during console setup by a call to uart_set_options(). The console-detach changes introduced a regression in several drivers by effectively removing that initialisation by not initialising the lock when the port is used as a console (which is always the case during console setup). Add back the early lock initialisation and instead use a new console-reinit flag to handle the case where a console is being re-attached through sysfs. The question whether the console-detach interface should have been added in the first place is left for another discussion. Note that the console-enabled check in uart_set_options() is not redundant because of kgdboc, which can end up reinitialising an already enabled console (see commit 42b6a1baa3ec ("serial_core: Don't re-initialize a previously initialized spinlock.")). Fixes: a3cb39d258ef ("serial: core: Allow detach and attach serial device for console") Cc: stable # 5.7 Signed-off-by: Johan Hovold Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20200909143101.15389-3-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 01fc4d9c9c54..8a99279a579b 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -248,6 +248,7 @@ struct uart_port { unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; + unsigned char console_reinit; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ -- cgit v1.2.3 From e6b1a44eccfcab5e5e280be376f65478c3b2c7a2 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Tue, 15 Sep 2020 22:07:50 +0800 Subject: locking/percpu-rwsem: Use this_cpu_{inc,dec}() for read_count The __this_cpu*() accessors are (in general) IRQ-unsafe which, given that percpu-rwsem is a blocking primitive, should be just fine. However, file_end_write() is used from IRQ context and will cause load-store issues on architectures where the per-cpu accessors are not natively irq-safe. Fix it by using the IRQ-safe this_cpu_*() for operations on read_count. This will generate more expensive code on a number of platforms, which might cause a performance regression for some of the other percpu-rwsem users. If any such is reported, we can consider alternative solutions. Fixes: 70fe2f48152e ("aio: fix freeze protection of aio writes") Signed-off-by: Hou Tao Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Acked-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20200915140750.137881-1-houtao1@huawei.com --- include/linux/percpu-rwsem.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 5e033fe1ff4e..5fda40f97fe9 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -60,7 +60,7 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem) * anything we did within this RCU-sched read-size critical section. */ if (likely(rcu_sync_is_idle(&sem->rss))) - __this_cpu_inc(*sem->read_count); + this_cpu_inc(*sem->read_count); else __percpu_down_read(sem, false); /* Unconditional memory barrier */ /* @@ -79,7 +79,7 @@ static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) - __this_cpu_inc(*sem->read_count); + this_cpu_inc(*sem->read_count); else ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ preempt_enable(); @@ -103,7 +103,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) { - __this_cpu_dec(*sem->read_count); + this_cpu_dec(*sem->read_count); } else { /* * slowpath; reader will only ever wake a single blocked @@ -115,7 +115,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) * aggregate zero, as that is the only time it matters) they * will also see our critical section. */ - __this_cpu_dec(*sem->read_count); + this_cpu_dec(*sem->read_count); rcuwait_wake_up(&sem->writer); } preempt_enable(); -- cgit v1.2.3 From 8747f2022fe8d8029193707ee86ff5c792cbef9b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Sep 2020 12:32:00 +0200 Subject: cpuidle: Allow cpuidle drivers to take over RCU-idle Some drivers have to do significant work, some of which relies on RCU still being active. Instead of using RCU_NONIDLE in the drivers and flipping RCU back on, allow drivers to take over RCU-idle duty. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ulf Hansson Tested-by: Borislav Petkov Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 75895e6363b8..6175c77bf25e 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -82,6 +82,7 @@ struct cpuidle_state { #define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ #define CPUIDLE_FLAG_OFF BIT(4) /* disable this state by default */ #define CPUIDLE_FLAG_TLB_FLUSHED BIT(5) /* idle-state flushes TLBs */ +#define CPUIDLE_FLAG_RCU_IDLE BIT(6) /* idle-state takes care of RCU */ struct cpuidle_device_kobj; struct cpuidle_state_kobj; -- cgit v1.2.3 From ffbc3dd1975f1e2dac7b1752aa8b5cac3cd5b459 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 16 Sep 2020 23:18:43 +0300 Subject: fs: fix cast in fsparam_u32hex() macro Signed-off-by: Alexey Dobriyan Signed-off-by: Al Viro --- include/linux/fs_parser.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 2eab6d5f6736..aab0ffc6bac6 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -120,7 +120,7 @@ static inline bool fs_validate_description(const char *name, #define fsparam_u32oct(NAME, OPT) \ __fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8) #define fsparam_u32hex(NAME, OPT) \ - __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *16)) + __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *)16) #define fsparam_s32(NAME, OPT) __fsparam(fs_param_is_s32, NAME, OPT, 0, NULL) #define fsparam_u64(NAME, OPT) __fsparam(fs_param_is_u64, NAME, OPT, 0, NULL) #define fsparam_enum(NAME, OPT, array) __fsparam(fs_param_is_enum, NAME, OPT, 0, array) -- cgit v1.2.3 From 75df529bec9110dad43ab30e2d9490242529e8b8 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Wed, 16 Sep 2020 17:45:30 +0200 Subject: arm64: paravirt: Initialize steal time when cpu is online Steal time initialization requires mapping a memory region which invokes a memory allocation. Doing this at CPU starting time results in the following trace when CONFIG_DEBUG_ATOMIC_SLEEP is enabled: BUG: sleeping function called from invalid context at mm/slab.h:498 in_atomic(): 1, irqs_disabled(): 128, non_block: 0, pid: 0, name: swapper/1 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.9.0-rc5+ #1 Call trace: dump_backtrace+0x0/0x208 show_stack+0x1c/0x28 dump_stack+0xc4/0x11c ___might_sleep+0xf8/0x130 __might_sleep+0x58/0x90 slab_pre_alloc_hook.constprop.101+0xd0/0x118 kmem_cache_alloc_node_trace+0x84/0x270 __get_vm_area_node+0x88/0x210 get_vm_area_caller+0x38/0x40 __ioremap_caller+0x70/0xf8 ioremap_cache+0x78/0xb0 memremap+0x9c/0x1a8 init_stolen_time_cpu+0x54/0xf0 cpuhp_invoke_callback+0xa8/0x720 notify_cpu_starting+0xc8/0xd8 secondary_start_kernel+0x114/0x180 CPU1: Booted secondary processor 0x0000000001 [0x431f0a11] However we don't need to initialize steal time at CPU starting time. We can simply wait until CPU online time, just sacrificing a bit of accuracy by returning zero for steal time until we know better. While at it, add __init to the functions that are only called by pv_time_init() which is __init. Signed-off-by: Andrew Jones Fixes: e0685fa228fd ("arm64: Retrieve stolen time as paravirtualized guest") Cc: stable@vger.kernel.org Reviewed-by: Steven Price Link: https://lore.kernel.org/r/20200916154530.40809-1-drjones@redhat.com Signed-off-by: Catalin Marinas --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 3215023d4852..bf9181cef444 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -142,7 +142,6 @@ enum cpuhp_state { /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, - CPUHP_AP_ARM_KVMPV_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, -- cgit v1.2.3 From 5ef64cc8987a9211d3f3667331ba3411a94ddc79 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Sep 2020 14:05:35 -0700 Subject: mm: allow a controlled amount of unfairness in the page lock Commit 2a9127fcf229 ("mm: rewrite wait_on_page_bit_common() logic") made the page locking entirely fair, in that if a waiter came in while the lock was held, the lock would be transferred to the lockers strictly in order. That was intended to finally get rid of the long-reported watchdog failures that involved the page lock under extreme load, where a process could end up waiting essentially forever, as other page lockers stole the lock from under it. It also improved some benchmarks, but it ended up causing huge performance regressions on others, simply because fair lock behavior doesn't end up giving out the lock as aggressively, causing better worst-case latency, but potentially much worse average latencies and throughput. Instead of reverting that change entirely, this introduces a controlled amount of unfairness, with a sysctl knob to tune it if somebody needs to. But the default value should hopefully be good for any normal load, allowing a few rounds of lock stealing, but enforcing the strict ordering before the lock has been stolen too many times. There is also a hint from Matthieu Baerts that the fair page coloring may end up exposing an ABBA deadlock that is hidden by the usual optimistic lock stealing, and while the unfairness doesn't fix the fundamental issue (and I'm still looking at that), it avoids it in practice. The amount of unfairness can be modified by writing a new value to the 'sysctl_page_lock_unfairness' variable (default value of 5, exposed through /proc/sys/vm/page_lock_unfairness), but that is hopefully something we'd use mainly for debugging rather than being necessary for any deep system tuning. This whole issue has exposed just how critical the page lock can be, and how contended it gets under certain locks. And the main contention doesn't really seem to be anything related to IO (which was the origin of this lock), but for things like just verifying that the page file mapping is stable while faulting in the page into a page table. Link: https://lore.kernel.org/linux-fsdevel/ed8442fd-6f54-dd84-cd4a-941e8b7ee603@MichaelLarabel.com/ Link: https://www.phoronix.com/scan.php?page=article&item=linux-50-59&num=1 Link: https://lore.kernel.org/linux-fsdevel/c560a38d-8313-51fb-b1ec-e904bd8836bc@tessares.net/ Reported-and-tested-by: Michael Larabel Tested-by: Matthieu Baerts Cc: Dave Chinner Cc: Matthew Wilcox Cc: Chris Mason Cc: Jan Kara Cc: Amir Goldstein Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ include/linux/wait.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ca6e6a81576b..b2f370f0b420 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -41,6 +41,8 @@ struct writeback_control; struct bdi_writeback; struct pt_regs; +extern int sysctl_page_lock_unfairness; + void init_mm_internals(void); #ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ diff --git a/include/linux/wait.h b/include/linux/wait.h index 898c890fc153..27fb99cfeb02 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -21,6 +21,7 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int #define WQ_FLAG_WOKEN 0x02 #define WQ_FLAG_BOOKMARK 0x04 #define WQ_FLAG_CUSTOM 0x08 +#define WQ_FLAG_DONE 0x10 /* * A single wait-queue entry structure: -- cgit v1.2.3 From b9df46d08a8d098ea2124cb9e3b84458a474b4d4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 18 Sep 2020 09:19:43 -0400 Subject: pNFS/flexfiles: Be consistent about mirror index types A mirror index is always of type u32. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9408f3252c8e..69cb46f7b8d2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1611,8 +1611,8 @@ struct nfs_pgio_header { __u64 mds_offset; /* Filelayout dense stripe */ struct nfs_page_array page_array; struct nfs_client *ds_clp; /* pNFS data server */ - int ds_commit_idx; /* ds index if ds_clp is set */ - int pgio_mirror_idx;/* mirror index in pgio layer */ + u32 ds_commit_idx; /* ds index if ds_clp is set */ + u32 pgio_mirror_idx;/* mirror index in pgio layer */ }; struct nfs_mds_commit_info { -- cgit v1.2.3 From 54fa9ba564b717fc2cf689427e195c360315999d Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Mon, 7 Sep 2020 11:32:07 +0200 Subject: ftrace: Let ftrace_enable_sysctl take a kernel pointer buffer Commit 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") changed ctl_table.proc_handler to take a kernel pointer. Adjust the signature of ftrace_enable_sysctl to match ctl_table.proc_handler which fixes the following sparse warning: kernel/trace/ftrace.c:7544:43: warning: incorrect type in argument 3 (different address spaces) kernel/trace/ftrace.c:7544:43: expected void * kernel/trace/ftrace.c:7544:43: got void [noderef] __user *buffer Link: https://lkml.kernel.org/r/20200907093207.13540-1-tklauser@distanz.ch Fixes: 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") Cc: Andrew Morton Cc: Ingo Molnar Cc: Christoph Hellwig Cc: Al Viro Signed-off-by: Tobias Klauser Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ce2c06f72e86..e5c2d5cc6e6a 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -85,8 +85,7 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val extern int ftrace_enabled; extern int ftrace_enable_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); struct ftrace_ops; -- cgit v1.2.3 From 82d083ab60c3693201c6f5c7a5f23a6ed422098d Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 10 Sep 2020 17:55:05 +0900 Subject: kprobes: tracing/kprobes: Fix to kill kprobes on initmem after boot Since kprobe_event= cmdline option allows user to put kprobes on the functions in initmem, kprobe has to make such probes gone after boot. Currently the probes on the init functions in modules will be handled by module callback, but the kernel init text isn't handled. Without this, kprobes may access non-exist text area to disable or remove it. Link: https://lkml.kernel.org/r/159972810544.428528.1839307531600646955.stgit@devnote2 Fixes: 970988e19eb0 ("tracing/kprobe: Add kprobe_event= boot parameter") Cc: Jonathan Corbet Cc: Shuah Khan Cc: Randy Dunlap Cc: Ingo Molnar Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 9be1bff4f586..8aab327b5539 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -373,6 +373,8 @@ void unregister_kretprobes(struct kretprobe **rps, int num); void kprobe_flush_task(struct task_struct *tk); void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); +void kprobe_free_init_mem(void); + int disable_kprobe(struct kprobe *kp); int enable_kprobe(struct kprobe *kp); @@ -435,6 +437,9 @@ static inline void unregister_kretprobes(struct kretprobe **rps, int num) static inline void kprobe_flush_task(struct task_struct *tk) { } +static inline void kprobe_free_init_mem(void) +{ +} static inline int disable_kprobe(struct kprobe *kp) { return -ENOSYS; -- cgit v1.2.3 From 7bb82ac30c3dd4ecf1485685cbe84d2ba10dddf4 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Fri, 18 Sep 2020 21:20:34 -0700 Subject: ftrace: let ftrace_enable_sysctl take a kernel pointer buffer Commit 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") changed ctl_table.proc_handler to take a kernel pointer. Adjust the signature of ftrace_enable_sysctl to match ctl_table.proc_handler which fixes the following sparse warning: kernel/trace/ftrace.c:7544:43: warning: incorrect type in argument 3 (different address spaces) kernel/trace/ftrace.c:7544:43: expected void * kernel/trace/ftrace.c:7544:43: got void [noderef] __user *buffer Fixes: 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") Signed-off-by: Tobias Klauser Signed-off-by: Andrew Morton Cc: Christoph Hellwig Cc: Al Viro Link: https://lkml.kernel.org/r/20200907093207.13540-1-tklauser@distanz.ch Signed-off-by: Linus Torvalds --- include/linux/ftrace.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ce2c06f72e86..e5c2d5cc6e6a 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -85,8 +85,7 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val extern int ftrace_enabled; extern int ftrace_enable_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); struct ftrace_ops; -- cgit v1.2.3 From 4773ef33fc6e59bad2e5d19e334de2fa79c27b74 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Fri, 18 Sep 2020 21:20:37 -0700 Subject: stackleak: let stack_erasing_sysctl take a kernel pointer buffer Commit 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") changed ctl_table.proc_handler to take a kernel pointer. Adjust the signature of stack_erasing_sysctl to match ctl_table.proc_handler which fixes the following sparse warning: kernel/stackleak.c:31:50: warning: incorrect type in argument 3 (different address spaces) kernel/stackleak.c:31:50: expected void * kernel/stackleak.c:31:50: got void [noderef] __user *buffer Fixes: 32927393dc1c ("sysctl: pass kernel pointers to ->proc_handler") Signed-off-by: Tobias Klauser Signed-off-by: Andrew Morton Cc: Christoph Hellwig Cc: Al Viro Link: https://lkml.kernel.org/r/20200907093253.13656-1-tklauser@distanz.ch Signed-off-by: Linus Torvalds --- include/linux/stackleak.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index 3d5c3271a9a8..a59db2f08e76 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -25,7 +25,7 @@ static inline void stackleak_task_init(struct task_struct *t) #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE int stack_erasing_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); #endif #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ -- cgit v1.2.3 From e2ec5128254518cae320d5dc631b71b94160f663 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Sun, 20 Sep 2020 08:54:42 -0700 Subject: dm: Call proper helper to determine dax support DM was calling generic_fsdax_supported() to determine whether a device referenced in the DM table supports DAX. However this is a helper for "leaf" device drivers so that they don't have to duplicate common generic checks. High level code should call dax_supported() helper which that calls into appropriate helper for the particular device. This problem manifested itself as kernel messages: dm-3: error: dax access failed (-95) when lvm2-testsuite run in cases where a DM device was stacked on top of another DM device. Fixes: 7bf7eac8d648 ("dax: Arrange for dax_supported check to span multiple devices") Cc: Tested-by: Adrian Huang Signed-off-by: Jan Kara Acked-by: Mike Snitzer Reported-by: kernel test robot Link: https://lore.kernel.org/r/160061715195.13131.5503173247632041975.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/dax.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 6904d4e0b2e0..497031392e0a 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -130,6 +130,8 @@ static inline bool generic_fsdax_supported(struct dax_device *dax_dev, return __generic_fsdax_supported(dax_dev, bdev, blocksize, start, sectors); } +bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, + int blocksize, sector_t start, sector_t len); static inline void fs_put_dax(struct dax_device *dax_dev) { @@ -157,6 +159,13 @@ static inline bool generic_fsdax_supported(struct dax_device *dax_dev, return false; } +static inline bool dax_supported(struct dax_device *dax_dev, + struct block_device *bdev, int blocksize, sector_t start, + sector_t len) +{ + return false; +} + static inline void fs_put_dax(struct dax_device *dax_dev) { } @@ -189,14 +198,23 @@ static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) } #endif +#if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); +#else +static inline int dax_read_lock(void) +{ + return 0; +} + +static inline void dax_read_unlock(int id) +{ +} +#endif /* CONFIG_DAX */ bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, -- cgit v1.2.3 From 88b67edd7247466bc47f01e1dc539b0d0d4b931e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 21 Sep 2020 11:33:23 +0200 Subject: dax: Fix compilation for CONFIG_DAX && !CONFIG_FS_DAX dax_supported() is defined whenever CONFIG_DAX is enabled. So dummy implementation should be defined only in !CONFIG_DAX case, not in !CONFIG_FS_DAX case. Fixes: e2ec51282545 ("dm: Call proper helper to determine dax support") Cc: Reported-by: Geert Uytterhoeven Reported-by: Naresh Kamboju Reported-by: kernel test robot Signed-off-by: Jan Kara Signed-off-by: Dan Williams --- include/linux/dax.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 497031392e0a..43b39ab9de1a 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -58,6 +58,8 @@ static inline void set_dax_synchronous(struct dax_device *dax_dev) { __set_dax_synchronous(dax_dev); } +bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, + int blocksize, sector_t start, sector_t len); /* * Check if given mapping is supported by the file / underlying device. */ @@ -104,6 +106,12 @@ static inline bool dax_synchronous(struct dax_device *dax_dev) static inline void set_dax_synchronous(struct dax_device *dax_dev) { } +static inline bool dax_supported(struct dax_device *dax_dev, + struct block_device *bdev, int blocksize, sector_t start, + sector_t len) +{ + return false; +} static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { @@ -130,8 +138,6 @@ static inline bool generic_fsdax_supported(struct dax_device *dax_dev, return __generic_fsdax_supported(dax_dev, bdev, blocksize, start, sectors); } -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len); static inline void fs_put_dax(struct dax_device *dax_dev) { @@ -159,13 +165,6 @@ static inline bool generic_fsdax_supported(struct dax_device *dax_dev, return false; } -static inline bool dax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t len) -{ - return false; -} - static inline void fs_put_dax(struct dax_device *dax_dev) { } -- cgit v1.2.3 From fce55cc8b7ade3c583f47eab5885e2f541ede1ee Mon Sep 17 00:00:00 2001 From: Ed Wildgoose Date: Sun, 20 Sep 2020 21:32:06 +0100 Subject: platform/x86: pcengines-apuv2: Fix typo on define of AMD_FCH_GPIO_REG_GPIO55_DEVSLP0 Schematics show that the GPIO number is 55 (not 59). Trivial typo. Signed-off-by: Ed Wildgoose Signed-off-by: Andy Shevchenko --- include/linux/platform_data/gpio/gpio-amd-fch.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio/gpio-amd-fch.h b/include/linux/platform_data/gpio/gpio-amd-fch.h index 9e46678edb2a..255d51c9d36d 100644 --- a/include/linux/platform_data/gpio/gpio-amd-fch.h +++ b/include/linux/platform_data/gpio/gpio-amd-fch.h @@ -19,7 +19,7 @@ #define AMD_FCH_GPIO_REG_GPIO49 0x40 #define AMD_FCH_GPIO_REG_GPIO50 0x41 #define AMD_FCH_GPIO_REG_GPIO51 0x42 -#define AMD_FCH_GPIO_REG_GPIO59_DEVSLP0 0x43 +#define AMD_FCH_GPIO_REG_GPIO55_DEVSLP0 0x43 #define AMD_FCH_GPIO_REG_GPIO57 0x44 #define AMD_FCH_GPIO_REG_GPIO58 0x45 #define AMD_FCH_GPIO_REG_GPIO59_DEVSLP1 0x46 -- cgit v1.2.3 From bb0890b4cd7f8203e3aa99c6d0f062d6acdaad27 Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Thu, 24 Sep 2020 09:40:53 -0400 Subject: fbdev, newport_con: Move FONT_EXTRA_WORDS macros into linux/font.h drivers/video/console/newport_con.c is borrowing FONT_EXTRA_WORDS macros from drivers/video/fbdev/core/fbcon.h. To keep things simple, move all definitions into . Since newport_con now uses four extra words, initialize the fourth word in newport_set_font() properly. Cc: stable@vger.kernel.org Signed-off-by: Peilin Ye Reviewed-by: Greg Kroah-Hartman Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/7fb8bc9b0abc676ada6b7ac0e0bd443499357267.1600953813.git.yepeilin.cs@gmail.com --- include/linux/font.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/font.h b/include/linux/font.h index 51b91c8b69d5..40ed008d7dad 100644 --- a/include/linux/font.h +++ b/include/linux/font.h @@ -59,4 +59,12 @@ extern const struct font_desc *get_default_font(int xres, int yres, /* Max. length for the name of a predefined font */ #define MAX_FONT_NAME 32 +/* Extra word getters */ +#define REFCOUNT(fd) (((int *)(fd))[-1]) +#define FNTSIZE(fd) (((int *)(fd))[-2]) +#define FNTCHARCNT(fd) (((int *)(fd))[-3]) +#define FNTSUM(fd) (((int *)(fd))[-4]) + +#define FONT_EXTRA_WORDS 4 + #endif /* _VIDEO_FONT_H */ -- cgit v1.2.3 From 6735b4632def0640dbdf4eb9f99816aca18c4f16 Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Thu, 24 Sep 2020 09:42:22 -0400 Subject: Fonts: Support FONT_EXTRA_WORDS macros for built-in fonts syzbot has reported an issue in the framebuffer layer, where a malicious user may overflow our built-in font data buffers. In order to perform a reliable range check, subsystems need to know `FONTDATAMAX` for each built-in font. Unfortunately, our font descriptor, `struct console_font` does not contain `FONTDATAMAX`, and is part of the UAPI, making it infeasible to modify it. For user-provided fonts, the framebuffer layer resolves this issue by reserving four extra words at the beginning of data buffers. Later, whenever a function needs to access them, it simply uses the following macros: Recently we have gathered all the above macros to . Let us do the same thing for built-in fonts, prepend four extra words (including `FONTDATAMAX`) to their data buffers, so that subsystems can use these macros for all fonts, no matter built-in or user-provided. This patch depends on patch "fbdev, newport_con: Move FONT_EXTRA_WORDS macros into linux/font.h". Cc: stable@vger.kernel.org Link: https://syzkaller.appspot.com/bug?id=08b8be45afea11888776f897895aef9ad1c3ecfd Signed-off-by: Peilin Ye Reviewed-by: Greg Kroah-Hartman Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/ef18af00c35fb3cc826048a5f70924ed6ddce95b.1600953813.git.yepeilin.cs@gmail.com --- include/linux/font.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/font.h b/include/linux/font.h index 40ed008d7dad..59faa80f586d 100644 --- a/include/linux/font.h +++ b/include/linux/font.h @@ -67,4 +67,9 @@ extern const struct font_desc *get_default_font(int xres, int yres, #define FONT_EXTRA_WORDS 4 +struct font_data { + unsigned int extra[FONT_EXTRA_WORDS]; + const unsigned char data[]; +} __packed; + #endif /* _VIDEO_FONT_H */ -- cgit v1.2.3 From 3aab91774bbd8e571cfaddaf839aafd07718333c Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Fri, 25 Sep 2020 14:00:31 +0800 Subject: block: remove unused BLK_QC_T_EAGAIN flag commit 7b6620d7db56 ("block: remove REQ_NOWAIT_INLINE") removed the REQ_NOWAIT_INLINE related code, but the diff wasn't applied to blk_types.h somehow. Then commit 2771cefeac49 ("block: remove the REQ_NOWAIT_INLINE flag") removed the REQ_NOWAIT_INLINE flag while the BLK_QC_T_EAGAIN flag still remains. Fixes: 7b6620d7db56 ("block: remove REQ_NOWAIT_INLINE") Signed-off-by: Jeffle Xu Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 4ecf4fed171f..b3fc5d3dd8ea 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -497,13 +497,12 @@ static inline int op_stat_group(unsigned int op) typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U -#define BLK_QC_T_EAGAIN -2U #define BLK_QC_T_SHIFT 16 #define BLK_QC_T_INTERNAL (1U << 31) static inline bool blk_qc_t_valid(blk_qc_t cookie) { - return cookie != BLK_QC_T_NONE && cookie != BLK_QC_T_EAGAIN; + return cookie != BLK_QC_T_NONE; } static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) -- cgit v1.2.3 From d3f7b1bb204099f2f7306318896223e8599bb6a2 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 25 Sep 2020 21:19:10 -0700 Subject: mm/gup: fix gup_fast with dynamic page table folding Currently to make sure that every page table entry is read just once gup_fast walks perform READ_ONCE and pass pXd value down to the next gup_pXd_range function by value e.g.: static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) ... pudp = pud_offset(&p4d, addr); This function passes a reference on that local value copy to pXd_offset, and might get the very same pointer in return. This happens when the level is folded (on most arches), and that pointer should not be iterated. On s390 due to the fact that each task might have different 5,4 or 3-level address translation and hence different levels folded the logic is more complex and non-iteratable pointer to a local copy leads to severe problems. Here is an example of what happens with gup_fast on s390, for a task with 3-level paging, crossing a 2 GB pud boundary: // addr = 0x1007ffff000, end = 0x10080001000 static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; // pud_offset returns &p4d itself (a pointer to a value on stack) pudp = pud_offset(&p4d, addr); do { // on second iteratation reading "random" stack value pud_t pud = READ_ONCE(*pudp); // next = 0x10080000000, due to PUD_SIZE/MASK != PGDIR_SIZE/MASK on s390 next = pud_addr_end(addr, end); ... } while (pudp++, addr = next, addr != end); // pudp++ iterating over stack return 1; } This happens since s390 moved to common gup code with commit d1874a0c2805 ("s390/mm: make the pxd_offset functions more robust") and commit 1a42010cdc26 ("s390/mm: convert to the generic get_user_pages_fast code"). s390 tried to mimic static level folding by changing pXd_offset primitives to always calculate top level page table offset in pgd_offset and just return the value passed when pXd_offset has to act as folded. What is crucial for gup_fast and what has been overlooked is that PxD_SIZE/MASK and thus pXd_addr_end should also change correspondingly. And the latter is not possible with dynamic folding. To fix the issue in addition to pXd values pass original pXdp pointers down to gup_pXd_range functions. And introduce pXd_offset_lockless helpers, which take an additional pXd entry value parameter. This has already been discussed in https://lkml.kernel.org/r/20190418100218.0a4afd51@mschwideX1 Fixes: 1a42010cdc26 ("s390/mm: convert to the generic get_user_pages_fast code") Signed-off-by: Vasily Gorbik Signed-off-by: Andrew Morton Reviewed-by: Gerald Schaefer Reviewed-by: Alexander Gordeev Reviewed-by: Jason Gunthorpe Reviewed-by: Mike Rapoport Reviewed-by: John Hubbard Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Dave Hansen Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Jeff Dike Cc: Richard Weinberger Cc: Dave Hansen Cc: Andy Lutomirski Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Arnd Bergmann Cc: Andrey Ryabinin Cc: Heiko Carstens Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: [5.2+] Link: https://lkml.kernel.org/r/patch.git-943f1e5dcff2.your-ad-here.call-01599856292-ext-8676@work.hours Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e8cbc2e795d5..90654cb63e9e 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1427,6 +1427,16 @@ typedef unsigned int pgtbl_mod_mask; #define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) #endif +#ifndef p4d_offset_lockless +#define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address) +#endif +#ifndef pud_offset_lockless +#define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address) +#endif +#ifndef pmd_offset_lockless +#define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address) +#endif + /* * p?d_leaf() - true if this entry is a final mapping to a physical address. * This differs from p?d_huge() by the fact that they are always available (if -- cgit v1.2.3 From c1d0da83358a2316d9be7f229f26126dbaa07468 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Fri, 25 Sep 2020 21:19:28 -0700 Subject: mm: replace memmap_context by meminit_context Patch series "mm: fix memory to node bad links in sysfs", v3. Sometimes, firmware may expose interleaved memory layout like this: Early memory node ranges node 1: [mem 0x0000000000000000-0x000000011fffffff] node 2: [mem 0x0000000120000000-0x000000014fffffff] node 1: [mem 0x0000000150000000-0x00000001ffffffff] node 0: [mem 0x0000000200000000-0x000000048fffffff] node 2: [mem 0x0000000490000000-0x00000007ffffffff] In that case, we can see memory blocks assigned to multiple nodes in sysfs: $ ls -l /sys/devices/system/memory/memory21 total 0 lrwxrwxrwx 1 root root 0 Aug 24 05:27 node1 -> ../../node/node1 lrwxrwxrwx 1 root root 0 Aug 24 05:27 node2 -> ../../node/node2 -rw-r--r-- 1 root root 65536 Aug 24 05:27 online -r--r--r-- 1 root root 65536 Aug 24 05:27 phys_device -r--r--r-- 1 root root 65536 Aug 24 05:27 phys_index drwxr-xr-x 2 root root 0 Aug 24 05:27 power -r--r--r-- 1 root root 65536 Aug 24 05:27 removable -rw-r--r-- 1 root root 65536 Aug 24 05:27 state lrwxrwxrwx 1 root root 0 Aug 24 05:25 subsystem -> ../../../../bus/memory -rw-r--r-- 1 root root 65536 Aug 24 05:25 uevent -r--r--r-- 1 root root 65536 Aug 24 05:27 valid_zones The same applies in the node's directory with a memory21 link in both the node1 and node2's directory. This is wrong but doesn't prevent the system to run. However when later, one of these memory blocks is hot-unplugged and then hot-plugged, the system is detecting an inconsistency in the sysfs layout and a BUG_ON() is raised: kernel BUG at /Users/laurent/src/linux-ppc/mm/memory_hotplug.c:1084! LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: rpadlpar_io rpaphp pseries_rng rng_core vmx_crypto gf128mul binfmt_misc ip_tables x_tables xfs libcrc32c crc32c_vpmsum autofs4 CPU: 8 PID: 10256 Comm: drmgr Not tainted 5.9.0-rc1+ #25 Call Trace: add_memory_resource+0x23c/0x340 (unreliable) __add_memory+0x5c/0xf0 dlpar_add_lmb+0x1b4/0x500 dlpar_memory+0x1f8/0xb80 handle_dlpar_errorlog+0xc0/0x190 dlpar_store+0x198/0x4a0 kobj_attr_store+0x30/0x50 sysfs_kf_write+0x64/0x90 kernfs_fop_write+0x1b0/0x290 vfs_write+0xe8/0x290 ksys_write+0xdc/0x130 system_call_exception+0x160/0x270 system_call_common+0xf0/0x27c This has been seen on PowerPC LPAR. The root cause of this issue is that when node's memory is registered, the range used can overlap another node's range, thus the memory block is registered to multiple nodes in sysfs. There are two issues here: (a) The sysfs memory and node's layouts are broken due to these multiple links (b) The link errors in link_mem_sections() should not lead to a system panic. To address (a) register_mem_sect_under_node should not rely on the system state to detect whether the link operation is triggered by a hot plug operation or not. This is addressed by the patches 1 and 2 of this series. Issue (b) will be addressed separately. This patch (of 2): The memmap_context enum is used to detect whether a memory operation is due to a hot-add operation or happening at boot time. Make it general to the hotplug operation and rename it as meminit_context. There is no functional change introduced by this patch Suggested-by: David Hildenbrand Signed-off-by: Laurent Dufour Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Cc: Greg Kroah-Hartman Cc: "Rafael J . Wysocki" Cc: Nathan Lynch Cc: Scott Cheloha Cc: Tony Luck Cc: Fenghua Yu Cc: Link: https://lkml.kernel.org/r/20200915094143.79181-1-ldufour@linux.ibm.com Link: https://lkml.kernel.org/r/20200915132624.9723-1-ldufour@linux.ibm.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- include/linux/mmzone.h | 11 ++++++++--- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index b2f370f0b420..48614513eb66 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2416,7 +2416,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, - enum memmap_context, struct vmem_altmap *); + enum meminit_context, struct vmem_altmap *); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 8379432f4f2f..0f7a4ff4b059 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -824,10 +824,15 @@ bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx); -enum memmap_context { - MEMMAP_EARLY, - MEMMAP_HOTPLUG, +/* + * Memory initialization context, use to differentiate memory added by + * the platform statically or via memory hotplug interface. + */ +enum meminit_context { + MEMINIT_EARLY, + MEMINIT_HOTPLUG, }; + extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); -- cgit v1.2.3 From f85086f95fa36194eb0db5cd5c12e56801b98523 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Fri, 25 Sep 2020 21:19:31 -0700 Subject: mm: don't rely on system state to detect hot-plug operations In register_mem_sect_under_node() the system_state's value is checked to detect whether the call is made during boot time or during an hot-plug operation. Unfortunately, that check against SYSTEM_BOOTING is wrong because regular memory is registered at SYSTEM_SCHEDULING state. In addition, memory hot-plug operation can be triggered at this system state by the ACPI [1]. So checking against the system state is not enough. The consequence is that on system with interleaved node's ranges like this: Early memory node ranges node 1: [mem 0x0000000000000000-0x000000011fffffff] node 2: [mem 0x0000000120000000-0x000000014fffffff] node 1: [mem 0x0000000150000000-0x00000001ffffffff] node 0: [mem 0x0000000200000000-0x000000048fffffff] node 2: [mem 0x0000000490000000-0x00000007ffffffff] This can be seen on PowerPC LPAR after multiple memory hot-plug and hot-unplug operations are done. At the next reboot the node's memory ranges can be interleaved and since the call to link_mem_sections() is made in topology_init() while the system is in the SYSTEM_SCHEDULING state, the node's id is not checked, and the sections registered to multiple nodes: $ ls -l /sys/devices/system/memory/memory21/node* total 0 lrwxrwxrwx 1 root root 0 Aug 24 05:27 node1 -> ../../node/node1 lrwxrwxrwx 1 root root 0 Aug 24 05:27 node2 -> ../../node/node2 In that case, the system is able to boot but if later one of theses memory blocks is hot-unplugged and then hot-plugged, the sysfs inconsistency is detected and this is triggering a BUG_ON(): kernel BUG at /Users/laurent/src/linux-ppc/mm/memory_hotplug.c:1084! Oops: Exception in kernel mode, sig: 5 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: rpadlpar_io rpaphp pseries_rng rng_core vmx_crypto gf128mul binfmt_misc ip_tables x_tables xfs libcrc32c crc32c_vpmsum autofs4 CPU: 8 PID: 10256 Comm: drmgr Not tainted 5.9.0-rc1+ #25 Call Trace: add_memory_resource+0x23c/0x340 (unreliable) __add_memory+0x5c/0xf0 dlpar_add_lmb+0x1b4/0x500 dlpar_memory+0x1f8/0xb80 handle_dlpar_errorlog+0xc0/0x190 dlpar_store+0x198/0x4a0 kobj_attr_store+0x30/0x50 sysfs_kf_write+0x64/0x90 kernfs_fop_write+0x1b0/0x290 vfs_write+0xe8/0x290 ksys_write+0xdc/0x130 system_call_exception+0x160/0x270 system_call_common+0xf0/0x27c This patch addresses the root cause by not relying on the system_state value to detect whether the call is due to a hot-plug operation. An extra parameter is added to link_mem_sections() detailing whether the operation is due to a hot-plug operation. [1] According to Oscar Salvador, using this qemu command line, ACPI memory hotplug operations are raised at SYSTEM_SCHEDULING state: $QEMU -enable-kvm -machine pc -smp 4,sockets=4,cores=1,threads=1 -cpu host -monitor pty \ -m size=$MEM,slots=255,maxmem=4294967296k \ -numa node,nodeid=0,cpus=0-3,mem=512 -numa node,nodeid=1,mem=512 \ -object memory-backend-ram,id=memdimm0,size=134217728 -device pc-dimm,node=0,memdev=memdimm0,id=dimm0,slot=0 \ -object memory-backend-ram,id=memdimm1,size=134217728 -device pc-dimm,node=0,memdev=memdimm1,id=dimm1,slot=1 \ -object memory-backend-ram,id=memdimm2,size=134217728 -device pc-dimm,node=0,memdev=memdimm2,id=dimm2,slot=2 \ -object memory-backend-ram,id=memdimm3,size=134217728 -device pc-dimm,node=0,memdev=memdimm3,id=dimm3,slot=3 \ -object memory-backend-ram,id=memdimm4,size=134217728 -device pc-dimm,node=1,memdev=memdimm4,id=dimm4,slot=4 \ -object memory-backend-ram,id=memdimm5,size=134217728 -device pc-dimm,node=1,memdev=memdimm5,id=dimm5,slot=5 \ -object memory-backend-ram,id=memdimm6,size=134217728 -device pc-dimm,node=1,memdev=memdimm6,id=dimm6,slot=6 \ Fixes: 4fbce633910e ("mm/memory_hotplug.c: make register_mem_sect_under_node() a callback of walk_memory_range()") Signed-off-by: Laurent Dufour Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Fenghua Yu Cc: Nathan Lynch Cc: Scott Cheloha Cc: Tony Luck Cc: Link: https://lkml.kernel.org/r/20200915094143.79181-3-ldufour@linux.ibm.com Signed-off-by: Linus Torvalds --- include/linux/node.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/node.h b/include/linux/node.h index 4866f32a02d8..014ba3ab2efd 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -99,11 +99,13 @@ extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) -extern int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn); +int link_mem_sections(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context); #else static inline int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn) + unsigned long end_pfn, + enum meminit_context context) { return 0; } @@ -128,7 +130,8 @@ static inline int register_one_node(int nid) if (error) return error; /* link memory sections under this node */ - error = link_mem_sections(nid, start_pfn, end_pfn); + error = link_mem_sections(nid, start_pfn, end_pfn, + MEMINIT_EARLY); } return error; -- cgit v1.2.3 From 008cfe4418b3dbda2ff820cdd7b1a5ce458ae444 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 25 Sep 2020 18:25:57 -0400 Subject: mm: Introduce mm_struct.has_pinned (Commit message majorly collected from Jason Gunthorpe) Reduce the chance of false positive from page_maybe_dma_pinned() by keeping track if the mm_struct has ever been used with pin_user_pages(). This allows cases that might drive up the page ref_count to avoid any penalty from handling dma_pinned pages. Future work is planned, to provide a more sophisticated solution, likely to turn it into a real counter. For now, make it atomic_t but use it as a boolean for simplicity. Suggested-by: Jason Gunthorpe Signed-off-by: Peter Xu Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 496c3ff97cce..ed028af3cb19 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -436,6 +436,16 @@ struct mm_struct { */ atomic_t mm_count; + /** + * @has_pinned: Whether this mm has pinned any pages. This can + * be either replaced in the future by @pinned_vm when it + * becomes stable, or grow into a counter on its own. We're + * aggresive on this bit now - even if the pinned pages were + * unpinned later on, we'll still keep this bit set for the + * lifecycle of this mm just for simplicity. + */ + atomic_t has_pinned; + #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif -- cgit v1.2.3 From 7a4830c380f3a8b3425f6383deff58e65b2557b5 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 25 Sep 2020 18:25:58 -0400 Subject: mm/fork: Pass new vma pointer into copy_page_range() This prepares for the future work to trigger early cow on pinned pages during fork(). No functional change intended. Signed-off-by: Peter Xu Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 48614513eb66..16b799a0522c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1646,7 +1646,7 @@ struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, - struct vm_area_struct *vma); + struct vm_area_struct *vma, struct vm_area_struct *new); int follow_pte_pmd(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); -- cgit v1.2.3 From 62c59a8786e6bb75569cee91dab66e9da3ff4b68 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 25 Sep 2020 16:49:51 +0800 Subject: memstick: Skip allocating card when removing host After commit 6827ca573c03 ("memstick: rtsx_usb_ms: Support runtime power management"), removing module rtsx_usb_ms will be stuck. The deadlock is caused by powering on and powering off at the same time, the former one is when memstick_check() is flushed, and the later is called by memstick_remove_host(). Soe let's skip allocating card to prevent this issue. Fixes: 6827ca573c03 ("memstick: rtsx_usb_ms: Support runtime power management") Signed-off-by: Kai-Heng Feng Link: https://lore.kernel.org/r/20200925084952.13220-1-kai.heng.feng@canonical.com Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- include/linux/memstick.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memstick.h b/include/linux/memstick.h index da4c65f9435f..ebf73d4ee969 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -281,6 +281,7 @@ struct memstick_host { struct memstick_dev *card; unsigned int retries; + bool removing; /* Notify the host that some requests are pending. */ void (*request)(struct memstick_host *host); -- cgit v1.2.3 From eff7423365a6938d2d34dbce989febed2ae1f957 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Fri, 25 Sep 2020 18:13:12 +0000 Subject: net: core: introduce struct netdev_nested_priv for nested interface infrastructure Functions related to nested interface infrastructure such as netdev_walk_all_{ upper | lower }_dev() pass both private functions and "data" pointer to handle their own things. At this point, the data pointer type is void *. In order to make it easier to expand common variables and functions, this new netdev_nested_priv structure is added. In the following patch, a new member variable will be added into this struct to fix the lockdep issue. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7bd4fcdd0738..313803d6c781 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4455,6 +4455,10 @@ extern int dev_rx_weight; extern int dev_tx_weight; extern int gro_normal_batch; +struct netdev_nested_priv { + void *data; +}; + bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); @@ -4470,8 +4474,8 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *upper_dev, - void *data), - void *data); + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev); @@ -4508,12 +4512,12 @@ struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, - void *data), - void *data); + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv); int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *lower_dev, - void *data), - void *data); + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv); void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); -- cgit v1.2.3 From 1fc70edb7d7b5ce1ae32b0cf90183f4879ad421a Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Fri, 25 Sep 2020 18:13:29 +0000 Subject: net: core: add nested_level variable in net_device This patch is to add a new variable 'nested_level' into the net_device structure. This variable will be used as a parameter of spin_lock_nested() of dev->addr_list_lock. netif_addr_lock() can be called recursively so spin_lock_nested() is used instead of spin_lock() and dev->lower_level is used as a parameter of spin_lock_nested(). But, dev->lower_level value can be updated while it is being used. So, lockdep would warn a possible deadlock scenario. When a stacked interface is deleted, netif_{uc | mc}_sync() is called recursively. So, spin_lock_nested() is called recursively too. At this moment, the dev->lower_level variable is used as a parameter of it. dev->lower_level value is updated when interfaces are being unlinked/linked immediately. Thus, After unlinking, dev->lower_level shouldn't be a parameter of spin_lock_nested(). A (macvlan) | B (vlan) | C (bridge) | D (macvlan) | E (vlan) | F (bridge) A->lower_level : 6 B->lower_level : 5 C->lower_level : 4 D->lower_level : 3 E->lower_level : 2 F->lower_level : 1 When an interface 'A' is removed, it releases resources. At this moment, netif_addr_lock() would be called. Then, netdev_upper_dev_unlink() is called recursively. Then dev->lower_level is updated. There is no problem. But, when the bridge module is removed, 'C' and 'F' interfaces are removed at once. If 'F' is removed first, a lower_level value is like below. A->lower_level : 5 B->lower_level : 4 C->lower_level : 3 D->lower_level : 2 E->lower_level : 1 F->lower_level : 1 Then, 'C' is removed. at this moment, netif_addr_lock() is called recursively. The ordering is like this. C(3)->D(2)->E(1)->F(1) At this moment, the lower_level value of 'E' and 'F' are the same. So, lockdep warns a possible deadlock scenario. In order to avoid this problem, a new variable 'nested_level' is added. This value is the same as dev->lower_level - 1. But this value is updated in rtnl_unlock(). So, this variable can be used as a parameter of spin_lock_nested() safely in the rtnl context. Test commands: ip link add br0 type bridge vlan_filtering 1 ip link add vlan1 link br0 type vlan id 10 ip link add macvlan2 link vlan1 type macvlan ip link add br3 type bridge vlan_filtering 1 ip link set macvlan2 master br3 ip link add vlan4 link br3 type vlan id 10 ip link add macvlan5 link vlan4 type macvlan ip link add br6 type bridge vlan_filtering 1 ip link set macvlan5 master br6 ip link add vlan7 link br6 type vlan id 10 ip link add macvlan8 link vlan7 type macvlan ip link set br0 up ip link set vlan1 up ip link set macvlan2 up ip link set br3 up ip link set vlan4 up ip link set macvlan5 up ip link set br6 up ip link set vlan7 up ip link set macvlan8 up modprobe -rv bridge Splat looks like: [ 36.057436][ T744] WARNING: possible recursive locking detected [ 36.058848][ T744] 5.9.0-rc6+ #728 Not tainted [ 36.059959][ T744] -------------------------------------------- [ 36.061391][ T744] ip/744 is trying to acquire lock: [ 36.062590][ T744] ffff8c4767509280 (&vlan_netdev_addr_lock_key){+...}-{2:2}, at: dev_set_rx_mode+0x19/0x30 [ 36.064922][ T744] [ 36.064922][ T744] but task is already holding lock: [ 36.066626][ T744] ffff8c4767769280 (&vlan_netdev_addr_lock_key){+...}-{2:2}, at: dev_uc_add+0x1e/0x60 [ 36.068851][ T744] [ 36.068851][ T744] other info that might help us debug this: [ 36.070731][ T744] Possible unsafe locking scenario: [ 36.070731][ T744] [ 36.072497][ T744] CPU0 [ 36.073238][ T744] ---- [ 36.074007][ T744] lock(&vlan_netdev_addr_lock_key); [ 36.075290][ T744] lock(&vlan_netdev_addr_lock_key); [ 36.076590][ T744] [ 36.076590][ T744] *** DEADLOCK *** [ 36.076590][ T744] [ 36.078515][ T744] May be due to missing lock nesting notation [ 36.078515][ T744] [ 36.080491][ T744] 3 locks held by ip/744: [ 36.081471][ T744] #0: ffffffff98571df0 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x236/0x490 [ 36.083614][ T744] #1: ffff8c4767769280 (&vlan_netdev_addr_lock_key){+...}-{2:2}, at: dev_uc_add+0x1e/0x60 [ 36.085942][ T744] #2: ffff8c476c8da280 (&bridge_netdev_addr_lock_key/4){+...}-{2:2}, at: dev_uc_sync+0x39/0x80 [ 36.088400][ T744] [ 36.088400][ T744] stack backtrace: [ 36.089772][ T744] CPU: 6 PID: 744 Comm: ip Not tainted 5.9.0-rc6+ #728 [ 36.091364][ T744] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 [ 36.093630][ T744] Call Trace: [ 36.094416][ T744] dump_stack+0x77/0x9b [ 36.095385][ T744] __lock_acquire+0xbc3/0x1f40 [ 36.096522][ T744] lock_acquire+0xb4/0x3b0 [ 36.097540][ T744] ? dev_set_rx_mode+0x19/0x30 [ 36.098657][ T744] ? rtmsg_ifinfo+0x1f/0x30 [ 36.099711][ T744] ? __dev_notify_flags+0xa5/0xf0 [ 36.100874][ T744] ? rtnl_is_locked+0x11/0x20 [ 36.101967][ T744] ? __dev_set_promiscuity+0x7b/0x1a0 [ 36.103230][ T744] _raw_spin_lock_bh+0x38/0x70 [ 36.104348][ T744] ? dev_set_rx_mode+0x19/0x30 [ 36.105461][ T744] dev_set_rx_mode+0x19/0x30 [ 36.106532][ T744] dev_set_promiscuity+0x36/0x50 [ 36.107692][ T744] __dev_set_promiscuity+0x123/0x1a0 [ 36.108929][ T744] dev_set_promiscuity+0x1e/0x50 [ 36.110093][ T744] br_port_set_promisc+0x1f/0x40 [bridge] [ 36.111415][ T744] br_manage_promisc+0x8b/0xe0 [bridge] [ 36.112728][ T744] __dev_set_promiscuity+0x123/0x1a0 [ 36.113967][ T744] ? __hw_addr_sync_one+0x23/0x50 [ 36.115135][ T744] __dev_set_rx_mode+0x68/0x90 [ 36.116249][ T744] dev_uc_sync+0x70/0x80 [ 36.117244][ T744] dev_uc_add+0x50/0x60 [ 36.118223][ T744] macvlan_open+0x18e/0x1f0 [macvlan] [ 36.119470][ T744] __dev_open+0xd6/0x170 [ 36.120470][ T744] __dev_change_flags+0x181/0x1d0 [ 36.121644][ T744] dev_change_flags+0x23/0x60 [ 36.122741][ T744] do_setlink+0x30a/0x11e0 [ 36.123778][ T744] ? __lock_acquire+0x92c/0x1f40 [ 36.124929][ T744] ? __nla_validate_parse.part.6+0x45/0x8e0 [ 36.126309][ T744] ? __lock_acquire+0x92c/0x1f40 [ 36.127457][ T744] __rtnl_newlink+0x546/0x8e0 [ 36.128560][ T744] ? lock_acquire+0xb4/0x3b0 [ 36.129623][ T744] ? deactivate_slab.isra.85+0x6a1/0x850 [ 36.130946][ T744] ? __lock_acquire+0x92c/0x1f40 [ 36.132102][ T744] ? lock_acquire+0xb4/0x3b0 [ 36.133176][ T744] ? is_bpf_text_address+0x5/0xe0 [ 36.134364][ T744] ? rtnl_newlink+0x2e/0x70 [ 36.135445][ T744] ? rcu_read_lock_sched_held+0x32/0x60 [ 36.136771][ T744] ? kmem_cache_alloc_trace+0x2d8/0x380 [ 36.138070][ T744] ? rtnl_newlink+0x2e/0x70 [ 36.139164][ T744] rtnl_newlink+0x47/0x70 [ ... ] Fixes: 845e0ebb4408 ("net: change addr_list_lock back to static key") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 52 +++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 44 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 313803d6c781..9fdb3ebef306 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1955,6 +1955,7 @@ struct net_device { unsigned short type; unsigned short hard_header_len; unsigned char min_header_len; + unsigned char name_assign_type; unsigned short needed_headroom; unsigned short needed_tailroom; @@ -1965,21 +1966,28 @@ struct net_device { unsigned char addr_len; unsigned char upper_level; unsigned char lower_level; + unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; spinlock_t addr_list_lock; - unsigned char name_assign_type; - bool uc_promisc; + struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; struct netdev_hw_addr_list dev_addrs; #ifdef CONFIG_SYSFS struct kset *queues_kset; +#endif +#ifdef CONFIG_LOCKDEP + struct list_head unlink_list; #endif unsigned int promiscuity; unsigned int allmulti; + bool uc_promisc; +#ifdef CONFIG_LOCKDEP + unsigned char nested_level; +#endif /* Protocol-specific pointers */ @@ -4260,17 +4268,23 @@ static inline void netif_tx_disable(struct net_device *dev) static inline void netif_addr_lock(struct net_device *dev) { - spin_lock(&dev->addr_list_lock); -} + unsigned char nest_level = 0; -static inline void netif_addr_lock_nested(struct net_device *dev) -{ - spin_lock_nested(&dev->addr_list_lock, dev->lower_level); +#ifdef CONFIG_LOCKDEP + nest_level = dev->nested_level; +#endif + spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_lock_bh(struct net_device *dev) { - spin_lock_bh(&dev->addr_list_lock); + unsigned char nest_level = 0; + +#ifdef CONFIG_LOCKDEP + nest_level = dev->nested_level; +#endif + local_bh_disable(); + spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_unlock(struct net_device *dev) @@ -4455,7 +4469,19 @@ extern int dev_rx_weight; extern int dev_tx_weight; extern int gro_normal_batch; +enum { + NESTED_SYNC_IMM_BIT, + NESTED_SYNC_TODO_BIT, +}; + +#define __NESTED_SYNC_BIT(bit) ((u32)1 << (bit)) +#define __NESTED_SYNC(name) __NESTED_SYNC_BIT(NESTED_SYNC_ ## name ## _BIT) + +#define NESTED_SYNC_IMM __NESTED_SYNC(IMM) +#define NESTED_SYNC_TODO __NESTED_SYNC(TODO) + struct netdev_nested_priv { + unsigned char flags; void *data; }; @@ -4465,6 +4491,16 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); +#ifdef CONFIG_LOCKDEP +static LIST_HEAD(net_unlink_list); + +static inline void net_unlink_todo(struct net_device *dev) +{ + if (list_empty(&dev->unlink_list)) + list_add_tail(&dev->unlink_list, &net_unlink_list); +} +#endif + /* iterate through upper list, must be called under RCU read lock */ #define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ for (iter = &(dev)->adj_list.upper, \ -- cgit v1.2.3 From 112c35237c726cb2c6eed32db660f285938fb666 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Tue, 29 Sep 2020 12:53:44 -0700 Subject: Partially revert "video: fbdev: amba-clcd: Retire elder CLCD driver" Also partially revert the follow-up change "drm: pl111: Absorb the external register header". This reverts the parts of commits 7e4e589db76a3cf4c1f534eb5a09cc6422766b93 and 0fb8125635e8eb5483fb095f98dcf0651206a7b8 that touch paths outside of drivers/gpu/drm/pl111. The fbdev driver is used by Android's FVP configuration. Using the DRM driver together with DRM's fbdev emulation results in a failure to boot Android. The root cause is that Android's generic fbdev userspace driver relies on the ability to set the pixel format via FBIOPUT_VSCREENINFO, which is not supported by fbdev emulation. There have been other less critical behavioral differences identified between the fbdev driver and the DRM driver with fbdev emulation. The DRM driver exposes different values for the panel's width, height and refresh rate, and the DRM driver fails a FBIOPUT_VSCREENINFO syscall with yres_virtual greater than the maximum supported value instead of letting the syscall succeed and setting yres_virtual based on yres. Signed-off-by: Peter Collingbourne Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20200929195344.2219796-1-pcc@google.com --- include/linux/amba/clcd-regs.h | 87 +++++++++++++ include/linux/amba/clcd.h | 290 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 377 insertions(+) create mode 100644 include/linux/amba/clcd-regs.h create mode 100644 include/linux/amba/clcd.h (limited to 'include/linux') diff --git a/include/linux/amba/clcd-regs.h b/include/linux/amba/clcd-regs.h new file mode 100644 index 000000000000..421b0fa90d6a --- /dev/null +++ b/include/linux/amba/clcd-regs.h @@ -0,0 +1,87 @@ +/* + * David A Rusling + * + * Copyright (C) 2001 ARM Limited + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ + +#ifndef AMBA_CLCD_REGS_H +#define AMBA_CLCD_REGS_H + +/* + * CLCD Controller Internal Register addresses + */ +#define CLCD_TIM0 0x00000000 +#define CLCD_TIM1 0x00000004 +#define CLCD_TIM2 0x00000008 +#define CLCD_TIM3 0x0000000c +#define CLCD_UBAS 0x00000010 +#define CLCD_LBAS 0x00000014 + +#define CLCD_PL110_IENB 0x00000018 +#define CLCD_PL110_CNTL 0x0000001c +#define CLCD_PL110_STAT 0x00000020 +#define CLCD_PL110_INTR 0x00000024 +#define CLCD_PL110_UCUR 0x00000028 +#define CLCD_PL110_LCUR 0x0000002C + +#define CLCD_PL111_CNTL 0x00000018 +#define CLCD_PL111_IENB 0x0000001c +#define CLCD_PL111_RIS 0x00000020 +#define CLCD_PL111_MIS 0x00000024 +#define CLCD_PL111_ICR 0x00000028 +#define CLCD_PL111_UCUR 0x0000002c +#define CLCD_PL111_LCUR 0x00000030 + +#define CLCD_PALL 0x00000200 +#define CLCD_PALETTE 0x00000200 + +#define TIM2_PCD_LO_MASK GENMASK(4, 0) +#define TIM2_PCD_LO_BITS 5 +#define TIM2_CLKSEL (1 << 5) +#define TIM2_ACB_MASK GENMASK(10, 6) +#define TIM2_IVS (1 << 11) +#define TIM2_IHS (1 << 12) +#define TIM2_IPC (1 << 13) +#define TIM2_IOE (1 << 14) +#define TIM2_BCD (1 << 26) +#define TIM2_PCD_HI_MASK GENMASK(31, 27) +#define TIM2_PCD_HI_BITS 5 +#define TIM2_PCD_HI_SHIFT 27 + +#define CNTL_LCDEN (1 << 0) +#define CNTL_LCDBPP1 (0 << 1) +#define CNTL_LCDBPP2 (1 << 1) +#define CNTL_LCDBPP4 (2 << 1) +#define CNTL_LCDBPP8 (3 << 1) +#define CNTL_LCDBPP16 (4 << 1) +#define CNTL_LCDBPP16_565 (6 << 1) +#define CNTL_LCDBPP16_444 (7 << 1) +#define CNTL_LCDBPP24 (5 << 1) +#define CNTL_LCDBW (1 << 4) +#define CNTL_LCDTFT (1 << 5) +#define CNTL_LCDMONO8 (1 << 6) +#define CNTL_LCDDUAL (1 << 7) +#define CNTL_BGR (1 << 8) +#define CNTL_BEBO (1 << 9) +#define CNTL_BEPO (1 << 10) +#define CNTL_LCDPWR (1 << 11) +#define CNTL_LCDVCOMP(x) ((x) << 12) +#define CNTL_LDMAFIFOTIME (1 << 15) +#define CNTL_WATERMARK (1 << 16) + +/* ST Microelectronics variant bits */ +#define CNTL_ST_1XBPP_444 0x0 +#define CNTL_ST_1XBPP_5551 (1 << 17) +#define CNTL_ST_1XBPP_565 (1 << 18) +#define CNTL_ST_CDWID_12 0x0 +#define CNTL_ST_CDWID_16 (1 << 19) +#define CNTL_ST_CDWID_18 (1 << 20) +#define CNTL_ST_CDWID_24 ((1 << 19)|(1 << 20)) +#define CNTL_ST_CEAEN (1 << 21) +#define CNTL_ST_LCDBPP24_PACKED (6 << 1) + +#endif /* AMBA_CLCD_REGS_H */ diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h new file mode 100644 index 000000000000..b6e0cbeaf533 --- /dev/null +++ b/include/linux/amba/clcd.h @@ -0,0 +1,290 @@ +/* + * linux/include/asm-arm/hardware/amba_clcd.h -- Integrator LCD panel. + * + * David A Rusling + * + * Copyright (C) 2001 ARM Limited + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ +#include +#include + +enum { + /* individual formats */ + CLCD_CAP_RGB444 = (1 << 0), + CLCD_CAP_RGB5551 = (1 << 1), + CLCD_CAP_RGB565 = (1 << 2), + CLCD_CAP_RGB888 = (1 << 3), + CLCD_CAP_BGR444 = (1 << 4), + CLCD_CAP_BGR5551 = (1 << 5), + CLCD_CAP_BGR565 = (1 << 6), + CLCD_CAP_BGR888 = (1 << 7), + + /* connection layouts */ + CLCD_CAP_444 = CLCD_CAP_RGB444 | CLCD_CAP_BGR444, + CLCD_CAP_5551 = CLCD_CAP_RGB5551 | CLCD_CAP_BGR5551, + CLCD_CAP_565 = CLCD_CAP_RGB565 | CLCD_CAP_BGR565, + CLCD_CAP_888 = CLCD_CAP_RGB888 | CLCD_CAP_BGR888, + + /* red/blue ordering */ + CLCD_CAP_RGB = CLCD_CAP_RGB444 | CLCD_CAP_RGB5551 | + CLCD_CAP_RGB565 | CLCD_CAP_RGB888, + CLCD_CAP_BGR = CLCD_CAP_BGR444 | CLCD_CAP_BGR5551 | + CLCD_CAP_BGR565 | CLCD_CAP_BGR888, + + CLCD_CAP_ALL = CLCD_CAP_BGR | CLCD_CAP_RGB, +}; + +struct backlight_device; + +struct clcd_panel { + struct fb_videomode mode; + signed short width; /* width in mm */ + signed short height; /* height in mm */ + u32 tim2; + u32 tim3; + u32 cntl; + u32 caps; + unsigned int bpp:8, + fixedtimings:1, + grayscale:1; + unsigned int connector; + struct backlight_device *backlight; + /* + * If the B/R lines are switched between the CLCD + * and the panel we need to know this and not try to + * compensate with the BGR bit in the control register. + */ + bool bgr_connection; +}; + +struct clcd_regs { + u32 tim0; + u32 tim1; + u32 tim2; + u32 tim3; + u32 cntl; + unsigned long pixclock; +}; + +struct clcd_fb; + +/* + * the board-type specific routines + */ +struct clcd_board { + const char *name; + + /* + * Optional. Hardware capability flags. + */ + u32 caps; + + /* + * Optional. Check whether the var structure is acceptable + * for this display. + */ + int (*check)(struct clcd_fb *fb, struct fb_var_screeninfo *var); + + /* + * Compulsory. Decode fb->fb.var into regs->*. In the case of + * fixed timing, set regs->* to the register values required. + */ + void (*decode)(struct clcd_fb *fb, struct clcd_regs *regs); + + /* + * Optional. Disable any extra display hardware. + */ + void (*disable)(struct clcd_fb *); + + /* + * Optional. Enable any extra display hardware. + */ + void (*enable)(struct clcd_fb *); + + /* + * Setup platform specific parts of CLCD driver + */ + int (*setup)(struct clcd_fb *); + + /* + * mmap the framebuffer memory + */ + int (*mmap)(struct clcd_fb *, struct vm_area_struct *); + + /* + * Remove platform specific parts of CLCD driver + */ + void (*remove)(struct clcd_fb *); +}; + +struct amba_device; +struct clk; + +/* this data structure describes each frame buffer device we find */ +struct clcd_fb { + struct fb_info fb; + struct amba_device *dev; + struct clk *clk; + struct clcd_panel *panel; + struct clcd_board *board; + void *board_data; + void __iomem *regs; + u16 off_ienb; + u16 off_cntl; + u32 clcd_cntl; + u32 cmap[16]; + bool clk_enabled; +}; + +static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs) +{ + struct fb_var_screeninfo *var = &fb->fb.var; + u32 val, cpl; + + /* + * Program the CLCD controller registers and start the CLCD + */ + val = ((var->xres / 16) - 1) << 2; + val |= (var->hsync_len - 1) << 8; + val |= (var->right_margin - 1) << 16; + val |= (var->left_margin - 1) << 24; + regs->tim0 = val; + + val = var->yres; + if (fb->panel->cntl & CNTL_LCDDUAL) + val /= 2; + val -= 1; + val |= (var->vsync_len - 1) << 10; + val |= var->lower_margin << 16; + val |= var->upper_margin << 24; + regs->tim1 = val; + + val = fb->panel->tim2; + val |= var->sync & FB_SYNC_HOR_HIGH_ACT ? 0 : TIM2_IHS; + val |= var->sync & FB_SYNC_VERT_HIGH_ACT ? 0 : TIM2_IVS; + + cpl = var->xres_virtual; + if (fb->panel->cntl & CNTL_LCDTFT) /* TFT */ + /* / 1 */; + else if (!var->grayscale) /* STN color */ + cpl = cpl * 8 / 3; + else if (fb->panel->cntl & CNTL_LCDMONO8) /* STN monochrome, 8bit */ + cpl /= 8; + else /* STN monochrome, 4bit */ + cpl /= 4; + + regs->tim2 = val | ((cpl - 1) << 16); + + regs->tim3 = fb->panel->tim3; + + val = fb->panel->cntl; + if (var->grayscale) + val |= CNTL_LCDBW; + + if (fb->panel->caps && fb->board->caps && var->bits_per_pixel >= 16) { + /* + * if board and panel supply capabilities, we can support + * changing BGR/RGB depending on supplied parameters. Here + * we switch to what the framebuffer is providing if need + * be, so if the framebuffer is BGR but the display connection + * is RGB (first case) we switch it around. Vice versa mutatis + * mutandis if the framebuffer is RGB but the display connection + * is BGR, we flip it around. + */ + if (var->red.offset == 0) + val &= ~CNTL_BGR; + else + val |= CNTL_BGR; + if (fb->panel->bgr_connection) + val ^= CNTL_BGR; + } + + switch (var->bits_per_pixel) { + case 1: + val |= CNTL_LCDBPP1; + break; + case 2: + val |= CNTL_LCDBPP2; + break; + case 4: + val |= CNTL_LCDBPP4; + break; + case 8: + val |= CNTL_LCDBPP8; + break; + case 16: + /* + * PL110 cannot choose between 5551 and 565 modes in its + * control register. It is possible to use 565 with + * custom external wiring. + */ + if (amba_part(fb->dev) == 0x110 || + var->green.length == 5) + val |= CNTL_LCDBPP16; + else if (var->green.length == 6) + val |= CNTL_LCDBPP16_565; + else + val |= CNTL_LCDBPP16_444; + break; + case 32: + val |= CNTL_LCDBPP24; + break; + } + + regs->cntl = val; + regs->pixclock = var->pixclock; +} + +static inline int clcdfb_check(struct clcd_fb *fb, struct fb_var_screeninfo *var) +{ + var->xres_virtual = var->xres = (var->xres + 15) & ~15; + var->yres_virtual = var->yres = (var->yres + 1) & ~1; + +#define CHECK(e,l,h) (var->e < l || var->e > h) + if (CHECK(right_margin, (5+1), 256) || /* back porch */ + CHECK(left_margin, (5+1), 256) || /* front porch */ + CHECK(hsync_len, (5+1), 256) || + var->xres > 4096 || + var->lower_margin > 255 || /* back porch */ + var->upper_margin > 255 || /* front porch */ + var->vsync_len > 32 || + var->yres > 1024) + return -EINVAL; +#undef CHECK + + /* single panel mode: PCD = max(PCD, 1) */ + /* dual panel mode: PCD = max(PCD, 5) */ + + /* + * You can't change the grayscale setting, and + * we can only do non-interlaced video. + */ + if (var->grayscale != fb->fb.var.grayscale || + (var->vmode & FB_VMODE_MASK) != FB_VMODE_NONINTERLACED) + return -EINVAL; + +#define CHECK(e) (var->e != fb->fb.var.e) + if (fb->panel->fixedtimings && + (CHECK(xres) || + CHECK(yres) || + CHECK(bits_per_pixel) || + CHECK(pixclock) || + CHECK(left_margin) || + CHECK(right_margin) || + CHECK(upper_margin) || + CHECK(lower_margin) || + CHECK(hsync_len) || + CHECK(vsync_len) || + CHECK(sync))) + return -EINVAL; +#undef CHECK + + var->nonstd = 0; + var->accel_flags = 0; + + return 0; +} -- cgit v1.2.3 From a509a66a9d0d4f4e304d58fad38c078d0336c445 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 29 Sep 2020 15:25:22 +0200 Subject: arm64: permit ACPI core to map kernel memory used for table overrides Jonathan reports that the strict policy for memory mapped by the ACPI core breaks the use case of passing ACPI table overrides via initramfs. This is due to the fact that the memory type used for loading the initramfs in memory is not recognized as a memory type that is typically used by firmware to pass firmware tables. Since the purpose of the strict policy is to ensure that no AML or other ACPI code can manipulate any memory that is used by the kernel to keep its internal state or the state of user tasks, we can relax the permission check, and allow mappings of memory that is reserved and marked as NOMAP via memblock, and therefore not covered by the linear mapping to begin with. Fixes: 1583052d111f ("arm64/acpi: disallow AML memory opregions to access kernel memory") Fixes: 325f5585ec36 ("arm64/acpi: disallow writeable AML opregion mapping for EFI code regions") Reported-by: Jonathan Cameron Signed-off-by: Ard Biesheuvel Tested-by: Jonathan Cameron Cc: Sudeep Holla Cc: Lorenzo Pieralisi Link: https://lore.kernel.org/r/20200929132522.18067-1-ardb@kernel.org Signed-off-by: Catalin Marinas --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1e4cdc6c7ae2..64ae25c59d55 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -958,7 +958,7 @@ void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b); -#ifdef CONFIG_X86 +#ifndef CONFIG_IA64 void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else static inline void arch_reserve_mem_area(acpi_physical_address addr, -- cgit v1.2.3 From 8a018eb55e3ac033592afbcb476b0ffe64465b12 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 1 Oct 2020 08:50:55 -0400 Subject: pipe: Fix memory leaks in create_pipe_files() Calling pipe2() with O_NOTIFICATION_PIPE could results in memory leaks unless watch_queue_init() is successful. In case of watch_queue_init() failure in pipe2() we are left with inode and pipe_inode_info instances that need to be freed. That failure exit has been introduced in commit c73be61cede5 ("pipe: Add general notification queue support") and its handling should've been identical to nearby treatment of alloc_file_pseudo() failures - it is dealing with the same situation. As it is, the mainline kernel leaks in that case. Another problem is that CONFIG_WATCH_QUEUE and !CONFIG_WATCH_QUEUE cases are treated differently (and the former leaks just pipe_inode_info, the latter - both pipe_inode_info and inode). Fixed by providing a dummy wacth_queue_init() in !CONFIG_WATCH_QUEUE case and by having failures of wacth_queue_init() handled the same way we handle alloc_file_pseudo() ones. Fixes: c73be61cede5 ("pipe: Add general notification queue support") Signed-off-by: Qian Cai Signed-off-by: Al Viro --- include/linux/watch_queue.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h index 5e08db2adc31..c994d1b2cdba 100644 --- a/include/linux/watch_queue.h +++ b/include/linux/watch_queue.h @@ -122,6 +122,12 @@ static inline void remove_watch_list(struct watch_list *wlist, u64 id) */ #define watch_sizeof(STRUCT) (sizeof(STRUCT) << WATCH_INFO_LENGTH__SHIFT) +#else +static inline int watch_queue_init(struct pipe_inode_info *pipe) +{ + return -ENOPKG; +} + #endif #endif /* _LINUX_WATCH_QUEUE_H */ -- cgit v1.2.3 From 472e5b056f000a778abb41f1e443de58eb259783 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 1 Oct 2020 19:14:36 -0700 Subject: pipe: remove pipe_wait() and fix wakeup race with splice The pipe splice code still used the old model of waiting for pipe IO by using a non-specific "pipe_wait()" that waited for any pipe event to happen, which depended on all pipe IO being entirely serialized by the pipe lock. So by checking the state you were waiting for, and then adding yourself to the wait queue before dropping the lock, you were guaranteed to see all the wakeups. Strictly speaking, the actual wakeups were not done under the lock, but the pipe_wait() model still worked, because since the waiter held the lock when checking whether it should sleep, it would always see the current state, and the wakeup was always done after updating the state. However, commit 0ddad21d3e99 ("pipe: use exclusive waits when reading or writing") split the single wait-queue into two, and in the process also made the "wait for event" code wait for _two_ wait queues, and that then showed a race with the wakers that were not serialized by the pipe lock. It's only splice that used that "pipe_wait()" model, so the problem wasn't obvious, but Josef Bacik reports: "I hit a hang with fstest btrfs/187, which does a btrfs send into /dev/null. This works by creating a pipe, the write side is given to the kernel to write into, and the read side is handed to a thread that splices into a file, in this case /dev/null. The box that was hung had the write side stuck here [pipe_write] and the read side stuck here [splice_from_pipe_next -> pipe_wait]. [ more details about pipe_wait() scenario ] The problem is we're doing the prepare_to_wait, which sets our state each time, however we can be woken up either with reads or writes. In the case above we race with the WRITER waking us up, and re-set our state to INTERRUPTIBLE, and thus never break out of schedule" Josef had a patch that avoided the issue in pipe_wait() by just making it set the state only once, but the deeper problem is that pipe_wait() depends on a level of synchonization by the pipe mutex that it really shouldn't. And the whole "wait for any pipe state change" model really isn't very good to begin with. So rather than trying to work around things in pipe_wait(), remove that legacy model of "wait for arbitrary pipe event" entirely, and actually create functions that wait for the pipe actually being readable or writable, and can do so without depending on the pipe lock serializing everything. Fixes: 0ddad21d3e99 ("pipe: use exclusive waits when reading or writing") Link: https://lore.kernel.org/linux-fsdevel/bfa88b5ad6f069b2b679316b9e495a970130416c.1601567868.git.josef@toxicpanda.com/ Reported-by: Josef Bacik Reviewed-and-tested-by: Josef Bacik Signed-off-by: Linus Torvalds --- include/linux/pipe_fs_i.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 50afd0d0084c..5d2705f1d01c 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -240,8 +240,9 @@ extern unsigned int pipe_max_size; extern unsigned long pipe_user_pages_hard; extern unsigned long pipe_user_pages_soft; -/* Drop the inode semaphore and wait for a pipe event, atomically */ -void pipe_wait(struct pipe_inode_info *pipe); +/* Wait for a pipe to be readable/writable while dropping the pipe lock */ +void pipe_wait_readable(struct pipe_inode_info *); +void pipe_wait_writable(struct pipe_inode_info *); struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); -- cgit v1.2.3 From be458311cdbb5d94820ffc4e40c5906085c0a507 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 1 Oct 2020 13:07:49 -0700 Subject: mm: memcg/slab: fix slab statistics in !SMP configuration Since commit ea426c2a7de8 ("mm: memcg: prepare for byte-sized vmstat items") the write side of slab counters accepts a value in bytes and converts it to pages. It happens in __mod_node_page_state(). However a non-SMP version of __mod_node_page_state() doesn't perform this conversion. It leads to incorrect (unrealistically high) slab counters values. Fix this by adding a similar conversion to the non-SMP version of __mod_node_page_state(). Signed-off-by: Roman Gushchin Reported-and-tested-by: Bastian Bittorf Fixes: ea426c2a7de8 ("mm: memcg: prepare for byte-sized vmstat items") Acked-by: Vlastimil Babka Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 91220ace31da..7557c1070fd7 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -312,6 +312,11 @@ static inline void __mod_zone_page_state(struct zone *zone, static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { + if (vmstat_item_in_bytes(item)) { + VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); + delta >>= PAGE_SHIFT; + } + node_page_state_add(delta, pgdat, item); } -- cgit v1.2.3 From 50b2412b7e7862c5af0cbf4b10d93bc5c712d021 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Tue, 4 Aug 2020 10:40:21 +0300 Subject: net/mlx5: Avoid possible free of command entry while timeout comp handler Upon command completion timeout, driver simulates a forced command completion. In a rare case where real interrupt for that command arrives simultaneously, it might release the command entry while the forced handler might still access it. Fix that by adding an entry refcount, to track current amount of allowed handlers. Command entry to be released only when this refcount is decremented to zero. Command refcount is always initialized to one. For callback commands, command completion handler is the symmetric flow to decrement it. For non-callback commands, it is wait_func(). Before ringing the doorbell, increment the refcount for the real completion handler. Once the real completion handler is called, it will decrement it. For callback commands, once the delayed work is scheduled, increment the refcount. Upon callback command completion handler, we will try to cancel the timeout callback. In case of success, we need to decrement the callback refcount as it will never run. In addition, gather the entry index free and the entry free into a one flow for all command types release. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Eran Ben Elisha Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c145de0473bc..897156822f0d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -767,6 +767,8 @@ struct mlx5_cmd_work_ent { u64 ts2; u16 op; bool polling; + /* Track the max comp handlers */ + refcount_t refcnt; }; struct mlx5_pas { -- cgit v1.2.3 From b898ce7bccf13087719c021d829dab607c175246 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 11 Sep 2020 11:48:55 -0700 Subject: net/mlx5: cmdif, Avoid skipping reclaim pages if FW is not accessible In case of pci is offline reclaim_pages_cmd() will still try to call the FW to release FW pages, cmd_exec() in this case will return a silent success without actually calling the FW. This is wrong and will cause page leaks, what we should do is to detect pci offline or command interface un-available before tying to access the FW and manually release the FW pages in the driver. In this patch we share the code to check for FW command interface availability and we call it in sensitive places e.g. reclaim_pages_cmd(). Alternative fix: 1. Remove MLX5_CMD_OP_MANAGE_PAGES form mlx5_internal_err_ret_value, command success simulation list. 2. Always Release FW pages even if cmd_exec fails in reclaim_pages_cmd(). Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 897156822f0d..372100c755e7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -935,6 +935,7 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); +bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); -- cgit v1.2.3 From a93bdcb94a0b3ca72046151412c2389dca681d2a Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 2 Oct 2020 07:49:45 +0200 Subject: net: core: document two new elements of struct net_device As warned by "make htmldocs", there are two new struct elements that aren't documented: ../include/linux/netdevice.h:2159: warning: Function parameter or member 'unlink_list' not described in 'net_device' ../include/linux/netdevice.h:2159: warning: Function parameter or member 'nested_level' not described in 'net_device' Fixes: 1fc70edb7d7b ("net: core: add nested_level variable in net_device") Signed-off-by: Mauro Carvalho Chehab Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9fdb3ebef306..18dec08439f9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1851,6 +1851,11 @@ enum netdev_priv_flags { * @udp_tunnel_nic: UDP tunnel offload state * @xdp_state: stores info on attached XDP BPF programs * + * @nested_level: Used as as a parameter of spin_lock_nested() of + * dev->addr_list_lock. + * @unlink_list: As netif_addr_lock() can be called recursively, + * keep a list of interfaces to be deleted. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ -- cgit v1.2.3 From c381b07941adc2274ce552daf86c94701c5e265a Mon Sep 17 00:00:00 2001 From: Coly Li Date: Fri, 2 Oct 2020 16:27:28 +0800 Subject: net: introduce helper sendpage_ok() in include/linux/net.h The original problem was from nvme-over-tcp code, who mistakenly uses kernel_sendpage() to send pages allocated by __get_free_pages() without __GFP_COMP flag. Such pages don't have refcount (page_count is 0) on tail pages, sending them by kernel_sendpage() may trigger a kernel panic from a corrupted kernel heap, because these pages are incorrectly freed in network stack as page_count 0 pages. This patch introduces a helper sendpage_ok(), it returns true if the checking page, - is not slab page: PageSlab(page) is false. - has page refcount: page_count(page) is not zero All drivers who want to send page to remote end by kernel_sendpage() may use this helper to check whether the page is OK. If the helper does not return true, the driver should try other non sendpage method (e.g. sock_no_sendpage()) to handle the page. Signed-off-by: Coly Li Cc: Chaitanya Kulkarni Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Jan Kara Cc: Jens Axboe Cc: Mikhail Skorzhinskii Cc: Philipp Reisner Cc: Sagi Grimberg Cc: Vlastimil Babka Cc: stable@vger.kernel.org Signed-off-by: David S. Miller --- include/linux/net.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index d48ff1180879..ae713c851342 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -286,6 +287,21 @@ do { \ #define net_get_random_once_wait(buf, nbytes) \ get_random_once_wait((buf), (nbytes)) +/* + * E.g. XFS meta- & log-data is in slab pages, or bcache meta + * data pages, or other high order pages allocated by + * __get_free_pages() without __GFP_COMP, which have a page_count + * of 0 and/or have PageSlab() set. We cannot use send_page for + * those, as that does get_page(); put_page(); and would cause + * either a VM_BUG directly, or __page_cache_release a page that + * would actually still be referenced by someone, leading to some + * obscure delayed Oops somewhere else. + */ +static inline bool sendpage_ok(struct page *page) +{ + return !PageSlab(page) && page_count(page) >= 1; +} + int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, -- cgit v1.2.3 From 8b7b2eb131d3476062ffd34358785b44be25172f Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Sat, 10 Oct 2020 23:16:37 -0700 Subject: mm: validate inode in mapping_set_error() The swap address_space doesn't have host. Thus, it makes kernel crash once swap write meets error. Fix it. Fixes: 735e4ae5ba28 ("vfs: track per-sb writeback errors and report them to syncfs") Signed-off-by: Minchan Kim Signed-off-by: Andrew Morton Acked-by: Jeff Layton Cc: Jan Kara Cc: Andres Freund Cc: Matthew Wilcox Cc: Al Viro Cc: Christoph Hellwig Cc: Dave Chinner Cc: David Howells Cc: Link: https://lkml.kernel.org/r/20201010000650.750063-1-minchan@kernel.org Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 7de11dcd534d..434c9c34aeb6 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -54,7 +54,8 @@ static inline void mapping_set_error(struct address_space *mapping, int error) __filemap_set_wb_err(mapping, error); /* Record it in superblock */ - errseq_set(&mapping->host->i_sb->s_wb_err, error); + if (mapping->host) + errseq_set(&mapping->host->i_sb->s_wb_err, error); /* Record it in flags for now, for legacy callers */ if (error == -ENOSPC) -- cgit v1.2.3 From 4aab2be0983031a05cb4a19696c9da5749523426 Mon Sep 17 00:00:00 2001 From: Vijay Balakrishna Date: Sat, 10 Oct 2020 23:16:40 -0700 Subject: mm: khugepaged: recalculate min_free_kbytes after memory hotplug as expected by khugepaged When memory is hotplug added or removed the min_free_kbytes should be recalculated based on what is expected by khugepaged. Currently after hotplug, min_free_kbytes will be set to a lower default and higher default set when THP enabled is lost. This change restores min_free_kbytes as expected for THP consumers. [vijayb@linux.microsoft.com: v5] Link: https://lkml.kernel.org/r/1601398153-5517-1-git-send-email-vijayb@linux.microsoft.com Fixes: f000565adb77 ("thp: set recommended min free kbytes") Signed-off-by: Vijay Balakrishna Signed-off-by: Andrew Morton Reviewed-by: Pavel Tatashin Acked-by: Michal Hocko Cc: Allen Pais Cc: Andrea Arcangeli Cc: "Kirill A. Shutemov" Cc: Oleg Nesterov Cc: Song Liu Cc: Link: https://lkml.kernel.org/r/1600305709-2319-2-git-send-email-vijayb@linux.microsoft.com Link: https://lkml.kernel.org/r/1600204258-13683-1-git-send-email-vijayb@linux.microsoft.com Signed-off-by: Linus Torvalds --- include/linux/khugepaged.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index bc45ea1efbf7..c941b7377321 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -15,6 +15,7 @@ extern int __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma, unsigned long vm_flags); +extern void khugepaged_min_free_kbytes_update(void); #ifdef CONFIG_SHMEM extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr); #else @@ -85,6 +86,10 @@ static inline void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) { } + +static inline void khugepaged_min_free_kbytes_update(void) +{ +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_KHUGEPAGED_H */ -- cgit v1.2.3 From 3b95bc57c86b064fd140ccec3642ad14f40b687f Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Wed, 18 Nov 2020 22:49:27 -0800 Subject: Input: adp5589-keys - remove setup/teardown hooks for gpios This is currently just dead code. It's from around a time when platform-data was used, and a board could hook it's own special callback for setup/teardown, and a private object (via 'context'). This change removes it, as there are no more users in mainline for this. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20201112074308.71351-4-alexandru.ardelean@analog.com Signed-off-by: Dmitry Torokhov --- include/linux/input/adp5589.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input/adp5589.h b/include/linux/input/adp5589.h index c0523af96893..0e4742c8c81e 100644 --- a/include/linux/input/adp5589.h +++ b/include/linux/input/adp5589.h @@ -175,13 +175,6 @@ struct i2c_client; /* forward declaration */ struct adp5589_gpio_platform_data { int gpio_start; /* GPIO Chip base # */ - int (*setup)(struct i2c_client *client, - int gpio, unsigned ngpio, - void *context); - int (*teardown)(struct i2c_client *client, - int gpio, unsigned ngpio, - void *context); - void *context; }; #endif -- cgit v1.2.3 From 278b13ce3a89698711c5a67792ba2dba41555433 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 2 Oct 2019 10:33:02 -0700 Subject: Input: remove input_polled_dev implementation Now that normal input devices support polling mode, and all users of input_polled_dev API have been converted, we can remove it. Signed-off-by: Dmitry Torokhov --- include/linux/input-polldev.h | 58 ------------------------------------------- 1 file changed, 58 deletions(-) delete mode 100644 include/linux/input-polldev.h (limited to 'include/linux') diff --git a/include/linux/input-polldev.h b/include/linux/input-polldev.h deleted file mode 100644 index 14821fd231c0..000000000000 --- a/include/linux/input-polldev.h +++ /dev/null @@ -1,58 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _INPUT_POLLDEV_H -#define _INPUT_POLLDEV_H - -/* - * Copyright (c) 2007 Dmitry Torokhov - */ - -#include -#include - -/** - * struct input_polled_dev - simple polled input device - * @private: private driver data. - * @open: driver-supplied method that prepares device for polling - * (enabled the device and maybe flushes device state). - * @close: driver-supplied method that is called when device is no - * longer being polled. Used to put device into low power mode. - * @poll: driver-supplied method that polls the device and posts - * input events (mandatory). - * @poll_interval: specifies how often the poll() method should be called. - * Defaults to 500 msec unless overridden when registering the device. - * @poll_interval_max: specifies upper bound for the poll interval. - * Defaults to the initial value of @poll_interval. - * @poll_interval_min: specifies lower bound for the poll interval. - * Defaults to 0. - * @input: input device structure associated with the polled device. - * Must be properly initialized by the driver (id, name, phys, bits). - * - * Polled input device provides a skeleton for supporting simple input - * devices that do not raise interrupts but have to be periodically - * scanned or polled to detect changes in their state. - */ -struct input_polled_dev { - void *private; - - void (*open)(struct input_polled_dev *dev); - void (*close)(struct input_polled_dev *dev); - void (*poll)(struct input_polled_dev *dev); - unsigned int poll_interval; /* msec */ - unsigned int poll_interval_max; /* msec */ - unsigned int poll_interval_min; /* msec */ - - struct input_dev *input; - -/* private: */ - struct delayed_work work; - - bool devres_managed; -}; - -struct input_polled_dev *input_allocate_polled_device(void); -struct input_polled_dev *devm_input_allocate_polled_device(struct device *dev); -void input_free_polled_device(struct input_polled_dev *dev); -int input_register_polled_device(struct input_polled_dev *dev); -void input_unregister_polled_device(struct input_polled_dev *dev); - -#endif -- cgit v1.2.3 From 39be39ceffd572baddfeff8b50aba931d3d6d785 Mon Sep 17 00:00:00 2001 From: Andrzej Pietrasiewicz Date: Sun, 4 Oct 2020 21:15:46 -0700 Subject: Input: add input_device_enabled() A helper function for drivers to decide if the device is used or not. A lockdep check is introduced as inspecting ->users should be done under input device's mutex. Signed-off-by: Andrzej Pietrasiewicz Link: https://lore.kernel.org/r/20200608112211.12125-2-andrzej.p@collabora.com Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 56f2fd32e609..eda4587dba67 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -502,6 +502,8 @@ bool input_match_device_id(const struct input_dev *dev, void input_enable_softrepeat(struct input_dev *dev, int delay, int period); +bool input_device_enabled(struct input_dev *dev); + extern struct class input_class; /** -- cgit v1.2.3 From a181616487dbdbc953e476d1da15365f887859ed Mon Sep 17 00:00:00 2001 From: Patrik Fimml Date: Wed, 2 Dec 2020 14:42:04 -0800 Subject: Input: Add "inhibited" property Userspace might want to implement a policy to temporarily disregard input from certain devices, including not treating them as wakeup sources. An example use case is a laptop, whose keyboard can be folded under the screen to create tablet-like experience. The user then must hold the laptop in such a way that it is difficult to avoid pressing the keyboard keys. It is therefore desirable to temporarily disregard input from the keyboard, until it is folded back. This obviously is a policy which should be kept out of the kernel, but the kernel must provide suitable means to implement such a policy. This patch adds a sysfs interface for exactly this purpose. To implement the said interface it adds an "inhibited" property to struct input_dev, and effectively creates four states a device can be in: closed uninhibited, closed inhibited, open uninhibited, open inhibited. It also defers calling driver's ->open() and ->close() to until they are actually needed, e.g. it makes no sense to prepare the underlying device for generating events (->open()) if the device is inhibited. uninhibit closed <------------ closed uninhibited ------------> inhibited | ^ inhibit | ^ 1st | | 1st | | open | | open | | | | | | | | last | | last | | close | | close v | uninhibit v | open <------------ open uninhibited ------------> inhibited The top inhibit/uninhibit transition happens when users == 0. The bottom inhibit/uninhibit transition happens when users > 0. The left open/close transition happens when !inhibited. The right open/close transition happens when inhibited. Due to all transitions being serialized with dev->mutex, it is impossible to have "diagonal" transitions between closed uninhibited and open inhibited or between open uninhibited and closed inhibited. No new callbacks are added to drivers, because their open() and close() serve exactly the purpose to tell the driver to start/stop providing events to the input core. Consequently, open() and close() - if provided - are called in both inhibit and uninhibit paths. Signed-off-by: Patrik Fimml Co-developed-by: Andrzej Pietrasiewicz Signed-off-by: Andrzej Pietrasiewicz Link: https://lore.kernel.org/r/20200608112211.12125-8-andrzej.p@collabora.com Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index eda4587dba67..0354b298d874 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -90,9 +90,11 @@ enum input_clock_type { * @open: this method is called when the very first user calls * input_open_device(). The driver must prepare the device * to start generating events (start polling thread, - * request an IRQ, submit URB, etc.) + * request an IRQ, submit URB, etc.). The meaning of open() is + * to start providing events to the input core. * @close: this method is called when the very last user calls - * input_close_device(). + * input_close_device(). The meaning of close() is to stop + * providing events to the input core. * @flush: purges the device. Most commonly used to get rid of force * feedback effects loaded into the device when disconnecting * from it @@ -127,6 +129,10 @@ enum input_clock_type { * and needs not be explicitly unregistered or freed. * @timestamp: storage for a timestamp set by input_set_timestamp called * by a driver + * @inhibited: indicates that the input device is inhibited. If that is + * the case then input core ignores any events generated by the device. + * Device's close() is called when it is being inhibited and its open() + * is called when it is being uninhibited. */ struct input_dev { const char *name; @@ -201,6 +207,8 @@ struct input_dev { bool devres_managed; ktime_t timestamp[INPUT_CLK_MAX]; + + bool inhibited; }; #define to_input_dev(d) container_of(d, struct input_dev, dev) -- cgit v1.2.3